2919 files changed, 113563 insertions, 17298 deletions

diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index f9fd615427fb..1d27f0a1abd1 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -195,7 +195,7 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 6e97e73d87b5..4dbba7e100a1 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -131,6 +131,20 @@ If you cannot condense your patch set into a smaller set of patches,
 then only post say 15 or so at a time and wait for review and integration.
 
 
+If your patch fixes a bug in a specific commit, e.g. you found an issue using
+git-bisect, please use the 'Fixes:' tag with the first 12 characters of the
+SHA-1 ID, and the one line summary.
+Example:
+
+	Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()")
+
+The following git-config settings can be used to add a pretty format for
+outputting the above style in the git log or git show commands
+
+	[core]
+		abbrev = 12
+	[pretty]
+		fixes = Fixes: %h (\"%s\")
 
 4) Style check your changes.
 
@@ -420,7 +434,7 @@ person it names.  This tag documents that potentially interested parties
 have been included in the discussion
 
 
-14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by:
+14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes:
 
 If this patch fixes a problem reported by somebody else, consider adding a
 Reported-by: tag to credit the reporter for their contribution.  Please
@@ -475,6 +489,12 @@ idea was not posted in a public forum. That said, if we diligently credit our
 idea reporters, they will, hopefully, be inspired to help us again in the
 future.
 
+A Fixes: tag indicates that the patch fixes an issue in a previous commit. It
+is used to make it easy to determine where a bug originated, which can help
+review a bug fix. This tag also assists the stable kernel team in determining
+which stable kernel versions should receive your fix. This is the preferred
+method for indicating a bug fixed by the patch. See #2 above for more details.
+
 
 15) The canonical patch format
 
diff --git a/Documentation/arm/small_task_packing.txt b/Documentation/arm/small_task_packing.txt
new file mode 100644
index 000000000000..43f0a8b80234
--- /dev/null
+++ b/Documentation/arm/small_task_packing.txt
@@ -0,0 +1,136 @@
+Small Task Packing in the big.LITTLE MP Reference Patch Set
+
+What is small task packing?
+----
+Simply that the scheduler will fit as many small tasks on a single CPU
+as possible before using other CPUs. A small task is defined as one
+whose tracked load is less than 90% of a NICE_0 task. This is a change
+from the usual behavior since the scheduler will normally use an idle
+CPU for a waking task unless that task is considered cache hot.
+
+
+How is it implemented?
+----
+Since all small tasks must wake up relatively frequently, the main
+requirement for packing small tasks is to select a partly-busy CPU when
+waking rather than looking for an idle CPU. We use the tracked load of
+the CPU runqueue to determine how heavily loaded each CPU is and the
+tracked load of the task to determine if it will fit on the CPU. We
+always start with the lowest-numbered CPU in a sched domain and stop
+looking when we find a CPU with enough space for the task.
+
+Some further tweaks are necessary to suppress load balancing when the
+CPU is not fully loaded, otherwise the scheduler attempts to spread
+tasks evenly across the domain.
+
+
+How does it interact with the HMP patches?
+----
+Firstly, we only enable packing on the little domain. The intent is that
+the big domain is intended to spread tasks amongst the available CPUs
+one-task-per-CPU. The little domain however is attempting to use as
+little power as possible while servicing its tasks.
+
+Secondly, since we offload big tasks onto little CPUs in order to try
+to devote one CPU to each task, we have a threshold above which we do
+not try to pack a task and instead will select an idle CPU if possible.
+This maintains maximum forward progress for busy tasks temporarily
+demoted from big CPUs.
+
+
+Can the behaviour be tuned?
+----
+Yes, the load level of a 'full' CPU can be easily modified in the source
+and is exposed through sysfs as /sys/kernel/hmp/packing_limit to be
+changed at runtime. The presence of the packing behaviour is controlled
+by CONFIG_SCHED_HMP_LITTLE_PACKING and can be disabled at run-time
+using /sys/kernel/hmp/packing_enable.
+The definition of a small task is hard coded as 90% of NICE_0_LOAD
+and cannot be modified at run time.
+
+
+Why do I need to tune it?
+----
+The optimal configuration is likely to be different depending upon the
+design and manufacturing of your SoC.
+
+In the main, there are two system effects from enabling small task
+packing.
+
+1. CPU operating point may increase
+2. wakeup latency of tasks may be increased
+
+There are also likely to be secondary effects from loading one CPU
+rather than spreading tasks.
+
+Note that all of these system effects are dependent upon the workload
+under consideration.
+
+
+CPU Operating Point
+----
+The primary impact of loading one CPU with a number of light tasks is to
+increase the compute requirement of that CPU since it is no longer idle
+as often. Increased compute requirement causes an increase in the
+frequency of the CPU through CPUfreq.
+
+Consider this example:
+We have a system with 3 CPUs which can operate at any frequency between
+350MHz and 1GHz. The system has 6 tasks which would each produce 10%
+load at 1GHz. The scheduler has frequency-invariant load scaling
+enabled. Our DVFS governor aims for 80% utilization at the chosen
+frequency.
+
+Without task packing, these tasks will be spread out amongst all CPUs
+such that each has 2. This will produce roughly 20% system load, and
+the frequency of the package will remain at 350MHz.
+
+With task packing set to the default packing_limit, all of these tasks
+will sit on one CPU and require a package frequency of ~750MHz to reach
+80% utilization. (0.75 = 0.6 * 0.8).
+
+When a package operates on a single frequency domain, all CPUs in that
+package share frequency and voltage.
+
+Depending upon the SoC implementation there can be a significant amount
+of energy lost to leakage from idle CPUs. The decision about how
+loaded a CPU must be to be considered 'full' is therefore controllable
+through sysfs (sys/kernel/hmp/packing_limit) and directly in the code.
+
+Continuing the example, lets set packing_limit to 450 which means we
+will pack tasks until the total load of all running tasks >= 450. In
+practise, this is very similar to a 55% idle 1Ghz CPU.
+
+Now we are only able to place 4 tasks on CPU0, and two will overflow
+onto CPU1. CPU0 will have a load of 40% and CPU1 will have a load of
+20%. In order to still hit 80% utilization, CPU0 now only needs to
+operate at (0.4*0.8=0.32) 320MHz, which means that the lowest operating
+point will be selected, the same as in the non-packing case, except that
+now CPU2 is no longer needed and can be power-gated.
+
+In order to use less energy, the saving from power-gating CPU2 must be
+more than the energy spent running CPU0 for the extra cycles. This
+depends upon the SoC implementation.
+
+This is obviously a contrived example requiring all the tasks to
+be runnable at the same time, but it illustrates the point.
+
+
+Wakeup Latency
+----
+This is an unavoidable consequence of trying to pack tasks together
+rather than giving them a CPU each. If you cannot find an acceptable
+level of wakeup latency, you should turn packing off.
+
+Cyclictest is a good test application for determining the added latency
+when configuring packing.
+
+
+Why is it turned off for the VersatileExpress V2P_CA15A7 CoreTile?
+----
+Simply, this core tile only has power gating for the whole A7 package.
+When small task packing is enabled, all our low-energy use cases
+normally fit onto one A7 CPU. We therefore end up with 2 mostly-idle
+CPUs and one mostly-busy CPU. This decreases the amount of time
+available where the whole package is idle and can be turned off.
+
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
index 264e9841563a..d9995f1f51b3 100644
--- a/Documentation/arm64/tagged-pointers.txt
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -18,17 +18,17 @@ this byte for application use, with the following caveats:
 	    parameters containing user virtual addresses *must* have
 	    their top byte cleared before trapping to the kernel.
 
-	(2) Tags are not guaranteed to be preserved when delivering
-	    signals. This means that signal handlers in applications
-	    making use of tags cannot rely on the tag information for
-	    user virtual addresses being maintained for fields inside
-	    siginfo_t. One exception to this rule is for signals raised
-	    in response to debug exceptions, where the tag information
+	(2) Non-zero tags are not preserved when delivering signals.
+	    This means that signal handlers in applications making use
+	    of tags cannot rely on the tag information for user virtual
+	    addresses being maintained for fields inside siginfo_t.
+	    One exception to this rule is for signals raised in response
+	    to watchpoint debug exceptions, where the tag information
 	    will be preserved.
 
 	(3) Special care should be taken when using tagged pointers,
 	    since it is likely that C compilers will not hazard two
-	    addresses differing only in the upper bits.
+	    virtual addresses differing only in the upper byte.
 
 The architecture prevents the use of a tagged PC, so the upper byte will
 be set to a sign-extension of bit 55 on exception return.
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index 20746e5abe6f..06fc7602593a 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -1,10 +1,14 @@
 * ARM architected timer
 
-ARM cores may have a per-core architected timer, which provides per-cpu timers.
+ARM cores may have a per-core architected timer, which provides per-cpu timers,
+or a memory mapped architected timer, which provides up to 8 frames with a
+physical and optional virtual timer per frame.
 
-The timer is attached to a GIC to deliver its per-processor interrupts.
+The per-core architected timer is attached to a GIC to deliver its
+per-processor interrupts via PPIs. The memory mapped timer is attached to a GIC
+to deliver its interrupts via SPIs.
 
-** Timer node properties:
+** CP15 Timer node properties:
 
 - compatible : Should at least contain one of
 	"arm,armv7-timer"
@@ -26,3 +30,52 @@ Example:
 			     <1 10 0xf08>;
 		clock-frequency = <100000000>;
 	};
+
+** Memory mapped timer node properties:
+
+- compatible : Should at least contain "arm,armv7-timer-mem".
+
+- clock-frequency : The frequency of the main counter, in Hz. Optional.
+
+- reg : The control frame base address.
+
+Note that #address-cells, #size-cells, and ranges shall be present to ensure
+the CPU can address a frame's registers.
+
+A timer node has up to 8 frame sub-nodes, each with the following properties:
+
+- frame-number: 0 to 7.
+
+- interrupts : Interrupt list for physical and virtual timers in that order.
+  The virtual timer interrupt is optional.
+
+- reg : The first and second view base addresses in that order. The second view
+  base address is optional.
+
+- status : "disabled" indicates the frame is not available for use. Optional.
+
+Example:
+
+	timer@f0000000 {
+		compatible = "arm,armv7-timer-mem";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		reg = <0xf0000000 0x1000>;
+		clock-frequency = <50000000>;
+
+		frame@f0001000 {
+			frame-number = <0>
+			interrupts = <0 13 0x8>,
+				     <0 14 0x8>;
+			reg = <0xf0001000 0x1000>,
+			      <0xf0002000 0x1000>;
+		};
+
+		frame@f0003000 {
+			frame-number = <1>
+			interrupts = <0 15 0x8>;
+			reg = <0xf0003000 0x1000>;
+			status = "disabled";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/cci.txt b/Documentation/devicetree/bindings/arm/cci.txt
new file mode 100644
index 000000000000..92d36e2aa877
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/cci.txt
@@ -0,0 +1,172 @@
+=======================================================
+ARM CCI cache coherent interconnect binding description
+=======================================================
+
+ARM multi-cluster systems maintain intra-cluster coherency through a
+cache coherent interconnect (CCI) that is capable of monitoring bus
+transactions and manage coherency, TLB invalidations and memory barriers.
+
+It allows snooping and distributed virtual memory message broadcast across
+clusters, through memory mapped interface, with a global control register
+space and multiple sets of interface control registers, one per slave
+interface.
+
+Bindings for the CCI node follow the ePAPR standard, available from:
+
+www.power.org/documentation/epapr-version-1-1/
+
+with the addition of the bindings described in this document which are
+specific to ARM.
+
+* CCI interconnect node
+
+	Description: Describes a CCI cache coherent Interconnect component
+
+	Node name must be "cci".
+	Node's parent must be the root node /, and the address space visible
+	through the CCI interconnect is the same as the one seen from the
+	root node (ie from CPUs perspective as per DT standard).
+	Every CCI node has to define the following properties:
+
+	- compatible
+		Usage: required
+		Value type: <string>
+		Definition: must be set to
+			    "arm,cci-400"
+
+	- reg
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property. Specifies base physical
+			    address of CCI control registers common to all
+			    interfaces.
+
+	- ranges:
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property. Follow rules in the ePAPR for
+			    hierarchical bus addressing. CCI interfaces
+			    addresses refer to the parent node addressing
+			    scheme to declare their register bases.
+
+	CCI interconnect node can define the following child nodes:
+
+	- CCI control interface nodes
+
+		Node name must be "slave-if".
+		Parent node must be CCI interconnect node.
+
+		A CCI control interface node must contain the following
+		properties:
+
+		- compatible
+			Usage: required
+			Value type: <string>
+			Definition: must be set to
+				    "arm,cci-400-ctrl-if"
+
+		- interface-type:
+			Usage: required
+			Value type: <string>
+			Definition: must be set to one of {"ace", "ace-lite"}
+				    depending on the interface type the node
+				    represents.
+
+		- reg:
+			Usage: required
+			Value type: <prop-encoded-array>
+			Definition: the base address and size of the
+				    corresponding interface programming
+				    registers.
+
+* CCI interconnect bus masters
+
+	Description: masters in the device tree connected to a CCI port
+		     (inclusive of CPUs and their cpu nodes).
+
+	A CCI interconnect bus master node must contain the following
+	properties:
+
+	- cci-control-port:
+		Usage: required
+		Value type: <phandle>
+		Definition: a phandle containing the CCI control interface node
+			    the master is connected to.
+
+Example:
+
+	cpus {
+		#size-cells = <0>;
+		#address-cells = <1>;
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			cci-control-port = <&cci_control1>;
+			reg = <0x0>;
+		};
+
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			cci-control-port = <&cci_control1>;
+			reg = <0x1>;
+		};
+
+		CPU2: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			cci-control-port = <&cci_control2>;
+			reg = <0x100>;
+		};
+
+		CPU3: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			cci-control-port = <&cci_control2>;
+			reg = <0x101>;
+		};
+
+	};
+
+	dma0: dma@3000000 {
+		compatible = "arm,pl330", "arm,primecell";
+		cci-control-port = <&cci_control0>;
+		reg = <0x0 0x3000000 0x0 0x1000>;
+		interrupts = <10>;
+		#dma-cells = <1>;
+		#dma-channels = <8>;
+		#dma-requests = <32>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0x0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x6000>;
+
+		cci_control0: slave-if@1000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace-lite";
+			reg = <0x1000 0x1000>;
+		};
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+This CCI node corresponds to a CCI component whose control registers sits
+at address 0x000000002c090000.
+CCI slave interface @0x000000002c091000 is connected to dma controller dma0.
+CCI slave interface @0x000000002c094000 is connected to CPUs {CPU0, CPU1};
+CCI slave interface @0x000000002c095000 is connected to CPUs {CPU2, CPU3};
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
new file mode 100644
index 000000000000..d790f49066f3
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -0,0 +1,204 @@
+* CoreSight Components:
+
+CoreSight components are compliant with the ARM CoreSight architecture
+specification and can be connected in various topologies to suit a particular
+SoCs tracing needs. These trace components can generally be classified as
+sinks, links and sources. Trace data produced by one or more sources flows
+through the intermediate links connecting the source to the currently selected
+sink. Each CoreSight component device should use these properties to describe
+its hardware characteristcs.
+
+* Required properties for all components *except* non-configurable replicators:
+
+	* compatible: These have to be supplemented with "arm,primecell" as
+	  drivers are using the AMBA bus interface.  Possible values include:
+		- "arm,coresight-etb10", "arm,primecell";
+		- "arm,coresight-tpiu", "arm,primecell";
+		- "arm,coresight-tmc", "arm,primecell";
+		- "arm,coresight-funnel", "arm,primecell";
+		- "arm,coresight-etm3x", "arm,primecell";
+
+	* reg: physical base address and length of the register
+	  set(s) of the component.
+
+	* clocks: the clock associated to this component.
+
+	* clock-names: the name of the clock as referenced by the code.
+	  Since we are using the AMBA framework, the name should be
+	  "apb_pclk".
+
+	* port or ports: The representation of the component's port
+	  layout using the generic DT graph presentation found in
+	  "bindings/graph.txt".
+
+* Required properties for devices that don't show up on the AMBA bus, such as
+  non-configurable replicators:
+
+	* compatible: Currently supported value is (note the absence of the
+	  AMBA markee):
+		- "arm,coresight-replicator"
+
+	* id: a unique number that will identify this replicator.
+
+	* port or ports: same as above.
+
+* Optional properties for ETM/PTMs:
+
+	* arm,cp14: must be present if the system accesses ETM/PTM management
+	  registers via co-processor 14.
+
+	* cpu: the cpu phandle this ETM/PTM is affined to. When omitted the
+	  source is considered to belong to CPU0.
+
+* Optional property for TMC:
+
+	* arm,buffer-size: size of contiguous buffer space for TMC ETR
+	 (embedded trace router)
+
+
+Example:
+
+1. Sinks
+	etb@20010000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		coresight-default-sink;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etb_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	tpiu@20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+2. Links
+	replicator {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+		/* this will show up in debugfs as "0.replicator" */
+		id = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&etb_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel_out_port0: endpoint {
+					remote-endpoint =
+							<&replicator_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+		};
+	};
+
+3. Sources
+	ptm@2201c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201c000 0 0x1000>;
+
+		cpu = <&cpu0>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port0>;
+			};
+		};
+	};
+
+	ptm@2201d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201d000 0 0x1000>;
+
+		cpu = <&cpu1>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port1>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
index 3dfb0c0384f5..535774577238 100644
--- a/Documentation/devicetree/bindings/arm/gic.txt
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -49,6 +49,11 @@ Optional
   regions, used when the GIC doesn't have banked registers. The offset is
   cpu-offset * cpu-nr.
 
+- arm,routable-irqs : Total number of gic irq inputs which are not directly
+		  connected from the peripherals, but are routed dynamically
+		  by a crossbar/multiplexer preceding the GIC. The GIC irq
+		  input line is assigned dynamically when the corresponding
+		  peripheral's crossbar line is mapped.
 Example:
 
 	intc: interrupt-controller@fff11000 {
@@ -56,6 +61,7 @@ Example:
 		#interrupt-cells = <3>;
 		#address-cells = <1>;
 		interrupt-controller;
+		arm,routable-irqs = <160>;
 		reg = <0xfff11000 0x1000>,
 		      <0xfff10100 0x100>;
 	};
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 343781b9f246..4ce82d045a6b 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -16,6 +16,9 @@ Required properties:
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
 - interrupts : 1 combined interrupt or 1 per core.
+- cluster : a phandle to the cluster to which it belongs
+	If there are more than one cluster with same CPU type
+	then there should be separate PMU nodes per cluster.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt b/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt
new file mode 100644
index 000000000000..3b8fbf3c00c5
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt
@@ -0,0 +1,19 @@
+ARM Dual Cluster System Configuration Block
+-------------------------------------------
+
+The Dual Cluster System Configuration Block (DCSCB) provides basic
+functionality for controlling clocks, resets and configuration pins in
+the Dual Cluster System implemented by the Real-Time System Model (RTSM).
+
+Required properties:
+
+- compatible : should be "arm,rtsm,dcscb"
+
+- reg : physical base address and the size of the registers window
+
+Example:
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0x60000000 0x1000>;
+	};
diff --git a/Documentation/devicetree/bindings/ata/marvell.txt b/Documentation/devicetree/bindings/ata/marvell.txt
index b5cdd20cde9c..1c8351604d38 100644
--- a/Documentation/devicetree/bindings/ata/marvell.txt
+++ b/Documentation/devicetree/bindings/ata/marvell.txt
@@ -1,7 +1,7 @@
 * Marvell Orion SATA
 
 Required Properties:
-- compatibility : "marvell,orion-sata"
+- compatibility : "marvell,orion-sata" or "marvell,armada-370-sata"
 - reg           : Address range of controller
 - interrupts    : Interrupt controller is using
 - nr-ports      : Number of SATA ports in use.
diff --git a/Documentation/devicetree/bindings/mailbox/mailbox.txt b/Documentation/devicetree/bindings/mailbox/mailbox.txt
new file mode 100644
index 000000000000..1a2cd3d266db
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/mailbox.txt
@@ -0,0 +1,38 @@
+* Generic Mailbox Controller and client driver bindings
+
+Generic binding to provide a way for Mailbox controller drivers to
+assign appropriate mailbox channel to client drivers.
+
+* Mailbox Controller
+
+Required property:
+- #mbox-cells: Must be at least 1. Number of cells in a mailbox
+		specifier.
+
+Example:
+	mailbox: mailbox {
+		...
+		#mbox-cells = <1>;
+	};
+
+
+* Mailbox Client
+
+Required property:
+- mboxes: List of phandle and mailbox channel specifiers.
+
+Optional property:
+- mbox-names: List of identifier strings for each mailbox channel
+		required by the client. The use of this property
+		is discouraged in favor of using index in list of
+		'mboxes' while requesting a mailbox. Instead the
+		platforms may define channel indices, in DT headers,
+		to something legible.
+
+Example:
+	pwr_cntrl: power {
+		...
+		mbox-names = "pwr-ctrl", "rpc";
+		mboxes = <&mailbox 0
+			&mailbox 1>;
+	};
diff --git a/Documentation/devicetree/bindings/mfd/vexpress-spc.txt b/Documentation/devicetree/bindings/mfd/vexpress-spc.txt
new file mode 100644
index 000000000000..1d71dc2ff151
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/vexpress-spc.txt
@@ -0,0 +1,35 @@
+* ARM Versatile Express Serial Power Controller device tree bindings
+
+Latest ARM development boards implement a power management interface (serial
+power controller - SPC) that is capable of managing power/voltage and
+operating point transitions, through memory mapped registers interface.
+
+On testchips like TC2 it also provides a configuration interface that can
+be used to read/write values which cannot be read/written through simple
+memory mapped reads/writes.
+
+- spc node
+
+	- compatible:
+		Usage: required
+		Value type: <stringlist>
+		Definition: must be
+			    "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc"
+	- reg:
+		Usage: required
+		Value type: <prop-encode-array>
+		Definition: A standard property that specifies the base address
+			    and the size of the SPC address space
+	- interrupts:
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition:  SPC interrupt configuration. A standard property
+			     that follows ePAPR interrupts specifications
+
+Example:
+
+spc: spc@7fff0000 {
+	compatible = "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc";
+	reg = <0 0x7FFF0000 0 0x1000>;
+	interrupts = <0 95 4>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
index c95ea8278f87..b275be49a546 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
@@ -126,3 +126,55 @@ device; they may be grandchildren, for example. Whether this is legal, and
 whether there is any interaction between the child and intermediate parent
 nodes, is again defined entirely by the binding for the individual pin
 controller device.
+
+== Using generic pinconfig options ==
+
+Generic pinconfig parameters can be used by defining a separate node containing
+the applicable parameters (and optional values), like:
+
+pcfg_pull_up: pcfg_pull_up {
+	bias-pull-up;
+	drive-strength = <20>;
+};
+
+This node should then be referenced in the appropriate pinctrl node as a phandle
+and parsed in the driver using the pinconf_generic_parse_dt_config function.
+
+Supported configuration parameters are:
+
+bias-disable		- disable any pin bias
+bias-high-impedance	- high impedance mode ("third-state", "floating")
+bias-bus-hold		- latch weakly
+bias-pull-up		- pull up the pin
+bias-pull-down		- pull down the pin
+bias-pull-pin-default	- use pin-default pull state
+drive-push-pull		- drive actively high and low
+drive-open-drain	- drive with open drain
+drive-open-source	- drive with open source
+drive-strength		- sink or source at most X mA
+input-enable		- enable input on pin (no effect on output)
+input-disable		- disable input on pin (no effect on output)
+input-schmitt-enable	- enable schmitt-trigger mode
+input-schmitt-disable	- disable schmitt-trigger mode
+input-debounce		- debounce mode with debound time X
+low-power-enable	- enable low power mode
+low-power-disable	- disable low power mode
+output-low		- set the pin to output mode with low level
+output-high		- set the pin to output mode with high level
+slew-rate		- set the slew rate
+
+Arguments for parameters:
+
+- bias-pull-up, -down and -pin-default take as optional argument 0 to disable
+  the pull, on hardware supporting it the pull strength in Ohm. bias-disable
+  will also disable any active pull.
+
+- drive-strength takes as argument the target strength in mA.
+
+- input-debounce takes the debounce time in usec as argument
+  or 0 to disable debouncing
+
+All parameters not listed here, do not take an argument.
+
+More in-depth documentation on these parameters can be found in
+<include/linux/pinctrl/pinconfig-generic.h>
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
new file mode 100644
index 000000000000..98c16672ab5f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -0,0 +1,49 @@
+* Generic PM domains
+
+System on chip designs are often divided into multiple PM domains that can be
+used for power gating of selected IP blocks for power saving by reduced leakage
+current.
+
+This device tree binding can be used to bind PM domain consumer devices with
+their PM domains provided by PM domain providers. A PM domain provider can be
+represented by any node in the device tree and can provide one or more PM
+domains. A consumer node can refer to the provider by a phandle and a set of
+phandle arguments (so called PM domain specifiers) of length specified by the
+#power-domain-cells property in the PM domain provider node.
+
+==PM domain providers==
+
+Required properties:
+ - #power-domain-cells : Number of cells in a PM domain specifier;
+   Typically 0 for nodes representing a single PM domain and 1 for nodes
+   providing multiple PM domains (e.g. power controllers), but can be any value
+   as specified by device tree binding documentation of particular provider.
+
+Example:
+
+	power: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+	};
+
+The node above defines a power controller that is a PM domain provider and
+expects one cell as its phandle argument.
+
+==PM domain consumers==
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+
+Example:
+
+	leaky-device@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 0>;
+	};
+
+The node above defines a typical PM domain consumer device, which is located
+inside a PM domain with index 0 of a power controller represented by a node
+with the label "power".
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
new file mode 100644
index 000000000000..f5db6b72a36f
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -0,0 +1,595 @@
+* Thermal Framework Device Tree descriptor
+
+This file describes a generic binding to provide a way of
+defining hardware thermal structure using device tree.
+A thermal structure includes thermal zones and their components,
+such as trip points, polling intervals, sensors and cooling devices
+binding descriptors.
+
+The target of device tree thermal descriptors is to describe only
+the hardware thermal aspects. The thermal device tree bindings are
+not about how the system must control or which algorithm or policy
+must be taken in place.
+
+There are five types of nodes involved to describe thermal bindings:
+- thermal sensors: devices which may be used to take temperature
+  measurements.
+- cooling devices: devices which may be used to dissipate heat.
+- trip points: describe key temperatures at which cooling is recommended. The
+  set of points should be chosen based on hardware limits.
+- cooling maps: used to describe links between trip points and cooling devices;
+- thermal zones: used to describe thermal data within the hardware;
+
+The following is a description of each of these node types.
+
+* Thermal sensor devices
+
+Thermal sensor devices are nodes providing temperature sensing capabilities on
+thermal zones. Typical devices are I2C ADC converters and bandgaps. These are
+nodes providing temperature data to thermal zones. Thermal sensor devices may
+control one or more internal sensors.
+
+Required property:
+- #thermal-sensor-cells: Used to provide sensor device specific information
+  Type: unsigned	 while referring to it. Typically 0 on thermal sensor
+  Size: one cell	 nodes with only one sensor, and at least 1 on nodes
+			 with several internal sensors, in order
+			 to identify uniquely the sensor instances within
+			 the IC. See thermal zone binding for more details
+			 on how consumers refer to sensor devices.
+
+* Cooling device nodes
+
+Cooling devices are nodes providing control on power dissipation. There
+are essentially two ways to provide control on power dissipation. First
+is by means of regulating device performance, which is known as passive
+cooling. A typical passive cooling is a CPU that has dynamic voltage and
+frequency scaling (DVFS), and uses lower frequencies as cooling states.
+Second is by means of activating devices in order to remove
+the dissipated heat, which is known as active cooling, e.g. regulating
+fan speeds. In both cases, cooling devices shall have a way to determine
+the state of cooling in which the device is.
+
+Any cooling device has a range of cooling states (i.e. different levels
+of heat dissipation). For example a fan's cooling states correspond to
+the different fan speeds possible. Cooling states are referred to by
+single unsigned integers, where larger numbers mean greater heat
+dissipation. The precise set of cooling states associated with a device
+(as referred to be the cooling-min-state and cooling-max-state
+properties) should be defined in a particular device's binding.
+For more examples of cooling devices, refer to the example sections below.
+
+Required properties:
+- cooling-min-state:	An integer indicating the smallest
+  Type: unsigned	cooling state accepted. Typically 0.
+  Size: one cell
+
+- cooling-max-state:	An integer indicating the largest
+  Type: unsigned	cooling state accepted.
+  Size: one cell
+
+- #cooling-cells:	Used to provide cooling device specific information
+  Type: unsigned	while referring to it. Must be at least 2, in order
+  Size: one cell      	to specify minimum and maximum cooling state used
+			in the reference. The first cell is the minimum
+			cooling state requested and the second cell is
+			the maximum cooling state requested in the reference.
+			See Cooling device maps section below for more details
+			on how consumers refer to cooling devices.
+
+* Trip points
+
+The trip node is a node to describe a point in the temperature domain
+in which the system takes an action. This node describes just the point,
+not the action.
+
+Required properties:
+- temperature:		An integer indicating the trip temperature level,
+  Type: signed		in millicelsius.
+  Size: one cell
+
+- hysteresis:		A low hysteresis value on temperature property (above).
+  Type: unsigned	This is a relative value, in millicelsius.
+  Size: one cell
+
+- type:			a string containing the trip type. Expected values are:
+	"active":	A trip point to enable active cooling
+	"passive":	A trip point to enable passive cooling
+	"hot":		A trip point to notify emergency
+	"critical":	Hardware not reliable.
+  Type: string
+
+* Cooling device maps
+
+The cooling device maps node is a node to describe how cooling devices
+get assigned to trip points of the zone. The cooling devices are expected
+to be loaded in the target system.
+
+Required properties:
+- cooling-device:	A phandle of a cooling device with its specifier,
+  Type: phandle +	referring to which cooling device is used in this
+    cooling specifier	binding. In the cooling specifier, the first cell
+			is the minimum cooling state and the second cell
+			is the maximum cooling state used in this map.
+- trip:			A phandle of a trip point node within the same thermal
+  Type: phandle of	zone.
+   trip point node
+
+Optional property:
+- contribution:		The cooling contribution to the thermal zone of the
+  Type: unsigned	referred cooling device at the referred trip point.
+  Size: one cell      	The contribution is a ratio of the sum
+			of all cooling contributions within a thermal zone.
+
+Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
+limit specifier means:
+(i)   - minimum state allowed for minimum cooling state used in the reference.
+(ii)  - maximum state allowed for maximum cooling state used in the reference.
+Refer to include/dt-bindings/thermal/thermal.h for definition of this constant.
+
+* Thermal zone nodes
+
+The thermal zone node is the node containing all the required info
+for describing a thermal zone, including its cooling device bindings. The
+thermal zone node must contain, apart from its own properties, one sub-node
+containing trip nodes and one sub-node containing all the zone cooling maps.
+
+Required properties:
+- polling-delay:	The maximum number of milliseconds to wait between polls
+  Type: unsigned	when checking this thermal zone.
+  Size: one cell
+
+- polling-delay-passive: The maximum number of milliseconds to wait
+  Type: unsigned	between polls when performing passive cooling.
+  Size: one cell
+
+- thermal-sensors:	A list of thermal sensor phandles and sensor specifier
+  Type: list of 	used while monitoring the thermal zone.
+  phandles + sensor
+  specifier
+
+- trips:		A sub-node which is a container of only trip point nodes
+  Type: sub-node	required to describe the thermal zone.
+
+- cooling-maps:		A sub-node which is a container of only cooling device
+  Type: sub-node	map nodes, used to describe the relation between trips
+			and cooling devices.
+
+Optional property:
+- coefficients:		An array of integers (one signed cell) containing
+  Type: array		coefficients to compose a linear relation between
+  Elem size: one cell	the sensors listed in the thermal-sensors property.
+  Elem type: signed	Coefficients defaults to 1, in case this property
+			is not specified. A simple linear polynomial is used:
+			Z = c0 * x0 + c1 + x1 + ... + c(n-1) * x(n-1) + cn.
+
+			The coefficients are ordered and they match with sensors
+			by means of sensor ID. Additional coefficients are
+			interpreted as constant offset.
+
+Note: The delay properties are bound to the maximum dT/dt (temperature
+derivative over time) in two situations for a thermal zone:
+(i)  - when passive cooling is activated (polling-delay-passive); and
+(ii) - when the zone just needs to be monitored (polling-delay) or
+when active cooling is activated.
+
+The maximum dT/dt is highly bound to hardware power consumption and dissipation
+capability. The delays should be chosen to account for said max dT/dt,
+such that a device does not cross several trip boundaries unexpectedly
+between polls. Choosing the right polling delays shall avoid having the
+device in temperature ranges that may damage the silicon structures and
+reduce silicon lifetime.
+
+* The thermal-zones node
+
+The "thermal-zones" node is a container for all thermal zone nodes. It shall
+contain only sub-nodes describing thermal zones as in the section
+"Thermal zone nodes". The "thermal-zones" node appears under "/".
+
+* Examples
+
+Below are several examples on how to use thermal data descriptors
+using device tree bindings:
+
+(a) - CPU thermal zone
+
+The CPU thermal zone example below describes how to setup one thermal zone
+using one single sensor as temperature source and many cooling devices and
+power dissipation control sources.
+
+#include <dt-bindings/thermal/thermal.h>
+
+cpus {
+	/*
+	 * Here is an example of describing a cooling device for a DVFS
+	 * capable CPU. The CPU node describes its four OPPs.
+	 * The cooling states possible are 0..3, and they are
+	 * used as OPP indexes. The minimum cooling state is 0, which means
+	 * all four OPPs can be available to the system. The maximum
+	 * cooling state is 3, which means only the lowest OPPs (198MHz@0.85V)
+	 * can be available in the system.
+	 */
+	cpu0: cpu@0 {
+		...
+		operating-points = <
+			/* kHz    uV */
+			970000  1200000
+			792000  1100000
+			396000  950000
+			198000  850000
+		>;
+		cooling-min-state = <0>;
+		cooling-max-state = <3>;
+		#cooling-cells = <2>; /* min followed by max */
+	};
+	...
+};
+
+&i2c1 {
+	...
+	/*
+	 * A simple fan controller which supports 10 speeds of operation
+	 * (represented as 0-9).
+	 */
+	fan0: fan@0x48 {
+		...
+		cooling-min-state = <0>;
+		cooling-max-state = <9>;
+		#cooling-cells = <2>; /* min followed by max */
+	};
+};
+
+ocp {
+	...
+	/*
+	 * A simple IC with a single bandgap temperature sensor.
+	 */
+	bandgap0: bandgap@0x0000ED00 {
+		...
+		#thermal-sensor-cells = <0>;
+	};
+};
+
+thermal-zones {
+	cpu-thermal: cpu-thermal {
+		polling-delay-passive = <250>; /* milliseconds */
+		polling-delay = <1000>; /* milliseconds */
+
+		thermal-sensors = <&bandgap0>;
+
+		trips {
+			cpu-alert0: cpu-alert {
+				temperature = <90000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "active";
+			};
+			cpu-alert1: cpu-alert {
+				temperature = <100000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			cpu-crit: cpu-crit {
+				temperature = <125000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			map0 {
+				trip = <&cpu-alert0>;
+				cooling-device = <&fan0 THERMAL_NO_LIMITS 4>;
+			};
+			map1 {
+				trip = <&cpu-alert1>;
+				cooling-device = <&fan0 5 THERMAL_NO_LIMITS>;
+			};
+			map2 {
+				trip = <&cpu-alert1>;
+				cooling-device =
+				    <&cpu0 THERMAL_NO_LIMITS THERMAL_NO_LIMITS>;
+			};
+		};
+	};
+};
+
+In the example above, the ADC sensor (bandgap0) at address 0x0000ED00 is
+used to monitor the zone 'cpu-thermal' using its sole sensor. A fan
+device (fan0) is controlled via I2C bus 1, at address 0x48, and has ten
+different cooling states 0-9. It is used to remove the heat out of
+the thermal zone 'cpu-thermal' using its cooling states
+from its minimum to 4, when it reaches trip point 'cpu-alert0'
+at 90C, as an example of active cooling. The same cooling device is used at
+'cpu-alert1', but from 5 to its maximum state. The cpu@0 device is also
+linked to the same thermal zone, 'cpu-thermal', as a passive cooling device,
+using all its cooling states at trip point 'cpu-alert1',
+which is a trip point at 100C. On the thermal zone 'cpu-thermal', at the
+temperature of 125C, represented by the trip point 'cpu-crit', the silicon
+is not reliable anymore.
+
+(b) - IC with several internal sensors
+
+The example below describes how to deploy several thermal zones based off a
+single sensor IC, assuming it has several internal sensors. This is a common
+case on SoC designs with several internal IPs that may need different thermal
+requirements, and thus may have their own sensor to monitor or detect internal
+hotspots in their silicon.
+
+#include <dt-bindings/thermal/thermal.h>
+
+ocp {
+	...
+	/*
+	 * A simple IC with several bandgap temperature sensors.
+	 */
+	bandgap0: bandgap@0x0000ED00 {
+		...
+		#thermal-sensor-cells = <1>;
+	};
+};
+
+thermal-zones {
+	cpu-thermal: cpu-thermal {
+		polling-delay-passive = <250>; /* milliseconds */
+		polling-delay = <1000>; /* milliseconds */
+
+				/* sensor       ID */
+		thermal-sensors = <&bandgap0     0>;
+
+		trips {
+			/* each zone within the SoC may have its own trips */
+			cpu-alert: cpu-alert {
+				temperature = <100000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			cpu-crit: cpu-crit {
+				temperature = <125000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			/* each zone within the SoC may have its own cooling */
+			...
+		};
+	};
+
+	gpu-thermal: gpu-thermal {
+		polling-delay-passive = <120>; /* milliseconds */
+		polling-delay = <1000>; /* milliseconds */
+
+				/* sensor       ID */
+		thermal-sensors = <&bandgap0     1>;
+
+		trips {
+			/* each zone within the SoC may have its own trips */
+			gpu-alert: gpu-alert {
+				temperature = <90000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			gpu-crit: gpu-crit {
+				temperature = <105000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			/* each zone within the SoC may have its own cooling */
+			...
+		};
+	};
+
+	dsp-thermal: dsp-thermal {
+		polling-delay-passive = <50>; /* milliseconds */
+		polling-delay = <1000>; /* milliseconds */
+
+				/* sensor       ID */
+		thermal-sensors = <&bandgap0     2>;
+
+		trips {
+			/* each zone within the SoC may have its own trips */
+			dsp-alert: gpu-alert {
+				temperature = <90000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			dsp-crit: gpu-crit {
+				temperature = <135000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			/* each zone within the SoC may have its own cooling */
+			...
+		};
+	};
+};
+
+In the example above, there is one bandgap IC which has the capability to
+monitor three sensors. The hardware has been designed so that sensors are
+placed on different places in the DIE to monitor different temperature
+hotspots: one for CPU thermal zone, one for GPU thermal zone and the
+other to monitor a DSP thermal zone.
+
+Thus, there is a need to assign each sensor provided by the bandgap IC
+to different thermal zones. This is achieved by means of using the
+#thermal-sensor-cells property and using the first cell of the sensor
+specifier as sensor ID. In the example, then, <bandgap 0> is used to
+monitor CPU thermal zone, <bandgap 1> is used to monitor GPU thermal
+zone and <bandgap 2> is used to monitor DSP thermal zone. Each zone
+may be uncorrelated, having its own dT/dt requirements, trips
+and cooling maps.
+
+
+(c) - Several sensors within one single thermal zone
+
+The example below illustrates how to use more than one sensor within
+one thermal zone.
+
+#include <dt-bindings/thermal/thermal.h>
+
+&i2c1 {
+	...
+	/*
+	 * A simple IC with a single temperature sensor.
+	 */
+	adc: sensor@0x49 {
+		...
+		#thermal-sensor-cells = <0>;
+	};
+};
+
+ocp {
+	...
+	/*
+	 * A simple IC with a single bandgap temperature sensor.
+	 */
+	bandgap0: bandgap@0x0000ED00 {
+		...
+		#thermal-sensor-cells = <0>;
+	};
+};
+
+thermal-zones {
+	cpu-thermal: cpu-thermal {
+		polling-delay-passive = <250>; /* milliseconds */
+		polling-delay = <1000>; /* milliseconds */
+
+		thermal-sensors = <&bandgap0>,	/* cpu */
+				  <&adc>;	/* pcb north */
+
+		/* hotspot = 100 * bandgap - 120 * adc + 484 */
+		coefficients = 		<100	-120	484>;
+
+		trips {
+			...
+		};
+
+		cooling-maps {
+			...
+		};
+	};
+};
+
+In some cases, there is a need to use more than one sensor to extrapolate
+a thermal hotspot in the silicon. The above example illustrates this situation.
+For instance, it may be the case that a sensor external to CPU IP may be placed
+close to CPU hotspot and together with internal CPU sensor, it is used
+to determine the hotspot. Assuming this is the case for the above example,
+the hypothetical extrapolation rule would be:
+		hotspot = 100 * bandgap - 120 * adc + 484
+
+In other context, the same idea can be used to add fixed offset. For instance,
+consider the hotspot extrapolation rule below:
+		hotspot = 1 * adc + 6000
+
+In the above equation, the hotspot is always 6C higher than what is read
+from the ADC sensor. The binding would be then:
+        thermal-sensors =  <&adc>;
+
+		/* hotspot = 1 * adc + 6000 */
+	coefficients = 		<1	6000>;
+
+(d) - Board thermal
+
+The board thermal example below illustrates how to setup one thermal zone
+with many sensors and many cooling devices.
+
+#include <dt-bindings/thermal/thermal.h>
+
+&i2c1 {
+	...
+	/*
+	 * An IC with several temperature sensor.
+	 */
+	adc-dummy: sensor@0x50 {
+		...
+		#thermal-sensor-cells = <1>; /* sensor internal ID */
+	};
+};
+
+thermal-zones {
+	batt-thermal {
+		polling-delay-passive = <500>; /* milliseconds */
+		polling-delay = <2500>; /* milliseconds */
+
+				/* sensor       ID */
+		thermal-sensors = <&adc-dummy     4>;
+
+		trips {
+			...
+		};
+
+		cooling-maps {
+			...
+		};
+	};
+
+	board-thermal: board-thermal {
+		polling-delay-passive = <1000>; /* milliseconds */
+		polling-delay = <2500>; /* milliseconds */
+
+				/* sensor       ID */
+		thermal-sensors = <&adc-dummy     0>, /* pcb top edge */
+				  <&adc-dummy     1>, /* lcd */
+				  <&adc-dymmy     2>; /* back cover */
+		/*
+		 * An array of coefficients describing the sensor
+		 * linear relation. E.g.:
+		 * z = c1*x1 + c2*x2 + c3*x3
+		 */
+		coefficients =		<1200	-345	890>;
+
+		trips {
+			/* Trips are based on resulting linear equation */
+			cpu-trip: cpu-trip {
+				temperature = <60000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			gpu-trip: gpu-trip {
+				temperature = <55000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			}
+			lcd-trip: lcp-trip {
+				temperature = <53000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "passive";
+			};
+			crit-trip: crit-trip {
+				temperature = <68000>; /* millicelsius */
+				hysteresis = <2000>; /* millicelsius */
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			map0 {
+				trip = <&cpu-trip>;
+				cooling-device = <&cpu0 0 2>;
+				contribution = <55>;
+			};
+			map1 {
+				trip = <&gpu-trip>;
+				cooling-device = <&gpu0 0 2>;
+				contribution = <20>;
+			};
+			map2 {
+				trip = <&lcd-trip>;
+				cooling-device = <&lcd0 5 10>;
+				contribution = <15>;
+			};
+		};
+	};
+};
+
+The above example is a mix of previous examples, a sensor IP with several internal
+sensors used to monitor different zones, one of them is composed by several sensors and
+with different cooling devices.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fd8d0d594fc7..954eab8c7fec 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1372,8 +1372,8 @@ may allocate from based on an estimation of its current memory and swap use.
 For example, if a task is using all allowed memory, its badness score will be
 1000.  If it is using half of its allowed memory, its score will be 500.
 
-There is an additional factor included in the badness score: root
-processes are given 3% extra memory over other tasks.
+There is an additional factor included in the badness score: the current memory
+and swap usage is discounted by 3% for root processes.
 
 The amount of "allowed" memory depends on the context in which the oom killer
 was called.  If it is due to the memory assigned to the allocating task's cpuset
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index d55b8ab2d10f..babe2ef16139 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -24,6 +24,9 @@ Supported adapters:
   * Intel Lynx Point-LP (PCH)
   * Intel Avoton (SOC)
   * Intel Wellsburg (PCH)
+  * Intel Coleto Creek (PCH)
+  * Intel Wildcat Point-LP (PCH)
+  * Intel BayTrail (SOC)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index 5602eb71ad5d..e1ae127ed099 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -504,9 +504,12 @@ byte 5:
 * reg_10
 
    bit   7   6   5   4   3   2   1   0
-         0   0   0   0   0   0   0   A
+         0   0   0   0   R   F   T   A
 
          A: 1 = enable absolute tracking
+         T: 1 = enable two finger mode auto correct
+         F: 1 = disable ABS Position Filter
+         R: 1 = enable real hardware resolution
 
 6.2 Native absolute mode 6 byte packet format
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 050d37fe6d40..46ed73593465 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -315,7 +315,7 @@ Andrew Morton ã�Œ Linux-kernel メーリングリストã�«ã‚«ãƒ¼ãƒ�ルリリーã
 も��2.6.x.y カー�ル�存在���場����番��一番大�� 2.6.x �
 最新�安定版カー�ル��。
 
-2.6.x.y � "stable" �ーム <stable@kernel.org> �メンテ�れ��り�必
+2.6.x.y � "stable" �ーム <stable@vger.kernel.org> �メンテ�れ��り�必
 ��応��リリース�れ��。通常�リリース期間� 2週間毎����差�迫�
 ��題���れ�も�少�長��る��も�り��。セキュリティ関連��題
 �場���れ�対�������場�����リリース��れ��。
diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt
index 14265837c4ce..9dbda9b5d21e 100644
--- a/Documentation/ja_JP/stable_kernel_rules.txt
+++ b/Documentation/ja_JP/stable_kernel_rules.txt
@@ -50,16 +50,16 @@ linux-2.6.29/Documentation/stable_kernel_rules.txt
 
 -stable ツリー�パッ�を�付�る手続�-
 
- - 上記��則�従���る�を確���後��stable@kernel.org �パッ�
+ - 上記��則�従���る�を確���後��stable@vger.kernel.org �パッ�
    を�る。
  - �信者�パッ��キュー���付�られ�際�� ACK を��下�れ�場�
    �� NAK を���る。���応�開発者���スケジュール�よ���数
    日��る場���る。
  - も����られ�ら�パッ��他�開発者���関連�るサブシステム�
    メンテナー�よるレビュー���� -stable キュー�追加�れる。
- - パッ�� stable@kernel.org �アドレス�付加�れ��る������れ
+ - パッ�� stable@vger.kernel.org �アドレス�付加�れ��る������れ
    � Linus �ツリー�入る時�自動的� stable �ーム� email �れる。
- - セキュリティパッ����エイリアス (stable@kernel.org) ��られる�
+ - セキュリティパッ����エイリアス (stable@vger.kernel.org) ��られる�
    ������代�り� security@kernel.org �アドレス��られる。
 
 レビューサイクル-
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 2fe6e767b3d6..15b24a2be6b1 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1240,6 +1240,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			See comment before ip2_setup() in
 			drivers/char/ip2/ip2base.c.
 
+	irqaffinity=	[SMP] Set the default irq affinity mask
+			Format:
+			<cpu number>,...,<cpu number>
+			or
+			<cpu number>-<cpu number>
+			(must be a positive range in ascending order)
+			or a mixture
+			<cpu number>,...,<cpu number>-<cpu number>
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken
@@ -1456,6 +1465,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 			* dump_id: dump IDENTIFY data.
 
+			* atapi_dmadir: Enable ATAPI DMADIR bridge support
+
+			* disable: Disable this device.
+
 			If there are multiple matching configurations changing
 			the same attribute, the last one is used.
 
@@ -3341,6 +3354,21 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			that this also can be controlled per-workqueue for
 			workqueues visible under /sys/bus/workqueue/.
 
+	workqueue.power_efficient
+			Per-cpu workqueues are generally preferred because
+			they show better performance thanks to cache
+			locality; unfortunately, per-cpu workqueues tend to
+			be more power hungry than unbound workqueues.
+
+			Enabling this makes the per-cpu workqueues which
+			were observed to contribute significantly to power
+			consumption unbound, leading to measurably lower
+			power usage at the cost of small performance
+			overhead.
+
+			The default value of this parameter is determined by
+			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
new file mode 100644
index 000000000000..ea45dd3901e3
--- /dev/null
+++ b/Documentation/lzo.txt
@@ -0,0 +1,164 @@
+
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+
+  This is not a specification. No specification seems to be publicly available
+  for the LZO stream format. This document describes what input format the LZO
+  decompressor as implemented in the Linux kernel understands. The file subject
+  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+  the compressor nor on any other implementations though it seems likely that
+  the format matches the standard one. The purpose of this document is to
+  better understand what the code does in order to propose more efficient fixes
+  for future bug reports.
+
+Description
+
+  The stream is composed of a series of instructions, operands, and data. The
+  instructions consist in a few bits representing an opcode, and bits forming
+  the operands for the instruction, whose size and position depend on the
+  opcode and on the number of literals copied by previous instruction. The
+  operands are used to indicate :
+
+    - a distance when copying data from the dictionary (past output buffer)
+    - a length (number of bytes to copy from dictionary)
+    - the number of literals to copy, which is retained in variable "state"
+      as a piece of information for next instructions.
+
+  Optionally depending on the opcode and operands, extra data may follow. These
+  extra data can be a complement for the operand (eg: a length or a distance
+  encoded on larger values), or a literal to be copied to the output buffer.
+
+  The first byte of the block follows a different encoding from other bytes, it
+  seems to be optimized for literal use only, since there is no dictionary yet
+  prior to that byte.
+
+  Lengths are always encoded on a variable size starting with a small number
+  of bits in the operand. If the number of bits isn't enough to represent the
+  length, up to 255 may be added in increments by consuming more bytes with a
+  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+  around 255:1). The variable length encoding using #bits is always the same :
+
+       length = byte & ((1 << #bits) - 1)
+       if (!length) {
+               length = ((1 << #bits) - 1)
+               length += 255*(number of zero bytes)
+               length += first-non-zero-byte
+       }
+       length += constant (generally 2 or 3)
+
+  For references to the dictionary, distances are relative to the output
+  pointer. Distances are encoded using very few bits belonging to certain
+  ranges, resulting in multiple copy instructions using different encodings.
+  Certain encodings involve one extra byte, others involve two extra bytes
+  forming a little-endian 16-bit quantity (marked LE16 below).
+
+  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+  are copied before starting the next instruction. The number of literals that
+  were copied may change the meaning and behaviour of the next instruction. In
+  practice, only one instruction needs to know whether 0, less than 4, or more
+  literals were copied. This is the information stored in the <state> variable
+  in this implementation. This number of immediate literals to be copied is
+  generally encoded in the last two bits of the instruction but may also be
+  taken from the last two bits of an extra operand (eg: distance).
+
+  End of stream is declared when a block copy of distance 0 is seen. Only one
+  instruction may encode this distance (0001HLLL), it takes one LE16 operand
+  for the distance, thus requiring 3 bytes.
+
+  IMPORTANT NOTE : in the code some length checks are missing because certain
+  instructions are called under the assumption that a certain number of bytes
+  follow because it has already been garanteed before parsing the instructions.
+  They just have to "refill" this credit if they consume extra bytes. This is
+  an implementation design choice independant on the algorithm or encoding.
+
+Byte sequences
+
+  First byte encoding :
+
+      0..17   : follow regular instruction encoding, see below. It is worth
+                noting that codes 16 and 17 will represent a block copy from
+                the dictionary which is empty, and that they will always be
+                invalid at this place.
+
+      18..21  : copy 0..3 literals
+                state = (byte - 17) = 0..3  [ copy <state> literals ]
+                skip byte
+
+      22..255 : copy literal string
+                length = (byte - 17) = 4..238
+                state = 4 [ don't copy extra literals ]
+                skip byte
+
+  Instruction encoding :
+
+      0 0 0 0 X X X X  (0..15)
+        Depends on the number of literals copied by the last instruction.
+        If last instruction did not copy any literal (state == 0), this
+        encoding will be a copy of 4 or more literal, and must be interpreted
+        like this :
+
+           0 0 0 0 L L L L  (0..15)  : copy long literal string
+           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+           state = 4  (no extra literals are copied)
+
+        If last instruction used to copy between 1 to 3 literals (encoded in
+        the instruction's opcode or distance), the instruction is a copy of a
+        2-byte block from the dictionary within a 1kB distance. It is worth
+        noting that this instruction provides little savings since it uses 2
+        bytes to encode a copy of 2 other bytes but it encodes the number of
+        following literals for free. It must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
+           length = 2
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 1
+
+        If last instruction used to copy 4 or more literals (as detected by
+        state == 4), the instruction becomes a copy of a 3-byte block from the
+        dictionary from a 2..3kB distance, and must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
+           length = 3
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 2049
+
+      0 0 0 1 H L L L  (16..31)
+           Copy of a block within 16..48kB distance (preferably less than 10B)
+           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = 16384 + (H << 14) + D
+           state = S (copy S literals after this block)
+           End of stream is reached if distance == 16384
+
+      0 0 1 L L L L L  (32..63)
+           Copy of small block within 16kB distance (preferably less than 34B)
+           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = D + 1
+           state = S (copy S literals after this block)
+
+      0 1 L D D D S S  (64..127)
+           Copy 3-4 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 3 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+      1 L L D D D S S  (128..255)
+           Copy 5-8 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 5 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+Authors
+
+  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+  analysis of the decompression code available in Linux 3.16-rc5. The code is
+  tricky, it is possible that this document contains mistakes or that a few
+  corner cases were overlooked. In any case, please report any doubt, fix, or
+  proposed updates to the author(s) so that the document can be updated.
diff --git a/Documentation/mailbox.txt b/Documentation/mailbox.txt
new file mode 100644
index 000000000000..60f43ff629aa
--- /dev/null
+++ b/Documentation/mailbox.txt
@@ -0,0 +1,122 @@
+		The Common Mailbox Framework
+		Jassi Brar <jaswinder.singh@linaro.org>
+
+ This document aims to help developers write client and controller
+drivers for the API. But before we start, let us note that the
+client (especially) and controller drivers are likely going to be
+very platform specific because the remote firmware is likely to be
+proprietary and implement non-standard protocol. So even if two
+platforms employ, say, PL320 controller, the client drivers can't
+be shared across them. Even the PL320 driver might need to accommodate
+some platform specific quirks. So the API is meant mainly to avoid
+similar copies of code written for each platform. Having said that,
+nothing prevents the remote f/w to also be Linux based and use the
+same api there. However none of that helps us locally because we only
+ever deal at client's protocol level.
+ Some of the choices made during implementation are the result of this
+peculiarity of this "common" framework.
+
+
+
+	Part 1 - Controller Driver (See include/linux/mailbox_controller.h)
+
+ Allocate mbox_controller and the array of mbox_chan.
+Populate mbox_chan_ops, except peek_data() all are mandatory.
+The controller driver might know a message has been consumed
+by the remote by getting an IRQ or polling some hardware flag
+or it can never know (the client knows by way of the protocol).
+The method in order of preference is IRQ -> Poll -> None, which
+the controller driver should set via 'txdone_irq' or 'txdone_poll'
+or neither.
+
+
+	Part 2 - Client Driver (See include/linux/mailbox_client.h)
+
+ The client might want to operate in blocking mode (synchronously
+send a message through before returning) or non-blocking/async mode (submit
+a message and a callback function to the API and return immediately).
+
+
+struct demo_client {
+	struct mbox_client cl;
+	struct mbox_chan *mbox;
+	struct completion c;
+	bool async;
+	/* ... */
+};
+
+/*
+ * This is the handler for data received from remote. The behaviour is purely
+ * dependent upon the protocol. This is just an example.
+ */
+static void message_from_remote(struct mbox_client *cl, void *mssg)
+{
+	struct demo_client *dc = container_of(mbox_client,
+						struct demo_client, cl);
+	if (dc->aysnc) {
+		if (is_an_ack(mssg)) {
+			/* An ACK to our last sample sent */
+			return; /* Or do something else here */
+		} else { /* A new message from remote */
+			queue_req(mssg);
+		}
+	} else {
+		/* Remote f/w sends only ACK packets on this channel */
+		return;
+	}
+}
+
+static void sample_sent(struct mbox_client *cl, void *mssg, int r)
+{
+	struct demo_client *dc = container_of(mbox_client,
+						struct demo_client, cl);
+	complete(&dc->c);
+}
+
+static void client_demo(struct platform_device *pdev)
+{
+	struct demo_client *dc_sync, *dc_async;
+	/* The controller already knows async_pkt and sync_pkt */
+	struct async_pkt ap;
+	struct sync_pkt sp;
+
+	dc_sync = kzalloc(sizeof(*dc_sync), GFP_KERNEL);
+	dc_async = kzalloc(sizeof(*dc_async), GFP_KERNEL);
+
+	/* Populate non-blocking mode client */
+	dc_async->cl.dev = &pdev->dev;
+	dc_async->cl.rx_callback = message_from_remote;
+	dc_async->cl.tx_done = sample_sent;
+	dc_async->cl.tx_block = false;
+	dc_async->cl.tx_tout = 0; /* doesn't matter here */
+	dc_async->cl.knows_txdone = false; /* depending upon protocol */
+	dc_async->async = true;
+	init_completion(&dc_async->c);
+
+	/* Populate blocking mode client */
+	dc_sync->cl.dev = &pdev->dev;
+	dc_sync->cl.rx_callback = message_from_remote;
+	dc_sync->cl.tx_done = NULL; /* operate in blocking mode */
+	dc_sync->cl.tx_block = true;
+	dc_sync->cl.tx_tout = 500; /* by half a second */
+	dc_sync->cl.knows_txdone = false; /* depending upon protocol */
+	dc_sync->async = false;
+
+	/* ASync mailbox is listed second in 'mboxes' property */
+	dc_async->mbox = mbox_request_channel(&dc_async->cl, 1);
+	/* Populate data packet */
+	/* ap.xxx = 123; etc */
+	/* Send async message to remote */
+	mbox_send_message(dc_async->mbox, &ap);
+
+	/* Sync mailbox is listed first in 'mboxes' property */
+	dc_sync->mbox = mbox_request_channel(&dc_sync->cl, 0);
+	/* Populate data packet */
+	/* sp.abc = 123; etc */
+	/* Send message to remote in blocking mode */
+	mbox_send_message(dc_sync->mbox, &sp);
+	/* At this point 'sp' has been sent */
+
+	/* Now wait for async chan to be done */
+	wait_for_completion(&dc_async->c);
+}
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3458d6343e01..a59ee432a98f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -478,6 +478,15 @@ tcp_syn_retries - INTEGER
 tcp_timestamps - BOOLEAN
 	Enable timestamps as defined in RFC1323.
 
+tcp_min_tso_segs - INTEGER
+	Minimal number of segments per TSO frame.
+	Since linux-3.12, TCP does an automatic sizing of TSO frames,
+	depending on flow rate, instead of filling 64Kbytes packets.
+	For specific usages, it's possible to force TCP to build big
+	TSO frames. Note that TCP stack might split too big TSO packets
+	if available window is too small.
+	Default: 2
+
 tcp_tso_win_divisor - INTEGER
 	This allows control over what percentage of the congestion window
 	can be consumed by a single TSO frame.
@@ -562,9 +571,6 @@ tcp_limit_output_bytes - INTEGER
 	typical pfifo_fast qdiscs.
 	tcp_limit_output_bytes limits the number of bytes on qdisc
 	or device to reduce artificial RTT/cwnd and reduce bufferbloat.
-	Note: For GSO/TSO enabled flows, we try to have at least two
-	packets in flight. Reducing tcp_limit_output_bytes might also
-	reduce the size of individual GSO packet (64KB being the max)
 	Default: 131072
 
 tcp_challenge_ack_limit - INTEGER
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 23dd80e82b8e..0f4376ec8852 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -123,6 +123,16 @@ Transmission process is similar to capture as shown below.
 [shutdown]  close() --------> destruction of the transmission socket and
                               deallocation of all associated resources.
 
+Socket creation and destruction is also straight forward, and is done
+the same way as in capturing described in the previous paragraph:
+
+ int fd = socket(PF_PACKET, mode, 0);
+
+The protocol can optionally be 0 in case we only want to transmit
+via this socket, which avoids an expensive call to packet_rcv().
+In this case, you also need to bind(2) the TX_RING with sll_protocol = 0
+set. Otherwise, htons(ETH_P_ALL) or any other protocol, for example.
+
 Binding the socket to your network interface is mandatory (with zero copy) to
 know the header size of frames used in the circular buffer.
 
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 447fd4cd54ec..c8763806c65e 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -203,15 +203,8 @@ using a certain resistor value - pull up and pull down - so that the pin has a
 stable value when nothing is driving the rail it is connected to, or when it's
 unconnected.
 
-Pin configuration can be programmed either using the explicit APIs described
-immediately below, or by adding configuration entries into the mapping table;
-see section "Board/machine configuration" below.
-
-For example, a platform may do the following to pull up a pin to VDD:
-
-#include <linux/pinctrl/consumer.h>
-
-ret = pin_config_set("foo-dev", "FOO_GPIO_PIN", PLATFORM_X_PULL_UP);
+Pin configuration can be programmed by adding configuration entries into the
+mapping table; see section "Board/machine configuration" below.
 
 The format and meaning of the configuration parameter, PLATFORM_X_PULL_UP
 above, is entirely defined by the pin controller driver.
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac4749d..5d8675615e59 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ survive after a restart.
 
 1. Ramoops concepts
 
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into "record_size" chunks (also rounded down to
 power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners:
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 95731a08f257..8f08b2a71791 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV66/AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
-    HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+    i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+    Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index b0714d8f678a..8dfb6a5f427d 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 
 Procedure for submitting patches to the -stable tree:
 
+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+   submission guidelines as described in
+   Documentation/networking/netdev-FAQ.txt
  - Send the patch, after verifying that it follows the above rules, to
    stable@vger.kernel.org.  You must note the upstream commit ID in the
    changelog of your submission, as well as the kernel version you wish
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ccd42589e124..8d90c42e5db6 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -289,13 +289,24 @@ Default value is "/sbin/hotplug".
 kptr_restrict:
 
 This toggle indicates whether restrictions are placed on
-exposing kernel addresses via /proc and other interfaces.  When
-kptr_restrict is set to (0), there are no restrictions.  When
-kptr_restrict is set to (1), the default, kernel pointers
-printed using the %pK format specifier will be replaced with 0's
-unless the user has CAP_SYSLOG.  When kptr_restrict is set to
-(2), kernel pointers printed using %pK will be replaced with 0's
-regardless of privileges.
+exposing kernel addresses via /proc and other interfaces.
+
+When kptr_restrict is set to (0), the default, there are no restrictions.
+
+When kptr_restrict is set to (1), kernel pointers printed using the %pK
+format specifier will be replaced with 0's unless the user has CAP_SYSLOG
+and effective user and group ids are equal to the real ids. This is
+because %pK checks are done at read() time rather than open() time, so
+if permissions are elevated between the open() and the read() (e.g via
+a setuid binary) then %pK will not leak kernel pointers to unprivileged
+users. Note, this is a temporary solution only. The correct long-term
+solution is to do the permission checks at open() time. Consider removing
+world read permissions from files that use %pK, and using dmesg_restrict
+to protect against uses of %pK in dmesg(8) if leaking kernel pointer
+values to unprivileged users is a concern.
+
+When kptr_restrict is set to (2), kernel pointers printed using
+%pK will be replaced with 0's regardless of privileges.
 
 ==============================================================
 
@@ -427,6 +438,32 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
 
 ==============================================================
 
+perf_cpu_time_max_percent:
+
+Hints to the kernel how much CPU time it should be allowed to
+use to handle perf sampling events.  If the perf subsystem
+is informed that its samples are exceeding this limit, it
+will drop its sampling frequency to attempt to reduce its CPU
+usage.
+
+Some perf sampling happens in NMIs.  If these samples
+unexpectedly take too long to execute, the NMIs can become
+stacked up next to each other so much that nothing else is
+allowed to execute.
+
+0: disable the mechanism.  Do not monitor or correct perf's
+   sampling rate no matter how CPU time it takes.
+
+1-100: attempt to throttle perf's sample rate to this
+   percentage of CPU.  Note: the kernel calculates an
+   "expected" length of each sample event.  100 here means
+   100% of that expected length.  Even if this is set to
+   100, you may still see sample throttling if this
+   length is exceeded.  Set to 0 if you truly do not care
+   how much CPU is consumed.
+
+==============================================================
+
 
 pid_max:
 
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index a71bd5b90fe8..37c54863f611 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -142,6 +142,11 @@ temperature) and throttle appropriate devices.
     This is an optional feature where some platforms can choose not to
     provide this data.
     .governor_name: Name of the thermal governor used for this zone
+    .no_hwmon: a boolean to indicate if the thermal to hwmon sysfs interface
+               is required. when no_hwmon == false, a hwmon sysfs interface
+               will be created. when no_hwmon == true, nothing will be done.
+               In case the thermal_zone_params is NULL, the hwmon interface
+               will be created (for backward compatibility).
     .num_tbps: Number of thermal_bind_params entries for this zone
     .tbp: thermal_bind_params entries
 
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
new file mode 100644
index 000000000000..bba7dbfc49ed
--- /dev/null
+++ b/Documentation/trace/coresight.txt
@@ -0,0 +1,299 @@
+		Coresight - HW Assisted Tracing on ARM
+		======================================
+
+   Author:   Mathieu Poirier <mathieu.poirier@linaro.org>
+   Date:     September 11th, 2014
+
+Introduction
+------------
+
+Coresight is an umbrella of technologies allowing for the debugging of ARM
+based SoC.  It includes solutions for JTAG and HW assisted tracing.  This
+document is concerned with the latter.
+
+HW assisted tracing is becoming increasingly useful when dealing with systems
+that have many SoCs and other components like GPU and DMA engines.  ARM has
+developed a HW assisted tracing solution by means of different components, each
+being added to a design at systhesis time to cater to specific tracing needs.
+Compoments are generally categorised as source, link and sinks and are
+(usually) discovered using the AMBA bus.
+
+"Sources" generate a compressed stream representing the processor instruction
+path based on tracing scenarios as configured by users.  From there the stream
+flows through the coresight system (via ATB bus) using links that are connecting
+the emanating source to a sink(s).  Sinks serve as endpoints to the coresight
+implementation, either storing the compressed stream in a memory buffer or
+creating an interface to the outside world where data can be transferred to a
+host without fear of filling up the onboard coresight memory buffer.
+
+At typical coresight system would look like this:
+
+  *****************************************************************
+ **************************** AMBA AXI  ****************************===||
+  *****************************************************************    ||
+        ^                    ^                            |            ||
+        |                    |                            *            **
+     0000000    :::::     0000000    :::::    :::::    @@@@@@@    ||||||||||||
+     0 CPU 0<-->: C :     0 CPU 0<-->: C :    : C :    @ STM @    || System ||
+  |->0000000    : T :  |->0000000    : T :    : T :<--->@@@@@     || Memory ||
+  |  #######<-->: I :  |  #######<-->: I :    : I :      @@@<-|   ||||||||||||
+  |  # ETM #    :::::  |  # PTM #    :::::    :::::       @   |
+  |   #####      ^ ^   |   #####      ^ !      ^ !        .   |   |||||||||
+  | |->###       | !   | |->###       | !      | !        .   |   || DAP ||
+  | |   #        | !   | |   #        | !      | !        .   |   |||||||||
+  | |   .        | !   | |   .        | !      | !        .   |      |  |
+  | |   .        | !   | |   .        | !      | !        .   |      |  *
+  | |   .        | !   | |   .        | !      | !        .   |      | SWD/
+  | |   .        | !   | |   .        | !      | !        .   |      | JTAG
+  *****************************************************************<-|
+ *************************** AMBA Debug ABP ************************
+  *****************************************************************
+   |    .          !         .          !        !        .    |
+   |    .          *         .          *        *        .    |
+  *****************************************************************
+ ******************** Cross Trigger Matrix (CTM) *******************
+  *****************************************************************
+   |    .     ^              .                            .    |
+   |    *     !              *                            *    |
+  *****************************************************************
+ ****************** AMBA Advanced Trace Bus (ATB) ******************
+  *****************************************************************
+   |          !                        ===============         |
+   |          *                         ===== F =====<---------|
+   |   :::::::::                         ==== U ====
+   |-->:: CTI ::<!!                       === N ===
+   |   :::::::::  !                        == N ==
+   |    ^         *                        == E ==
+   |    !  &&&&&&&&&       IIIIIII         == L ==
+   |------>&& ETB &&<......II     I        =======
+   |    !  &&&&&&&&&       II     I           .
+   |    !                    I     I          .
+   |    !                    I REP I<..........
+   |    !                    I     I
+   |    !!>&&&&&&&&&       II     I           *Source: ARM ltd.
+   |------>& TPIU  &<......II    I            DAP = Debug Access Port
+           &&&&&&&&&       IIIIIII            ETM = Embedded Trace Macrocell
+               ;                              PTM = Program Trace Macrocell
+               ;                              CTI = Cross Trigger Interface
+               *                              ETB = Embedded Trace Buffer
+          To trace port                       TPIU= Trace Port Interface Unit
+                                              SWD = Serial Wire Debug
+
+While on target configuration of the components is done via the ABP bus,
+all trace data are carried out-of-band on the ATB bus.  The CTM provides
+a way to aggregate and distribute signals between CoreSight components.
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  This first implementation centers on
+the basic tracing functionality, enabling components such ETM/PTM, funnel,
+replicator, TMC, TPIU and ETB.  Future work will enable more
+intricate IP blocks such as STM and CTI.
+
+
+Acronyms and Classification
+---------------------------
+
+Acronyms:
+
+PTM:     Program Trace Macrocell
+ETM:     Embedded Trace Macrocell
+STM:     System trace Macrocell
+ETB:     Embedded Trace Buffer
+ITM:     Instrumentation Trace Macrocell
+TPIU:    Trace Port Interface Unit
+TMC-ETR: Trace Memory Controller, configured as Embedded Trace Router
+TMC-ETF: Trace Memory Controller, configured as Embedded Trace FIFO
+CTI:     Cross Trigger Interface
+
+Classification:
+
+Source:
+   ETMv3.x ETMv4, PTMv1.0, PTMv1.1, STM, STM500, ITM
+Link:
+   Funnel, replicator (intelligent or not), TMC-ETR
+Sinks:
+   ETBv1.0, ETB1.1, TPIU, TMC-ETF
+Misc:
+   CTI
+
+
+Device Tree Bindings
+----------------------
+
+See Documentation/devicetree/bindings/arm/coresight.txt for details.
+
+As of this writing drivers for ITM, STMs and CTIs are not provided but are
+expected to be added as the solution matures.
+
+
+Framework and implementation
+----------------------------
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  Any coresight compliant device can
+register with the framework for as long as they use the right APIs:
+
+struct coresight_device *coresight_register(struct coresight_desc *desc);
+void coresight_unregister(struct coresight_device *csdev);
+
+The registering function is taking a "struct coresight_device *csdev" and
+register the device with the core framework.  The unregister function takes
+a reference to a "strut coresight_device", obtained at registration time.
+
+If everything goes well during the registration process the new devices will
+show up under /sys/bus/coresight/devices, as showns here for a TC2 platform:
+
+root:~# ls /sys/bus/coresight/devices/
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:~#
+
+The functions take a "struct coresight_device", which looks like this:
+
+struct coresight_desc {
+        enum coresight_dev_type type;
+        struct coresight_dev_subtype subtype;
+        const struct coresight_ops *ops;
+        struct coresight_platform_data *pdata;
+        struct device *dev;
+        const struct attribute_group **groups;
+};
+
+
+The "coresight_dev_type" identifies what the device is, i.e, source link or
+sink while the "coresight_dev_subtype" will characterise that type further.
+
+The "struct coresight_ops" is mandatory and will tell the framework how to
+perform base operations related to the components, each component having
+a different set of requirement.  For that "struct coresight_ops_sink",
+"struct coresight_ops_link" and "struct coresight_ops_source" have been
+provided.
+
+The next field, "struct coresight_platform_data *pdata" is acquired by calling
+"of_get_coresight_platform_data()", as part of the driver's _probe routine and
+"struct device *dev" gets the device reference embedded in the "amba_device":
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ ...
+ ...
+ drvdata->dev = &adev->dev;
+ ...
+}
+
+Specific class of device (source, link, or sink) have generic operations
+that can be performed on them (see "struct coresight_ops").  The
+"**groups" is a list of sysfs entries pertaining to operations
+specific to that component only.  "Implementation defined" customisations are
+expected to be accessed and controlled using those entries.
+
+Last but not least, "struct module *owner" is expected to be set to reflect
+the information carried in "THIS_MODULE".
+
+How to use
+----------
+
+Before trace collection can start, a coresight sink needs to be identify.
+There is no limit on the amount of sinks (nor sources) that can be enabled at
+any given moment.  As a generic operation, all device pertaining to the sink
+class will have an "active" entry in sysfs:
+
+root:/sys/bus/coresight/devices# ls
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:/sys/bus/coresight/devices# ls 20010000.etb
+enable_sink  status  trigger_cntr
+root:/sys/bus/coresight/devices# echo 1 > 20010000.etb/enable_sink
+root:/sys/bus/coresight/devices# cat 20010000.etb/enable_sink
+1
+root:/sys/bus/coresight/devices#
+
+At boot time the current etm3x driver will configure the first address
+comparator with "_stext" and "_etext", essentially tracing any instruction
+that falls within that range.  As such "enabling" a source will immediately
+trigger a trace capture:
+
+root:/sys/bus/coresight/devices# echo 1 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices# cat 2201c000.ptm/enable_source
+1
+root:/sys/bus/coresight/devices# cat 20010000.etb/status
+Depth:          0x2000
+Status:         0x1
+RAM read ptr:   0x0
+RAM wrt ptr:    0x19d3   <----- The write pointer is moving
+Trigger cnt:    0x0
+Control:        0x1
+Flush status:   0x0
+Flush ctrl:     0x2001
+root:/sys/bus/coresight/devices#
+
+Trace collection is stopped the same way:
+
+root:/sys/bus/coresight/devices# echo 0 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices#
+
+The content of the ETB buffer can be harvested directly from /dev:
+
+root:/sys/bus/coresight/devices# dd if=/dev/20010000.etb \
+of=~/cstrace.bin
+
+64+0 records in
+64+0 records out
+32768 bytes (33 kB) copied, 0.00125258 s, 26.2 MB/s
+root:/sys/bus/coresight/devices#
+
+The file cstrace.bin can be decompressed using "ptm2human", DS-5 or Trace32.
+
+Following is a DS-5 output of an experimental loop that increments a variable up
+to a certain value.  The example is simple and yet provides a glimpse of the
+wealth of possibilities that coresight provides.
+
+Info                                    Tracing enabled
+Instruction     106378866       0x8026B53C      E52DE004        false   PUSH     {lr}
+Instruction     0       0x8026B540      E24DD00C        false   SUB      sp,sp,#0xc
+Instruction     0       0x8026B544      E3A03000        false   MOV      r3,#0
+Instruction     0       0x8026B548      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Timestamp                                       Timestamp: 17106715833
+Instruction     319     0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     9       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     10      0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     6       0x8026B560      EE1D3F30        false   MRC      p15,#0x0,r3,c13,c0,#1
+Instruction     0       0x8026B564      E1A0100D        false   MOV      r1,sp
+Instruction     0       0x8026B568      E3C12D7F        false   BIC      r2,r1,#0x1fc0
+Instruction     0       0x8026B56C      E3C2203F        false   BIC      r2,r2,#0x3f
+Instruction     0       0x8026B570      E59D1004        false   LDR      r1,[sp,#4]
+Instruction     0       0x8026B574      E59F0010        false   LDR      r0,[pc,#16] ; [0x8026B58C] = 0x80550368
+Instruction     0       0x8026B578      E592200C        false   LDR      r2,[r2,#0xc]
+Instruction     0       0x8026B57C      E59221D0        false   LDR      r2,[r2,#0x1d0]
+Instruction     0       0x8026B580      EB07A4CF        true    BL       {pc}+0x1e9344 ; 0x804548c4
+Info                                    Tracing enabled
+Instruction     13570831        0x8026B584      E28DD00C        false   ADD      sp,sp,#0xc
+Instruction     0       0x8026B588      E8BD8000        true    LDM      sp!,{pc}
+Timestamp                                       Timestamp: 17107041535
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1e6b6531bbcc..d2ba80bb7af5 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -55,6 +55,7 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
 sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		0458:7045	Genius Look 1320 V2
 sn9c20x		0458:704a	Genius Slim 1320
 sn9c20x		0458:704c	Genius i-Look 1321
 sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f75c9c..bd4370487b07 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO
index 7fba5aab9ef9..7599eb38b764 100644
--- a/Documentation/zh_CN/HOWTO
+++ b/Documentation/zh_CN/HOWTO
@@ -237,7 +237,7 @@ kernel.org网站的pub/linux/kernel/v2.6/目录下找到它。它的开��循
 如果没有2.6.x.y版本内核存在，那么最新的2.6.x版本内核就相当于是当�的稳定
 版内核。
 
-2.6.x.y版本由“稳定版��组（邮件地�<stable@kernel.org>）维护，一般隔周�
+2.6.x.y版本由“稳定版��组（邮件地�<stable@vger.kernel.org>）维护，一般隔周�
 布新版本。
 
 内核��中的Documentation/stable_kernel_rules.txt文件具体�述了�被稳定
diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt
index b5b9b0ab02fd..26ea5ed7cd9c 100644
--- a/Documentation/zh_CN/stable_kernel_rules.txt
+++ b/Documentation/zh_CN/stable_kernel_rules.txt
@@ -42,7 +42,7 @@ Documentation/stable_kernel_rules.txt 的中文翻译
 
 �稳定版代�树�交补�的过程：
 
-  - 在确认了补�符�以上的规则�，将补���到stable@kernel.org。
+  - 在确认了补�符�以上的规则�，将补���到stable@vger.kernel.org。
   - 如果补�被接�到队列里，��者会收到一个ACK回�，如果没有被接�，收
     到的是NAK回�。回�需�几天的时间，这�决于开�者的时间安排。
   - 被接�的补�会被加到稳定版本队列里，等待其他开�者的审查。
diff --git a/MAINTAINERS b/MAINTAINERS
index 823010fce98a..8a8a48b39cd8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -783,6 +783,14 @@ M:	Hubert Feurstein <hubert.feurstein@contec.at>
 S:	Maintained
 F:	arch/arm/mach-ep93xx/micro9.c
 
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/coresight/*
+F:	Documentation/trace/coresight.txt
+F:	Documentation/devicetree/bindings/arm/coresight.txt
+
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
 S:	Maintained
@@ -5161,6 +5169,14 @@ S:	Maintained
 F:	drivers/net/macvlan.c
 F:	include/linux/if_macvlan.h
 
+MAILBOX API
+M:	Jassi Brar <jassisinghbrar@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/mailbox/
+F:	include/linux/mailbox_client.h
+F:	include/linux/mailbox_controller.h
+
 MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7
 M:	Michael Kerrisk <mtk.manpages@gmail.com>
 W:	http://www.kernel.org/doc/man-pages
@@ -8082,6 +8098,7 @@ S:      Supported
 F:      drivers/thermal/
 F:      include/linux/thermal.h
 F:      include/linux/cpu_cooling.h
+F:      Documentation/devicetree/bindings/thermal/
 
 THINGM BLINK(1) USB RGB LED DRIVER
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
diff --git a/Makefile b/Makefile
index 25d38b79b3e0..7889b38766db 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 13
+SUBLEVEL = 65
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 
@@ -614,6 +614,8 @@ KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
 endif
 
+KBUILD_CFLAGS   += $(call cc-option, -fno-var-tracking-assignments)
+
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
 KBUILD_AFLAGS	+= -gdwarf-2
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132dd3507..98838a05ba6d 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	const struct exception_table_entry *fixup;
 	int fault, si_code = SEGV_MAPERR;
 	siginfo_t info;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (cause > 0 ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
 	   (or is suppressed by the PALcode).  Support that for older CPUs
@@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	if (address >= TASK_SIZE)
 		goto vmalloc_fault;
 #endif
-
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -142,6 +142,7 @@ retry:
 	} else {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	}
 
 	/* If for any reason at all we couldn't handle the fault,
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index ea16d782af58..398064cef746 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,13 +11,16 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <80000000>;	/* 80 MHZ */
+	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
 
 	chosen {
-		bootargs = "console=tty0 consoleblank=0";
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
 	};
 
 	aliases {
@@ -44,15 +47,14 @@
 		};
 
 		uart0: serial@c0000000 {
-			compatible = "snps,dw-apb-uart";
+			compatible = "ns8250";
 			reg = <0xc0000000 0x2000>;
 			interrupts = <11>;
-			#clock-frequency = <80000000>;
 			clock-frequency = <3686400>;
 			baud = <115200>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			status = "okay";
+			no-loopback-test = <1>;
 		};
 
 		pgu0: pgu@c9000000 {
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 446c96c24eff..00788e741ce7 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 442ce5d0f709..43de30256981 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -53,11 +53,10 @@ static inline void __udelay(unsigned long usecs)
 {
 	unsigned long loops;
 
-	/* (long long) cast ensures 64 bit MPY - real or emulated
+	/* (u64) cast ensures 64 bit MPY - real or emulated
 	 * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
 	 */
-	loops = ((long long)(usecs * 4295 * HZ) *
-		 (long long)(loops_per_jiffy)) >> 32;
+	loops = ((u64) usecs * 4295 * HZ * loops_per_jiffy) >> 32;
 
 	__delay(loops);
 }
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
index eac071668201..c29d56587bf0 100644
--- a/arch/arc/include/asm/irqflags.h
+++ b/arch/arc/include/asm/irqflags.h
@@ -137,13 +137,6 @@ static inline void arch_unmask_irq(unsigned int irq)
 	flag	\scratch
 .endm
 
-.macro IRQ_DISABLE_SAVE  scratch, save
-	lr	\scratch, [status32]
-	mov	\save, \scratch		/* Make a copy */
-	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-.endm
-
 .macro IRQ_ENABLE  scratch
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
index 4930957ca3d3..e897610c657a 100644
--- a/arch/arc/include/asm/kgdb.h
+++ b/arch/arc/include/asm/kgdb.h
@@ -19,7 +19,7 @@
  * register API yet */
 #undef DBG_MAX_REG_NUM
 
-#define GDB_MAX_REGS		39
+#define GDB_MAX_REGS		87
 
 #define BREAK_INSTR_SIZE	2
 #define CACHE_FLUSH_IS_SAFE	1
@@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void)
 
 extern void kgdb_trap(struct pt_regs *regs, int param);
 
-enum arc700_linux_regnums {
+/* This is the numbering of registers according to the GDB. See GDB's
+ * arc-tdep.h for details.
+ *
+ * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */
+enum arc_linux_regnums {
 	_R0		= 0,
 	_R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13,
 	_R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24,
 	_R25, _R26,
-	_BTA		= 27,
-	_LP_START	= 28,
-	_LP_END		= 29,
-	_LP_COUNT	= 30,
-	_STATUS32	= 31,
-	_BLINK		= 32,
-	_FP		= 33,
-	__SP		= 34,
-	_EFA		= 35,
-	_RET		= 36,
-	_ORIG_R8	= 37,
-	_STOP_PC	= 38
+	_FP		= 27,
+	__SP		= 28,
+	_R30		= 30,
+	_BLINK		= 31,
+	_LP_COUNT	= 60,
+	_STOP_PC	= 64,
+	_RET		= 64,
+	_LP_START	= 65,
+	_LP_END		= 66,
+	_STATUS32	= 67,
+	_ECR		= 76,
+	_BTA		= 82,
 };
 
 #else
diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h
index 6fc1159dfefe..764f1e3ba752 100644
--- a/arch/arc/include/asm/sections.h
+++ b/arch/arc/include/asm/sections.h
@@ -11,7 +11,6 @@
 
 #include <asm-generic/sections.h>
 
-extern char _int_vec_base_lds[];
 extern char __arc_dccm_base[];
 extern char __dtb_start[];
 
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index f158197ac5b0..b6a8c2dfbe6e 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	__asm__ __volatile__(
+	"	ex  %0, [%1]		\n"
+	: "+r" (tmp)
+	: "r"(&(lock->slock))
+	: "memory");
+
 	smp_mb();
 }
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 32420824375b..30c9baffa96f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
  * Because it essentially checks if buffer end is within limit and @len is
  * non-ngeative, which implies that buffer start will be within limit too.
  *
- * The reason for rewriting being, for majorit yof cases, @len is generally
+ * The reason for rewriting being, for majority of cases, @len is generally
  * compile time constant, causing first sub-expression to be compile time
  * subsumed.
  *
@@ -53,7 +53,7 @@
  *
  */
 #define __user_ok(addr, sz)	(((sz) <= TASK_SIZE) && \
-				 (((addr)+(sz)) <= get_fs()))
+				 ((addr) <= (get_fs() - (sz))))
 #define __access_ok(addr, sz)	(unlikely(__kernel_ok) || \
 				 likely(__user_ok((addr), (sz))))
 
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 30333cec0fef..ef9d79a3db25 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI__ASM_ARC_PTRACE_H
 #define _UAPI__ASM_ARC_PTRACE_H
 
+#define PTRACE_GET_THREAD_AREA	25
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 6dbe359c760d..6f3cd0fb4b54 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -589,11 +589,7 @@ ARC_ENTRY ret_from_exception
 	; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32
 	ld  r8, [sp, PT_status32]   ; returning to User/Kernel Mode
 
-#ifdef CONFIG_PREEMPT
 	bbit0  r8, STATUS_U_BIT, resume_kernel_mode
-#else
-	bbit0  r8, STATUS_U_BIT, restore_regs
-#endif
 
 	; Before returning to User mode check-for-and-complete any pending work
 	; such as rescheduling/signal-delivery etc.
@@ -653,10 +649,15 @@ resume_user_mode_begin:
 	b      resume_user_mode_begin	; unconditionally back to U mode ret chks
 					; for single exit point from this block
 
-#ifdef CONFIG_PREEMPT
-
 resume_kernel_mode:
 
+	; Disable Interrupts from this point on
+	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
+	IRQ_DISABLE	r9
+
+#ifdef CONFIG_PREEMPT
+
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
@@ -666,8 +667,6 @@ resume_kernel_mode:
 	ld  r9, [r10, THREAD_INFO_FLAGS]
 	bbit0  r9, TIF_NEED_RESCHED, restore_regs
 
-	IRQ_DISABLE	r9
-
 	; Invoke PREEMPTION
 	bl      preempt_schedule_irq
 
@@ -680,12 +679,11 @@ resume_kernel_mode:
 ;
 ; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
 ; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
 
 restore_regs :
 
-	; Disable Interrupts while restoring reg-file back
-	; XXX can this be optimised out
-	IRQ_DISABLE_SAVE    r9, r10	;@r10 has prisitine (pre-disable) copy
+	lr	r10, [status32]
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Restore User R25
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 006dec3fc353..0f944f024513 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -27,11 +27,16 @@ stext:
 	; Don't clobber r0-r4 yet. It might have bootloader provided info
 	;-------------------------------------------------------------------
 
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
 #ifdef CONFIG_SMP
 	; Only Boot (Master) proceeds. Others wait in platform dependent way
 	;	IDENTITY Reg [ 3  2  1  0 ]
 	;	(cpu-id)             ^^^	=> Zero for UP ARC700
 	;					=> #Core-ID if SMP (Master 0)
+	; Note that non-boot CPUs might not land here if halt-on-reset and
+	; instead breath life from @first_lines_of_secondary, but we still
+	; need to make sure only boot cpu takes this path.
 	GET_CPU_ID  r5
 	cmp	r5, 0
 	jnz	arc_platform_smp_wait_to_boot
@@ -96,6 +101,8 @@ stext:
 
 first_lines_of_secondary:
 
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
 	; setup per-cpu idle task as "current" on this CPU
 	ld	r0, [@secondary_idle_tsk]
 	SET_CURR_TASK_ON_CPU  r0, r1
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 8115fa531575..a199471ce01e 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -24,7 +24,6 @@
  * -Needed for each CPU (hence not foldable into init_IRQ)
  *
  * what it does ?
- * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000
  * -Disable all IRQs (on CPU side)
  * -Optionally, setup the High priority Interrupts as Level 2 IRQs
  */
@@ -32,8 +31,6 @@ void __cpuinit arc_init_IRQ(void)
 {
 	int level_mask = 0;
 
-	write_aux_reg(AUX_INTR_VEC_BASE, _int_vec_base_lds);
-
 	/* Disable all IRQs: enable them as devices request */
 	write_aux_reg(AUX_IENABLE, 0);
 
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index c6a81c58d0f3..f8a36ed9e0d5 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -92,7 +92,7 @@ static int genregs_set(struct task_struct *target,
 	REG_IN_CHUNK(scratch, callee, ptregs);	/* pt_regs[bta..orig_r8] */
 	REG_IN_CHUNK(callee, efa, cregs);	/* callee_regs[r25..r13] */
 	REG_IGNORE_ONE(efa);			/* efa update invalid */
-	REG_IN_ONE(stop_pc, &ptregs->ret);	/* stop_pc: PC update */
+	REG_IGNORE_ONE(stop_pc);			/* PC updated via @ret */
 
 	return ret;
 }
@@ -136,6 +136,10 @@ long arch_ptrace(struct task_struct *child, long request,
 	pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
 
 	switch (request) {
+	case PTRACE_GET_THREAD_AREA:
+		ret = put_user(task_thread_info(child)->thr_ptr,
+			       (unsigned long __user *)data);
+		break;
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		break;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index b2b3731dd1e9..2d7786b69a8a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,10 +47,7 @@ void __cpuinit read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 
 	cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR);
-
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
-	if (cpu->vec_base == 0)
-		cpu->vec_base = (unsigned int)_int_vec_base_lds;
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
 	cpu->uncached_base = uncached_space.start << 24;
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index ee6ef2f60a28..7e95e1a86510 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -101,7 +101,6 @@ SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct rt_sigframe __user *sf;
 	unsigned int magic;
-	int err;
 	struct pt_regs *regs = current_pt_regs();
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -119,15 +118,16 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
 		goto badframe;
 
-	err = restore_usr_regs(regs, sf);
-	err |= __get_user(magic, &sf->sigret_magic);
-	if (err)
+	if (__get_user(magic, &sf->sigret_magic))
 		goto badframe;
 
 	if (unlikely(is_do_ss_needed(magic)))
 		if (restore_altstack(&sf->uc.uc_stack))
 			goto badframe;
 
+	if (restore_usr_regs(regs, sf))
+		goto badframe;
+
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
@@ -191,6 +191,15 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info,
 		return 1;
 
 	/*
+	 * w/o SA_SIGINFO, struct ucontext is partially populated (only
+	 * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
+	 * during signal handler execution. This works for SA_SIGINFO as well
+	 * although the semantics are now overloaded (the same reg state can be
+	 * inspected by userland: but are they allowed to fiddle with it ?
+	 */
+	err |= stash_usr_regs(sf, regs, set);
+
+	/*
 	 * SA_SIGINFO requires 3 args to signal handler:
 	 *  #1: sig-no (common to any handler)
 	 *  #2: struct siginfo
@@ -213,14 +222,6 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info,
 		magic = MAGIC_SIGALTSTK;
 	}
 
-	/*
-	 * w/o SA_SIGINFO, struct ucontext is partially populated (only
-	 * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
-	 * during signal handler execution. This works for SA_SIGINFO as well
-	 * although the semantics are now overloaded (the same reg state can be
-	 * inspected by userland: but are they allowed to fiddle with it ?
-	 */
-	err |= stash_usr_regs(sf, regs, set);
 	err |= __put_user(magic, &sf->sigret_magic);
 	if (err)
 		return err;
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 4cd81633febd..116d3e09b5b5 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -233,6 +233,12 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
+
+		/* handle zero-overhead-loop */
+		if ((regs->ret == regs->lp_end) && (regs->lp_count)) {
+			regs->ret = regs->lp_start;
+			regs->lp_count--;
+		}
 	}
 
 	return 0;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 689ffd86d5e9..50533b750a99 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -16,7 +16,7 @@
 #include <linux/kdebug.h>
 #include <asm/pgalloc.h>
 
-static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address)
+static int handle_vmalloc_fault(unsigned long address)
 {
 	/*
 	 * Synchronize this task's top level page-table
@@ -26,7 +26,7 @@ static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address)
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
-	pgd = pgd_offset_fast(mm, address);
+	pgd = pgd_offset_fast(current->active_mm, address);
 	pgd_k = pgd_offset_k(address);
 
 	if (!pgd_present(*pgd_k))
@@ -59,8 +59,7 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
 	struct mm_struct *mm = tsk->mm;
 	siginfo_t info;
 	int fault, ret;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
@@ -72,7 +71,7 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
 	 * nothing more.
 	 */
 	if (address >= VMALLOC_START && address <= VMALLOC_END) {
-		ret = handle_vmalloc_fault(mm, address);
+		ret = handle_vmalloc_fault(address);
 		if (unlikely(ret))
 			goto bad_area_nosemaphore;
 		else
@@ -88,6 +87,8 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -115,12 +116,12 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
 
-survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -200,14 +201,12 @@ no_context:
 	die("Oops", regs, address, cause_code);
 
 out_of_memory:
-	if (is_global_init(tsk)) {
-		yield();
-		goto survive;
-	}
 	up_read(&mm->mmap_sem);
 
-	if (user_mode(regs))
-		do_group_exit(SIGKILL);	/* This will never return */
+	if (user_mode(regs)) {
+		pagefault_out_of_memory();
+		return;
+	}
 
 	goto no_context;
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 18a9f5ef643a..c1d6aa708ccd 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -4,6 +4,7 @@ config ARM
 	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU
@@ -474,6 +475,7 @@ config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select CPU_XSCALE
@@ -1494,6 +1496,109 @@ config SCHED_SMT
 	  MultiThreading at a cost of slightly increased overhead in some
 	  places. If unsure say N here.
 
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+	bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+	help
+	  Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+	  When turned on, this option adds sys/kernel/hmp directory which
+	  contains the following files:
+	  up_threshold - the load average threshold used for up migration
+	                 (0 - 1023)
+	  down_threshold - the load average threshold used for down migration
+	                 (0 - 1023)
+	  hmp_domains - a list of cpumasks for the present HMP domains,
+	                starting with the 'biggest' and ending with the
+	                'smallest'.
+	  Note that both the threshold files can be written at runtime to
+	  control scheduler behaviour.
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the load average period value
+	  for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  used for HMP migration. 'load_avg_period_ms' is the time in ms to
+	  reach a load average of 0.5 for an idle task of 0 load average
+	  ratio which becomes 100% busy.
+	  For example, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but removes intermediate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on SCHED_HMP && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1521,6 +1626,31 @@ config MCPM
 	  for (multi-)cluster based systems, such as big.LITTLE based
 	  systems.
 
+config BIG_LITTLE
+	bool "big.LITTLE support (Experimental)"
+	depends on CPU_V7 && SMP
+	select MCPM
+	help
+	  This option enables support for the big.LITTLE architecture.
+
+config BL_SWITCHER
+	bool "big.LITTLE switcher support"
+	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+	select CPU_PM
+	select ARM_CPU_SUSPEND
+	help
+	  The big.LITTLE "switcher" provides the core functionality to
+	  transparently handle transition between a cluster of A15's
+	  and a cluster of A7's in a big.LITTLE system.
+
+config BL_SWITCHER_DUMMY_IF
+	tristate "Simple big.LITTLE switcher user interface"
+	depends on BL_SWITCHER && DEBUG_KERNEL
+	help
+	  This is a simple and dummy char dev interface to control
+	  the big.LITTLE switcher core code.  It is meant for
+	  debugging purposes only.
+
 choice
 	prompt "Memory split"
 	default VMSPLIT_3G
@@ -1731,6 +1861,14 @@ config HW_PERF_EVENTS
 	  Enable hardware performance counter support for perf events. If
 	  disabled, perf events will use software events only.
 
+config SYS_SUPPORTS_HUGETLBFS
+       def_bool y
+       depends on ARM_LPAE
+
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       def_bool y
+       depends on ARM_LPAE
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 1d41908d5cda..5fdb6dbc5f89 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -669,14 +669,6 @@ config EARLY_PRINTK
 	  kernel low-level debugging functions. Add earlyprintk to your
 	  kernel parameters to enable this console.
 
-config OC_ETM
-	bool "On-chip ETM and ETB"
-	depends on ARM_AMBA
-	help
-	  Enables the on-chip embedded trace macrocell and embedded trace
-	  buffer driver that will allow you to collect traces of the
-	  kernel code.
-
 config ARM_KPROBES_TEST
 	tristate "Kprobes test module"
 	depends on KPROBES && MODULES
@@ -692,4 +684,70 @@ config PID_IN_CONTEXTIDR
 	  additional instructions during context switch. Say Y here only if you
 	  are planning to use hardware trace tools with this kernel.
 
+config DEBUG_SET_MODULE_RONX
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	---help---
+	  This option helps catch unintended modifications to loadable
+	  kernel module's text and read-only data. It also prevents execution
+	  of module data. Such protection may interfere with run-time code
+	  patching and dynamic kernel tracing - and they might also protect
+	  against certain classes of kernel exploits.
+	  If in doubt, say "N".
+
+menuconfig CORESIGHT
+	bool "CoreSight Tracing Support"
+	select ARM_AMBA
+	help
+	  This framework provides a kernel interface for the CoreSight debug
+	  and trace drivers to register themselves with. It's intended to build
+	  a topological view of the CoreSight components based on a DT
+	  specification and configure the right serie of components when a
+	  trace source gets enabled.
+
+if CORESIGHT
+config CORESIGHT_LINKS_AND_SINKS
+	bool "CoreSight Link and Sink drivers"
+	help
+	  This enables support for CoreSight link and sink drivers that are
+	  responsible for transporting and collecting the trace data
+	  respectively.  Link and sinks are dynamically aggregated with a trace
+	  entity at run time to form a complete trace path.
+
+config CORESIGHT_LINK_AND_SINK_TMC
+	bool "Coresight generic TMC driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Memory Controller driver.  Depending
+	  on its configuration the device can act as a link (embedded trace router
+	  - ETR) or sink (embedded trace FIFO).  The driver complies with the
+	  generic implementation of the component without special enhancement or
+	  added features.
+
+config CORESIGHT_SINK_TPIU
+	bool "Coresight generic TPIU driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Port Interface Unit driver, responsible
+	  for bridging the gap between the on-chip coresight components and a trace
+	  port collection engine, typically connected to an external host for use
+	  case capturing more traces than the on-board coresight memory can handle.
+
+config CORESIGHT_SINK_ETBV10
+	bool "Coresight ETBv1.0 driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Embedded Trace Buffer version 1.0 driver
+	  that complies with the generic implementation of the component without
+	  special enhancement or added features.
+
+config CORESIGHT_SOURCE_ETM3X
+	bool "CoreSight Embedded Trace Macrocell 3.x driver"
+	select CORESIGHT_LINKS_AND_SINKS
+	help
+	  This driver provides support for processor ETM3.x and PTM1.x modules,
+	  which allows tracing the instructions that a processor is executing
+	  This is primarily useful for instruction level tracing.  Depending
+	  the ETM version data tracing may also be available.
+endif
 endmenu
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 1ba358ba16b8..70bc19e2274f 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -16,6 +16,7 @@ LDFLAGS		:=
 LDFLAGS_vmlinux	:=-p --no-undefined -X
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
+LDFLAGS_MODULE	+= --be8
 endif
 
 OBJCOPYFLAGS	:=-O binary -R .comment -S
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 032a8d987148..f6e34be012ff 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -135,6 +135,7 @@ start:
 		.word	_edata			@ zImage end address
  THUMB(		.thumb			)
 1:
+ ARM_BE8(	setend	be )			@ go BE8 if compiled for BE8
 		mrs	r9, cpsr
 #ifdef CONFIG_ARM_VIRT_EXT
 		bl	__hyp_stub_install	@ get into SVC mode, reversibly
@@ -679,9 +680,7 @@ __armv4_mmu_cache_on:
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x0030
-#ifdef CONFIG_CPU_ENDIAN_BE8
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
 		bl	__common_mmu_cache_on
 		mov	r0, #0
 		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
@@ -708,9 +707,7 @@ __armv7_mmu_cache_on:
 		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
 						@ (needed for ARM1176)
 #ifdef CONFIG_MMU
-#ifdef CONFIG_CPU_ENDIAN_BE8
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
 		mrcne   p15, 0, r6, c2, c0, 2   @ read ttb control reg
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index f0895c581a89..00baf9f5766a 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -202,7 +202,14 @@ dtb-$(CONFIG_ARCH_VERSATILE) += versatile-ab.dtb \
 dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
 	vexpress-v2p-ca9.dtb \
 	vexpress-v2p-ca15-tc1.dtb \
-	vexpress-v2p-ca15_a7.dtb
+	vexpress-v2p-ca15_a7.dtb \
+	rtsm_ve-cortex_a9x2.dtb \
+	rtsm_ve-cortex_a9x4.dtb \
+	rtsm_ve-cortex_a15x1.dtb \
+	rtsm_ve-cortex_a15x2.dtb \
+	rtsm_ve-cortex_a15x4.dtb \
+	rtsm_ve-v2p-ca15x1-ca7x1.dtb \
+	rtsm_ve-v2p-ca15x4-ca7x4.dtb
 dtb-$(CONFIG_ARCH_VIRT) += xenvm-4.2.dtb
 dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \
 	wm8505-ref.dtb \
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 550eb772c30e..ddd068bb1457 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -51,7 +51,7 @@
 
 			coherency-fabric@20200 {
 				compatible = "marvell,coherency-fabric";
-				reg = <0x20200 0xb0>, <0x21810 0x1c>;
+				reg = <0x20200 0xb0>, <0x21010 0x1c>;
 			};
 
 			serial@12000 {
@@ -92,6 +92,7 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x72004 0x4>;
+				clocks = <&gateclk 4>;
 			};
 
 			ethernet@70000 {
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 76db557adbe7..f97550420fcc 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -124,7 +124,7 @@
 				/* Device Bus parameters are required */
 
 				/* Read parameters */
-				devbus,bus-width    = <8>;
+				devbus,bus-width    = <16>;
 				devbus,turn-off-ps  = <60000>;
 				devbus,badr-skew-ps = <0>;
 				devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index f8eaa383e07f..f94cdbc579cb 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -81,7 +81,7 @@
 			/*
 			 * MV78230 has 2 PCIe units Gen2.0: One unit can be
 			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
+			 * x1 only.
 			 */
 			pcie-controller {
 				compatible = "marvell,armada-xp-pcie";
@@ -94,10 +94,10 @@
 				bus-range = <0x00 0xff>;
 
 				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x42000 0x42000 0 0x00002000   /* Port 2.0 registers */
 					0x82000000 0 0x44000 0x44000 0 0x00002000   /* Port 0.1 registers */
 					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
 					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
+					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
 					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
 					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
 
@@ -165,19 +165,19 @@
 					status = "disabled";
 				};
 
-				pcie@9,0 {
+				pcie@5,0 {
 					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
+					assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+					reg = <0x2800 0 0 0 0>;
 					#address-cells = <3>;
 					#size-cells = <2>;
 					#interrupt-cells = <1>;
 					ranges;
 					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
+					interrupt-map = <0 0 0 0 &mpic 62>;
+					marvell,pcie-port = <1>;
 					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
+					clocks = <&gateclk 9>;
 					status = "disabled";
 				};
 			};
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index f4029f015aff..55cdd58c155f 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -101,7 +101,7 @@
 			/*
 			 * MV78260 has 3 PCIe units Gen2.0: Two units can be
 			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
+			 * x4 only.
 			 */
 			pcie-controller {
 				compatible = "marvell,armada-xp-pcie";
@@ -119,7 +119,9 @@
 					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
 					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
 					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
-					0x82000000 0 0x82000 0x82000 0 0x00002000   /* Port 3.0 registers */
+					0x82000000 0 0x84000 0x84000 0 0x00002000   /* Port 1.1 registers */
+					0x82000000 0 0x88000 0x88000 0 0x00002000   /* Port 1.2 registers */
+					0x82000000 0 0x8c000 0x8c000 0 0x00002000   /* Port 1.3 registers */
 					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
 					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
 
@@ -187,35 +189,83 @@
 					status = "disabled";
 				};
 
-				pcie@9,0 {
+				pcie@5,0 {
 					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
+					assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+					reg = <0x2800 0 0 0 0>;
 					#address-cells = <3>;
 					#size-cells = <2>;
 					#interrupt-cells = <1>;
 					ranges;
 					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
+					interrupt-map = <0 0 0 0 &mpic 62>;
+					marvell,pcie-port = <1>;
 					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
+					clocks = <&gateclk 9>;
+					status = "disabled";
+				};
+
+				pcie@6,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x84000 0 0x2000>;
+					reg = <0x3000 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 63>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <1>;
+					clocks = <&gateclk 10>;
+					status = "disabled";
+				};
+
+				pcie@7,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x88000 0 0x2000>;
+					reg = <0x3800 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 64>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <2>;
+					clocks = <&gateclk 11>;
 					status = "disabled";
 				};
 
-				pcie@10,0 {
+				pcie@8,0 {
 					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x82000 0 0x2000>;
-					reg = <0x5000 0 0 0 0>;
+					assigned-addresses = <0x82000800 0 0x8c000 0 0x2000>;
+					reg = <0x4000 0 0 0 0>;
 					#address-cells = <3>;
 					#size-cells = <2>;
 					#interrupt-cells = <1>;
 					ranges;
 					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 103>;
-					marvell,pcie-port = <3>;
+					interrupt-map = <0 0 0 0 &mpic 65>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <3>;
+					clocks = <&gateclk 12>;
+					status = "disabled";
+				};
+
+				pcie@9,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
+					reg = <0x4800 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 99>;
+					marvell,pcie-port = <2>;
 					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 27>;
+					clocks = <&gateclk 26>;
 					status = "disabled";
 				};
 			};
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index fdea75c73411..9746d0e7fcb4 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -152,7 +152,7 @@
 				/* Device Bus parameters are required */
 
 				/* Read parameters */
-				devbus,bus-width    = <8>;
+				devbus,bus-width    = <16>;
 				devbus,turn-off-ps  = <60000>;
 				devbus,badr-skew-ps = <0>;
 				devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index 1e12aeff403b..aa537ed13f0a 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -85,6 +85,8 @@
 			reg = <0x7e205000 0x1000>;
 			interrupts = <2 21>;
 			clocks = <&clk_i2c>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -93,6 +95,8 @@
 			reg = <0x7e804000 0x1000>;
 			interrupts = <2 21>;
 			clocks = <&clk_i2c>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi
new file mode 100644
index 000000000000..0b0ff6ead4b2
--- /dev/null
+++ b/arch/arm/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "VGA";
+			refresh		= <60>;
+			xres		= <640>;
+			yres		= <480>;
+			pixclock	= <39721>;
+			left_margin	= <40>;
+			right_margin	= <24>;
+			upper_margin	= <32>;
+			lower_margin	= <11>;
+			hsync_len	= <96>;
+			vsync_len	= <2>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+
+		panel@1 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/cros5250-common.dtsi b/arch/arm/boot/dts/cros5250-common.dtsi
index 3f0239ec1bc5..49d8da2779a6 100644
--- a/arch/arm/boot/dts/cros5250-common.dtsi
+++ b/arch/arm/boot/dts/cros5250-common.dtsi
@@ -27,6 +27,13 @@
 		i2c2_bus: i2c2-bus {
 			samsung,pin-pud = <0>;
 		};
+
+		max77686_irq: max77686-irq {
+			samsung,pins = "gpx3-2";
+			samsung,pin-function = <0>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
 	};
 
 	i2c@12C60000 {
@@ -35,6 +42,11 @@
 
 		max77686@09 {
 			compatible = "maxim,max77686";
+			interrupt-parent = <&gpx3>;
+			interrupts = <2 0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&max77686_irq>;
+			wakeup-source;
 			reg = <0x09>;
 
 			voltage-regulators {
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index 02cfc76d002f..b64cb43a7295 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -263,6 +263,7 @@
 					regulator-name = "vdd_g3d";
 					regulator-min-microvolt = <1000000>;
 					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
 					regulator-boot-on;
 					op_mode = <1>;
 				};
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index fc9fb3d526e2..cdbdc4dfef22 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -545,7 +545,7 @@
 			compatible = "arm,pl330", "arm,primecell";
 			reg = <0x10800000 0x1000>;
 			interrupts = <0 33 0>;
-			clocks = <&clock 271>;
+			clocks = <&clock 346>;
 			clock-names = "apb_pclk";
 			#dma-cells = <1>;
 			#dma-channels = <8>;
diff --git a/arch/arm/boot/dts/hip04.dtsi b/arch/arm/boot/dts/hip04.dtsi
new file mode 100644
index 000000000000..238814596a87
--- /dev/null
+++ b/arch/arm/boot/dts/hip04.dtsi
@@ -0,0 +1,984 @@
+/*
+ * Hisilicon Ltd. HiP04 SoC
+ *
+ * Copyright (C) 2013-2014 Hisilicon Ltd.
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ *
+ * Author: Haojian Zhuang <haojian.zhuang@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	/* memory bus is 64-bit */
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	bootwrapper {
+		compatible = "hisilicon,hip04-bootwrapper";
+		boot-method = <0x10c00000 0x10000>, <0xe0000100 0x1000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+				core2 {
+					cpu = <&CPU2>;
+				};
+				core3 {
+					cpu = <&CPU3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&CPU4>;
+				};
+				core1 {
+					cpu = <&CPU5>;
+				};
+				core2 {
+					cpu = <&CPU6>;
+				};
+				core3 {
+					cpu = <&CPU7>;
+				};
+			};
+			cluster2 {
+				core0 {
+					cpu = <&CPU8>;
+				};
+				core1 {
+					cpu = <&CPU9>;
+				};
+				core2 {
+					cpu = <&CPU10>;
+				};
+				core3 {
+					cpu = <&CPU11>;
+				};
+			};
+			cluster3 {
+				core0 {
+					cpu = <&CPU12>;
+				};
+				core1 {
+					cpu = <&CPU13>;
+				};
+				core2 {
+					cpu = <&CPU14>;
+				};
+				core3 {
+					cpu = <&CPU15>;
+				};
+			};
+		};
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+		CPU2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+		CPU3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+		CPU4: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x100>;
+		};
+		CPU5: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x101>;
+		};
+		CPU6: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x102>;
+		};
+		CPU7: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x103>;
+		};
+		CPU8: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x200>;
+		};
+		CPU9: cpu@201 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x201>;
+		};
+		CPU10: cpu@202 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x202>;
+		};
+		CPU11: cpu@203 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x203>;
+		};
+		CPU12: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x300>;
+		};
+		CPU13: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x301>;
+		};
+		CPU14: cpu@302 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x302>;
+		};
+		CPU15: cpu@303 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x303>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	clk_50m: clk_50m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <50000000>;
+	};
+
+	clk_168m: clk_168m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <168000000>;
+	};
+
+	clk_375m: clk_375m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <375000000>;
+	};
+
+	soc {
+		/* It's a 32-bit SoC. */
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges = <0 0 0xe0000000 0x10000000>;
+
+		gic: interrupt-controller@c01000 {
+			compatible = "hisilicon,hip04-intc";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			interrupts = <1 9 0xf04>;
+
+			reg = <0xc01000 0x1000>, <0xc02000 0x1000>,
+			      <0xc04000 0x2000>, <0xc06000 0x2000>;
+		};
+
+		sysctrl: sysctrl {
+			compatible = "hisilicon,sysctrl";
+			reg = <0x3e00000 0x00100000>;
+		};
+
+		fabric: fabric {
+			compatible = "hisilicon,hip04-fabric";
+			reg = <0x302a000 0x1000>;
+		};
+
+		dual_timer0: dual_timer@3000000 {
+			compatible = "arm,sp804", "arm,primecell";
+			reg = <0x3000000 0x1000>;
+			interrupts = <0 224 4>;
+			clocks = <&clk_50m>, <&clk_50m>;
+			clock-names = "apb_pclk";
+		};
+
+		arm-pmu {
+			compatible = "arm,cortex-a15-pmu";
+			interrupts = <0 64 4>,
+				     <0 65 4>,
+				     <0 66 4>,
+				     <0 67 4>,
+				     <0 68 4>,
+				     <0 69 4>,
+				     <0 70 4>,
+				     <0 71 4>,
+				     <0 72 4>,
+				     <0 73 4>,
+				     <0 74 4>,
+				     <0 75 4>,
+				     <0 76 4>,
+				     <0 77 4>,
+				     <0 78 4>,
+				     <0 79 4>;
+		};
+
+		uart0: uart@4007000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x4007000 0x1000>;
+			interrupts = <0 381 4>;
+			clocks = <&clk_168m>;
+			clock-names = "uartclk";
+			reg-shift = <2>;
+			status = "disabled";
+		};
+
+		sata0: sata@a000000 {
+			compatible = "hisilicon,hisi-ahci";
+			reg = <0xa000000 0x1000000>;
+			interrupts = <0 372 4>;
+		};
+
+	};
+
+	etb@0,e3c42000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c42000 0 0x1000>;
+
+		coresight-default-sink;
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb0_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator0_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3c82000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c82000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb1_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator1_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3cc2000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3cc2000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb2_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator2_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3d02000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3d02000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb3_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator3_out_port0>;
+			};
+		};
+	};
+
+	tpiu@0,e3c05000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0xe3c05000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&funnel4_out_port0>;
+			};
+		};
+	};
+
+	replicator0 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator0_out_port0: endpoint {
+					remote-endpoint = <&etb0_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator0_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port0>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel0_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator1 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator1_out_port0: endpoint {
+					remote-endpoint = <&etb1_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator1_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port1>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel1_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator2 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator2_out_port0: endpoint {
+					remote-endpoint = <&etb2_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+					replicator2_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port2>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel2_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator3 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator3_out_port0: endpoint {
+					remote-endpoint = <&etb3_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator3_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port3>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel3_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c41000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c41000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel0_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator0_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel0_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel0_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm2_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel0_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm3_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c81000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c81000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel1_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator1_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm4_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel1_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm5_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel1_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm6_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel1_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm7_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3cc1000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3cc1000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel2_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator2_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm8_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel2_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm9_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel2_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm10_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel2_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm11_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3d01000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3d01000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel3_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator3_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm12_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel3_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm13_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel3_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm14_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel3_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm15_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c04000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c04000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel4_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel4_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator0_out_port1>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel4_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator1_out_port1>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel4_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator2_out_port1>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel4_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator3_out_port1>;
+				};
+			};
+		};
+	};
+
+	ptm@0,e3c7c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU0>;
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3c7d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU1>;
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3c7e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU2>;
+		port {
+			ptm2_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3c7f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU3>;
+		port {
+			ptm3_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cbc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU4>;
+		port {
+			ptm4_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cbd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbd000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU5>;
+		port {
+			ptm5_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cbe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU6>;
+		port {
+			ptm6_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cbf000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbf000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU7>;
+		port {
+			ptm7_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cfc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU8>;
+		port {
+			ptm8_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cfd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfd000 0 0x1000>;
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU9>;
+		port {
+			ptm9_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cfe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU10>;
+		port {
+			ptm10_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cff000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cff000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU11>;
+		port {
+			ptm11_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3d3c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU12>;
+		port {
+			ptm12_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3d3d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU13>;
+		port {
+			ptm13_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3d3e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU14>;
+		port {
+			ptm14_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3d3f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU15>;
+		port {
+			ptm15_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port3>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index eb83aa039b8b..e524316998f4 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -71,7 +71,7 @@
 		ipu: ipu@18000000 {
 			#crtc-cells = <1>;
 			compatible = "fsl,imx53-ipu";
-			reg = <0x18000000 0x080000000>;
+			reg = <0x18000000 0x08000000>;
 			interrupts = <11 10>;
 			clocks = <&clks 59>, <&clks 110>, <&clks 61>;
 			clock-names = "bus", "di0", "di1";
diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts
index ff1aea0ee043..72693a69f830 100644
--- a/arch/arm/boot/dts/integratorcp.dts
+++ b/arch/arm/boot/dts/integratorcp.dts
@@ -9,11 +9,6 @@
 	model = "ARM Integrator/CP";
 	compatible = "arm,integrator-cp";
 
-	aliases {
-		arm,timer-primary = &timer2;
-		arm,timer-secondary = &timer1;
-	};
-
 	chosen {
 		bootargs = "root=/dev/ram0 console=ttyAMA0,38400n8 earlyprintk";
 	};
@@ -24,14 +19,18 @@
 	};
 
 	timer0: timer@13000000 {
+		/* TIMER0 runs @ 25MHz */
 		compatible = "arm,integrator-cp-timer";
+		status = "disabled";
 	};
 
 	timer1: timer@13000100 {
+		/* TIMER1 runs @ 1MHz */
 		compatible = "arm,integrator-cp-timer";
 	};
 
 	timer2: timer@13000200 {
+		/* TIMER2 runs @ 1MHz */
 		compatible = "arm,integrator-cp-timer";
 	};
 
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
new file mode 100644
index 000000000000..c9eee916aa7e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
@@ -0,0 +1,159 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x1CT
+ *
+ * RTSM_VE_Cortex_A15x1.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
new file mode 100644
index 000000000000..853a166e3c32
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
@@ -0,0 +1,165 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x2CT
+ *
+ * RTSM_VE_Cortex_A15x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
new file mode 100644
index 000000000000..c1947a3a5c88
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
@@ -0,0 +1,177 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ *
+ * RTSM_VE_Cortex_A15x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
new file mode 100644
index 000000000000..fca6b2f79677
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
@@ -0,0 +1,171 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx2CT
+ *
+ * RTSM_VE_Cortex_A9x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
new file mode 100644
index 000000000000..fd8a6ed97a04
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
@@ -0,0 +1,183 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx4CT
+ *
+ * RTSM_VE_Cortex_A9x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
new file mode 100644
index 000000000000..a2d895ee5faa
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
@@ -0,0 +1,231 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * Motherboard component
+ *
+ * VEMotherBoard.lisa
+ */
+
+	motherboard {
+		compatible = "arm,vexpress,v2m-p1", "simple-bus";
+		arm,hbi = <0x190>;
+		arm,vexpress,site = <0>;
+		arm,v2m-memory-map = "rs1";
+		#address-cells = <2>; /* SMB chipselect number and offset */
+		#size-cells = <1>;
+		#interrupt-cells = <1>;
+		ranges;
+
+		flash@0,00000000 {
+			compatible = "arm,vexpress-flash", "cfi-flash";
+			reg = <0 0x00000000 0x04000000>,
+			      <4 0x00000000 0x04000000>;
+			bank-width = <4>;
+		};
+
+		vram@2,00000000 {
+			compatible = "arm,vexpress-vram";
+			reg = <2 0x00000000 0x00800000>;
+		};
+
+		ethernet@2,02000000 {
+			compatible = "smsc,lan91c111";
+			reg = <2 0x02000000 0x10000>;
+			interrupts = <15>;
+		};
+
+		iofpga@3,00000000 {
+			compatible = "arm,amba-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 3 0 0x200000>;
+
+			v2m_sysreg: sysreg@010000 {
+				compatible = "arm,vexpress-sysreg";
+				reg = <0x010000 0x1000>;
+				gpio-controller;
+				#gpio-cells = <2>;
+			};
+
+			v2m_sysctl: sysctl@020000 {
+				compatible = "arm,sp810", "arm,primecell";
+				reg = <0x020000 0x1000>;
+				clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+				clock-names = "refclk", "timclk", "apb_pclk";
+				#clock-cells = <1>;
+				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+			};
+
+			aaci@040000 {
+				compatible = "arm,pl041", "arm,primecell";
+				reg = <0x040000 0x1000>;
+				interrupts = <11>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			mmci@050000 {
+				compatible = "arm,pl180", "arm,primecell";
+				reg = <0x050000 0x1000>;
+				interrupts = <9 10>;
+				cd-gpios = <&v2m_sysreg 0 0>;
+				wp-gpios = <&v2m_sysreg 1 0>;
+				max-frequency = <12000000>;
+				vmmc-supply = <&v2m_fixed_3v3>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "mclk", "apb_pclk";
+			};
+
+			kmi@060000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x060000 0x1000>;
+				interrupts = <12>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			kmi@070000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x070000 0x1000>;
+				interrupts = <13>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			v2m_serial0: uart@090000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x090000 0x1000>;
+				interrupts = <5>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial1: uart@0a0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0a0000 0x1000>;
+				interrupts = <6>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial2: uart@0b0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0b0000 0x1000>;
+				interrupts = <7>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial3: uart@0c0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0c0000 0x1000>;
+				interrupts = <8>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			wdt@0f0000 {
+				compatible = "arm,sp805", "arm,primecell";
+				reg = <0x0f0000 0x1000>;
+				interrupts = <0>;
+				clocks = <&v2m_refclk32khz>, <&smbclk>;
+				clock-names = "wdogclk", "apb_pclk";
+			};
+
+			v2m_timer01: timer@110000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x110000 0x1000>;
+				interrupts = <2>;
+				clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			v2m_timer23: timer@120000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x120000 0x1000>;
+				interrupts = <3>;
+				clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			rtc@170000 {
+				compatible = "arm,pl031", "arm,primecell";
+				reg = <0x170000 0x1000>;
+				interrupts = <4>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			clcd@1f0000 {
+				compatible = "arm,pl111", "arm,primecell";
+				reg = <0x1f0000 0x1000>;
+				interrupts = <14>;
+				clocks = <&v2m_oscclk1>, <&smbclk>;
+				clock-names = "v2m:oscclk1", "apb_pclk";
+				mode = "VGA";
+				use_dma = <0>;
+				framebuffer = <0x18000000 0x00180000>;
+			};
+
+			virtio_block@0130000 {
+				compatible = "virtio,mmio";
+				reg = <0x130000 0x200>;
+				interrupts = <42>;
+			};
+
+		};
+
+		v2m_fixed_3v3: fixedregulator@0 {
+			compatible = "regulator-fixed";
+			regulator-name = "3V3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
+		v2m_clk24mhz: clk24mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <24000000>;
+			clock-output-names = "v2m:clk24mhz";
+		};
+
+		v2m_refclk1mhz: refclk1mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <1000000>;
+			clock-output-names = "v2m:refclk1mhz";
+		};
+
+		v2m_refclk32khz: refclk32khz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "v2m:refclk32khz";
+		};
+
+		mcc {
+			compatible = "simple-bus";
+			arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+			v2m_oscclk1: osc@1 {
+				/* CLCD clock */
+				compatible = "arm,vexpress-osc";
+				arm,vexpress-sysreg,func = <1 1>;
+				freq-range = <23750000 63500000>;
+				#clock-cells = <0>;
+				clock-output-names = "v2m:oscclk1";
+			};
+
+			muxfpga@0 {
+				compatible = "arm,vexpress-muxfpga";
+				arm,vexpress-sysreg,func = <7 0>;
+			};
+
+			shutdown@0 {
+				compatible = "arm,vexpress-shutdown";
+				arm,vexpress-sysreg,func = <8 0>;
+			};
+		};
+	};
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
new file mode 100644
index 000000000000..fe8cf5dc8570
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
@@ -0,0 +1,244 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x1_A7x1.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x1-A7x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core1: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core1>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+
+		gic-cpuif@0 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <0>;
+			cpu = <&cpu0>;
+		};
+		gic-cpuif@1 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <1>;
+			cpu = <&cpu1>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
new file mode 100644
index 000000000000..f715285131d8
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
@@ -0,0 +1,358 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x4_A7x4.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x4-A7x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+				core2: core@2 {
+					reg = <2>;
+				};
+
+				core3: core@3 {
+					reg = <3>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core4: core@0 {
+					reg = <0>;
+				};
+
+				core5: core@1 {
+					reg = <1>;
+				};
+
+				core6: core@2 {
+					reg = <2>;
+				};
+				
+				core7: core@3 {
+					reg = <3>;
+				};
+				
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+			cluster = <&cluster0>;
+			core = <&core2>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+			cluster = <&cluster0>;
+			core = <&core3>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu4: cpu@4 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+
+		cpu5: cpu@5 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x101>;
+			cluster = <&cluster1>;
+			core = <&core5>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu6: cpu@6 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x102>;
+			cluster = <&cluster1>;
+			core = <&core6>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu7: cpu@7 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x103>;
+			cluster = <&cluster1>;
+			core = <&core7>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+
+		gic-cpuif@0 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <0>;
+			cpu = <&cpu0>;
+		};
+		gic-cpuif@1 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <1>;
+			cpu = <&cpu1>;
+		};
+		gic-cpuif@2 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <2>;
+			cpu = <&cpu2>;
+		};
+		gic-cpuif@3 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <3>;
+			cpu = <&cpu3>;
+		};
+		gic-cpuif@4 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <4>;
+			cpu = <&cpu4>;
+		};
+		gic-cpuif@5 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <5>;
+			cpu = <&cpu5>;
+		};
+		gic-cpuif@6 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <6>;
+			cpu = <&cpu6>;
+		};
+		gic-cpuif@7 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <7>;
+			cpu = <&cpu7>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index ac870fb3fa0d..9584232ee6b6 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -228,6 +228,7 @@
 			};
 
 			clcd@1f0000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f0000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index f1420368355b..6593398c11ae 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -227,6 +227,7 @@
 			};
 
 			clcd@1f000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 9420053acc14..cc6a8c0cfe33 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA15";
 	arm,hbi = <0x237>;
@@ -57,6 +59,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xff000000 0 0x01000000>;
 	};
 
 	memory-controller@2b0a0000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index d2803be4e1a8..f1dc620c5c45 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -9,11 +9,13 @@
 
 /dts-v1/;
 
+/memreserve/ 0xff000000 0x01000000;
+
 / {
 	model = "V2P-CA15_CA7";
 	arm,hbi = <0x249>;
 	arm,vexpress,site = <0xf>;
-	compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress";
+	compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic";
 	interrupt-parent = <&gic>;
 	#address-cells = <2>;
 	#size-cells = <2>;
@@ -29,44 +31,106 @@
 		i2c1 = &v2m_i2c_pcie;
 	};
 
-	cpus {
+	clusters {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster0: cluster@0 {
 			reg = <0>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+			};
 		};
 
-		cpu1: cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster1: cluster@1 {
 			reg = <1>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core2: core@0 {
+					reg = <0>;
+				};
+
+				core3: core@1 {
+					reg = <1>;
+				};
+
+				core4: core@2 {
+					reg = <2>;
+				};
+			};
 		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core2>;
+			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
 		};
 
 		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
+			cluster = <&cluster1>;
+			core = <&core3>;
+			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
 		};
 
 		cpu4: cpu@4 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
 		};
 	};
 
 	memory@80000000 {
 		device_type = "memory";
-		reg = <0 0x80000000 0 0x40000000>;
+		reg = <0 0x80000000 0 0x80000000>;
 	};
 
 	wdt@2a490000 {
@@ -81,6 +145,8 @@
 		compatible = "arm,hdlcd";
 		reg = <0 0x2b000000 0 0x1000>;
 		interrupts = <0 85 4>;
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xff000000 0 0x01000000>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
 	};
@@ -102,6 +168,64 @@
 		      <0 0x2c004000 0 0x2000>,
 		      <0 0x2c006000 0 0x2000>;
 		interrupts = <1 9 0xf04>;
+
+		gic-cpuif@0 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <0>;
+			cpu = <&cpu0>;
+		};
+		gic-cpuif@1 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <1>;
+			cpu = <&cpu1>;
+		};
+		gic-cpuif@2 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <2>;
+			cpu = <&cpu2>;
+		};
+
+		gic-cpuif@3 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <3>;
+			cpu = <&cpu3>;
+		};
+
+		gic-cpuif@4 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <4>;
+			cpu = <&cpu4>;
+		};
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	cci-pmu@2c099000 {
+		compatible = "arm,cci-400-pmu";
+		reg = <0 0x2c099000 0 0x6000>;
+		interrupts = <0 101 4>,
+			     <0 102 4>,
+			     <0 103 4>,
+			     <0 104 4>,
+			     <0 105 4>;
 	};
 
 	memory-controller@7ffd0000 {
@@ -125,6 +249,12 @@
 		clock-names = "apb_pclk";
 	};
 
+	spc@7fff0000 {
+		compatible = "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc";
+		reg = <0 0x7fff0000 0 0x1000>;
+		interrupts = <0 95 4>;
+	};
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts = <1 13 0xf08>,
@@ -133,12 +263,21 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
+		cluster  = <&cluster0>;
 		interrupts = <0 68 4>,
 			     <0 69 4>;
 	};
 
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		cluster  = <&cluster1>;
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+	};
+
 	oscclk6a: oscclk6a {
 		/* Reference 24MHz clock */
 		compatible = "fixed-clock";
@@ -147,6 +286,15 @@
 		clock-output-names = "oscclk6a";
 	};
 
+	psci {
+		compatible      = "arm,psci";
+		method          = "smc";
+		cpu_suspend     = <0x80100001>;
+		cpu_off         = <0x80100002>;
+		cpu_on          = <0x80100003>;
+		migrate         = <0x80100004>;
+	};
+
 	dcc {
 		compatible = "arm,vexpress,config-bus";
 		arm,vexpress,config-bridge = <&v2m_sysreg>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index c544a5504591..cf633ed6a1b4 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA5s";
 	arm,hbi = <0x225>;
@@ -59,6 +61,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk3>;
 		clock-names = "pxlclk";
+		mode = "640x480-16@60";
+		framebuffer = <0xbf000000 0x01000000>;
 	};
 
 	memory-controller@2a150000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 62d9b225dcce..f83706bd3f9a 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/include/ "clcd-panels.dtsi"
+
 / {
 	model = "V2P-CA9";
 	arm,hbi = <0x191>;
@@ -73,6 +75,8 @@
 		interrupts = <0 44 4>;
 		clocks = <&oscclk1>, <&oscclk2>;
 		clock-names = "clcdclk", "apb_pclk";
+		mode = "XVGA";
+		use_dma = <1>;
 	};
 
 	memory-controller@100e0000 {
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 48434cbe3e89..462cd580fc2d 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -14,5 +14,9 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+obj-$(CONFIG_BL_SWITCHER)	+= bL_switcher.o
+obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o
+
 AFLAGS_mcpm_head.o		:= -march=armv7-a
 AFLAGS_vlock.o			:= -march=armv7-a
+CFLAGS_REMOVE_mcpm_entry.o	= -pg
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
new file mode 100644
index 000000000000..8fee70dfb302
--- /dev/null
+++ b/arch/arm/common/bL_switcher.c
@@ -0,0 +1,864 @@
+/*
+ * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
+ *
+ * Created by:	Nicolas Pitre, March 2012
+ * Copyright:	(C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/atomic.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kthread.h>
+#include <linux/wait.h>
+#include <linux/time.h>
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/notifier.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/moduleparam.h>
+
+#include <asm/smp_plat.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/suspend.h>
+#include <asm/mcpm.h>
+#include <asm/bL_switcher.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power_cpu_migrate.h>
+
+
+/*
+ * Use our own MPIDR accessors as the generic ones in asm/cputype.h have
+ * __attribute_const__ and we don't want the compiler to assume any
+ * constness here as the value _does_ change along some code paths.
+ */
+
+static int read_mpidr(void)
+{
+	unsigned int id;
+	asm volatile ("mrc\tp15, 0, %0, c0, c0, 5" : "=r" (id));
+	return id & MPIDR_HWID_BITMASK;
+}
+
+/*
+ * Get a global nanosecond time stamp for tracing.
+ */
+static s64 get_ns(void)
+{
+	struct timespec ts;
+	getnstimeofday(&ts);
+	return timespec_to_ns(&ts);
+}
+
+/*
+ * bL switcher core code.
+ */
+
+static void bL_do_switch(void *_arg)
+{
+	unsigned ib_mpidr, ib_cpu, ib_cluster;
+	long volatile handshake, **handshake_ptr = _arg;
+
+	pr_debug("%s\n", __func__);
+
+	ib_mpidr = cpu_logical_map(smp_processor_id());
+	ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+	ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+	/* Advertise our handshake location */
+	if (handshake_ptr) {
+		handshake = 0;
+		*handshake_ptr = &handshake;
+	} else
+		handshake = -1;
+
+	/*
+	 * Our state has been saved at this point.  Let's release our
+	 * inbound CPU.
+	 */
+	mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume);
+	sev();
+
+	/*
+	 * From this point, we must assume that our counterpart CPU might
+	 * have taken over in its parallel world already, as if execution
+	 * just returned from cpu_suspend().  It is therefore important to
+	 * be very careful not to make any change the other guy is not
+	 * expecting.  This is why we need stack isolation.
+	 *
+	 * Fancy under cover tasks could be performed here.  For now
+	 * we have none.
+	 */
+
+	/*
+	 * Let's wait until our inbound is alive.
+	 */
+	while (!handshake) {
+		wfe();
+		smp_mb();
+	}
+
+	/* Let's put ourself down. */
+	mcpm_cpu_power_down();
+
+	/* should never get here */
+	BUG();
+}
+
+/*
+ * Stack isolation.  To ensure 'current' remains valid, we just use another
+ * piece of our thread's stack space which should be fairly lightly used.
+ * The selected area starts just above the thread_info structure located
+ * at the very bottom of the stack, aligned to a cache line, and indexed
+ * with the cluster number.
+ */
+#define STACK_SIZE 512
+extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+static int bL_switchpoint(unsigned long _arg)
+{
+	unsigned int mpidr = read_mpidr();
+	unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	void *stack = current_thread_info() + 1;
+	stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
+	stack += clusterid * STACK_SIZE + STACK_SIZE;
+	call_with_stack(bL_do_switch, (void *)_arg, stack);
+	BUG();
+}
+
+/*
+ * Generic switcher interface
+ */
+
+static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS];
+static int bL_switcher_cpu_pairing[NR_CPUS];
+
+/*
+ * bL_switch_to - Switch to a specific cluster for the current CPU
+ * @new_cluster_id: the ID of the cluster to switch to.
+ *
+ * This function must be called on the CPU to be switched.
+ * Returns 0 on success, else a negative status code.
+ */
+static int bL_switch_to(unsigned int new_cluster_id)
+{
+	unsigned int mpidr, this_cpu, that_cpu;
+	unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster;
+	struct completion inbound_alive;
+	struct tick_device *tdev;
+	enum clock_event_mode tdev_mode;
+	long volatile *handshake_ptr;
+	int ipi_nr, ret;
+
+	this_cpu = smp_processor_id();
+	ob_mpidr = read_mpidr();
+	ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0);
+	ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1);
+	BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr);
+
+	if (new_cluster_id == ob_cluster)
+		return 0;
+
+	that_cpu = bL_switcher_cpu_pairing[this_cpu];
+	ib_mpidr = cpu_logical_map(that_cpu);
+	ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+	ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+	pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n",
+		 this_cpu, ob_mpidr, ib_mpidr);
+
+	this_cpu = smp_processor_id();
+
+	/* Close the gate for our entry vectors */
+	mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL);
+	mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL);
+
+	/* Install our "inbound alive" notifier. */
+	init_completion(&inbound_alive);
+	ipi_nr = register_ipi_completion(&inbound_alive, this_cpu);
+	ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]);
+	mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr);
+
+	/*
+	 * Let's wake up the inbound CPU now in case it requires some delay
+	 * to come online, but leave it gated in our entry vector code.
+	 */
+	ret = mcpm_cpu_power_up(ib_cpu, ib_cluster);
+	if (ret) {
+		pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
+		return ret;
+	}
+
+	/*
+	 * Raise a SGI on the inbound CPU to make sure it doesn't stall
+	 * in a possible WFI, such as in bL_power_down().
+	 */
+	gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0);
+
+	/*
+	 * Wait for the inbound to come up.  This allows for other
+	 * tasks to be scheduled in the mean time.
+	 */
+	wait_for_completion(&inbound_alive);
+	mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0);
+
+	/*
+	 * From this point we are entering the switch critical zone
+	 * and can't sleep/schedule anymore.
+	 */
+	local_irq_disable();
+	local_fiq_disable();
+	trace_cpu_migrate_begin(get_ns(), ob_mpidr);
+
+	/* redirect GIC's SGIs to our counterpart */
+	gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
+
+	tdev = tick_get_device(this_cpu);
+	if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
+		tdev = NULL;
+	if (tdev) {
+		tdev_mode = tdev->evtdev->mode;
+		clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+	}
+
+	ret = cpu_pm_enter();
+
+	/* we can not tolerate errors at this point */
+	if (ret)
+		panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);
+
+	/*
+	 * Swap the physical CPUs in the logical map for this logical CPU.
+	 * This must be flushed to RAM as the resume code
+	 * needs to access it while the caches are still disabled.
+	 */
+	cpu_logical_map(this_cpu) = ib_mpidr;
+	cpu_logical_map(that_cpu) = ob_mpidr;
+	sync_cache_w(&cpu_logical_map(this_cpu));
+
+	/* Let's do the actual CPU switch. */
+	ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint);
+	if (ret > 0)
+		panic("%s: cpu_suspend() returned %d\n", __func__, ret);
+
+	/* We are executing on the inbound CPU at this point */
+	mpidr = read_mpidr();
+	pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr);
+	BUG_ON(mpidr != ib_mpidr);
+
+	mcpm_cpu_powered_up();
+
+	ret = cpu_pm_exit();
+
+	if (tdev) {
+		clockevents_set_mode(tdev->evtdev, tdev_mode);
+		clockevents_program_event(tdev->evtdev,
+					  tdev->evtdev->next_event, 1);
+	}
+
+	trace_cpu_migrate_finish(get_ns(), ib_mpidr);
+	local_fiq_enable();
+	local_irq_enable();
+
+	*handshake_ptr = 1;
+	dsb_sev();
+
+	if (ret)
+		pr_err("%s exiting with error %d\n", __func__, ret);
+	return ret;
+}
+
+struct bL_thread {
+	spinlock_t lock;
+	struct task_struct *task;
+	wait_queue_head_t wq;
+	int wanted_cluster;
+	struct completion started;
+	bL_switch_completion_handler completer;
+	void *completer_cookie;
+};
+
+static struct bL_thread bL_threads[NR_CPUS];
+
+static int bL_switcher_thread(void *arg)
+{
+	struct bL_thread *t = arg;
+	struct sched_param param = { .sched_priority = 1 };
+	int cluster;
+	bL_switch_completion_handler completer;
+	void *completer_cookie;
+
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+	complete(&t->started);
+
+	do {
+		if (signal_pending(current))
+			flush_signals(current);
+		wait_event_interruptible(t->wq,
+				t->wanted_cluster != -1 ||
+				kthread_should_stop());
+
+		spin_lock(&t->lock);
+		cluster = t->wanted_cluster;
+		completer = t->completer;
+		completer_cookie = t->completer_cookie;
+		t->wanted_cluster = -1;
+		t->completer = NULL;
+		spin_unlock(&t->lock);
+
+		if (cluster != -1) {
+			bL_switch_to(cluster);
+
+			if (completer)
+				completer(completer_cookie);
+		}
+	} while (!kthread_should_stop());
+
+	return 0;
+}
+
+static struct task_struct * bL_switcher_thread_create(int cpu, void *arg)
+{
+	struct task_struct *task;
+
+	task = kthread_create_on_node(bL_switcher_thread, arg,
+				      cpu_to_node(cpu), "kswitcher_%d", cpu);
+	if (!IS_ERR(task)) {
+		kthread_bind(task, cpu);
+		wake_up_process(task);
+	} else
+		pr_err("%s failed for CPU %d\n", __func__, cpu);
+	return task;
+}
+
+/*
+ * bL_switch_request_cb - Switch to a specific cluster for the given CPU,
+ *      with completion notification via a callback
+ *
+ * @cpu: the CPU to switch
+ * @new_cluster_id: the ID of the cluster to switch to.
+ * @completer: switch completion callback.  if non-NULL,
+ *	@completer(@completer_cookie) will be called on completion of
+ *	the switch, in non-atomic context.
+ * @completer_cookie: opaque context argument for @completer.
+ *
+ * This function causes a cluster switch on the given CPU by waking up
+ * the appropriate switcher thread.  This function may or may not return
+ * before the switch has occurred.
+ *
+ * If a @completer callback function is supplied, it will be called when
+ * the switch is complete.  This can be used to determine asynchronously
+ * when the switch is complete, regardless of when bL_switch_request()
+ * returns.  When @completer is supplied, no new switch request is permitted
+ * for the affected CPU until after the switch is complete, and @completer
+ * has returned.
+ */
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie)
+{
+	struct bL_thread *t;
+
+	if (cpu >= ARRAY_SIZE(bL_threads)) {
+		pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+		return -EINVAL;
+	}
+
+	t = &bL_threads[cpu];
+
+	if (IS_ERR(t->task))
+		return PTR_ERR(t->task);
+	if (!t->task)
+		return -ESRCH;
+
+	spin_lock(&t->lock);
+	if (t->completer) {
+		spin_unlock(&t->lock);
+		return -EBUSY;
+	}
+	t->completer = completer;
+	t->completer_cookie = completer_cookie;
+	t->wanted_cluster = new_cluster_id;
+	spin_unlock(&t->lock);
+	wake_up(&t->wq);
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_cb);
+
+/*
+ * Detach an outstanding switch request.
+ *
+ * The switcher will continue with the switch request in the background,
+ * but the completer function will not be called.
+ *
+ * This may be necessary if the completer is in a kernel module which is
+ * about to be unloaded.
+ */
+void bL_switch_request_detach(unsigned int cpu,
+			      bL_switch_completion_handler completer)
+{
+	struct bL_thread *t;
+
+	if (cpu >= ARRAY_SIZE(bL_threads)) {
+		pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+		return;
+	}
+
+	t = &bL_threads[cpu];
+
+	if (IS_ERR(t->task) || !t->task)
+		return;
+
+	spin_lock(&t->lock);
+	if (t->completer == completer)
+		t->completer = NULL;
+	spin_unlock(&t->lock);
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_detach);
+
+/*
+ * Activation and configuration code.
+ */
+
+static DEFINE_MUTEX(bL_switcher_activation_lock);
+static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier);
+static unsigned int bL_switcher_active;
+static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS];
+static cpumask_t bL_switcher_removed_logical_cpus;
+
+int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_register_notifier);
+
+int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier);
+
+static int bL_activation_notify(unsigned long val)
+{
+	int ret;
+       
+	ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL);
+	if (ret & NOTIFY_STOP_MASK)
+		pr_err("%s: notifier chain failed with status 0x%x\n",
+			__func__, ret);
+	return notifier_to_errno(ret);
+}
+
+static void bL_switcher_restore_cpus(void)
+{
+	int i;
+
+	for_each_cpu(i, &bL_switcher_removed_logical_cpus)
+		cpu_up(i);
+}
+
+static int bL_switcher_halve_cpus(void)
+{
+	int i, j, cluster_0, gic_id, ret;
+	unsigned int cpu, cluster, mask;
+	cpumask_t available_cpus;
+
+	/* First pass to validate what we have */
+	mask = 0;
+	for_each_online_cpu(i) {
+		cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+		cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+		if (cluster >= 2) {
+			pr_err("%s: only dual cluster systems are supported\n", __func__);
+			return -EINVAL;
+		}
+		if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER))
+			return -EINVAL;
+		mask |= (1 << cluster);
+	}
+	if (mask != 3) {
+		pr_err("%s: no CPU pairing possible\n", __func__);
+		return -EINVAL;
+	}
+
+	/*
+	 * Now let's do the pairing.  We match each CPU with another CPU
+	 * from a different cluster.  To get a uniform scheduling behavior
+	 * without fiddling with CPU topology and compute capacity data,
+	 * we'll use logical CPUs initially belonging to the same cluster.
+	 */
+	memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing));
+	cpumask_copy(&available_cpus, cpu_online_mask);
+	cluster_0 = -1;
+	for_each_cpu(i, &available_cpus) {
+		int match = -1;
+		cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+		if (cluster_0 == -1)
+			cluster_0 = cluster;
+		if (cluster != cluster_0)
+			continue;
+		cpumask_clear_cpu(i, &available_cpus);
+		for_each_cpu(j, &available_cpus) {
+			cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1);
+			/*
+			 * Let's remember the last match to create "odd"
+			 * pairing on purpose in order for other code not
+			 * to assume any relation between physical and
+			 * logical CPU numbers.
+			 */
+			if (cluster != cluster_0)
+				match = j;
+		}
+		if (match != -1) {
+			bL_switcher_cpu_pairing[i] = match;
+			cpumask_clear_cpu(match, &available_cpus);
+			pr_info("CPU%d paired with CPU%d\n", i, match);
+		}
+	}
+
+	/*
+	 * Now we disable the unwanted CPUs i.e. everything that has no
+	 * pairing information (that includes the pairing counterparts).
+	 */ 
+	cpumask_clear(&bL_switcher_removed_logical_cpus);
+	for_each_online_cpu(i) {
+		cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+		cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+
+		/* Let's take note of the GIC ID for this CPU */
+		gic_id = gic_get_cpu_id(i);
+		if (gic_id < 0) {
+			pr_err("%s: bad GIC ID for CPU %d\n", __func__, i);
+			bL_switcher_restore_cpus();
+			return -EINVAL;
+		}
+		bL_gic_id[cpu][cluster] = gic_id;
+		pr_info("GIC ID for CPU %u cluster %u is %u\n",
+			cpu, cluster, gic_id);
+
+		if (bL_switcher_cpu_pairing[i] != -1) {
+			bL_switcher_cpu_original_cluster[i] = cluster;
+			continue;
+		}
+
+		ret = cpu_down(i);
+		if (ret) {
+			bL_switcher_restore_cpus();
+			return ret;
+		}
+		cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus);
+	}
+
+	return 0;
+}
+
+/* Determine the logical CPU a given physical CPU is grouped on. */
+int bL_switcher_get_logical_index(u32 mpidr)
+{
+	int cpu;
+
+	if (!bL_switcher_active)
+		return -EUNATCH;
+
+	mpidr &= MPIDR_HWID_BITMASK;
+	for_each_online_cpu(cpu) {
+		int pairing = bL_switcher_cpu_pairing[cpu];
+		if (pairing == -1)
+			continue;
+		if ((mpidr == cpu_logical_map(cpu)) ||
+		    (mpidr == cpu_logical_map(pairing)))
+			return cpu;
+	}
+	return -EINVAL;
+}
+
+static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
+{
+	trace_cpu_migrate_current(get_ns(), read_mpidr());
+}
+
+int bL_switcher_trace_trigger(void)
+{
+	int ret;
+
+	preempt_disable();
+
+	bL_switcher_trace_trigger_cpu(NULL);
+	ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true);
+
+	preempt_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger);
+
+static int bL_switcher_enable(void)
+{
+	int cpu, ret;
+
+	mutex_lock(&bL_switcher_activation_lock);
+	cpu_hotplug_driver_lock();
+	if (bL_switcher_active) {
+		cpu_hotplug_driver_unlock();
+		mutex_unlock(&bL_switcher_activation_lock);
+		return 0;
+	}
+
+	pr_info("big.LITTLE switcher initializing\n");
+
+	ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE);
+	if (ret)
+		goto error;
+
+	ret = bL_switcher_halve_cpus();
+	if (ret)
+		goto error;
+
+	bL_switcher_trace_trigger();
+
+	for_each_online_cpu(cpu) {
+		struct bL_thread *t = &bL_threads[cpu];
+		spin_lock_init(&t->lock);
+		init_waitqueue_head(&t->wq);
+		init_completion(&t->started);
+		t->wanted_cluster = -1;
+		t->task = bL_switcher_thread_create(cpu, t);
+	}
+
+	bL_switcher_active = 1;
+	bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+	pr_info("big.LITTLE switcher initialized\n");
+	goto out;
+
+error:
+	pr_warning("big.LITTLE switcher initialization failed\n");
+	bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+	cpu_hotplug_driver_unlock();
+	mutex_unlock(&bL_switcher_activation_lock);
+	return ret;
+}
+
+#ifdef CONFIG_SYSFS
+
+static void bL_switcher_disable(void)
+{
+	unsigned int cpu, cluster;
+	struct bL_thread *t;
+	struct task_struct *task;
+
+	mutex_lock(&bL_switcher_activation_lock);
+	cpu_hotplug_driver_lock();
+
+	if (!bL_switcher_active)
+		goto out;
+
+	if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) {
+		bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+		goto out;
+	}
+
+	bL_switcher_active = 0;
+
+	/*
+	 * To deactivate the switcher, we must shut down the switcher
+	 * threads to prevent any other requests from being accepted.
+	 * Then, if the final cluster for given logical CPU is not the
+	 * same as the original one, we'll recreate a switcher thread
+	 * just for the purpose of switching the CPU back without any
+	 * possibility for interference from external requests.
+	 */
+	for_each_online_cpu(cpu) {
+		t = &bL_threads[cpu];
+		task = t->task;
+		t->task = NULL;
+		if (!task || IS_ERR(task))
+			continue;
+		kthread_stop(task);
+		/* no more switch may happen on this CPU at this point */
+		cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+		if (cluster == bL_switcher_cpu_original_cluster[cpu])
+			continue;
+		init_completion(&t->started);
+		t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu];
+		task = bL_switcher_thread_create(cpu, t);
+		if (!IS_ERR(task)) {
+			wait_for_completion(&t->started);
+			kthread_stop(task);
+			cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+			if (cluster == bL_switcher_cpu_original_cluster[cpu])
+				continue;
+		}
+		/* If execution gets here, we're in trouble. */
+		pr_crit("%s: unable to restore original cluster for CPU %d\n",
+			__func__, cpu);
+		pr_crit("%s: CPU %d can't be restored\n",
+			__func__, bL_switcher_cpu_pairing[cpu]);
+		cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu],
+				  &bL_switcher_removed_logical_cpus);
+	}
+
+	bL_switcher_restore_cpus();
+	bL_switcher_trace_trigger();
+
+	bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+	cpu_hotplug_driver_unlock();
+	mutex_unlock(&bL_switcher_activation_lock);
+}
+
+static ssize_t bL_switcher_active_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", bL_switcher_active);
+}
+
+static ssize_t bL_switcher_active_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	int ret;
+
+	switch (buf[0]) {
+	case '0':
+		bL_switcher_disable();
+		ret = 0;
+		break;
+	case '1':
+		ret = bL_switcher_enable();
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return (ret >= 0) ? count : ret;
+}
+
+static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	int ret = bL_switcher_trace_trigger();
+
+	return ret ? ret : count;
+}
+
+static struct kobj_attribute bL_switcher_active_attr =
+	__ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store);
+
+static struct kobj_attribute bL_switcher_trace_trigger_attr =
+	__ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store);
+
+static struct attribute *bL_switcher_attrs[] = {
+	&bL_switcher_active_attr.attr,
+	&bL_switcher_trace_trigger_attr.attr,
+	NULL,
+};
+
+static struct attribute_group bL_switcher_attr_group = {
+	.attrs = bL_switcher_attrs,
+};
+
+static struct kobject *bL_switcher_kobj;
+
+static int __init bL_switcher_sysfs_init(void)
+{
+	int ret;
+
+	bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj);
+	if (!bL_switcher_kobj)
+		return -ENOMEM;
+	ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group);
+	if (ret)
+		kobject_put(bL_switcher_kobj);
+	return ret;
+}
+
+#endif  /* CONFIG_SYSFS */
+
+bool bL_switcher_get_enabled(void)
+{
+	mutex_lock(&bL_switcher_activation_lock);
+
+	return bL_switcher_active;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_get_enabled);
+
+void bL_switcher_put_enabled(void)
+{
+	mutex_unlock(&bL_switcher_activation_lock);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_put_enabled);
+
+/*
+ * Veto any CPU hotplug operation while the switcher is active.
+ * We're just not ready to deal with that given the trickery involved.
+ */
+static int bL_switcher_hotplug_callback(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_DOWN_PREPARE:
+		if (bL_switcher_active)
+			return NOTIFY_BAD;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block bL_switcher_hotplug_notifier =
+        { &bL_switcher_hotplug_callback, NULL, 0 };
+
+#ifdef CONFIG_SCHED_HMP
+static bool no_bL_switcher = true;
+#else
+static bool no_bL_switcher;
+#endif
+core_param(no_bL_switcher, no_bL_switcher, bool, 0644);
+
+static int __init bL_switcher_init(void)
+{
+	int ret;
+
+	if (MAX_NR_CLUSTERS != 2) {
+		pr_err("%s: only dual cluster systems are supported\n", __func__);
+		return -EINVAL;
+	}
+
+	register_cpu_notifier(&bL_switcher_hotplug_notifier);
+
+	if (!no_bL_switcher) {
+		ret = bL_switcher_enable();
+		if (ret)
+			return ret;
+	}
+
+#ifdef CONFIG_SYSFS
+	ret = bL_switcher_sysfs_init();
+	if (ret)
+		pr_err("%s: unable to create sysfs entry\n", __func__);
+#endif
+
+	return 0;
+}
+
+late_initcall(bL_switcher_init);
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
new file mode 100644
index 000000000000..5e2dd197e728
--- /dev/null
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface
+ *
+ * Created by:	Nicolas Pitre, November 2012
+ * Copyright:	(C) 2012  Linaro Limited
+ *
+ * Dummy interface to user space for debugging purpose only.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <asm/uaccess.h>
+#include <asm/bL_switcher.h>
+
+static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
+			size_t len, loff_t *pos)
+{
+	unsigned char val[3];
+	unsigned int cpu, cluster;
+	int ret;
+
+	pr_debug("%s\n", __func__);
+
+	if (len < 3)
+		return -EINVAL;
+
+	if (copy_from_user(val, buf, 3))
+		return -EFAULT;
+
+	/* format: <cpu#>,<cluster#> */
+	if (val[0] < '0' || val[0] > '4' ||
+	    val[1] != ',' ||
+	    val[2] < '0' || val[2] > '1')
+		return -EINVAL;
+
+	cpu = val[0] - '0';
+	cluster = val[2] - '0';
+	ret = bL_switch_request(cpu, cluster);
+
+	return ret ? : len;
+}
+
+static const struct file_operations bL_switcher_fops = {
+	.write		= bL_switcher_write,
+	.owner	= THIS_MODULE,
+};
+
+static struct miscdevice bL_switcher_device = {
+        MISC_DYNAMIC_MINOR,
+        "b.L_switcher",
+        &bL_switcher_fops
+};
+
+static int __init bL_switcher_dummy_if_init(void)
+{
+	return misc_register(&bL_switcher_device);
+}
+
+static void __exit bL_switcher_dummy_if_exit(void)
+{
+	misc_deregister(&bL_switcher_device);
+}
+
+module_init(bL_switcher_dummy_if_init);
+module_exit(bL_switcher_dummy_if_exit);
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 370236dd1a03..4a2b32fd53a1 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
 	sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
 }
 
+extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
+
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val)
+{
+	unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
+	poke[0] = poke_phys_addr;
+	poke[1] = poke_val;
+	__cpuc_flush_dcache_area((void *)poke, 8);
+	outer_clean_range(__pa(poke), __pa(poke + 2));
+}
+
 static const struct mcpm_platform_ops *platform_ops;
 
 int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 8178705c4b24..0decb3c07165 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -15,6 +15,7 @@
 
 #include <linux/linkage.h>
 #include <asm/mcpm.h>
+#include <asm/assembler.h>
 
 #include "vlock.h"
 
@@ -47,6 +48,7 @@
 
 ENTRY(mcpm_entry_point)
 
+ ARM_BE8(setend        be)
  THUMB(	adr	r12, BSYM(1f)	)
  THUMB(	bx	r12		)
  THUMB(	.thumb			)
@@ -71,12 +73,19 @@ ENTRY(mcpm_entry_point)
 	 * position independent way.
 	 */
 	adr	r5, 3f
-	ldmia	r5, {r6, r7, r8, r11}
+	ldmia	r5, {r0, r6, r7, r8, r11}
+	add	r0, r5, r0			@ r0 = mcpm_entry_early_pokes
 	add	r6, r5, r6			@ r6 = mcpm_entry_vectors
 	ldr	r7, [r5, r7]			@ r7 = mcpm_power_up_setup_phys
 	add	r8, r5, r8			@ r8 = mcpm_sync
 	add	r11, r5, r11			@ r11 = first_man_locks
 
+	@ Perform an early poke, if any
+	add	r0, r0, r4, lsl #3
+	ldmia	r0, {r0, r1}
+	teq	r0, #0
+	strne	r1, [r0]
+
 	mov	r0, #MCPM_SYNC_CLUSTER_SIZE
 	mla	r8, r0, r10, r8			@ r8 = sync cluster base
 
@@ -195,7 +204,8 @@ mcpm_entry_gated:
 
 	.align	2
 
-3:	.word	mcpm_entry_vectors - .
+3:	.word	mcpm_entry_early_pokes - .
+	.word	mcpm_entry_vectors - 3b
 	.word	mcpm_power_up_setup_phys - 3b
 	.word	mcpm_sync - 3b
 	.word	first_man_locks - 3b
@@ -214,6 +224,10 @@ first_man_locks:
 ENTRY(mcpm_entry_vectors)
 	.space	4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
 
+	.type	mcpm_entry_early_pokes, #object
+ENTRY(mcpm_entry_early_pokes)
+	.space	8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
 	.type	mcpm_power_up_setup_phys, #object
 ENTRY(mcpm_power_up_setup_phys)
 	.space  4		@ set by mcpm_sync_init()
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 2e67a272df70..adb9aa5c88c7 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,6 +1,7 @@
 CONFIG_EXPERIMENTAL=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BLK_DEV_INITRD=y
 CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_ARMADA_370=y
 CONFIG_ARCH_SIRF=y
@@ -22,6 +23,7 @@ CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_HIGHPTE=y
 CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_NET=y
@@ -46,6 +48,8 @@ CONFIG_SERIAL_SIRFSOC=y
 CONFIG_SERIAL_SIRFSOC_CONSOLE=y
 CONFIG_SERIAL_VT8500=y
 CONFIG_SERIAL_VT8500_CONSOLE=y
+CONFIG_SERIAL_XILINX_PS_UART=y
+CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_IPMI_HANDLER=y
 CONFIG_IPMI_SI=y
 CONFIG_I2C=y
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 19d6cd6f29f9..3a14ea8fe97e 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -148,7 +148,7 @@ AES_Te:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_encrypt)
-	sub	r3,pc,#8		@ AES_encrypt
+	adr	r3,AES_encrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
@@ -381,7 +381,7 @@ _armv4_AES_encrypt:
 .align	5
 ENTRY(private_AES_set_encrypt_key)
 _armv4_AES_set_encrypt_key:
-	sub	r3,pc,#8		@ AES_set_encrypt_key
+	adr	r3,_armv4_AES_set_encrypt_key
 	teq	r0,#0
 	moveq	r0,#-1
 	beq	.Labrt
@@ -843,7 +843,7 @@ AES_Td:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_decrypt)
-	sub	r3,pc,#8		@ AES_decrypt
+	adr	r3,AES_decrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index accefe099182..4b26d14e41b3 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -17,7 +17,8 @@ int arch_timer_arch_init(void);
  * nicely work out which register we want, and chuck away the rest of
  * the code. At least it does so with a recent GCC (4.6.3).
  */
-static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
@@ -28,9 +29,7 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
 			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
 			break;
 		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
@@ -44,7 +43,8 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
 	isb();
 }
 
-static inline u32 arch_timer_reg_read(const int access, const int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
 	u32 val = 0;
 
@@ -57,9 +57,7 @@ static inline u32 arch_timer_reg_read(const int access, const int reg)
 			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
 			break;
 		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
@@ -89,17 +87,43 @@ static inline u64 arch_counter_get_cntvct(void)
 	return cval;
 }
 
-static inline void __cpuinit arch_counter_set_user_access(void)
+static inline u32 arch_timer_get_cntkctl(void)
 {
 	u32 cntkctl;
-
 	asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
+	return cntkctl;
+}
 
-	/* disable user access to everything */
-	cntkctl &= ~((3 << 8) | (7 << 0));
-
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
 	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
 }
+
+static inline void __cpuinit arch_counter_set_user_access(void)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	/* Disable user access to both physical/virtual counters/timers */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_VCT_ACCESS_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+	arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+	/* Set the divider and enable virtual event stream */
+	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+			| ARCH_TIMER_VIRT_EVT_EN;
+	arch_timer_set_cntkctl(cntkctl);
+	elf_hwcap |= HWCAP_EVTSTRM;
+}
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index cab788045029..f0963bb79935 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -53,6 +53,13 @@
 #define put_byte_3      lsl #0
 #endif
 
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
 /*
  * Data preload for architectures that support it
  */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index da1c77d39327..6447a0b7b127 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -301,8 +301,8 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_add\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -320,8 +320,8 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -341,8 +341,8 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_sub\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -360,8 +360,8 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -428,9 +428,9 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, #1\n"
-"	sbc	%H0, %H0, #0\n"
-"	teq	%H0, #0\n"
+"	subs	%Q0, %Q0, #1\n"
+"	sbc	%R0, %R0, #0\n"
+"	teq	%R0, #0\n"
 "	bmi	2f\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
@@ -459,8 +459,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 "	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %6\n"
-"	adc	%H0, %H0, %H6\n"
+"	adds	%Q0, %Q0, %Q6\n"
+"	adc	%R0, %R0, %R6\n"
 "	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 000000000000..482383b45c91
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,83 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+	return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+#ifdef CONFIG_BL_SWITCHER
+
+void bL_switch_request_detach(unsigned int cpu,
+			      bL_switch_completion_handler completer);
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled.  Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled().  These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static void bL_switch_request_detach(unsigned int cpu,
+				     bL_switch_completion_handler completer) { }
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 7af5c6c3653a..b274bde24905 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -2,6 +2,8 @@
 #define _ASMARM_BUG_H
 
 #include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_BUG
 
@@ -12,10 +14,10 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 #define BUG_INSTR_VALUE 0xde02
-#define BUG_INSTR_TYPE ".hword "
+#define BUG_INSTR(__value) __inst_thumb16(__value)
 #else
 #define BUG_INSTR_VALUE 0xe7f001f2
-#define BUG_INSTR_TYPE ".word "
+#define BUG_INSTR(__value) __inst_arm(__value)
 #endif
 
 
@@ -33,7 +35,7 @@
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
+	asm volatile("1:\t" BUG_INSTR(__value) "\n"  \
 		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
@@ -48,7 +50,7 @@ do {								\
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile(BUG_INSTR_TYPE #__value);			\
+	asm volatile(BUG_INSTR(__value) "\n");			\
 	unreachable();						\
 } while (0)
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 17d0ae8672fa..2059f019bef4 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -212,6 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 static inline void __flush_icache_all(void)
 {
 	__flush_icache_preferred();
+	dsb();
 }
 
 /*
@@ -436,4 +437,50 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 #define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
 #define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
 
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ *   however some exceptions may exist.  Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ *   fp is preserved to the stack explicitly prior disabling the cache
+ *   since adding it to the clobber list is incompatible with having
+ *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
+ *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+	asm volatile( \
+	"stmfd	sp!, {fp, ip} \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
+	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
+	"isb	\n\t" \
+	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
+	"clrex	\n\t" \
+	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
+	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
+	"isb	\n\t" \
+	"dsb	\n\t" \
+	"ldmfd	sp!, {fp, ip}" \
+	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+	      "r9","r10","lr","memory" )
+
 #endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 1f3262e99d81..cedd3721318b 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -61,6 +61,20 @@ static inline void set_cr(unsigned int val)
 	isb();
 }
 
+static inline unsigned int get_auxcr(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 1	@ get AUXCR" : "=r" (val));
+	return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 1	@ set AUXCR"
+	  : : "r" (val));
+	isb();
+}
+
 #ifndef CONFIG_SMP
 extern void adjust_cr(unsigned long mask, unsigned long set);
 #endif
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index fe92ccf1d0b0..a66061aef29c 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -156,7 +156,7 @@
 		/* Select the best insn combination to perform the   */	\
 		/* actual __m * __n / (__p << 64) operation.         */	\
 		if (!__c) {						\
-			asm (	"umull	%Q0, %R0, %1, %Q2\n\t"		\
+			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
 				"mov	%Q0, #0"			\
 				: "=&r" (__res)				\
 				: "r" (__m), "r" (__n)			\
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index f89515adac60..39eb16b0066f 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,15 +52,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index e42cf597f6e6..2aff798fbef4 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -3,11 +3,6 @@
 
 #ifdef __KERNEL__
 
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
@@ -164,6 +159,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 2740c2a2df63..3d7351c844aa 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	6
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
deleted file mode 100644
index 0cf7a6b842ff..000000000000
--- a/arch/arm/include/asm/hardware/coresight.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/*
- * linux/arch/arm/include/asm/hardware/coresight.h
- *
- * CoreSight components' registers
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_HARDWARE_CORESIGHT_H
-#define __ASM_HARDWARE_CORESIGHT_H
-
-#define TRACER_ACCESSED_BIT	0
-#define TRACER_RUNNING_BIT	1
-#define TRACER_CYCLE_ACC_BIT	2
-#define TRACER_ACCESSED		BIT(TRACER_ACCESSED_BIT)
-#define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
-#define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
-
-#define TRACER_TIMEOUT 10000
-
-#define etm_writel(t, v, x) \
-	(__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
-
-/* CoreSight Management Registers */
-#define CSMR_LOCKACCESS 0xfb0
-#define CSMR_LOCKSTATUS 0xfb4
-#define CSMR_AUTHSTATUS 0xfb8
-#define CSMR_DEVID	0xfc8
-#define CSMR_DEVTYPE	0xfcc
-/* CoreSight Component Registers */
-#define CSCR_CLASS	0xff4
-
-#define CS_LAR_KEY	0xc5acce55
-
-/* ETM control register, "ETM Architecture", 3.3.1 */
-#define ETMR_CTRL		0
-#define ETMCTRL_POWERDOWN	1
-#define ETMCTRL_PROGRAM		(1 << 10)
-#define ETMCTRL_PORTSEL		(1 << 11)
-#define ETMCTRL_DO_CONTEXTID	(3 << 14)
-#define ETMCTRL_PORTMASK1	(7 << 4)
-#define ETMCTRL_PORTMASK2	(1 << 21)
-#define ETMCTRL_PORTMASK	(ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
-#define ETMCTRL_PORTSIZE(x) ((((x) & 7) << 4) | (!!((x) & 8)) << 21)
-#define ETMCTRL_DO_CPRT		(1 << 1)
-#define ETMCTRL_DATAMASK	(3 << 2)
-#define ETMCTRL_DATA_DO_DATA	(1 << 2)
-#define ETMCTRL_DATA_DO_ADDR	(1 << 3)
-#define ETMCTRL_DATA_DO_BOTH	(ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
-#define ETMCTRL_BRANCH_OUTPUT	(1 << 8)
-#define ETMCTRL_CYCLEACCURATE	(1 << 12)
-
-/* ETM configuration code register */
-#define ETMR_CONFCODE		(0x04)
-
-/* ETM trace start/stop resource control register */
-#define ETMR_TRACESSCTRL	(0x18)
-
-/* ETM trigger event register */
-#define ETMR_TRIGEVT		(0x08)
-
-/* address access type register bits, "ETM architecture",
- * table 3-27 */
-/* - access type */
-#define ETMAAT_IFETCH		0
-#define ETMAAT_IEXEC		1
-#define ETMAAT_IEXECPASS	2
-#define ETMAAT_IEXECFAIL	3
-#define ETMAAT_DLOADSTORE	4
-#define ETMAAT_DLOAD		5
-#define ETMAAT_DSTORE		6
-/* - comparison access size */
-#define ETMAAT_JAVA		(0 << 3)
-#define ETMAAT_THUMB		(1 << 3)
-#define ETMAAT_ARM		(3 << 3)
-/* - data value comparison control */
-#define ETMAAT_NOVALCMP		(0 << 5)
-#define ETMAAT_VALMATCH		(1 << 5)
-#define ETMAAT_VALNOMATCH	(3 << 5)
-/* - exact match */
-#define ETMAAT_EXACTMATCH	(1 << 7)
-/* - context id comparator control */
-#define ETMAAT_IGNCONTEXTID	(0 << 8)
-#define ETMAAT_VALUE1		(1 << 8)
-#define ETMAAT_VALUE2		(2 << 8)
-#define ETMAAT_VALUE3		(3 << 8)
-/* - security level control */
-#define ETMAAT_IGNSECURITY	(0 << 10)
-#define ETMAAT_NSONLY		(1 << 10)
-#define ETMAAT_SONLY		(2 << 10)
-
-#define ETMR_COMP_VAL(x)	(0x40 + (x) * 4)
-#define ETMR_COMP_ACC_TYPE(x)	(0x80 + (x) * 4)
-
-/* ETM status register, "ETM Architecture", 3.3.2 */
-#define ETMR_STATUS		(0x10)
-#define ETMST_OVERFLOW		BIT(0)
-#define ETMST_PROGBIT		BIT(1)
-#define ETMST_STARTSTOP		BIT(2)
-#define ETMST_TRIGGER		BIT(3)
-
-#define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
-#define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
-#define etm_triggered(t)	(etm_readl((t), ETMR_STATUS) & ETMST_TRIGGER)
-
-#define ETMR_TRACEENCTRL2	0x1c
-#define ETMR_TRACEENCTRL	0x24
-#define ETMTE_INCLEXCL		BIT(24)
-#define ETMR_TRACEENEVT		0x20
-#define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
-				ETMCTRL_DATA_DO_ADDR | \
-				ETMCTRL_BRANCH_OUTPUT | \
-				ETMCTRL_DO_CONTEXTID)
-
-/* ETM management registers, "ETM Architecture", 3.5.24 */
-#define ETMMR_OSLAR	0x300
-#define ETMMR_OSLSR	0x304
-#define ETMMR_OSSRR	0x308
-#define ETMMR_PDSR	0x314
-
-/* ETB registers, "CoreSight Components TRM", 9.3 */
-#define ETBR_DEPTH		0x04
-#define ETBR_STATUS		0x0c
-#define ETBR_READMEM		0x10
-#define ETBR_READADDR		0x14
-#define ETBR_WRITEADDR		0x18
-#define ETBR_TRIGGERCOUNT	0x1c
-#define ETBR_CTRL		0x20
-#define ETBR_FORMATTERCTRL	0x304
-#define ETBFF_ENFTC		1
-#define ETBFF_ENFCONT		BIT(1)
-#define ETBFF_FONFLIN		BIT(4)
-#define ETBFF_MANUAL_FLUSH	BIT(6)
-#define ETBFF_TRIGIN		BIT(8)
-#define ETBFF_TRIGEVT		BIT(9)
-#define ETBFF_TRIGFL		BIT(10)
-
-#define etb_writel(t, v, x) \
-	(__raw_writel((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
-
-#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etm_unlock(t) \
-	do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etb_unlock(t) \
-	do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#endif /* __ASM_HARDWARE_CORESIGHT_H */
-
diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h
new file mode 100644
index 000000000000..61576dc58ede
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cp14.h
@@ -0,0 +1,542 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_HARDWARE_CP14_H
+#define __ASM_HARDWARE_CP14_H
+
+#include <linux/types.h>
+
+/* Accessors for CP14 registers */
+#define dbg_read(reg)			RCP14_##reg()
+#define dbg_write(val, reg)		WCP14_##reg(val)
+#define etm_read(reg)			RCP14_##reg()
+#define etm_write(val, reg)		WCP14_##reg(val)
+
+/* MRC14 and MCR14 */
+#define MRC14(op1, crn, crm, op2)					\
+({									\
+u32 val;								\
+asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val));	\
+val;									\
+})
+
+#define MCR14(val, op1, crn, crm, op2)					\
+({									\
+asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\
+})
+
+/*
+ * Debug Registers
+ *
+ * Available only in DBGv7
+ * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR
+ *
+ * Available only in DBGv7.1
+ * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1
+ *
+ * Read only
+ * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR,
+ * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID
+ *
+ * Write only
+ * DBGDTRTXint, DBGOSLAR
+ */
+#define RCP14_DBGDIDR()			MRC14(0, c0, c0, 0)
+#define RCP14_DBGDSCRint()		MRC14(0, c0, c1, 0)
+#define RCP14_DBGDTRRXint()		MRC14(0, c0, c5, 0)
+#define RCP14_DBGWFAR()			MRC14(0, c0, c6, 0)
+#define RCP14_DBGVCR()			MRC14(0, c0, c7, 0)
+#define RCP14_DBGECR()			MRC14(0, c0, c9, 0)
+#define RCP14_DBGDSCCR()		MRC14(0, c0, c10, 0)
+#define RCP14_DBGDSMCR()		MRC14(0, c0, c11, 0)
+#define RCP14_DBGDTRRXext()		MRC14(0, c0, c0, 2)
+#define RCP14_DBGDSCRext()		MRC14(0, c0, c2, 2)
+#define RCP14_DBGDTRTXext()		MRC14(0, c0, c3, 2)
+#define RCP14_DBGDRCR()			MRC14(0, c0, c4, 2)
+#define RCP14_DBGBVR0()			MRC14(0, c0, c0, 4)
+#define RCP14_DBGBVR1()			MRC14(0, c0, c1, 4)
+#define RCP14_DBGBVR2()			MRC14(0, c0, c2, 4)
+#define RCP14_DBGBVR3()			MRC14(0, c0, c3, 4)
+#define RCP14_DBGBVR4()			MRC14(0, c0, c4, 4)
+#define RCP14_DBGBVR5()			MRC14(0, c0, c5, 4)
+#define RCP14_DBGBVR6()			MRC14(0, c0, c6, 4)
+#define RCP14_DBGBVR7()			MRC14(0, c0, c7, 4)
+#define RCP14_DBGBVR8()			MRC14(0, c0, c8, 4)
+#define RCP14_DBGBVR9()			MRC14(0, c0, c9, 4)
+#define RCP14_DBGBVR10()		MRC14(0, c0, c10, 4)
+#define RCP14_DBGBVR11()		MRC14(0, c0, c11, 4)
+#define RCP14_DBGBVR12()		MRC14(0, c0, c12, 4)
+#define RCP14_DBGBVR13()		MRC14(0, c0, c13, 4)
+#define RCP14_DBGBVR14()		MRC14(0, c0, c14, 4)
+#define RCP14_DBGBVR15()		MRC14(0, c0, c15, 4)
+#define RCP14_DBGBCR0()			MRC14(0, c0, c0, 5)
+#define RCP14_DBGBCR1()			MRC14(0, c0, c1, 5)
+#define RCP14_DBGBCR2()			MRC14(0, c0, c2, 5)
+#define RCP14_DBGBCR3()			MRC14(0, c0, c3, 5)
+#define RCP14_DBGBCR4()			MRC14(0, c0, c4, 5)
+#define RCP14_DBGBCR5()			MRC14(0, c0, c5, 5)
+#define RCP14_DBGBCR6()			MRC14(0, c0, c6, 5)
+#define RCP14_DBGBCR7()			MRC14(0, c0, c7, 5)
+#define RCP14_DBGBCR8()			MRC14(0, c0, c8, 5)
+#define RCP14_DBGBCR9()			MRC14(0, c0, c9, 5)
+#define RCP14_DBGBCR10()		MRC14(0, c0, c10, 5)
+#define RCP14_DBGBCR11()		MRC14(0, c0, c11, 5)
+#define RCP14_DBGBCR12()		MRC14(0, c0, c12, 5)
+#define RCP14_DBGBCR13()		MRC14(0, c0, c13, 5)
+#define RCP14_DBGBCR14()		MRC14(0, c0, c14, 5)
+#define RCP14_DBGBCR15()		MRC14(0, c0, c15, 5)
+#define RCP14_DBGWVR0()			MRC14(0, c0, c0, 6)
+#define RCP14_DBGWVR1()			MRC14(0, c0, c1, 6)
+#define RCP14_DBGWVR2()			MRC14(0, c0, c2, 6)
+#define RCP14_DBGWVR3()			MRC14(0, c0, c3, 6)
+#define RCP14_DBGWVR4()			MRC14(0, c0, c4, 6)
+#define RCP14_DBGWVR5()			MRC14(0, c0, c5, 6)
+#define RCP14_DBGWVR6()			MRC14(0, c0, c6, 6)
+#define RCP14_DBGWVR7()			MRC14(0, c0, c7, 6)
+#define RCP14_DBGWVR8()			MRC14(0, c0, c8, 6)
+#define RCP14_DBGWVR9()			MRC14(0, c0, c9, 6)
+#define RCP14_DBGWVR10()		MRC14(0, c0, c10, 6)
+#define RCP14_DBGWVR11()		MRC14(0, c0, c11, 6)
+#define RCP14_DBGWVR12()		MRC14(0, c0, c12, 6)
+#define RCP14_DBGWVR13()		MRC14(0, c0, c13, 6)
+#define RCP14_DBGWVR14()		MRC14(0, c0, c14, 6)
+#define RCP14_DBGWVR15()		MRC14(0, c0, c15, 6)
+#define RCP14_DBGWCR0()			MRC14(0, c0, c0, 7)
+#define RCP14_DBGWCR1()			MRC14(0, c0, c1, 7)
+#define RCP14_DBGWCR2()			MRC14(0, c0, c2, 7)
+#define RCP14_DBGWCR3()			MRC14(0, c0, c3, 7)
+#define RCP14_DBGWCR4()			MRC14(0, c0, c4, 7)
+#define RCP14_DBGWCR5()			MRC14(0, c0, c5, 7)
+#define RCP14_DBGWCR6()			MRC14(0, c0, c6, 7)
+#define RCP14_DBGWCR7()			MRC14(0, c0, c7, 7)
+#define RCP14_DBGWCR8()			MRC14(0, c0, c8, 7)
+#define RCP14_DBGWCR9()			MRC14(0, c0, c9, 7)
+#define RCP14_DBGWCR10()		MRC14(0, c0, c10, 7)
+#define RCP14_DBGWCR11()		MRC14(0, c0, c11, 7)
+#define RCP14_DBGWCR12()		MRC14(0, c0, c12, 7)
+#define RCP14_DBGWCR13()		MRC14(0, c0, c13, 7)
+#define RCP14_DBGWCR14()		MRC14(0, c0, c14, 7)
+#define RCP14_DBGWCR15()		MRC14(0, c0, c15, 7)
+#define RCP14_DBGDRAR()			MRC14(0, c1, c0, 0)
+#define RCP14_DBGBXVR0()		MRC14(0, c1, c0, 1)
+#define RCP14_DBGBXVR1()		MRC14(0, c1, c1, 1)
+#define RCP14_DBGBXVR2()		MRC14(0, c1, c2, 1)
+#define RCP14_DBGBXVR3()		MRC14(0, c1, c3, 1)
+#define RCP14_DBGBXVR4()		MRC14(0, c1, c4, 1)
+#define RCP14_DBGBXVR5()		MRC14(0, c1, c5, 1)
+#define RCP14_DBGBXVR6()		MRC14(0, c1, c6, 1)
+#define RCP14_DBGBXVR7()		MRC14(0, c1, c7, 1)
+#define RCP14_DBGBXVR8()		MRC14(0, c1, c8, 1)
+#define RCP14_DBGBXVR9()		MRC14(0, c1, c9, 1)
+#define RCP14_DBGBXVR10()		MRC14(0, c1, c10, 1)
+#define RCP14_DBGBXVR11()		MRC14(0, c1, c11, 1)
+#define RCP14_DBGBXVR12()		MRC14(0, c1, c12, 1)
+#define RCP14_DBGBXVR13()		MRC14(0, c1, c13, 1)
+#define RCP14_DBGBXVR14()		MRC14(0, c1, c14, 1)
+#define RCP14_DBGBXVR15()		MRC14(0, c1, c15, 1)
+#define RCP14_DBGOSLSR()		MRC14(0, c1, c1, 4)
+#define RCP14_DBGOSSRR()		MRC14(0, c1, c2, 4)
+#define RCP14_DBGOSDLR()		MRC14(0, c1, c3, 4)
+#define RCP14_DBGPRCR()			MRC14(0, c1, c4, 4)
+#define RCP14_DBGPRSR()			MRC14(0, c1, c5, 4)
+#define RCP14_DBGDSAR()			MRC14(0, c2, c0, 0)
+#define RCP14_DBGITCTRL()		MRC14(0, c7, c0, 4)
+#define RCP14_DBGCLAIMSET()		MRC14(0, c7, c8, 6)
+#define RCP14_DBGCLAIMCLR()		MRC14(0, c7, c9, 6)
+#define RCP14_DBGAUTHSTATUS()		MRC14(0, c7, c14, 6)
+#define RCP14_DBGDEVID2()		MRC14(0, c7, c0, 7)
+#define RCP14_DBGDEVID1()		MRC14(0, c7, c1, 7)
+#define RCP14_DBGDEVID()		MRC14(0, c7, c2, 7)
+
+#define WCP14_DBGDTRTXint(val)		MCR14(val, 0, c0, c5, 0)
+#define WCP14_DBGWFAR(val)		MCR14(val, 0, c0, c6, 0)
+#define WCP14_DBGVCR(val)		MCR14(val, 0, c0, c7, 0)
+#define WCP14_DBGECR(val)		MCR14(val, 0, c0, c9, 0)
+#define WCP14_DBGDSCCR(val)		MCR14(val, 0, c0, c10, 0)
+#define WCP14_DBGDSMCR(val)		MCR14(val, 0, c0, c11, 0)
+#define WCP14_DBGDTRRXext(val)		MCR14(val, 0, c0, c0, 2)
+#define WCP14_DBGDSCRext(val)		MCR14(val, 0, c0, c2, 2)
+#define WCP14_DBGDTRTXext(val)		MCR14(val, 0, c0, c3, 2)
+#define WCP14_DBGDRCR(val)		MCR14(val, 0, c0, c4, 2)
+#define WCP14_DBGBVR0(val)		MCR14(val, 0, c0, c0, 4)
+#define WCP14_DBGBVR1(val)		MCR14(val, 0, c0, c1, 4)
+#define WCP14_DBGBVR2(val)		MCR14(val, 0, c0, c2, 4)
+#define WCP14_DBGBVR3(val)		MCR14(val, 0, c0, c3, 4)
+#define WCP14_DBGBVR4(val)		MCR14(val, 0, c0, c4, 4)
+#define WCP14_DBGBVR5(val)		MCR14(val, 0, c0, c5, 4)
+#define WCP14_DBGBVR6(val)		MCR14(val, 0, c0, c6, 4)
+#define WCP14_DBGBVR7(val)		MCR14(val, 0, c0, c7, 4)
+#define WCP14_DBGBVR8(val)		MCR14(val, 0, c0, c8, 4)
+#define WCP14_DBGBVR9(val)		MCR14(val, 0, c0, c9, 4)
+#define WCP14_DBGBVR10(val)		MCR14(val, 0, c0, c10, 4)
+#define WCP14_DBGBVR11(val)		MCR14(val, 0, c0, c11, 4)
+#define WCP14_DBGBVR12(val)		MCR14(val, 0, c0, c12, 4)
+#define WCP14_DBGBVR13(val)		MCR14(val, 0, c0, c13, 4)
+#define WCP14_DBGBVR14(val)		MCR14(val, 0, c0, c14, 4)
+#define WCP14_DBGBVR15(val)		MCR14(val, 0, c0, c15, 4)
+#define WCP14_DBGBCR0(val)		MCR14(val, 0, c0, c0, 5)
+#define WCP14_DBGBCR1(val)		MCR14(val, 0, c0, c1, 5)
+#define WCP14_DBGBCR2(val)		MCR14(val, 0, c0, c2, 5)
+#define WCP14_DBGBCR3(val)		MCR14(val, 0, c0, c3, 5)
+#define WCP14_DBGBCR4(val)		MCR14(val, 0, c0, c4, 5)
+#define WCP14_DBGBCR5(val)		MCR14(val, 0, c0, c5, 5)
+#define WCP14_DBGBCR6(val)		MCR14(val, 0, c0, c6, 5)
+#define WCP14_DBGBCR7(val)		MCR14(val, 0, c0, c7, 5)
+#define WCP14_DBGBCR8(val)		MCR14(val, 0, c0, c8, 5)
+#define WCP14_DBGBCR9(val)		MCR14(val, 0, c0, c9, 5)
+#define WCP14_DBGBCR10(val)		MCR14(val, 0, c0, c10, 5)
+#define WCP14_DBGBCR11(val)		MCR14(val, 0, c0, c11, 5)
+#define WCP14_DBGBCR12(val)		MCR14(val, 0, c0, c12, 5)
+#define WCP14_DBGBCR13(val)		MCR14(val, 0, c0, c13, 5)
+#define WCP14_DBGBCR14(val)		MCR14(val, 0, c0, c14, 5)
+#define WCP14_DBGBCR15(val)		MCR14(val, 0, c0, c15, 5)
+#define WCP14_DBGWVR0(val)		MCR14(val, 0, c0, c0, 6)
+#define WCP14_DBGWVR1(val)		MCR14(val, 0, c0, c1, 6)
+#define WCP14_DBGWVR2(val)		MCR14(val, 0, c0, c2, 6)
+#define WCP14_DBGWVR3(val)		MCR14(val, 0, c0, c3, 6)
+#define WCP14_DBGWVR4(val)		MCR14(val, 0, c0, c4, 6)
+#define WCP14_DBGWVR5(val)		MCR14(val, 0, c0, c5, 6)
+#define WCP14_DBGWVR6(val)		MCR14(val, 0, c0, c6, 6)
+#define WCP14_DBGWVR7(val)		MCR14(val, 0, c0, c7, 6)
+#define WCP14_DBGWVR8(val)		MCR14(val, 0, c0, c8, 6)
+#define WCP14_DBGWVR9(val)		MCR14(val, 0, c0, c9, 6)
+#define WCP14_DBGWVR10(val)		MCR14(val, 0, c0, c10, 6)
+#define WCP14_DBGWVR11(val)		MCR14(val, 0, c0, c11, 6)
+#define WCP14_DBGWVR12(val)		MCR14(val, 0, c0, c12, 6)
+#define WCP14_DBGWVR13(val)		MCR14(val, 0, c0, c13, 6)
+#define WCP14_DBGWVR14(val)		MCR14(val, 0, c0, c14, 6)
+#define WCP14_DBGWVR15(val)		MCR14(val, 0, c0, c15, 6)
+#define WCP14_DBGWCR0(val)		MCR14(val, 0, c0, c0, 7)
+#define WCP14_DBGWCR1(val)		MCR14(val, 0, c0, c1, 7)
+#define WCP14_DBGWCR2(val)		MCR14(val, 0, c0, c2, 7)
+#define WCP14_DBGWCR3(val)		MCR14(val, 0, c0, c3, 7)
+#define WCP14_DBGWCR4(val)		MCR14(val, 0, c0, c4, 7)
+#define WCP14_DBGWCR5(val)		MCR14(val, 0, c0, c5, 7)
+#define WCP14_DBGWCR6(val)		MCR14(val, 0, c0, c6, 7)
+#define WCP14_DBGWCR7(val)		MCR14(val, 0, c0, c7, 7)
+#define WCP14_DBGWCR8(val)		MCR14(val, 0, c0, c8, 7)
+#define WCP14_DBGWCR9(val)		MCR14(val, 0, c0, c9, 7)
+#define WCP14_DBGWCR10(val)		MCR14(val, 0, c0, c10, 7)
+#define WCP14_DBGWCR11(val)		MCR14(val, 0, c0, c11, 7)
+#define WCP14_DBGWCR12(val)		MCR14(val, 0, c0, c12, 7)
+#define WCP14_DBGWCR13(val)		MCR14(val, 0, c0, c13, 7)
+#define WCP14_DBGWCR14(val)		MCR14(val, 0, c0, c14, 7)
+#define WCP14_DBGWCR15(val)		MCR14(val, 0, c0, c15, 7)
+#define WCP14_DBGBXVR0(val)		MCR14(val, 0, c1, c0, 1)
+#define WCP14_DBGBXVR1(val)		MCR14(val, 0, c1, c1, 1)
+#define WCP14_DBGBXVR2(val)		MCR14(val, 0, c1, c2, 1)
+#define WCP14_DBGBXVR3(val)		MCR14(val, 0, c1, c3, 1)
+#define WCP14_DBGBXVR4(val)		MCR14(val, 0, c1, c4, 1)
+#define WCP14_DBGBXVR5(val)		MCR14(val, 0, c1, c5, 1)
+#define WCP14_DBGBXVR6(val)		MCR14(val, 0, c1, c6, 1)
+#define WCP14_DBGBXVR7(val)		MCR14(val, 0, c1, c7, 1)
+#define WCP14_DBGBXVR8(val)		MCR14(val, 0, c1, c8, 1)
+#define WCP14_DBGBXVR9(val)		MCR14(val, 0, c1, c9, 1)
+#define WCP14_DBGBXVR10(val)		MCR14(val, 0, c1, c10, 1)
+#define WCP14_DBGBXVR11(val)		MCR14(val, 0, c1, c11, 1)
+#define WCP14_DBGBXVR12(val)		MCR14(val, 0, c1, c12, 1)
+#define WCP14_DBGBXVR13(val)		MCR14(val, 0, c1, c13, 1)
+#define WCP14_DBGBXVR14(val)		MCR14(val, 0, c1, c14, 1)
+#define WCP14_DBGBXVR15(val)		MCR14(val, 0, c1, c15, 1)
+#define WCP14_DBGOSLAR(val)		MCR14(val, 0, c1, c0, 4)
+#define WCP14_DBGOSSRR(val)		MCR14(val, 0, c1, c2, 4)
+#define WCP14_DBGOSDLR(val)		MCR14(val, 0, c1, c3, 4)
+#define WCP14_DBGPRCR(val)		MCR14(val, 0, c1, c4, 4)
+#define WCP14_DBGITCTRL(val)		MCR14(val, 0, c7, c0, 4)
+#define WCP14_DBGCLAIMSET(val)		MCR14(val, 0, c7, c8, 6)
+#define WCP14_DBGCLAIMCLR(val)		MCR14(val, 0, c7, c9, 6)
+
+/*
+ * ETM Registers
+ *
+ * Available only in ETMv3.3, 3.4, 3.5
+ * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3,
+ * ETMDCVRn, ETMDCMRn
+ *
+ * Available only in ETMv3.5 as read only
+ * ETMIDR2
+ *
+ * Available only in ETMv3.5, PFTv1.0, 1.1
+ * ETMTSEVR, ETMVMIDCVR, ETMPDCR
+ *
+ * Read only
+ * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR
+ * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6,
+ * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0,
+ * ETMCIDR1, ETMCIDR2, ETMCIDR3
+ *
+ * Write only
+ * ETMOSLAR, ETMLAR
+ * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec.
+ */
+#define RCP14_ETMCR()			MRC14(1, c0, c0, 0)
+#define RCP14_ETMCCR()			MRC14(1, c0, c1, 0)
+#define RCP14_ETMTRIGGER()		MRC14(1, c0, c2, 0)
+#define RCP14_ETMASICCR()		MRC14(1, c0, c3, 0)
+#define RCP14_ETMSR()			MRC14(1, c0, c4, 0)
+#define RCP14_ETMSCR()			MRC14(1, c0, c5, 0)
+#define RCP14_ETMTSSCR()		MRC14(1, c0, c6, 0)
+#define RCP14_ETMTECR2()		MRC14(1, c0, c7, 0)
+#define RCP14_ETMTEEVR()		MRC14(1, c0, c8, 0)
+#define RCP14_ETMTECR1()		MRC14(1, c0, c9, 0)
+#define RCP14_ETMFFRR()			MRC14(1, c0, c10, 0)
+#define RCP14_ETMFFLR()			MRC14(1, c0, c11, 0)
+#define RCP14_ETMVDEVR()		MRC14(1, c0, c12, 0)
+#define RCP14_ETMVDCR1()		MRC14(1, c0, c13, 0)
+#define RCP14_ETMVDCR2()		MRC14(1, c0, c14, 0)
+#define RCP14_ETMVDCR3()		MRC14(1, c0, c15, 0)
+#define RCP14_ETMACVR0()		MRC14(1, c0, c0, 1)
+#define RCP14_ETMACVR1()		MRC14(1, c0, c1, 1)
+#define RCP14_ETMACVR2()		MRC14(1, c0, c2, 1)
+#define RCP14_ETMACVR3()		MRC14(1, c0, c3, 1)
+#define RCP14_ETMACVR4()		MRC14(1, c0, c4, 1)
+#define RCP14_ETMACVR5()		MRC14(1, c0, c5, 1)
+#define RCP14_ETMACVR6()		MRC14(1, c0, c6, 1)
+#define RCP14_ETMACVR7()		MRC14(1, c0, c7, 1)
+#define RCP14_ETMACVR8()		MRC14(1, c0, c8, 1)
+#define RCP14_ETMACVR9()		MRC14(1, c0, c9, 1)
+#define RCP14_ETMACVR10()		MRC14(1, c0, c10, 1)
+#define RCP14_ETMACVR11()		MRC14(1, c0, c11, 1)
+#define RCP14_ETMACVR12()		MRC14(1, c0, c12, 1)
+#define RCP14_ETMACVR13()		MRC14(1, c0, c13, 1)
+#define RCP14_ETMACVR14()		MRC14(1, c0, c14, 1)
+#define RCP14_ETMACVR15()		MRC14(1, c0, c15, 1)
+#define RCP14_ETMACTR0()		MRC14(1, c0, c0, 2)
+#define RCP14_ETMACTR1()		MRC14(1, c0, c1, 2)
+#define RCP14_ETMACTR2()		MRC14(1, c0, c2, 2)
+#define RCP14_ETMACTR3()		MRC14(1, c0, c3, 2)
+#define RCP14_ETMACTR4()		MRC14(1, c0, c4, 2)
+#define RCP14_ETMACTR5()		MRC14(1, c0, c5, 2)
+#define RCP14_ETMACTR6()		MRC14(1, c0, c6, 2)
+#define RCP14_ETMACTR7()		MRC14(1, c0, c7, 2)
+#define RCP14_ETMACTR8()		MRC14(1, c0, c8, 2)
+#define RCP14_ETMACTR9()		MRC14(1, c0, c9, 2)
+#define RCP14_ETMACTR10()		MRC14(1, c0, c10, 2)
+#define RCP14_ETMACTR11()		MRC14(1, c0, c11, 2)
+#define RCP14_ETMACTR12()		MRC14(1, c0, c12, 2)
+#define RCP14_ETMACTR13()		MRC14(1, c0, c13, 2)
+#define RCP14_ETMACTR14()		MRC14(1, c0, c14, 2)
+#define RCP14_ETMACTR15()		MRC14(1, c0, c15, 2)
+#define RCP14_ETMDCVR0()		MRC14(1, c0, c0, 3)
+#define RCP14_ETMDCVR2()		MRC14(1, c0, c2, 3)
+#define RCP14_ETMDCVR4()		MRC14(1, c0, c4, 3)
+#define RCP14_ETMDCVR6()		MRC14(1, c0, c6, 3)
+#define RCP14_ETMDCVR8()		MRC14(1, c0, c8, 3)
+#define RCP14_ETMDCVR10()		MRC14(1, c0, c10, 3)
+#define RCP14_ETMDCVR12()		MRC14(1, c0, c12, 3)
+#define RCP14_ETMDCVR14()		MRC14(1, c0, c14, 3)
+#define RCP14_ETMDCMR0()		MRC14(1, c0, c0, 4)
+#define RCP14_ETMDCMR2()		MRC14(1, c0, c2, 4)
+#define RCP14_ETMDCMR4()		MRC14(1, c0, c4, 4)
+#define RCP14_ETMDCMR6()		MRC14(1, c0, c6, 4)
+#define RCP14_ETMDCMR8()		MRC14(1, c0, c8, 4)
+#define RCP14_ETMDCMR10()		MRC14(1, c0, c10, 4)
+#define RCP14_ETMDCMR12()		MRC14(1, c0, c12, 4)
+#define RCP14_ETMDCMR14()		MRC14(1, c0, c14, 4)
+#define RCP14_ETMCNTRLDVR0()		MRC14(1, c0, c0, 5)
+#define RCP14_ETMCNTRLDVR1()		MRC14(1, c0, c1, 5)
+#define RCP14_ETMCNTRLDVR2()		MRC14(1, c0, c2, 5)
+#define RCP14_ETMCNTRLDVR3()		MRC14(1, c0, c3, 5)
+#define RCP14_ETMCNTENR0()		MRC14(1, c0, c4, 5)
+#define RCP14_ETMCNTENR1()		MRC14(1, c0, c5, 5)
+#define RCP14_ETMCNTENR2()		MRC14(1, c0, c6, 5)
+#define RCP14_ETMCNTENR3()		MRC14(1, c0, c7, 5)
+#define RCP14_ETMCNTRLDEVR0()		MRC14(1, c0, c8, 5)
+#define RCP14_ETMCNTRLDEVR1()		MRC14(1, c0, c9, 5)
+#define RCP14_ETMCNTRLDEVR2()		MRC14(1, c0, c10, 5)
+#define RCP14_ETMCNTRLDEVR3()		MRC14(1, c0, c11, 5)
+#define RCP14_ETMCNTVR0()		MRC14(1, c0, c12, 5)
+#define RCP14_ETMCNTVR1()		MRC14(1, c0, c13, 5)
+#define RCP14_ETMCNTVR2()		MRC14(1, c0, c14, 5)
+#define RCP14_ETMCNTVR3()		MRC14(1, c0, c15, 5)
+#define RCP14_ETMSQ12EVR()		MRC14(1, c0, c0, 6)
+#define RCP14_ETMSQ21EVR()		MRC14(1, c0, c1, 6)
+#define RCP14_ETMSQ23EVR()		MRC14(1, c0, c2, 6)
+#define RCP14_ETMSQ31EVR()		MRC14(1, c0, c3, 6)
+#define RCP14_ETMSQ32EVR()		MRC14(1, c0, c4, 6)
+#define RCP14_ETMSQ13EVR()		MRC14(1, c0, c5, 6)
+#define RCP14_ETMSQR()			MRC14(1, c0, c7, 6)
+#define RCP14_ETMEXTOUTEVR0()		MRC14(1, c0, c8, 6)
+#define RCP14_ETMEXTOUTEVR1()		MRC14(1, c0, c9, 6)
+#define RCP14_ETMEXTOUTEVR2()		MRC14(1, c0, c10, 6)
+#define RCP14_ETMEXTOUTEVR3()		MRC14(1, c0, c11, 6)
+#define RCP14_ETMCIDCVR0()		MRC14(1, c0, c12, 6)
+#define RCP14_ETMCIDCVR1()		MRC14(1, c0, c13, 6)
+#define RCP14_ETMCIDCVR2()		MRC14(1, c0, c14, 6)
+#define RCP14_ETMCIDCMR()		MRC14(1, c0, c15, 6)
+#define RCP14_ETMIMPSPEC0()		MRC14(1, c0, c0, 7)
+#define RCP14_ETMIMPSPEC1()		MRC14(1, c0, c1, 7)
+#define RCP14_ETMIMPSPEC2()		MRC14(1, c0, c2, 7)
+#define RCP14_ETMIMPSPEC3()		MRC14(1, c0, c3, 7)
+#define RCP14_ETMIMPSPEC4()		MRC14(1, c0, c4, 7)
+#define RCP14_ETMIMPSPEC5()		MRC14(1, c0, c5, 7)
+#define RCP14_ETMIMPSPEC6()		MRC14(1, c0, c6, 7)
+#define RCP14_ETMIMPSPEC7()		MRC14(1, c0, c7, 7)
+#define RCP14_ETMSYNCFR()		MRC14(1, c0, c8, 7)
+#define RCP14_ETMIDR()			MRC14(1, c0, c9, 7)
+#define RCP14_ETMCCER()			MRC14(1, c0, c10, 7)
+#define RCP14_ETMEXTINSELR()		MRC14(1, c0, c11, 7)
+#define RCP14_ETMTESSEICR()		MRC14(1, c0, c12, 7)
+#define RCP14_ETMEIBCR()		MRC14(1, c0, c13, 7)
+#define RCP14_ETMTSEVR()		MRC14(1, c0, c14, 7)
+#define RCP14_ETMAUXCR()		MRC14(1, c0, c15, 7)
+#define RCP14_ETMTRACEIDR()		MRC14(1, c1, c0, 0)
+#define RCP14_ETMIDR2()			MRC14(1, c1, c2, 0)
+#define RCP14_ETMVMIDCVR()		MRC14(1, c1, c0, 1)
+#define RCP14_ETMOSLSR()		MRC14(1, c1, c1, 4)
+/* Not available in PFTv1.1 */
+#define RCP14_ETMOSSRR()		MRC14(1, c1, c2, 4)
+#define RCP14_ETMPDCR()			MRC14(1, c1, c4, 4)
+#define RCP14_ETMPDSR()			MRC14(1, c1, c5, 4)
+#define RCP14_ETMITCTRL()		MRC14(1, c7, c0, 4)
+#define RCP14_ETMCLAIMSET()		MRC14(1, c7, c8, 6)
+#define RCP14_ETMCLAIMCLR()		MRC14(1, c7, c9, 6)
+#define RCP14_ETMLSR()			MRC14(1, c7, c13, 6)
+#define RCP14_ETMAUTHSTATUS()		MRC14(1, c7, c14, 6)
+#define RCP14_ETMDEVID()		MRC14(1, c7, c2, 7)
+#define RCP14_ETMDEVTYPE()		MRC14(1, c7, c3, 7)
+#define RCP14_ETMPIDR4()		MRC14(1, c7, c4, 7)
+#define RCP14_ETMPIDR5()		MRC14(1, c7, c5, 7)
+#define RCP14_ETMPIDR6()		MRC14(1, c7, c6, 7)
+#define RCP14_ETMPIDR7()		MRC14(1, c7, c7, 7)
+#define RCP14_ETMPIDR0()		MRC14(1, c7, c8, 7)
+#define RCP14_ETMPIDR1()		MRC14(1, c7, c9, 7)
+#define RCP14_ETMPIDR2()		MRC14(1, c7, c10, 7)
+#define RCP14_ETMPIDR3()		MRC14(1, c7, c11, 7)
+#define RCP14_ETMCIDR0()		MRC14(1, c7, c12, 7)
+#define RCP14_ETMCIDR1()		MRC14(1, c7, c13, 7)
+#define RCP14_ETMCIDR2()		MRC14(1, c7, c14, 7)
+#define RCP14_ETMCIDR3()		MRC14(1, c7, c15, 7)
+
+#define WCP14_ETMCR(val)		MCR14(val, 1, c0, c0, 0)
+#define WCP14_ETMTRIGGER(val)		MCR14(val, 1, c0, c2, 0)
+#define WCP14_ETMASICCR(val)		MCR14(val, 1, c0, c3, 0)
+#define WCP14_ETMSR(val)		MCR14(val, 1, c0, c4, 0)
+#define WCP14_ETMTSSCR(val)		MCR14(val, 1, c0, c6, 0)
+#define WCP14_ETMTECR2(val)		MCR14(val, 1, c0, c7, 0)
+#define WCP14_ETMTEEVR(val)		MCR14(val, 1, c0, c8, 0)
+#define WCP14_ETMTECR1(val)		MCR14(val, 1, c0, c9, 0)
+#define WCP14_ETMFFRR(val)		MCR14(val, 1, c0, c10, 0)
+#define WCP14_ETMFFLR(val)		MCR14(val, 1, c0, c11, 0)
+#define WCP14_ETMVDEVR(val)		MCR14(val, 1, c0, c12, 0)
+#define WCP14_ETMVDCR1(val)		MCR14(val, 1, c0, c13, 0)
+#define WCP14_ETMVDCR2(val)		MCR14(val, 1, c0, c14, 0)
+#define WCP14_ETMVDCR3(val)		MCR14(val, 1, c0, c15, 0)
+#define WCP14_ETMACVR0(val)		MCR14(val, 1, c0, c0, 1)
+#define WCP14_ETMACVR1(val)		MCR14(val, 1, c0, c1, 1)
+#define WCP14_ETMACVR2(val)		MCR14(val, 1, c0, c2, 1)
+#define WCP14_ETMACVR3(val)		MCR14(val, 1, c0, c3, 1)
+#define WCP14_ETMACVR4(val)		MCR14(val, 1, c0, c4, 1)
+#define WCP14_ETMACVR5(val)		MCR14(val, 1, c0, c5, 1)
+#define WCP14_ETMACVR6(val)		MCR14(val, 1, c0, c6, 1)
+#define WCP14_ETMACVR7(val)		MCR14(val, 1, c0, c7, 1)
+#define WCP14_ETMACVR8(val)		MCR14(val, 1, c0, c8, 1)
+#define WCP14_ETMACVR9(val)		MCR14(val, 1, c0, c9, 1)
+#define WCP14_ETMACVR10(val)		MCR14(val, 1, c0, c10, 1)
+#define WCP14_ETMACVR11(val)		MCR14(val, 1, c0, c11, 1)
+#define WCP14_ETMACVR12(val)		MCR14(val, 1, c0, c12, 1)
+#define WCP14_ETMACVR13(val)		MCR14(val, 1, c0, c13, 1)
+#define WCP14_ETMACVR14(val)		MCR14(val, 1, c0, c14, 1)
+#define WCP14_ETMACVR15(val)		MCR14(val, 1, c0, c15, 1)
+#define WCP14_ETMACTR0(val)		MCR14(val, 1, c0, c0, 2)
+#define WCP14_ETMACTR1(val)		MCR14(val, 1, c0, c1, 2)
+#define WCP14_ETMACTR2(val)		MCR14(val, 1, c0, c2, 2)
+#define WCP14_ETMACTR3(val)		MCR14(val, 1, c0, c3, 2)
+#define WCP14_ETMACTR4(val)		MCR14(val, 1, c0, c4, 2)
+#define WCP14_ETMACTR5(val)		MCR14(val, 1, c0, c5, 2)
+#define WCP14_ETMACTR6(val)		MCR14(val, 1, c0, c6, 2)
+#define WCP14_ETMACTR7(val)		MCR14(val, 1, c0, c7, 2)
+#define WCP14_ETMACTR8(val)		MCR14(val, 1, c0, c8, 2)
+#define WCP14_ETMACTR9(val)		MCR14(val, 1, c0, c9, 2)
+#define WCP14_ETMACTR10(val)		MCR14(val, 1, c0, c10, 2)
+#define WCP14_ETMACTR11(val)		MCR14(val, 1, c0, c11, 2)
+#define WCP14_ETMACTR12(val)		MCR14(val, 1, c0, c12, 2)
+#define WCP14_ETMACTR13(val)		MCR14(val, 1, c0, c13, 2)
+#define WCP14_ETMACTR14(val)		MCR14(val, 1, c0, c14, 2)
+#define WCP14_ETMACTR15(val)		MCR14(val, 1, c0, c15, 2)
+#define WCP14_ETMDCVR0(val)		MCR14(val, 1, c0, c0, 3)
+#define WCP14_ETMDCVR2(val)		MCR14(val, 1, c0, c2, 3)
+#define WCP14_ETMDCVR4(val)		MCR14(val, 1, c0, c4, 3)
+#define WCP14_ETMDCVR6(val)		MCR14(val, 1, c0, c6, 3)
+#define WCP14_ETMDCVR8(val)		MCR14(val, 1, c0, c8, 3)
+#define WCP14_ETMDCVR10(val)		MCR14(val, 1, c0, c10, 3)
+#define WCP14_ETMDCVR12(val)		MCR14(val, 1, c0, c12, 3)
+#define WCP14_ETMDCVR14(val)		MCR14(val, 1, c0, c14, 3)
+#define WCP14_ETMDCMR0(val)		MCR14(val, 1, c0, c0, 4)
+#define WCP14_ETMDCMR2(val)		MCR14(val, 1, c0, c2, 4)
+#define WCP14_ETMDCMR4(val)		MCR14(val, 1, c0, c4, 4)
+#define WCP14_ETMDCMR6(val)		MCR14(val, 1, c0, c6, 4)
+#define WCP14_ETMDCMR8(val)		MCR14(val, 1, c0, c8, 4)
+#define WCP14_ETMDCMR10(val)		MCR14(val, 1, c0, c10, 4)
+#define WCP14_ETMDCMR12(val)		MCR14(val, 1, c0, c12, 4)
+#define WCP14_ETMDCMR14(val)		MCR14(val, 1, c0, c14, 4)
+#define WCP14_ETMCNTRLDVR0(val)		MCR14(val, 1, c0, c0, 5)
+#define WCP14_ETMCNTRLDVR1(val)		MCR14(val, 1, c0, c1, 5)
+#define WCP14_ETMCNTRLDVR2(val)		MCR14(val, 1, c0, c2, 5)
+#define WCP14_ETMCNTRLDVR3(val)		MCR14(val, 1, c0, c3, 5)
+#define WCP14_ETMCNTENR0(val)		MCR14(val, 1, c0, c4, 5)
+#define WCP14_ETMCNTENR1(val)		MCR14(val, 1, c0, c5, 5)
+#define WCP14_ETMCNTENR2(val)		MCR14(val, 1, c0, c6, 5)
+#define WCP14_ETMCNTENR3(val)		MCR14(val, 1, c0, c7, 5)
+#define WCP14_ETMCNTRLDEVR0(val)	MCR14(val, 1, c0, c8, 5)
+#define WCP14_ETMCNTRLDEVR1(val)	MCR14(val, 1, c0, c9, 5)
+#define WCP14_ETMCNTRLDEVR2(val)	MCR14(val, 1, c0, c10, 5)
+#define WCP14_ETMCNTRLDEVR3(val)	MCR14(val, 1, c0, c11, 5)
+#define WCP14_ETMCNTVR0(val)		MCR14(val, 1, c0, c12, 5)
+#define WCP14_ETMCNTVR1(val)		MCR14(val, 1, c0, c13, 5)
+#define WCP14_ETMCNTVR2(val)		MCR14(val, 1, c0, c14, 5)
+#define WCP14_ETMCNTVR3(val)		MCR14(val, 1, c0, c15, 5)
+#define WCP14_ETMSQ12EVR(val)		MCR14(val, 1, c0, c0, 6)
+#define WCP14_ETMSQ21EVR(val)		MCR14(val, 1, c0, c1, 6)
+#define WCP14_ETMSQ23EVR(val)		MCR14(val, 1, c0, c2, 6)
+#define WCP14_ETMSQ31EVR(val)		MCR14(val, 1, c0, c3, 6)
+#define WCP14_ETMSQ32EVR(val)		MCR14(val, 1, c0, c4, 6)
+#define WCP14_ETMSQ13EVR(val)		MCR14(val, 1, c0, c5, 6)
+#define WCP14_ETMSQR(val)		MCR14(val, 1, c0, c7, 6)
+#define WCP14_ETMEXTOUTEVR0(val)	MCR14(val, 1, c0, c8, 6)
+#define WCP14_ETMEXTOUTEVR1(val)	MCR14(val, 1, c0, c9, 6)
+#define WCP14_ETMEXTOUTEVR2(val)	MCR14(val, 1, c0, c10, 6)
+#define WCP14_ETMEXTOUTEVR3(val)	MCR14(val, 1, c0, c11, 6)
+#define WCP14_ETMCIDCVR0(val)		MCR14(val, 1, c0, c12, 6)
+#define WCP14_ETMCIDCVR1(val)		MCR14(val, 1, c0, c13, 6)
+#define WCP14_ETMCIDCVR2(val)		MCR14(val, 1, c0, c14, 6)
+#define WCP14_ETMCIDCMR(val)		MCR14(val, 1, c0, c15, 6)
+#define WCP14_ETMIMPSPEC0(val)		MCR14(val, 1, c0, c0, 7)
+#define WCP14_ETMIMPSPEC1(val)		MCR14(val, 1, c0, c1, 7)
+#define WCP14_ETMIMPSPEC2(val)		MCR14(val, 1, c0, c2, 7)
+#define WCP14_ETMIMPSPEC3(val)		MCR14(val, 1, c0, c3, 7)
+#define WCP14_ETMIMPSPEC4(val)		MCR14(val, 1, c0, c4, 7)
+#define WCP14_ETMIMPSPEC5(val)		MCR14(val, 1, c0, c5, 7)
+#define WCP14_ETMIMPSPEC6(val)		MCR14(val, 1, c0, c6, 7)
+#define WCP14_ETMIMPSPEC7(val)		MCR14(val, 1, c0, c7, 7)
+/* Can be read only in ETMv3.4, ETMv3.5 */
+#define WCP14_ETMSYNCFR(val)		MCR14(val, 1, c0, c8, 7)
+#define WCP14_ETMEXTINSELR(val)		MCR14(val, 1, c0, c11, 7)
+#define WCP14_ETMTESSEICR(val)		MCR14(val, 1, c0, c12, 7)
+#define WCP14_ETMEIBCR(val)		MCR14(val, 1, c0, c13, 7)
+#define WCP14_ETMTSEVR(val)		MCR14(val, 1, c0, c14, 7)
+#define WCP14_ETMAUXCR(val)		MCR14(val, 1, c0, c15, 7)
+#define WCP14_ETMTRACEIDR(val)		MCR14(val, 1, c1, c0, 0)
+#define WCP14_ETMIDR2(val)		MCR14(val, 1, c1, c2, 0)
+#define WCP14_ETMVMIDCVR(val)		MCR14(val, 1, c1, c0, 1)
+#define WCP14_ETMOSLAR(val)		MCR14(val, 1, c1, c0, 4)
+/* Not available in PFTv1.1 */
+#define WCP14_ETMOSSRR(val)		MCR14(val, 1, c1, c2, 4)
+#define WCP14_ETMPDCR(val)		MCR14(val, 1, c1, c4, 4)
+#define WCP14_ETMPDSR(val)		MCR14(val, 1, c1, c5, 4)
+#define WCP14_ETMITCTRL(val)		MCR14(val, 1, c7, c0, 4)
+#define WCP14_ETMCLAIMSET(val)		MCR14(val, 1, c7, c8, 6)
+#define WCP14_ETMCLAIMCLR(val)		MCR14(val, 1, c7, c9, 6)
+/* Writes to this from CP14 interface are ignored */
+#define WCP14_ETMLAR(val)		MCR14(val, 1, c7, c12, 6)
+
+#endif
diff --git a/arch/arm/include/asm/hardware/debug-pl01x.S b/arch/arm/include/asm/hardware/debug-pl01x.S
index f9fd083eff63..6489d1ffe3c8 100644
--- a/arch/arm/include/asm/hardware/debug-pl01x.S
+++ b/arch/arm/include/asm/hardware/debug-pl01x.S
@@ -18,12 +18,14 @@
 
 		.macro	waituart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_TXFF
 		bne	1001b
 		.endm
 
 		.macro	busyuart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_BUSY
 		bne	1001b
 		.endm
diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
new file mode 100644
index 000000000000..d4014fbe5ea3
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/include/asm/hugetlb-3level.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_3LEVEL_H
+#define _ASM_ARM_HUGETLB_3LEVEL_H
+
+
+/*
+ * If our huge pte is non-zero then mark the valid bit.
+ * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero
+ * ptes.
+ * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
+ */
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	pte_t retval = *ptep;
+	if (pte_val(retval))
+		pte_val(retval) |= L_PTE_VALID;
+	return retval;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+#endif /* _ASM_ARM_HUGETLB_3LEVEL_H */
diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
new file mode 100644
index 000000000000..1f1b1cd112f3
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb.h
@@ -0,0 +1,84 @@
+/*
+ * arch/arm/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_H
+#define _ASM_ARM_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+#include <asm/hugetlb-3level.h>
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+					 unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* _ASM_ARM_HUGETLB_H */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 652b56086de7..d070741b2b37 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -130,16 +130,16 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
  */
 extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
 	size_t, unsigned int, void *);
-extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
 
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
+extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
 extern void __arm_iounmap(volatile void __iomem *addr);
 
-extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
 extern void (*arch_iounmap)(volatile void __iomem *);
 
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c75913..863c892b4aaa 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 48066ce9ea34..0a9d5dd93294 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -11,6 +11,7 @@
 #define __ARM_KGDB_H__
 
 #include <linux/ptrace.h>
+#include <asm/opcodes.h>
 
 /*
  * GDB assumes that we're a user process being debugged, so
@@ -41,7 +42,7 @@
 
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm(".word 0xe7ffdeff");
+	asm(__inst_arm(0xe7ffdeff));
 }
 
 extern void kgdb_handle_bus_error(void);
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 308ad7d6f98b..75bf07910b81 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -8,6 +8,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/types.h>
+
 #ifndef __ASSEMBLY__
 
 struct tag;
@@ -16,8 +18,10 @@ struct pt_regs;
 struct smp_operations;
 #ifdef CONFIG_SMP
 #define smp_ops(ops) (&(ops))
+#define smp_init_ops(ops) (&(ops))
 #else
 #define smp_ops(ops) (struct smp_operations *)NULL
+#define smp_init_ops(ops) (bool (*)(void))NULL
 #endif
 
 struct machine_desc {
@@ -41,6 +45,7 @@ struct machine_desc {
 	unsigned char		reserve_lp2 :1;	/* never has lp2	*/
 	char			restart_mode;	/* default restart mode	*/
 	struct smp_operations	*smp;		/* SMP operations	*/
+	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 0f7b7620e9a5..7626a7fd4938 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -42,6 +42,14 @@ extern void mcpm_entry_point(void);
 void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
 
 /*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated.  The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val);
+
+/*
  * CPU/cluster power operations API for higher subsystems to use.
  */
 
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index 6f18da09668b..64fd15159b7d 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -16,7 +16,7 @@ typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 #define ASID_BITS	8
 #define ASID_MASK	((~0ULL) << ASID_BITS)
-#define ASID(mm)	((mm)->context.id.counter & ~ASID_MASK)
+#define ASID(mm)	((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
 #else
 #define ASID(mm)	(0)
 #endif
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 12f71a190422..f94784f0e3a6 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -37,10 +37,10 @@ struct outer_cache_fns {
 	void (*resume)(void);
 };
 
-#ifdef CONFIG_OUTER_CACHE
-
 extern struct outer_cache_fns outer_cache;
 
+#ifdef CONFIG_OUTER_CACHE
+
 static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
 {
 	if (outer_cache.inv_range)
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index f97ee02386ee..c98c9c89b95c 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -140,6 +140,7 @@
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index 18f5cef82ad5..f088c864c992 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -30,6 +30,7 @@
 #define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 #define PMD_BIT4		(_AT(pmdval_t, 0))
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
 #define PMD_APTABLE_SHIFT	(61)
@@ -41,6 +42,8 @@
  */
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
@@ -66,6 +69,7 @@
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
 #define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
 #define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index ad52938bb264..c5d94b31bde4 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -62,6 +62,14 @@
 #define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
 
 /*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+/*
  * "Linux" PTE definitions for LPAE.
  *
  * These bits overlap with the hardware bits but the naming is preserved for
@@ -79,6 +87,11 @@
 #define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
 
+#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
+#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+
 /*
  * To be used in assembly code with the upper page attributes.
  */
@@ -168,8 +181,83 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 		clean_pmd_entry(pmdp);	\
 	} while (0)
 
+/*
+ * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes
+ * that are written to a page table but not for ptes created with mk_pte.
+ *
+ * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to
+ * hugetlb_cow, where it is compared with an entry in a page table.
+ * This comparison test fails erroneously leading ultimately to a memory leak.
+ *
+ * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is
+ * present before running the comparison.
+ */
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(pte_a,pte_b)	((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG	\
+					: pte_val(pte_a))				\
+				== (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG	\
+					: pte_val(pte_b)))
+
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
 
+#define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+#define pmd_mknotpresent(pmd)	(__pmd(0))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
+				PMD_SECT_VALID | PMD_SECT_NONE;
+	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+	return pmd;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	BUG_ON(addr >= TASK_SIZE);
+
+	/* create a faulting entry if PROT_NONE protected */
+	if (pmd_val(pmd) & PMD_SECT_NONE)
+		pmd_val(pmd) &= ~PMD_SECT_VALID;
+
+	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
+	flush_pmd_entry(pmdp);
+}
+
+static inline int has_transparent_hugepage(void)
+{
+	return 1;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 8afc60c55e82..b1b7a4907489 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -24,6 +24,9 @@
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 
+
+#include <asm/tlbflush.h>
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level.h>
 #else
@@ -58,7 +61,7 @@ extern void __pgd_error(const char *file, int line, pgd_t);
  * mapping to be mapped at.  This is particularly important for
  * non-high vector CPUs.
  */
-#define FIRST_USER_ADDRESS	PAGE_SIZE
+#define FIRST_USER_ADDRESS	(PAGE_SIZE * 2)
 
 /*
  * Use TASK_SIZE as the ceiling argument for free_pgtables() and
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c70..0cd7824ca762 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -62,9 +62,19 @@ struct pmu_hw_events {
 	raw_spinlock_t		pmu_lock;
 };
 
+struct cpupmu_regs {
+	u32 pmc;
+	u32 pmcntenset;
+	u32 pmuseren;
+	u32 pmintenset;
+	u32 pmxevttype[8];
+	u32 pmxevtcnt[8];
+};
+
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	valid_cpus;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct perf_event *event);
@@ -81,6 +91,8 @@ struct arm_pmu {
 	int		(*request_irq)(struct arm_pmu *, irq_handler_t handler);
 	void		(*free_irq)(struct arm_pmu *);
 	int		(*map_event)(struct perf_event *event);
+	void		(*save_regs)(struct arm_pmu *, struct cpupmu_regs *);
+	void		(*restore_regs)(struct arm_pmu *, struct cpupmu_regs *);
 	int		num_events;
 	atomic_t	active_events;
 	struct mutex	reserve_mutex;
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index b93e34a9fdf1..f0a8627c9f1c 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,6 +16,10 @@
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL0	0
+#define PSCI_POWER_STATE_AFFINITY_LEVEL1	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL2	2
+#define PSCI_POWER_STATE_AFFINITY_LEVEL3	3
 
 struct psci_power_state {
 	u16	id;
@@ -29,20 +33,25 @@ struct psci_operations {
 	int (*cpu_off)(struct psci_power_state state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
 	int (*migrate)(unsigned long cpuid);
-	int (*affinity_info)(unsigned long target_affinity,
-			unsigned long lowest_affinity_level);
-	int (*migrate_info_type)(void);
 };
 
 extern struct psci_operations psci_ops;
 extern struct smp_operations psci_smp_ops;
 
 #ifdef CONFIG_ARM_PSCI
-int psci_init(void);
+void psci_init(void);
 bool psci_smp_available(void);
 #else
-static inline int psci_init(void) { }
+static inline void psci_init(void) { }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 
+#ifdef CONFIG_ARM_PSCI
+extern int __init psci_probe(void);
+#else
+static inline int psci_probe(void)
+{
+	return -ENODEV;
+}
+#endif
 #endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d3a22bebe6ce..610ccf33f5e7 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -81,6 +81,8 @@ extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
 
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
 struct smp_operations {
 #ifdef CONFIG_SMP
 	/*
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 6220e9fdf4c7..b07c09e5a0ac 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -97,19 +97,22 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned long tmp;
+	unsigned long contended, res;
 	u32 slock;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	subs	%1, %0, %0, ror #16\n"
-"	addeq	%0, %0, %3\n"
-"	strexeq	%1, %0, [%2]"
-	: "=&r" (slock), "=&r" (tmp)
-	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
-	: "cc");
-
-	if (tmp == 0) {
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%3]\n"
+		"	mov	%2, #0\n"
+		"	subs	%1, %0, %0, ror #16\n"
+		"	addeq	%0, %0, %4\n"
+		"	strexeq	%2, %0, [%3]"
+		: "=&r" (slock), "=&r" (contended), "=&r" (res)
+		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+		: "cc");
+	} while (res);
+
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
@@ -165,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp;
-
-	__asm__ __volatile__(
-"	ldrex	%0, [%1]\n"
-"	teq	%0, #0\n"
-"	strexeq	%0, %2, [%1]"
-	: "=&r" (tmp)
-	: "r" (&rw->lock), "r" (0x80000000)
-	: "cc");
-
-	if (tmp == 0) {
+	unsigned long contended, res;
+
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	teq	%0, #0\n"
+		"	strexeq	%1, %3, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock), "r" (0x80000000)
+		: "cc");
+	} while (res);
+
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
@@ -251,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp, tmp2 = 1;
-
-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	adds	%0, %0, #1\n"
-"	strexpl	%1, %0, [%2]\n"
-	: "=&r" (tmp), "+r" (tmp2)
-	: "r" (&rw->lock)
-	: "cc");
-
-	smp_mb();
-	return tmp2 == 0;
+	unsigned long contended, res;
+
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	adds	%0, %0, #1\n"
+		"	strexpl	%1, %0, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock)
+		: "cc");
+	} while (res);
+
+	/* If the lock is negative, then it is already held for write. */
+	if (contended < 0x80000000) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index f1d96d4e8092..73ddd7239b33 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
 		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		pr_warning("%s called with max args %d, handling only %d\n",
 			   __func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index aa9b4ac3fdf6..0baf7f0d9394 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -207,6 +207,12 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 #endif
 }
 
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index a3625d141c1d..c37459299fc9 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -535,6 +535,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 }
 #endif
 
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd2..983fa7c153a2 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -26,11 +26,45 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 0,					\
+	.wake_idx		= 0,					\
+	.forkexec_idx		= 0,					\
+									\
+	.flags			= 0*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_BALANCE_WAKE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				,					\
+	.last_balance		 = jiffies,				\
+	.balance_interval	= 1,					\
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
 
 #else
 
 static inline void init_cpu_topology(void) { }
 static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+	cpumask_t *cluster_mask) { return -EINVAL; }
 
 #endif
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7e1f76027f66..20e1c994669e 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -164,8 +164,9 @@ extern int __put_user_8(void *, unsigned long long);
 #define __put_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
+		const typeof(*(p)) __user *__tmp_p = (p);		\
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
-		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 141baa3f9a72..cbd61977c996 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -48,6 +48,5 @@
  */
 #define __IGNORE_fadvise64_64
 #define __IGNORE_migrate_pages
-#define __IGNORE_kcmp
 
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index 3688fd15a32d..7dcc10d67253 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -25,6 +25,7 @@
 #define HWCAP_IDIVT	(1 << 18)
 #define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
-
+#define HWCAP_LPAE	(1 << 20)
+#define HWCAP_EVTSTRM	(1 << 21)
 
 #endif /* _UAPI__ASMARM_HWCAP_H */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index dd9d90ab65d0..65160d5fe850 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,13 +17,13 @@ CFLAGS_REMOVE_return_address.o = -pg
 
 obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o sched_clock.o \
-		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
+		   setup.o signal.o sigreturn_codes.o \
+		   stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
 
-obj-$(CONFIG_OC_ETM)		+= etm.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c
index 90c50d4b43f7..5d1286d51154 100644
--- a/arch/arm/kernel/crash_dump.c
+++ b/arch/arm/kernel/crash_dump.c
@@ -39,7 +39,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!csize)
 		return 0;
 
-	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE);
 	if (!vaddr)
 		return -ENOMEM;
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d43c7e54ec6c..45a68d6bb2a3 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -192,6 +192,7 @@ __dabt_svc:
 	svc_entry
 	mov	r2, sp
 	dabt_helper
+ THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
@@ -415,9 +416,8 @@ __und_usr:
 	bne	__und_usr_thumb
 	sub	r4, r2, #4			@ ARM instr at LR - 4
 1:	ldrt	r0, [r4]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r0, r0				@ little endian instruction
-#endif
+ ARM_BE8(rev	r0, r0)				@ little endian instruction
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index bc5bc0a97131..11d68917d3b1 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -362,6 +362,16 @@ ENTRY(vector_swi)
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 	zero_fp
 
+#ifdef CONFIG_ALIGNMENT_TRAP
+	ldr	ip, __cr_alignment
+	ldr	ip, [ip]
+	mcr	p15, 0, ip, c1, c0		@ update control register
+#endif
+
+	enable_irq
+	ct_user_exit
+	get_thread_info tsk
+
 	/*
 	 * Get the system call number.
 	 */
@@ -375,13 +385,11 @@ ENTRY(vector_swi)
 #ifdef CONFIG_ARM_THUMB
 	tst	r8, #PSR_T_BIT
 	movne	r10, #0				@ no thumb OABI emulation
-	ldreq	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldreq	r10, [lr, #-4]		)	@ get SWI instruction
 #else
-	ldr	r10, [lr, #-4]			@ get SWI instruction
-#endif
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r10, r10			@ little endian instruction
+ USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
+ ARM_BE8(rev	r10, r10)			@ little endian instruction
 
 #elif defined(CONFIG_AEABI)
 
@@ -392,22 +400,13 @@ ENTRY(vector_swi)
 	/* Legacy ABI only, possibly thumb mode. */
 	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
-	ldreq	scno, [lr, #-4]
+ USER(	ldreq	scno, [lr, #-4]		)
 
 #else
 	/* Legacy ABI only. */
-	ldr	scno, [lr, #-4]			@ get SWI instruction
-#endif
-
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	ip, __cr_alignment
-	ldr	ip, [ip]
-	mcr	p15, 0, ip, c1, c0		@ update control register
+ USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
-	enable_irq
-	ct_user_exit
 
-	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -442,6 +441,21 @@ local_restart:
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+
+#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
+	/*
+	 * We failed to handle a fault trying to access the page
+	 * containing the swi instruction, but we're not really in a
+	 * position to return -EFAULT. Instead, return back to the
+	 * instruction and re-enter the user fault handling path trying
+	 * to page it in. This will likely result in sending SEGV to the
+	 * current task.
+	 */
+9001:
+	sub	lr, lr, #4
+	str	lr, [sp, #S_PC]
+	b	ret_fast_syscall
+#endif
 ENDPROC(vector_swi)
 
 	/*
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
deleted file mode 100644
index 8ff0ecdc637f..000000000000
--- a/arch/arm/kernel/etm.c
+++ /dev/null
@@ -1,660 +0,0 @@
-/*
- * linux/arch/arm/kernel/etm.c
- *
- * Driver for ARM's Embedded Trace Macrocell and Embedded Trace Buffer.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/sysrq.h>
-#include <linux/device.h>
-#include <linux/clk.h>
-#include <linux/amba/bus.h>
-#include <linux/fs.h>
-#include <linux/uaccess.h>
-#include <linux/miscdevice.h>
-#include <linux/vmalloc.h>
-#include <linux/mutex.h>
-#include <linux/module.h>
-#include <asm/hardware/coresight.h>
-#include <asm/sections.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/*
- * ETM tracer state
- */
-struct tracectx {
-	unsigned int	etb_bufsz;
-	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
-	unsigned long	flags;
-	int		ncmppairs;
-	int		etm_portsz;
-	struct device	*dev;
-	struct clk	*emu_clk;
-	struct mutex	mutex;
-};
-
-static struct tracectx tracer;
-
-static inline bool trace_isrunning(struct tracectx *t)
-{
-	return !!(t->flags & TRACER_RUNNING);
-}
-
-static int etm_setup_address_range(struct tracectx *t, int n,
-		unsigned long start, unsigned long end, int exclude, int data)
-{
-	u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \
-		    ETMAAT_NOVALCMP;
-
-	if (n < 1 || n > t->ncmppairs)
-		return -EINVAL;
-
-	/* comparators and ranges are numbered starting with 1 as opposed
-	 * to bits in a word */
-	n--;
-
-	if (data)
-		flags |= ETMAAT_DLOADSTORE;
-	else
-		flags |= ETMAAT_IEXEC;
-
-	/* first comparator for the range */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2));
-	etm_writel(t, start, ETMR_COMP_VAL(n * 2));
-
-	/* second comparator is right next to it */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
-	etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1));
-
-	flags = exclude ? ETMTE_INCLEXCL : 0;
-	etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL);
-
-	return 0;
-}
-
-static int trace_start(struct tracectx *t)
-{
-	u32 v;
-	unsigned long timeout = TRACER_TIMEOUT;
-
-	etb_unlock(t);
-
-	etb_writel(t, 0, ETBR_FORMATTERCTRL);
-	etb_writel(t, 1, ETBR_CTRL);
-
-	etb_lock(t);
-
-	/* configure etm */
-	v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
-
-	if (t->flags & TRACER_CYCLE_ACC)
-		v |= ETMCTRL_CYCLEACCURATE;
-
-	etm_unlock(t);
-
-	etm_writel(t, v, ETMR_CTRL);
-
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_setup_address_range(t, 1, (unsigned long)_stext,
-			(unsigned long)_etext, 0, 0);
-	etm_writel(t, 0, ETMR_TRACEENCTRL2);
-	etm_writel(t, 0, ETMR_TRACESSCTRL);
-	etm_writel(t, 0x6f, ETMR_TRACEENEVT);
-
-	v &= ~ETMCTRL_PROGRAM;
-	v |= ETMCTRL_PORTSEL;
-
-	etm_writel(t, v, ETMR_CTRL);
-
-	timeout = TRACER_TIMEOUT;
-	while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_lock(t);
-
-	t->flags |= TRACER_RUNNING;
-
-	return 0;
-}
-
-static int trace_stop(struct tracectx *t)
-{
-	unsigned long timeout = TRACER_TIMEOUT;
-
-	etm_unlock(t);
-
-	etm_writel(t, 0x440, ETMR_CTRL);
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_lock(t);
-
-	etb_unlock(t);
-	etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
-
-	timeout = TRACER_TIMEOUT;
-	while (etb_readl(t, ETBR_FORMATTERCTRL) &
-			ETBFF_MANUAL_FLUSH && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for formatter flush to commence "
-				"timed out\n");
-		etb_lock(t);
-		return -EFAULT;
-	}
-
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_lock(t);
-
-	t->flags &= ~TRACER_RUNNING;
-
-	return 0;
-}
-
-static int etb_getdatalen(struct tracectx *t)
-{
-	u32 v;
-	int rp, wp;
-
-	v = etb_readl(t, ETBR_STATUS);
-
-	if (v & 1)
-		return t->etb_bufsz;
-
-	rp = etb_readl(t, ETBR_READADDR);
-	wp = etb_readl(t, ETBR_WRITEADDR);
-
-	if (rp > wp) {
-		etb_writel(t, 0, ETBR_READADDR);
-		etb_writel(t, 0, ETBR_WRITEADDR);
-
-		return 0;
-	}
-
-	return wp - rp;
-}
-
-/* sysrq+v will always stop the running trace and leave it at that */
-static void etm_dump(void)
-{
-	struct tracectx *t = &tracer;
-	u32 first = 0;
-	int length;
-
-	if (!t->etb_regs) {
-		printk(KERN_INFO "No tracing hardware found\n");
-		return;
-	}
-
-	if (trace_isrunning(t))
-		trace_stop(t);
-
-	etb_unlock(t);
-
-	length = etb_getdatalen(t);
-
-	if (length == t->etb_bufsz)
-		first = etb_readl(t, ETBR_WRITEADDR);
-
-	etb_writel(t, first, ETBR_READADDR);
-
-	printk(KERN_INFO "Trace buffer contents length: %d\n", length);
-	printk(KERN_INFO "--- ETB buffer begin ---\n");
-	for (; length; length--)
-		printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM)));
-	printk(KERN_INFO "\n--- ETB buffer end ---\n");
-
-	/* deassert the overflow bit */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_WRITEADDR);
-
-	etb_lock(t);
-}
-
-static void sysrq_etm_dump(int key)
-{
-	dev_dbg(tracer.dev, "Dumping ETB buffer\n");
-	etm_dump();
-}
-
-static struct sysrq_key_op sysrq_etm_op = {
-	.handler = sysrq_etm_dump,
-	.help_msg = "etm-buffer-dump(v)",
-	.action_msg = "etm",
-};
-
-static int etb_open(struct inode *inode, struct file *file)
-{
-	if (!tracer.etb_regs)
-		return -ENODEV;
-
-	file->private_data = &tracer;
-
-	return nonseekable_open(inode, file);
-}
-
-static ssize_t etb_read(struct file *file, char __user *data,
-		size_t len, loff_t *ppos)
-{
-	int total, i;
-	long length;
-	struct tracectx *t = file->private_data;
-	u32 first = 0;
-	u32 *buf;
-
-	mutex_lock(&t->mutex);
-
-	if (trace_isrunning(t)) {
-		length = 0;
-		goto out;
-	}
-
-	etb_unlock(t);
-
-	total = etb_getdatalen(t);
-	if (total == t->etb_bufsz)
-		first = etb_readl(t, ETBR_WRITEADDR);
-
-	etb_writel(t, first, ETBR_READADDR);
-
-	length = min(total * 4, (int)len);
-	buf = vmalloc(length);
-
-	dev_dbg(t->dev, "ETB buffer length: %d\n", total);
-	dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS));
-	for (i = 0; i < length / 4; i++)
-		buf[i] = etb_readl(t, ETBR_READMEM);
-
-	/* the only way to deassert overflow bit in ETB status is this */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_WRITEADDR);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-
-	etb_lock(t);
-
-	length -= copy_to_user(data, buf, length);
-	vfree(buf);
-
-out:
-	mutex_unlock(&t->mutex);
-
-	return length;
-}
-
-static int etb_release(struct inode *inode, struct file *file)
-{
-	/* there's nothing to do here, actually */
-	return 0;
-}
-
-static const struct file_operations etb_fops = {
-	.owner = THIS_MODULE,
-	.read = etb_read,
-	.open = etb_open,
-	.release = etb_release,
-	.llseek = no_llseek,
-};
-
-static struct miscdevice etb_miscdev = {
-	.name = "tracebuf",
-	.minor = 0,
-	.fops = &etb_fops,
-};
-
-static int etb_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct tracectx *t = &tracer;
-	int ret = 0;
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret)
-		goto out;
-
-	t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
-	if (!t->etb_regs) {
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
-	amba_set_drvdata(dev, t);
-
-	etb_miscdev.parent = &dev->dev;
-
-	ret = misc_register(&etb_miscdev);
-	if (ret)
-		goto out_unmap;
-
-	t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
-	if (IS_ERR(t->emu_clk)) {
-		dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
-		return -EFAULT;
-	}
-
-	clk_enable(t->emu_clk);
-
-	etb_unlock(t);
-	t->etb_bufsz = etb_readl(t, ETBR_DEPTH);
-	dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz);
-
-	/* make sure trace capture is disabled */
-	etb_writel(t, 0, ETBR_CTRL);
-	etb_writel(t, 0x1000, ETBR_FORMATTERCTRL);
-	etb_lock(t);
-
-	dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n");
-
-out:
-	return ret;
-
-out_unmap:
-	amba_set_drvdata(dev, NULL);
-	iounmap(t->etb_regs);
-
-out_release:
-	amba_release_regions(dev);
-
-	return ret;
-}
-
-static int etb_remove(struct amba_device *dev)
-{
-	struct tracectx *t = amba_get_drvdata(dev);
-
-	amba_set_drvdata(dev, NULL);
-
-	iounmap(t->etb_regs);
-	t->etb_regs = NULL;
-
-	clk_disable(t->emu_clk);
-	clk_put(t->emu_clk);
-
-	amba_release_regions(dev);
-
-	return 0;
-}
-
-static struct amba_id etb_ids[] = {
-	{
-		.id	= 0x0003b907,
-		.mask	= 0x0007ffff,
-	},
-	{ 0, 0 },
-};
-
-static struct amba_driver etb_driver = {
-	.drv		= {
-		.name	= "etb",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= etb_probe,
-	.remove		= etb_remove,
-	.id_table	= etb_ids,
-};
-
-/* use a sysfs file "trace_running" to start/stop tracing */
-static ssize_t trace_running_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	return sprintf(buf, "%x\n", trace_isrunning(&tracer));
-}
-
-static ssize_t trace_running_store(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   const char *buf, size_t n)
-{
-	unsigned int value;
-	int ret;
-
-	if (sscanf(buf, "%u", &value) != 1)
-		return -EINVAL;
-
-	mutex_lock(&tracer.mutex);
-	ret = value ? trace_start(&tracer) : trace_stop(&tracer);
-	mutex_unlock(&tracer.mutex);
-
-	return ret ? : n;
-}
-
-static struct kobj_attribute trace_running_attr =
-	__ATTR(trace_running, 0644, trace_running_show, trace_running_store);
-
-static ssize_t trace_info_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st;
-	int datalen;
-
-	etb_unlock(&tracer);
-	datalen = etb_getdatalen(&tracer);
-	etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
-	etb_ra = etb_readl(&tracer, ETBR_READADDR);
-	etb_st = etb_readl(&tracer, ETBR_STATUS);
-	etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
-	etb_lock(&tracer);
-
-	etm_unlock(&tracer);
-	etm_ctrl = etm_readl(&tracer, ETMR_CTRL);
-	etm_st = etm_readl(&tracer, ETMR_STATUS);
-	etm_lock(&tracer);
-
-	return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
-			"ETBR_WRITEADDR:\t%08x\n"
-			"ETBR_READADDR:\t%08x\n"
-			"ETBR_STATUS:\t%08x\n"
-			"ETBR_FORMATTERCTRL:\t%08x\n"
-			"ETMR_CTRL:\t%08x\n"
-			"ETMR_STATUS:\t%08x\n",
-			datalen,
-			tracer.ncmppairs,
-			etb_wa,
-			etb_ra,
-			etb_st,
-			etb_fc,
-			etm_ctrl,
-			etm_st
-			);
-}
-
-static struct kobj_attribute trace_info_attr =
-	__ATTR(trace_info, 0444, trace_info_show, NULL);
-
-static ssize_t trace_mode_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	return sprintf(buf, "%d %d\n",
-			!!(tracer.flags & TRACER_CYCLE_ACC),
-			tracer.etm_portsz);
-}
-
-static ssize_t trace_mode_store(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   const char *buf, size_t n)
-{
-	unsigned int cycacc, portsz;
-
-	if (sscanf(buf, "%u %u", &cycacc, &portsz) != 2)
-		return -EINVAL;
-
-	mutex_lock(&tracer.mutex);
-	if (cycacc)
-		tracer.flags |= TRACER_CYCLE_ACC;
-	else
-		tracer.flags &= ~TRACER_CYCLE_ACC;
-
-	tracer.etm_portsz = portsz & 0x0f;
-	mutex_unlock(&tracer.mutex);
-
-	return n;
-}
-
-static struct kobj_attribute trace_mode_attr =
-	__ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store);
-
-static int etm_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct tracectx *t = &tracer;
-	int ret = 0;
-
-	if (t->etm_regs) {
-		dev_dbg(&dev->dev, "ETM already initialized\n");
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret)
-		goto out;
-
-	t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
-	if (!t->etm_regs) {
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
-	amba_set_drvdata(dev, t);
-
-	mutex_init(&t->mutex);
-	t->dev = &dev->dev;
-	t->flags = TRACER_CYCLE_ACC;
-	t->etm_portsz = 1;
-
-	etm_unlock(t);
-	(void)etm_readl(t, ETMMR_PDSR);
-	/* dummy first read */
-	(void)etm_readl(&tracer, ETMMR_OSSRR);
-
-	t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
-	etm_writel(t, 0x440, ETMR_CTRL);
-	etm_lock(t);
-
-	ret = sysfs_create_file(&dev->dev.kobj,
-			&trace_running_attr.attr);
-	if (ret)
-		goto out_unmap;
-
-	/* failing to create any of these two is not fatal */
-	ret = sysfs_create_file(&dev->dev.kobj, &trace_info_attr.attr);
-	if (ret)
-		dev_dbg(&dev->dev, "Failed to create trace_info in sysfs\n");
-
-	ret = sysfs_create_file(&dev->dev.kobj, &trace_mode_attr.attr);
-	if (ret)
-		dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n");
-
-	dev_dbg(t->dev, "ETM AMBA driver initialized.\n");
-
-out:
-	return ret;
-
-out_unmap:
-	amba_set_drvdata(dev, NULL);
-	iounmap(t->etm_regs);
-
-out_release:
-	amba_release_regions(dev);
-
-	return ret;
-}
-
-static int etm_remove(struct amba_device *dev)
-{
-	struct tracectx *t = amba_get_drvdata(dev);
-
-	amba_set_drvdata(dev, NULL);
-
-	iounmap(t->etm_regs);
-	t->etm_regs = NULL;
-
-	amba_release_regions(dev);
-
-	sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr);
-	sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr);
-	sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr);
-
-	return 0;
-}
-
-static struct amba_id etm_ids[] = {
-	{
-		.id	= 0x0003b921,
-		.mask	= 0x0007ffff,
-	},
-	{ 0, 0 },
-};
-
-static struct amba_driver etm_driver = {
-	.drv		= {
-		.name   = "etm",
-		.owner  = THIS_MODULE,
-	},
-	.probe		= etm_probe,
-	.remove		= etm_remove,
-	.id_table	= etm_ids,
-};
-
-static int __init etm_init(void)
-{
-	int retval;
-
-	retval = amba_driver_register(&etb_driver);
-	if (retval) {
-		printk(KERN_ERR "Failed to register etb\n");
-		return retval;
-	}
-
-	retval = amba_driver_register(&etm_driver);
-	if (retval) {
-		amba_driver_unregister(&etb_driver);
-		printk(KERN_ERR "Failed to probe etm\n");
-		return retval;
-	}
-
-	/* not being able to install this handler is not fatal */
-	(void)register_sysrq_key('v', &sysrq_etm_op);
-
-	return 0;
-}
-
-device_initcall(etm_init);
-
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 8bac553fe213..11284e744c80 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -77,6 +77,7 @@
 
 	__HEAD
 ENTRY(stext)
+ ARM_BE8(setend	be )			@ ensure we are in BE8 mode
 
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
@@ -342,7 +343,6 @@ __turn_mmu_on_loc:
 	.long	__turn_mmu_on_end
 
 #if defined(CONFIG_SMP)
-	__CPUINIT
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
@@ -351,6 +351,9 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
+
+ ARM_BE8(setend	be)				@ ensure we are in BE8 mode
+
 #ifdef CONFIG_ARM_VIRT_EXT
 	bl	__hyp_stub_install_secondary
 #endif
@@ -584,8 +587,10 @@ __fixup_a_pv_table:
 	b	2f
 1:	add     r7, r3
 	ldrh	ip, [r7, #2]
+ARM_BE8(rev16	ip, ip)
 	and	ip, 0x8f00
 	orr	ip, r6	@ mask in offset bits 31-24
+ARM_BE8(rev16	ip, ip)
 	strh	ip, [r7, #2]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
@@ -594,8 +599,14 @@ __fixup_a_pv_table:
 #else
 	b	2f
 1:	ldr	ip, [r7, r3]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	@ in BE8, we load data in BE, but instructions still in LE
+	bic	ip, ip, #0xff000000
+	orr	ip, ip, r6, lsl#24
+#else
 	bic	ip, ip, #0x000000ff
 	orr	ip, ip, r6	@ mask in offset bits 31-24
+#endif
 	str	ip, [r7, r3]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 1fd749ee4a1b..7eee611b6ee5 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -29,6 +29,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/smp.h>
 #include <linux/cpu_pm.h>
+#include <linux/coresight.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
@@ -36,7 +37,6 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/kdebug.h>
 #include <asm/traps.h>
-#include <asm/hardware/coresight.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -975,7 +975,7 @@ static void reset_ctrl_regs(void *unused)
 	 * Unconditionally clear the OS lock by writing a value
 	 * other than CS_LAR_KEY to the access register.
 	 */
-	ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY);
+	ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK);
 	isb();
 
 	/*
@@ -1049,7 +1049,8 @@ static struct notifier_block dbg_cpu_pm_nb = {
 
 static void __init pm_init(void)
 {
-	cpu_pm_register_notifier(&dbg_cpu_pm_nb);
+	if (has_ossr)
+		cpu_pm_register_notifier(&dbg_cpu_pm_nb);
 }
 #else
 static inline void pm_init(void)
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 1315c4ccfa56..dbe21107945a 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -153,6 +153,8 @@ THUMB(	orr	r7, #(1 << 30)	)	@ HSCTLR.TE
 	mrc	p15, 4, r7, c14, c1, 0	@ CNTHCTL
 	orr	r7, r7, #3		@ PL1PCEN | PL1PCTEN
 	mcr	p15, 4, r7, c14, c1, 0	@ CNTHCTL
+	mov	r7, #0
+	mcrr	p15, 4, r7, r7, c14	@ CNTVOFF
 1:
 #endif
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17b8f38..1e782bdeee49 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index 18a76282970e..380c20fb9c85 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <asm/system_info.h>
+#include <asm/opcodes.h>
 
 #include "kprobes.h"
 
@@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 	if (handler) {
 		/* We can emulate the instruction in (possibly) modified form */
-		asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+		asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) |
+						   (rn << 16) | reglist);
 		asi->insn_handler = handler;
 		return INSN_GOOD;
 	}
@@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 #ifdef CONFIG_THUMB2_KERNEL
 	if (thumb) {
 		u16 *thumb_insn = (u16 *)asi->insn;
-		thumb_insn[1] = 0x4770; /* Thumb bx lr */
-		thumb_insn[2] = 0x4770; /* Thumb bx lr */
+		/* Thumb bx lr */
+		thumb_insn[1] = __opcode_to_mem_thumb16(0x4770);
+		thumb_insn[2] = __opcode_to_mem_thumb16(0x4770);
 		return insn;
 	}
-	asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */
 #else
-	asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */
 #endif
 	/* Make an ARM instruction unconditional */
 	if (insn < 0xe0000000)
@@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 	if (thumb) {
 		u16 *ip = (u16 *)asi->insn;
 		if (is_wide_instruction(insn))
-			*ip++ = insn >> 16;
-		*ip++ = insn;
+			*ip++ = __opcode_to_mem_thumb16(insn >> 16);
+		*ip++ = __opcode_to_mem_thumb16(insn);
 		return;
 	}
 #endif
-	asi->insn[0] = insn;
+	asi->insn[0] = __opcode_to_mem_arm(insn);
 }
 
 /*
diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c
index 6123daf397a7..b82e798983c4 100644
--- a/arch/arm/kernel/kprobes-thumb.c
+++ b/arch/arm/kernel/kprobes-thumb.c
@@ -163,9 +163,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi);
 
 	/* Fixup modified instruction to have halfwords in correct order...*/
-	insn = asi->insn[0];
-	((u16 *)asi->insn)[0] = insn >> 16;
-	((u16 *)asi->insn)[1] = insn & 0xffff;
+	insn = __mem_to_opcode_arm(asi->insn[0]);
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16);
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff);
 
 	return ret;
 }
@@ -1153,7 +1153,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
 	insn &= ~0x00ff;
 	insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
-	((u16 *)asi->insn)[0] = insn;
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn);
 	asi->insn_handler = t16_emulate_hiregs;
 	return INSN_GOOD;
 }
@@ -1182,8 +1182,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * and call it with R9=SP and LR in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe929;		/* 1st half STMDB R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half STMDB R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = t16_emulate_push;
 	return INSN_GOOD;
 }
@@ -1232,8 +1234,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * and call it with R9=SP and PC in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe8b9;		/* 1st half LDMIA R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half LDMIA R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc
 					 : t16_emulate_pop_nopc;
 	return INSN_GOOD;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 170e9f34003f..1c6ece51781c 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -26,6 +26,7 @@
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
+#include <asm/opcodes.h>
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
@@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 #ifdef CONFIG_THUMB2_KERNEL
 	thumb = true;
 	addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
-	insn = ((u16 *)addr)[0];
+	insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
 	if (is_wide_instruction(insn)) {
-		insn <<= 16;
-		insn |= ((u16 *)addr)[1];
+		u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
+		insn = __opcode_thumb32_compose(insn, inst2);
 		decode_insn = thumb32_kprobe_decode_insn;
 	} else
 		decode_insn = thumb16_kprobe_decode_insn;
@@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	thumb = false;
 	if (addr & 0x3)
 		return -EINVAL;
-	insn = *p->addr;
+	insn = __mem_to_opcode_arm(*p->addr);
 	decode_insn = arm_kprobe_decode_insn;
 #endif
 
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c446bf..70ae735dec53 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -14,10 +14,11 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/fncpy.h>
 #include <asm/mach-types.h>
 #include <asm/system_misc.h>
 
-extern const unsigned char relocate_new_kernel[];
+extern void relocate_new_kernel(void);
 extern const unsigned int relocate_new_kernel_size;
 
 extern unsigned long kexec_start_address;
@@ -73,6 +74,7 @@ void machine_crash_nonpanic_core(void *unused)
 	crash_save_cpu(&regs, smp_processor_id());
 	flush_cache_all();
 
+	set_cpu_online(smp_processor_id(), false);
 	atomic_dec(&waiting_for_crash_ipi);
 	while (1)
 		cpu_relax();
@@ -132,6 +134,8 @@ void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list;
 	unsigned long reboot_code_buffer_phys;
+	unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
+	unsigned long reboot_entry_phys;
 	void *reboot_code_buffer;
 
 	if (num_online_cpus() > 1) {
@@ -155,16 +159,23 @@ void machine_kexec(struct kimage *image)
 
 
 	/* copy our kernel relocation code to the control code page */
-	memcpy(reboot_code_buffer,
-	       relocate_new_kernel, relocate_new_kernel_size);
+	reboot_entry = fncpy(reboot_code_buffer,
+			     reboot_entry,
+			     relocate_new_kernel_size);
+	reboot_entry_phys = (unsigned long)reboot_entry +
+		(reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
 
-
-	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	if (kexec_reinit)
 		kexec_reinit();
 
-	soft_restart(reboot_code_buffer_phys);
+	soft_restart(reboot_entry_phys);
+}
+
+void arch_crash_save_vmcoreinfo(void)
+{
+#ifdef CONFIG_ARM_LPAE
+	VMCOREINFO_CONFIG(ARM_LPAE);
+#endif
 }
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 1e9be5d25e56..7e137873083d 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -24,6 +24,7 @@
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
 #include <asm/unwind.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_XIP_KERNEL
 /*
@@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		Elf32_Sym *sym;
 		const char *symname;
 		s32 offset;
+		u32 tmp;
 #ifdef CONFIG_THUMB2_KERNEL
 		u32 upper, lower, sign, j1, j2;
 #endif
@@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		case R_ARM_PC24:
 		case R_ARM_CALL:
 		case R_ARM_JUMP24:
-			offset = (*(u32 *)loc & 0x00ffffff) << 2;
+			offset = __mem_to_opcode_arm(*(u32 *)loc);
+			offset = (offset & 0x00ffffff) << 2;
 			if (offset & 0x02000000)
 				offset -= 0x04000000;
 
@@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			}
 
 			offset >>= 2;
+			offset &= 0x00ffffff;
 
-			*(u32 *)loc &= 0xff000000;
-			*(u32 *)loc |= offset & 0x00ffffff;
+			*(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
+			*(u32 *)loc |= __opcode_to_mem_arm(offset);
 			break;
 
 	       case R_ARM_V4BX:
@@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			* other bits to re-code instruction as
 			* MOV PC,Rm.
 			*/
-		       *(u32 *)loc &= 0xf000000f;
-		       *(u32 *)loc |= 0x01a0f000;
+		       *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
+		       *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
 		       break;
 
 		case R_ARM_PREL31:
@@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
 		case R_ARM_MOVW_ABS_NC:
 		case R_ARM_MOVT_ABS:
-			offset = *(u32 *)loc;
+			offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
 			offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
 			offset = (offset ^ 0x8000) - 0x8000;
 
@@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
 				offset >>= 16;
 
-			*(u32 *)loc &= 0xfff0f000;
-			*(u32 *)loc |= ((offset & 0xf000) << 4) |
-					(offset & 0x0fff);
+			tmp &= 0xfff0f000;
+			tmp |= ((offset & 0xf000) << 4) |
+				(offset & 0x0fff);
+
+			*(u32 *)loc = __opcode_to_mem_arm(tmp);
 			break;
 
 #ifdef CONFIG_THUMB2_KERNEL
 		case R_ARM_THM_CALL:
 		case R_ARM_THM_JUMP24:
-			upper = *(u16 *)loc;
-			lower = *(u16 *)(loc + 2);
+			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
 			/*
 			 * 25 bit signed address range (Thumb-2 BL and B.W
@@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			sign = (offset >> 24) & 1;
 			j1 = sign ^ (~(offset >> 23) & 1);
 			j2 = sign ^ (~(offset >> 22) & 1);
-			*(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+			upper = (u16)((upper & 0xf800) | (sign << 10) |
 					    ((offset >> 12) & 0x03ff));
-			*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
-						  (j1 << 13) | (j2 << 11) |
-						  ((offset >> 1) & 0x07ff));
+			lower = (u16)((lower & 0xd000) |
+				      (j1 << 13) | (j2 << 11) |
+				      ((offset >> 1) & 0x07ff));
+
+			*(u16 *)loc = __opcode_to_mem_thumb16(upper);
+			*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
 			break;
 
 		case R_ARM_THM_MOVW_ABS_NC:
 		case R_ARM_THM_MOVT_ABS:
-			upper = *(u16 *)loc;
-			lower = *(u16 *)(loc + 2);
+			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
 			/*
 			 * MOVT/MOVW instructions encoding in Thumb-2:
@@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
 				offset >>= 16;
 
-			*(u16 *)loc = (u16)((upper & 0xfbf0) |
-					    ((offset & 0xf000) >> 12) |
-					    ((offset & 0x0800) >> 1));
-			*(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
-						  ((offset & 0x0700) << 4) |
-						  (offset & 0x00ff));
+			upper = (u16)((upper & 0xfbf0) |
+				      ((offset & 0xf000) >> 12) |
+				      ((offset & 0x0800) >> 1));
+			lower = (u16)((lower & 0x8f00) |
+				      ((offset & 0x0700) << 4) |
+				      (offset & 0x00ff));
+			*(u16 *)loc = __opcode_to_mem_thumb16(upper);
+			*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
 			break;
 #endif
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index e19edc6f2d15..b41749fe56dc 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -86,6 +87,9 @@ armpmu_map_event(struct perf_event *event,
 		return armpmu_map_cache_event(cache_map, config);
 	case PERF_TYPE_RAW:
 		return armpmu_map_raw_event(raw_event_mask, config);
+	default:
+		if (event->attr.type >= PERF_TYPE_MAX)
+			return armpmu_map_raw_event(raw_event_mask, config);
 	}
 
 	return -ENOENT;
@@ -163,6 +167,8 @@ armpmu_stop(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -179,6 +185,8 @@ static void armpmu_start(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -206,6 +214,9 @@ armpmu_del(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
+
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
@@ -222,6 +233,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return 0;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -303,11 +318,18 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
 	struct platform_device *plat_device = armpmu->plat_device;
 	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
+	int ret;
+	u64 start_clock, finish_clock;
 
+	start_clock = sched_clock();
 	if (plat && plat->handle_irq)
-		return plat->handle_irq(irq, dev, armpmu->handle_irq);
+		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
 	else
-		return armpmu->handle_irq(irq, dev);
+		ret = armpmu->handle_irq(irq, dev);
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+	return ret;
 }
 
 static void
@@ -424,6 +446,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 0e9609657c79..e0665b871f5b 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) "CPU PMU: " fmt
 
 #include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
@@ -31,33 +32,36 @@
 #include <asm/pmu.h>
 
 /* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu);
 
 static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
 static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
 static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 
+static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs);
+
 /*
  * Despite the names, these two functions are CPU-specific and are used
  * by the OProfile/perf code.
  */
 const char *perf_pmu_name(void)
 {
-	if (!cpu_pmu)
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
+	if (!pmu)
 		return NULL;
 
-	return cpu_pmu->name;
+	return pmu->name;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_name);
 
 int perf_num_counters(void)
 {
-	int max_events = 0;
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
 
-	if (cpu_pmu != NULL)
-		max_events = cpu_pmu->num_events;
+	if (!pmu)
+		return 0;
 
-	return max_events;
+	return pmu->num_events;
 }
 EXPORT_SYMBOL_GPL(perf_num_counters);
 
@@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
+		if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 			continue;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq >= 0)
@@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 {
 	int i, err, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	if (!pmu_device)
 		return -ENODEV;
@@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 
 	for (i = 0; i < irqs; ++i) {
 		err = 0;
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
@@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		 * assume that we're running on a uniprocessor machine and
 		 * continue. Otherwise, continue without this interrupt.
 		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+		if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
 			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
 				    irq, i);
 			continue;
@@ -126,7 +134,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 			return err;
 		}
 
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
 	}
 
 	return 0;
@@ -135,7 +143,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int cpu;
-	for_each_possible_cpu(cpu) {
+	for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
 		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
@@ -148,7 +156,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+		on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
 }
 
 /*
@@ -160,21 +168,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 static int __cpuinit cpu_pmu_notify(struct notifier_block *b,
 				    unsigned long action, void *hcpu)
 {
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu);
+
 	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
 		return NOTIFY_DONE;
 
-	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(cpu_pmu);
+	if (pmu && pmu->reset)
+		pmu->reset(pmu);
 	else
 		return NOTIFY_DONE;
 
 	return NOTIFY_OK;
 }
 
+static int cpu_pmu_pm_notify(struct notifier_block *b,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = smp_processor_id();
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu);
+	struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu);
+
+	if (!pmu)
+		return NOTIFY_DONE;
+
+	if (action == CPU_PM_ENTER && pmu->save_regs) {
+		pmu->save_regs(pmu, pmuregs);
+	} else if (action == CPU_PM_EXIT && pmu->restore_regs) {
+		pmu->restore_regs(pmu, pmuregs);
+	}
+
+	return NOTIFY_OK;
+}
+
 static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = {
 	.notifier_call = cpu_pmu_notify,
 };
 
+static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = {
+	.notifier_call = cpu_pmu_pm_notify,
+};
+
 /*
  * PMU platform driver and devicetree bindings.
  */
@@ -236,6 +269,9 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		break;
 	}
 
+	/* assume PMU support all the CPUs in this case */
+	cpumask_setall(&pmu->valid_cpus);
+
 	put_cpu();
 	return ret;
 }
@@ -243,15 +279,10 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
-	int ret = -ENODEV;
-
-	if (cpu_pmu) {
-		pr_info("attempt to register multiple PMU devices!");
-		return -ENOSPC;
-	}
+	int ret = 0;
+	int cpu;
 
 	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
 	if (!pmu) {
@@ -260,8 +291,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-		ret = init_fn(pmu);
+		smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+		struct device_node *ncluster;
+		int cluster = -1;
+		cpumask_t sibling_mask;
+
+		ncluster = of_parse_phandle(node, "cluster", 0);
+		if (ncluster) {
+			int len;
+			const u32 *hwid;
+			hwid = of_get_property(ncluster, "reg", &len);
+			if (hwid && len == 4)
+				cluster = be32_to_cpup(hwid);
+		}
+		/* set sibling mask to all cpu mask if socket is not specified */
+		if (cluster == -1 ||
+			cluster_to_logical_mask(cluster, &sibling_mask))
+			cpumask_setall(&sibling_mask);
+
+		smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+		/* now set the valid_cpus after init */
+		cpumask_copy(&pmu->valid_cpus, &sibling_mask);
 	} else {
 		ret = probe_current_pmu(pmu);
 	}
@@ -271,10 +322,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
-	cpu_pmu_init(cpu_pmu);
-	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+	for_each_cpu_mask(cpu, pmu->valid_cpus)
+		per_cpu(cpu_pmu, cpu) = pmu;
+
+	pmu->plat_device = pdev;
+	cpu_pmu_init(pmu);
+	ret = armpmu_register(pmu, -1);
 
 	if (!ret)
 		return 0;
@@ -303,9 +356,17 @@ static int __init register_pmu_driver(void)
 	if (err)
 		return err;
 
+	err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier);
+	if (err) {
+		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+		return err;
+	}
+
 	err = platform_driver_register(&cpu_pmu_driver);
-	if (err)
+	if (err) {
+		cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier);
 		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+	}
 
 	return err;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb053a7..654db5030c31 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 }
 #endif
 
+static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc));
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset));
+	asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren));
+	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset));
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mrc p15, 0, %0, c9, c13, 1"
+					: "=r"(regs->pmxevttype[cnt]));
+		asm volatile("mrc p15, 0, %0, c9, c13, 2"
+					: "=r"(regs->pmxevtcnt[cnt]));
+	}
+	return;
+}
+
+static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset));
+	asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren));
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset));
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mcr p15, 0, %0, c9, c13, 1"
+					: : "r"(regs->pmxevttype[cnt]));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2"
+					: : "r"(regs->pmxevtcnt[cnt]));
+	}
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc));
+}
+
 static void armv7pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
@@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
+	cpu_pmu->save_regs	= armv7pmu_save_regs;
+	cpu_pmu->restore_regs	= armv7pmu_restore_regs;
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
@@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void)
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A8";
+	cpu_pmu->name		= "ARMv7_Cortex_A8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A9";
+	cpu_pmu->name		= "ARMv7_Cortex_A9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A5";
+	cpu_pmu->name		= "ARMv7_Cortex_A5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A15";
+	cpu_pmu->name		= "ARMv7_Cortex_A15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A7";
+	cpu_pmu->name		= "ARMv7_Cortex_A7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 5bc2615268d4..ac4c2e5e17e4 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -408,6 +408,7 @@ EXPORT_SYMBOL(dump_fpu);
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
+	unsigned long stack_page;
 	int count = 0;
 	if (!p || p == current || p->state == TASK_RUNNING)
 		return 0;
@@ -416,9 +417,11 @@ unsigned long get_wchan(struct task_struct *p)
 	frame.sp = thread_saved_sp(p);
 	frame.lr = 0;			/* recovered from the stack */
 	frame.pc = thread_saved_pc(p);
+	stack_page = (unsigned long)task_stack_page(p);
 	do {
-		int ret = unwind_frame(&frame);
-		if (ret < 0)
+		if (frame.sp < stack_page ||
+		    frame.sp >= stack_page + THREAD_SIZE ||
+		    unwind_frame(&frame) < 0)
 			return 0;
 		if (!in_sched_functions(frame.pc))
 			return frame.pc;
@@ -466,7 +469,7 @@ int in_gate_area_no_mm(unsigned long addr)
 {
 	return in_gate_area(NULL, addr);
 }
-#define is_gate_vma(vma)	((vma) = &gate_vma)
+#define is_gate_vma(vma)	((vma) == &gate_vma)
 #else
 #define is_gate_vma(vma)	0
 #endif
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index f73891b6b730..0daf4f252284 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -17,58 +17,72 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/reboot.h>
-#include <linux/pm.h>
-#include <uapi/linux/psci.h>
+#include <linux/string.h>
 
 #include <asm/compiler.h>
 #include <asm/errno.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/psci.h>
-#include <asm/system_misc.h>
 
 struct psci_operations psci_ops;
 
+/* Type of psci support. Currently can only be enabled or disabled */
+#define PSCI_SUP_DISABLED		0
+#define PSCI_SUP_ENABLED		1
+
+static unsigned int psci;
 static int (*invoke_psci_fn)(u32, u32, u32, u32);
-typedef int (*psci_initcall_t)(const struct device_node *);
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
-	PSCI_FN_AFFINITY_INFO,
-	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
 static u32 psci_function_id[PSCI_FN_MAX];
 
+#define PSCI_RET_SUCCESS		0
+#define PSCI_RET_EOPNOTSUPP		-1
+#define PSCI_RET_EINVAL			-2
+#define PSCI_RET_EPERM			-3
+#define PSCI_RET_EALREADYON		-4
+
 static int psci_to_linux_errno(int errno)
 {
 	switch (errno) {
 	case PSCI_RET_SUCCESS:
 		return 0;
-	case PSCI_RET_NOT_SUPPORTED:
+	case PSCI_RET_EOPNOTSUPP:
 		return -EOPNOTSUPP;
-	case PSCI_RET_INVALID_PARAMS:
+	case PSCI_RET_EINVAL:
 		return -EINVAL;
-	case PSCI_RET_DENIED:
+	case PSCI_RET_EPERM:
 		return -EPERM;
+	case PSCI_RET_EALREADYON:
+		return -EAGAIN;
 	};
 
 	return -EINVAL;
 }
 
+#define PSCI_POWER_STATE_ID_MASK	0xffff
+#define PSCI_POWER_STATE_ID_SHIFT	0
+#define PSCI_POWER_STATE_TYPE_MASK	0x1
+#define PSCI_POWER_STATE_TYPE_SHIFT	16
+#define PSCI_POWER_STATE_AFFL_MASK	0x3
+#define PSCI_POWER_STATE_AFFL_SHIFT	24
+
 static u32 psci_power_state_pack(struct psci_power_state state)
 {
-	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
-			& PSCI_0_2_POWER_STATE_ID_MASK) |
-		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
-		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
-		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
-		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
+	return	((state.id & PSCI_POWER_STATE_ID_MASK)
+			<< PSCI_POWER_STATE_ID_SHIFT)	|
+		((state.type & PSCI_POWER_STATE_TYPE_MASK)
+			<< PSCI_POWER_STATE_TYPE_SHIFT)	|
+		((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
+			<< PSCI_POWER_STATE_AFFL_SHIFT);
 }
 
 /*
@@ -105,14 +119,6 @@ static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
 	return function_id;
 }
 
-static int psci_get_version(void)
-{
-	int err;
-
-	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
-	return err;
-}
-
 static int psci_cpu_suspend(struct psci_power_state state,
 			    unsigned long entry_point)
 {
@@ -156,36 +162,29 @@ static int psci_migrate(unsigned long cpuid)
 	return psci_to_linux_errno(err);
 }
 
-static int psci_affinity_info(unsigned long target_affinity,
-		unsigned long lowest_affinity_level)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
-	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
-	return err;
-}
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci",	},
+	{},
+};
 
-static int psci_migrate_info_type(void)
+void __init psci_init(void)
 {
-	int err;
-	u32 fn;
+	struct device_node *np;
+	const char *method;
+	u32 id;
 
-	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
-	err = invoke_psci_fn(fn, 0, 0, 0);
-	return err;
-}
+	if (psci == PSCI_SUP_DISABLED)
+		return;
 
-static int get_set_conduit_method(struct device_node *np)
-{
-	const char *method;
+	np = of_find_matching_node(NULL, psci_of_match);
+	if (!np)
+		return;
 
-	pr_info("probing for conduit method from DT.\n");
+	pr_info("probing function IDs from device-tree\n");
 
 	if (of_property_read_string(np, "method", &method)) {
-		pr_warn("missing \"method\" property\n");
-		return -ENXIO;
+		pr_warning("missing \"method\" property\n");
+		goto out_put_node;
 	}
 
 	if (!strcmp("hvc", method)) {
@@ -193,99 +192,10 @@ static int get_set_conduit_method(struct device_node *np)
 	} else if (!strcmp("smc", method)) {
 		invoke_psci_fn = __invoke_psci_fn_smc;
 	} else {
-		pr_warn("invalid \"method\" property: %s\n", method);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
-}
-
-static void psci_sys_poweroff(void)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
-}
-
-/*
- * PSCI Function IDs for v0.2+ are well defined so use
- * standard values.
- */
-static int psci_0_2_init(struct device_node *np)
-{
-	int err, ver;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
+		pr_warning("invalid \"method\" property: %s\n", method);
 		goto out_put_node;
-
-	ver = psci_get_version();
-
-	if (ver == PSCI_RET_NOT_SUPPORTED) {
-		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
-		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
-		err = -EOPNOTSUPP;
-		goto out_put_node;
-	} else {
-		pr_info("PSCIv%d.%d detected in firmware.\n",
-				PSCI_VERSION_MAJOR(ver),
-				PSCI_VERSION_MINOR(ver));
-
-		if (PSCI_VERSION_MAJOR(ver) == 0 &&
-				PSCI_VERSION_MINOR(ver) < 2) {
-			err = -EINVAL;
-			pr_err("Conflicting PSCI version detected.\n");
-			goto out_put_node;
-		}
 	}
 
-	pr_info("Using standard PSCI v0.2 function IDs\n");
-	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
-	psci_ops.cpu_suspend = psci_cpu_suspend;
-
-	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
-	psci_ops.cpu_off = psci_cpu_off;
-
-	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
-	psci_ops.cpu_on = psci_cpu_on;
-
-	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
-	psci_ops.migrate = psci_migrate;
-
-	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
-	psci_ops.affinity_info = psci_affinity_info;
-
-	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
-		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
-	psci_ops.migrate_info_type = psci_migrate_info_type;
-
-	arm_pm_restart = psci_sys_reset;
-
-	pm_power_off = psci_sys_poweroff;
-
-out_put_node:
-	of_node_put(np);
-	return err;
-}
-
-/*
- * PSCI < v0.2 get PSCI Function IDs via DT.
- */
-static int psci_0_1_init(struct device_node *np)
-{
-	u32 id;
-	int err;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
-		goto out_put_node;
-
-	pr_info("Using PSCI v0.1 Function IDs from DT\n");
-
 	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
 		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
 		psci_ops.cpu_suspend = psci_cpu_suspend;
@@ -308,25 +218,35 @@ static int psci_0_1_init(struct device_node *np)
 
 out_put_node:
 	of_node_put(np);
-	return err;
+	return;
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci", .data = psci_0_1_init},
-	{ .compatible = "arm,psci-0.2", .data = psci_0_2_init},
-	{},
-};
-
-int __init psci_init(void)
+int __init psci_probe(void)
 {
 	struct device_node *np;
-	const struct of_device_id *matched_np;
-	psci_initcall_t init_fn;
+	int ret = -ENODEV;
 
-	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
-	if (!np)
-		return -ENODEV;
+	if (psci == PSCI_SUP_ENABLED) {
+		np = of_find_matching_node(NULL, psci_of_match);
+		if (np)
+			ret = 0;
+	}
+
+	of_node_put(np);
+	return ret;
+}
+
+static int __init early_psci(char *val)
+{
+	int ret = 0;
+
+	if (strcmp(val, "enable") == 0)
+		psci = PSCI_SUP_ENABLED;
+	else if (strcmp(val, "disable") == 0)
+		psci = PSCI_SUP_DISABLED;
+	else
+		ret = -EINVAL;
 
-	init_fn = (psci_initcall_t)matched_np->data;
-	return init_fn(np);
+	return ret;
 }
+early_param("psci", early_psci);
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
index fc1dbd258255..23a11424c568 100644
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@@ -14,10 +14,9 @@
  */
 
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic.h>
 #include <linux/smp.h>
 #include <linux/of.h>
-#include <linux/delay.h>
-#include <uapi/linux/psci.h>
 
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
@@ -69,36 +68,8 @@ void __ref psci_cpu_die(unsigned int cpu)
        /* We should never return */
        panic("psci: cpu %d failed to shutdown\n", cpu);
 }
-
-int __ref psci_cpu_kill(unsigned int cpu)
-{
-	int err, i;
-
-	if (!psci_ops.affinity_info)
-		return 1;
-	/*
-	 * cpu_kill could race with cpu_die and we can
-	 * potentially end up declaring this cpu undead
-	 * while it is dying. So, try again a few times.
-	 */
-
-	for (i = 0; i < 10; i++) {
-		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
-		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
-			return 1;
-		}
-
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
-
-	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
-			cpu, err);
-	/* Make platform_cpu_kill() fail. */
-	return 0;
-}
-
+#else
+#define psci_cpu_die NULL
 #endif
 
 bool __init psci_smp_available(void)
@@ -109,8 +80,5 @@ bool __init psci_smp_available(void)
 
 struct smp_operations __initdata psci_smp_ops = {
 	.smp_boot_secondary	= psci_boot_secondary,
-#ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= psci_cpu_die,
-	.cpu_kill		= psci_cpu_kill,
-#endif
 };
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index d0cdedf4864d..95858966d84e 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -2,10 +2,12 @@
  * relocate_kernel.S - put the kernel image in place to boot
  */
 
+#include <linux/linkage.h>
 #include <asm/kexec.h>
 
-	.globl relocate_new_kernel
-relocate_new_kernel:
+	.align	3	/* not needed for this code, but keeps fncpy() happy */
+
+ENTRY(relocate_new_kernel)
 
 	ldr	r0,kexec_indirection_page
 	ldr	r1,kexec_start_address
@@ -79,6 +81,8 @@ kexec_mach_type:
 kexec_boot_atags:
 	.long	0x0
 
+ENDPROC(relocate_new_kernel)
+
 relocate_new_kernel_end:
 
 	.globl relocate_new_kernel_size
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index e8edcaa0e432..a57cc5d33540 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -51,10 +51,11 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace sched_clock_32(void)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;
+	u32 cyc;
 
 	if (cd.suspended)
 		return cd.epoch_ns;
@@ -73,7 +74,9 @@ static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 		smp_rmb();
 	} while (epoch_cyc != cd.epoch_cyc_copy);
 
-	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
+	cyc = read_sched_clock();
+	cyc = (cyc - epoch_cyc) & sched_clock_mask;
+	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
 }
 
 /*
@@ -165,12 +168,6 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-static unsigned long long notrace sched_clock_32(void)
-{
-	u32 cyc = read_sched_clock();
-	return cyc_to_sched_clock(cyc, sched_clock_mask);
-}
-
 unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
 
 unsigned long long notrace sched_clock(void)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 860952438bd3..29beb8c76560 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -262,6 +262,19 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 	int aliasing_icache;
 	unsigned int id_reg, num_sets, line_size;
 
+#ifdef CONFIG_BIG_LITTLE
+	/*
+	 * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+	 * A7 = VIPT aliasing I-cache
+	 * A15 = PIPT (non-aliasing) I-cache
+	 * To cater for this discrepancy, let's assume aliasing I-cache
+	 * all the time.  This means unneeded extra work on the A15 but
+	 * only ptrace is affected which is not performance critical.
+	 */
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+		return 1;
+#endif
+
 	/* PIPT caches never alias. */
 	if (icache_is_pipt())
 		return 0;
@@ -531,6 +544,7 @@ void __init dump_machine_table(void)
 int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 {
 	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
+	u64 aligned_start;
 
 	if (meminfo.nr_banks >= NR_BANKS) {
 		printk(KERN_CRIT "NR_BANKS too low, "
@@ -543,10 +557,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 	 * Size is appropriately rounded down, start is rounded up.
 	 */
 	size -= start & ~PAGE_MASK;
-	bank->start = PAGE_ALIGN(start);
+	aligned_start = PAGE_ALIGN(start);
+
+#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+	if (aligned_start > ULONG_MAX) {
+		printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
+		       "32-bit physical address space\n", (long long)start);
+		return -EINVAL;
+	}
 
-#ifndef CONFIG_ARM_LPAE
-	if (bank->start + size < bank->start) {
+	if (aligned_start + size > ULONG_MAX) {
 		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
 			"32-bit physical address space\n", (long long)start);
 		/*
@@ -554,10 +574,25 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
 		 * This means we lose a page after masking.
 		 */
-		size = ULONG_MAX - bank->start;
+		size = ULONG_MAX - aligned_start;
 	}
 #endif
 
+	if (aligned_start < PHYS_OFFSET) {
+		if (aligned_start + size <= PHYS_OFFSET) {
+			pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+				aligned_start, aligned_start + size);
+			return -EINVAL;
+		}
+
+		pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+			aligned_start, (u64)PHYS_OFFSET);
+
+		size -= PHYS_OFFSET - aligned_start;
+		aligned_start = PHYS_OFFSET;
+	}
+
+	bank->start = aligned_start;
 	bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
 	/*
@@ -800,10 +835,12 @@ void __init setup_arch(char **cmdline_p)
 	psci_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
-		if (psci_smp_available())
-			smp_set_ops(&psci_smp_ops);
-		else if (mdesc->smp)
-			smp_set_ops(mdesc->smp);
+		if (!mdesc->smp_init || !mdesc->smp_init()) {
+			if (psci_smp_available())
+				smp_set_ops(&psci_smp_ops);
+			else if (mdesc->smp)
+				smp_set_ops(mdesc->smp);
+		}
 		smp_init_cpus();
 	}
 #endif
@@ -877,6 +914,9 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"vfpd32",
+	"lpae",
+	"evtstrm",
 	NULL
 };
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 5a42c12767af..3c23086dc8e2 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -21,29 +21,7 @@
 #include <asm/unistd.h>
 #include <asm/vfp.h>
 
-/*
- * For ARM syscalls, we encode the syscall number into the instruction.
- */
-#define SWI_SYS_SIGRETURN	(0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-#define SWI_SYS_RT_SIGRETURN	(0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-
-/*
- * With EABI, the syscall number has to be loaded into r7.
- */
-#define MOV_R7_NR_SIGRETURN	(0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define MOV_R7_NR_RT_SIGRETURN	(0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-/*
- * For Thumb syscalls, we pass the syscall number via r7.  We therefore
- * need two 16-bit instructions.
- */
-#define SWI_THUMB_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define SWI_THUMB_RT_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-static const unsigned long sigreturn_codes[7] = {
-	MOV_R7_NR_SIGRETURN,    SWI_SYS_SIGRETURN,    SWI_THUMB_SIGRETURN,
-	MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
-};
+extern const unsigned long sigreturn_codes[7];
 
 static unsigned long signal_return_offset;
 
diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S
new file mode 100644
index 000000000000..3c5d0f2170fd
--- /dev/null
+++ b/arch/arm/kernel/sigreturn_codes.S
@@ -0,0 +1,80 @@
+/*
+ * sigreturn_codes.S - code sinpets for sigreturn syscalls
+ *
+ * Created by:	Victor Kamensky, 2013-08-13
+ * Copyright:	(C) 2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <asm/unistd.h>
+
+/*
+ * For ARM syscalls, we encode the syscall number into the instruction.
+ * With EABI, the syscall number has to be loaded into r7. As result
+ * ARM syscall sequence snippet will have move and svc in .arm encoding
+ *
+ * For Thumb syscalls, we pass the syscall number via r7.  We therefore
+ * need two 16-bit instructions in .thumb encoding
+ *
+ * Please note sigreturn_codes code are not executed in place. Instead
+ * they just copied by kernel into appropriate places. Code inside of
+ * arch/arm/kernel/signal.c is very sensitive to layout of these code
+ * snippets.
+ */
+
+#if __LINUX_ARM_ARCH__ <= 4
+	/*
+	 * Note we manually set minimally required arch that supports
+	 * required thumb opcodes for early arch versions. It is OK
+	 * for this file to be used in combination with other
+	 * lower arch variants, since these code snippets are only
+	 * used as input data.
+	 */
+	.arch armv4t
+#endif
+
+	.section .rodata
+	.global sigreturn_codes
+	.type	sigreturn_codes, #object
+
+	.arm
+
+sigreturn_codes:
+
+	/* ARM sigreturn syscall code snippet */
+	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+	/* Thumb sigreturn syscall code snippet */
+	.thumb
+	movs	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+	swi	#0
+
+	/* ARM sigreturn_rt syscall code snippet */
+	.arm
+	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+	/* Thumb sigreturn_rt syscall code snippet */
+	.thumb
+	movs	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+	swi	#0
+
+	/*
+	 * Note on addtional space: setup_return in signal.c
+	 * algorithm uses two words copy regardless whether
+	 * it is thumb case or not, so we need additional
+	 * word after real last entry.
+	 */
+	.arm
+	.space	4
+
+	.size	sigreturn_codes, . - sigreturn_codes
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 987dcf33415c..baf4d28213a5 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,6 +4,7 @@
 #include <asm/assembler.h>
 #include <asm/glue-cache.h>
 #include <asm/glue-proc.h>
+#include "entry-header.S"
 	.text
 
 /*
@@ -30,9 +31,8 @@ ENTRY(__cpu_suspend)
 	mov	r2, r5			@ virtual SP
 	ldr	r3, =sleep_save_sp
 #ifdef CONFIG_SMP
-	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
-	ALT_UP(mov lr, #0)
-	and	lr, lr, #15
+	get_thread_info	r5
+	ldr	lr, [r5, #TI_CPU] 	@ cpu logical index
 	add	r3, r3, lr, lsl #2
 #endif
 	bl	__cpu_suspend_save
@@ -81,11 +81,15 @@ ENDPROC(cpu_resume_after_mmu)
 	.data
 	.align
 ENTRY(cpu_resume)
+ARM_BE8(setend be)			@ ensure we are in BE mode
 #ifdef CONFIG_SMP
+	mov	r1, #0			@ fall-back logical index for UP
+	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
+	ALT_UP_B(1f)
+	bic	r0, #0xff000000
+	bl	cpu_logical_index 	@ return logical index in r1
+1:
 	adr	r0, sleep_save_sp
-	ALT_SMP(mrc p15, 0, r1, c0, c0, 5)
-	ALT_UP(mov r1, #0)
-	and	r1, r1, #15
 	ldr	r0, [r0, r1, lsl #2]	@ stack phys addr
 #else
 	ldr	r0, sleep_save_sp	@ stack phys addr
@@ -102,3 +106,20 @@ sleep_save_sp:
 	.rept	CONFIG_NR_CPUS
 	.long	0				@ preserve stack phys ptr here
 	.endr
+
+#ifdef CONFIG_SMP
+cpu_logical_index:
+	adr	r3, cpu_map_ptr
+	ldr	r2, [r3]
+	add	r3, r3, r2		@ virt_to_phys(__cpu_logical_map)
+	mov	r1, #0
+1:
+	ldr	r2, [r3, r1, lsl #2]
+	cmp	r2, r0
+	moveq	pc, lr
+	add	r1, r1, #1
+	b	1b
+
+cpu_map_ptr:
+	.long __cpu_logical_map - .
+#endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5a8ad2c8eda0..d6e3d1ca4ddf 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -46,6 +46,9 @@
 #include <asm/virt.h>
 #include <asm/mach/arch.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/arm-ipi.h>
+
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
  * so we need some other way of telling a new secondary core
@@ -57,7 +60,7 @@ struct secondary_data secondary_data;
  * control for which core is the next to come out of the secondary
  * boot "holding pen"
  */
-volatile int __cpuinitdata pen_release = -1;
+volatile int pen_release = -1;
 
 enum ipi_msg_type {
 	IPI_WAKEUP,
@@ -66,6 +69,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
+	IPI_COMPLETION,
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -463,6 +467,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_COMPLETION, "completion interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -588,6 +593,19 @@ static void ipi_cpu_stop(unsigned int cpu)
 		cpu_relax();
 }
 
+static DEFINE_PER_CPU(struct completion *, cpu_completion);
+
+int register_ipi_completion(struct completion *completion, int cpu)
+{
+	per_cpu(cpu_completion, cpu) = completion;
+	return IPI_COMPLETION;
+}
+
+static void ipi_complete(unsigned int cpu)
+{
+	complete(per_cpu(cpu_completion, cpu));
+}
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -604,6 +622,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	if (ipinr < NR_IPI)
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 
+	trace_arm_ipi_entry(ipinr);
 	switch (ipinr) {
 	case IPI_WAKEUP:
 		break;
@@ -638,11 +657,18 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+	case IPI_COMPLETION:
+		irq_enter();
+		ipi_complete(cpu);
+		irq_exit();
+		break;
+
 	default:
 		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
 		       cpu, ipinr);
 		break;
 	}
+	trace_arm_ipi_exit(ipinr);
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 5bc1a63284e3..1aafa0d785eb 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -28,7 +28,7 @@
  */
 unsigned int __init scu_get_core_count(void __iomem *scu_base)
 {
-	unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG);
+	unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG);
 	return (ncores & 0x03) + 1;
 }
 
@@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base)
 #ifdef CONFIG_ARM_ERRATA_764369
 	/* Cortex-A9 only */
 	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
-		scu_ctrl = __raw_readl(scu_base + 0x30);
+		scu_ctrl = readl_relaxed(scu_base + 0x30);
 		if (!(scu_ctrl & 1))
-			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+			writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30);
 	}
 #endif
 
-	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
+	scu_ctrl = readl_relaxed(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
 		return;
 
 	scu_ctrl |= 1;
-	__raw_writel(scu_ctrl, scu_base + SCU_CTRL);
+	writel_relaxed(scu_ctrl, scu_base + SCU_CTRL);
 
 	/*
 	 * Ensure that the data accessed by CPU0 before the SCU was
@@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode)
 	if (mode > 3 || mode == 1 || cpu > 3)
 		return -EINVAL;
 
-	val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
+	val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
 	val |= mode;
-	__raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu);
+	writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index f6fd1d4398c6..4971ccf012ca 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_PERIODIC:
 		ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
 			| TWD_TIMER_CONTROL_PERIODIC;
-		__raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
+		writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
 			twd_base + TWD_TIMER_LOAD);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
@@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode,
 		ctrl = 0;
 	}
 
-	__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
 }
 
 static int twd_set_next_event(unsigned long evt,
 			struct clock_event_device *unused)
 {
-	unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
+	unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL);
 
 	ctrl |= TWD_TIMER_CONTROL_ENABLE;
 
-	__raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
-	__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER);
+	writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
 
 	return 0;
 }
@@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt,
  */
 static int twd_timer_ack(void)
 {
-	if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
-		__raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
+	if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) {
+		writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT);
 		return 1;
 	}
 
@@ -209,15 +209,15 @@ static void __cpuinit twd_calibrate_rate(void)
 		waitjiffies += 5;
 
 				 /* enable, no interrupt or reload */
-		__raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
+		writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL);
 
 				 /* maximum value */
-		__raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
+		writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
 
 		while (get_jiffies_64() < waitjiffies)
 			udelay(10);
 
-		count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
+		count = readl_relaxed(twd_base + TWD_TIMER_COUNTER);
 
 		twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
 
@@ -275,7 +275,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	 * bother with the below.
 	 */
 	if (per_cpu(percpu_setup_called, cpu)) {
-		__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+		writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
 		clockevents_register_device(*__this_cpu_ptr(twd_evt));
 		enable_percpu_irq(clk->irq, 0);
 		return 0;
@@ -288,7 +288,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	 * The following is done once per CPU the first time .setup() is
 	 * called.
 	 */
-	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
 
 	clk->name = "local_timer";
 	clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 00f79e59985b..6582c4adc182 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -31,7 +31,7 @@ int notrace unwind_frame(struct stackframe *frame)
 	high = ALIGN(low, THREAD_SIZE);
 
 	/* check current frame pointer is within bounds */
-	if (fp < (low + 12) || fp + 4 >= high)
+	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
 
 	/* restore the registers from the stack frame */
@@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d)
 	return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+	struct stack_trace *trace, unsigned int nosched)
 {
 	struct stack_trace_data data;
 	struct stackframe frame;
 
 	data.trace = trace;
 	data.skip = trace->skip;
+	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
 #ifdef CONFIG_SMP
@@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
-		data.no_sched_functions = 1;
 		frame.fp = thread_saved_fp(tsk);
 		frame.sp = thread_saved_sp(tsk);
 		frame.lr = 0;		/* recovered from the stack */
@@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	} else {
 		register unsigned long current_sp asm ("sp");
 
-		data.no_sched_functions = 0;
+		/* We don't want this function nor the caller */
+		data.skip += 2;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_sp;
 		frame.lr = (unsigned long)__builtin_return_address(0);
-		frame.pc = (unsigned long)save_stack_trace_tsk;
+		frame.pc = (unsigned long)__save_stack_trace;
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace, 1);
+}
+
 void save_stack_trace(struct stack_trace *trace)
 {
-	save_stack_trace_tsk(current, trace);
+	__save_stack_trace(current, trace, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a256..677da58d9e88 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 
 #include <asm/cputype.h>
+#include <asm/smp_plat.h>
 #include <asm/topology.h>
 
 /*
@@ -289,6 +290,140 @@ void store_cpu_topology(unsigned int cpuid)
 		cpu_topology[cpuid].socket_id, mpidr);
 }
 
+
+#ifdef CONFIG_SCHED_HMP
+
+static const char * const little_cores[] = {
+	"arm,cortex-a7",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 4) {
+			pr_err("* %s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu)
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+
+	return -EINVAL;
+}
+
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 6b9567e19bdc..b4fd850c34b2 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -34,8 +34,15 @@
 #include <asm/unwind.h>
 #include <asm/tls.h>
 #include <asm/system_misc.h>
-
-static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
+#include <asm/opcodes.h>
+
+static const char *handler[]= {
+	"prefetch abort",
+	"data abort",
+	"address exception",
+	"interrupt",
+	"undefined instruction",
+};
 
 void *vectors_page;
 
@@ -341,15 +348,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs,
 int is_valid_bugaddr(unsigned long pc)
 {
 #ifdef CONFIG_THUMB2_KERNEL
-	unsigned short bkpt;
+	u16 bkpt;
+	u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE);
 #else
-	unsigned long bkpt;
+	u32 bkpt;
+	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
 	if (probe_kernel_address((unsigned *)pc, bkpt))
 		return 0;
 
-	return bkpt == BUG_INSTR_VALUE;
+	return bkpt == insn;
 }
 
 #endif
@@ -402,25 +411,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (processor_mode(regs) == SVC_MODE) {
 #ifdef CONFIG_THUMB2_KERNEL
 		if (thumb_mode(regs)) {
-			instr = ((u16 *)pc)[0];
+			instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]);
 			if (is_wide_instruction(instr)) {
-				instr <<= 16;
-				instr |= ((u16 *)pc)[1];
+				u16 inst2;
+				inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]);
+				instr = __opcode_thumb32_compose(instr, inst2);
 			}
 		} else
 #endif
-			instr = *(u32 *) pc;
+			instr = __mem_to_opcode_arm(*(u32 *) pc);
 	} else if (thumb_mode(regs)) {
 		if (get_user(instr, (u16 __user *)pc))
 			goto die_sig;
+		instr = __mem_to_opcode_thumb16(instr);
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
 			if (get_user(instr2, (u16 __user *)pc+1))
 				goto die_sig;
-			instr <<= 16;
-			instr |= instr2;
+			instr2 = __mem_to_opcode_thumb16(instr2);
+			instr = __opcode_thumb32_compose(instr, instr2);
 		}
 	} else if (get_user(instr, (u32 __user *)pc)) {
+		instr = __mem_to_opcode_arm(instr);
 		goto die_sig;
 	}
 
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index 788562dccb43..c336efdf8f13 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y		:= irq.o gpio.o setup.o
+obj-y		:= irq.o gpio.o setup.o sysirq_mask.o
 obj-m		:=
 obj-n		:=
 obj-		:=
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index a8ce24538da6..cdb1fb695edf 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -351,6 +351,8 @@ static void __init at91sam9260_initialize(void)
 	at91_extern_irq = (1 << AT91SAM9260_ID_IRQ0) | (1 << AT91SAM9260_ID_IRQ1)
 			| (1 << AT91SAM9260_ID_IRQ2);
 
+	at91_sysirq_mask_rtt(AT91SAM9260_BASE_RTT);
+
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91sam9260_gpio, 3);
 }
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index 25efb5ac30f1..7c9d2ea5bb88 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -293,6 +293,8 @@ static void __init at91sam9261_initialize(void)
 	at91_extern_irq = (1 << AT91SAM9261_ID_IRQ0) | (1 << AT91SAM9261_ID_IRQ1)
 			| (1 << AT91SAM9261_ID_IRQ2);
 
+	at91_sysirq_mask_rtt(AT91SAM9261_BASE_RTT);
+
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91sam9261_gpio, 3);
 }
diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c
index f44ffd2105a7..c6b2f477c71f 100644
--- a/arch/arm/mach-at91/at91sam9263.c
+++ b/arch/arm/mach-at91/at91sam9263.c
@@ -329,6 +329,9 @@ static void __init at91sam9263_initialize(void)
 	arm_pm_restart = at91sam9_alt_restart;
 	at91_extern_irq = (1 << AT91SAM9263_ID_IRQ0) | (1 << AT91SAM9263_ID_IRQ1);
 
+	at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT0);
+	at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT1);
+
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91sam9263_gpio, 5);
 }
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 8b7fce067652..e381fa125011 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -376,6 +376,9 @@ static void __init at91sam9g45_initialize(void)
 	arm_pm_restart = at91sam9g45_restart;
 	at91_extern_irq = (1 << AT91SAM9G45_ID_IRQ0);
 
+	at91_sysirq_mask_rtc(AT91SAM9G45_BASE_RTC);
+	at91_sysirq_mask_rtt(AT91SAM9G45_BASE_RTT);
+
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91sam9g45_gpio, 5);
 }
diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c
index c7d670d11802..4d6001c355f5 100644
--- a/arch/arm/mach-at91/at91sam9n12.c
+++ b/arch/arm/mach-at91/at91sam9n12.c
@@ -223,7 +223,13 @@ static void __init at91sam9n12_map_io(void)
 	at91_init_sram(0, AT91SAM9N12_SRAM_BASE, AT91SAM9N12_SRAM_SIZE);
 }
 
+static void __init at91sam9n12_initialize(void)
+{
+	at91_sysirq_mask_rtc(AT91SAM9N12_BASE_RTC);
+}
+
 AT91_SOC_START(at91sam9n12)
 	.map_io = at91sam9n12_map_io,
 	.register_clocks = at91sam9n12_register_clocks,
+	.init = at91sam9n12_initialize,
 AT91_SOC_END
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index f77fae5591bc..5615d28a5b96 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -295,6 +295,9 @@ static void __init at91sam9rl_initialize(void)
 	arm_pm_restart = at91sam9_alt_restart;
 	at91_extern_irq = (1 << AT91SAM9RL_ID_IRQ0);
 
+	at91_sysirq_mask_rtc(AT91SAM9RL_BASE_RTC);
+	at91_sysirq_mask_rtt(AT91SAM9RL_BASE_RTT);
+
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91sam9rl_gpio, 4);
 }
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index e631fec040ce..7b4f848312eb 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -318,6 +318,11 @@ static void __init at91sam9x5_map_io(void)
 	at91_init_sram(0, AT91SAM9X5_SRAM_BASE, AT91SAM9X5_SRAM_SIZE);
 }
 
+static void __init at91sam9x5_initialize(void)
+{
+	at91_sysirq_mask_rtc(AT91SAM9X5_BASE_RTC);
+}
+
 /* --------------------------------------------------------------------
  *  Interrupt initialization
  * -------------------------------------------------------------------- */
@@ -325,4 +330,5 @@ static void __init at91sam9x5_map_io(void)
 AT91_SOC_START(at91sam9x5)
 	.map_io = at91sam9x5_map_io,
 	.register_clocks = at91sam9x5_register_clocks,
+	.init = at91sam9x5_initialize,
 AT91_SOC_END
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index da841885d01c..64f9f1045539 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -947,6 +947,7 @@ static int __init at91_clock_reset(void)
 	}
 
 	at91_pmc_write(AT91_PMC_SCDR, scdr);
+	at91_pmc_write(AT91_PMC_PCDR, pcdr);
 	if (cpu_is_sama5d3())
 		at91_pmc_write(AT91_PMC_PCDR1, pcdr1);
 
diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
index 78ab06548658..d949ab4e26fa 100644
--- a/arch/arm/mach-at91/generic.h
+++ b/arch/arm/mach-at91/generic.h
@@ -33,6 +33,8 @@ extern int  __init at91_aic_of_init(struct device_node *node,
 				    struct device_node *parent);
 extern int  __init at91_aic5_of_init(struct device_node *node,
 				    struct device_node *parent);
+extern void __init at91_sysirq_mask_rtc(u32 rtc_base);
+extern void __init at91_sysirq_mask_rtt(u32 rtt_base);
 
 
  /* Timer */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9n12.h b/arch/arm/mach-at91/include/mach/at91sam9n12.h
index d374b87c0459..0151bcf6163c 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9n12.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9n12.h
@@ -49,6 +49,11 @@
 #define AT91SAM9N12_BASE_USART3	0xf8028000
 
 /*
+ * System Peripherals
+ */
+#define AT91SAM9N12_BASE_RTC	0xfffffeb0
+
+/*
  * Internal Memory.
  */
 #define AT91SAM9N12_SRAM_BASE	0x00300000	/* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9x5.h b/arch/arm/mach-at91/include/mach/at91sam9x5.h
index c75ee19b58d3..2fc76c49e97c 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9x5.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9x5.h
@@ -55,6 +55,11 @@
 #define AT91SAM9X5_BASE_USART2	0xf8024000
 
 /*
+ * System Peripherals
+ */
+#define AT91SAM9X5_BASE_RTC	0xfffffeb0
+
+/*
  * Internal Memory.
  */
 #define AT91SAM9X5_SRAM_BASE	0x00300000	/* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/include/mach/sama5d3.h b/arch/arm/mach-at91/include/mach/sama5d3.h
index 6dc81ee38048..3abbc4286875 100644
--- a/arch/arm/mach-at91/include/mach/sama5d3.h
+++ b/arch/arm/mach-at91/include/mach/sama5d3.h
@@ -65,6 +65,11 @@
 #define SAMA5D3_ID_IRQ0		47	/* Advanced Interrupt Controller (IRQ0) */
 
 /*
+ * System Peripherals
+ */
+#define SAMA5D3_BASE_RTC	0xfffffeb0
+
+/*
  * Internal Memory
  */
 #define SAMA5D3_SRAM_BASE	0x00300000	/* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/sam9_smc.c b/arch/arm/mach-at91/sam9_smc.c
index 99a0a1d2b7dc..b26156bf15db 100644
--- a/arch/arm/mach-at91/sam9_smc.c
+++ b/arch/arm/mach-at91/sam9_smc.c
@@ -101,7 +101,7 @@ static void sam9_smc_cs_read(void __iomem *base,
 	/* Pulse register */
 	val = __raw_readl(base + AT91_SMC_PULSE);
 
-	config->nwe_setup = val & AT91_SMC_NWEPULSE;
+	config->nwe_pulse = val & AT91_SMC_NWEPULSE;
 	config->ncs_write_pulse = (val & AT91_SMC_NCS_WRPULSE) >> 8;
 	config->nrd_pulse = (val & AT91_SMC_NRDPULSE) >> 16;
 	config->ncs_read_pulse = (val & AT91_SMC_NCS_RDPULSE) >> 24;
diff --git a/arch/arm/mach-at91/sama5d3.c b/arch/arm/mach-at91/sama5d3.c
index 401279715ab1..a28873fe3049 100644
--- a/arch/arm/mach-at91/sama5d3.c
+++ b/arch/arm/mach-at91/sama5d3.c
@@ -95,19 +95,19 @@ static struct clk twi0_clk = {
 	.name		= "twi0_clk",
 	.pid		= SAMA5D3_ID_TWI0,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk twi1_clk = {
 	.name		= "twi1_clk",
 	.pid		= SAMA5D3_ID_TWI1,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk twi2_clk = {
 	.name		= "twi2_clk",
 	.pid		= SAMA5D3_ID_TWI2,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk mmc0_clk = {
 	.name		= "mci0_clk",
@@ -371,7 +371,13 @@ static void __init sama5d3_map_io(void)
 	at91_init_sram(0, SAMA5D3_SRAM_BASE, SAMA5D3_SRAM_SIZE);
 }
 
+static void __init sama5d3_initialize(void)
+{
+	at91_sysirq_mask_rtc(SAMA5D3_BASE_RTC);
+}
+
 AT91_SOC_START(sama5d3)
 	.map_io = sama5d3_map_io,
 	.register_clocks = sama5d3_register_clocks,
+	.init = sama5d3_initialize,
 AT91_SOC_END
diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c
new file mode 100644
index 000000000000..f8bc3511a8c8
--- /dev/null
+++ b/arch/arm/mach-at91/sysirq_mask.c
@@ -0,0 +1,75 @@
+/*
+ * sysirq_mask.c - System-interrupt masking
+ *
+ * Copyright (C) 2013 Johan Hovold <jhovold@gmail.com>
+ *
+ * Functions to disable system interrupts from backup-powered peripherals.
+ *
+ * The RTC and RTT-peripherals are generally powered by backup power (VDDBU)
+ * and are not reset on wake-up, user, watchdog or software reset. This means
+ * that their interrupts may be enabled during early boot (e.g. after a user
+ * reset).
+ *
+ * As the RTC and RTT share the system-interrupt line with the PIT, an
+ * interrupt occurring before a handler has been installed would lead to the
+ * system interrupt being disabled and prevent the system from booting.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <mach/at91_rtt.h>
+
+#include "generic.h"
+
+#define AT91_RTC_IDR		0x24	/* Interrupt Disable Register */
+#define AT91_RTC_IMR		0x28	/* Interrupt Mask Register */
+#define AT91_RTC_IRQ_MASK	0x1f	/* Available IRQs mask */
+
+void __init at91_sysirq_mask_rtc(u32 rtc_base)
+{
+	void __iomem *base;
+
+	base = ioremap(rtc_base, 64);
+	if (!base)
+		return;
+
+	/*
+	 * sam9x5 SoCs have the following errata:
+	 * "RTC: Interrupt Mask Register cannot be used
+	 *  Interrupt Mask Register read always returns 0."
+	 *
+	 * Hence we're not relying on IMR values to disable
+	 * interrupts.
+	 */
+	writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR);
+	(void)readl_relaxed(base + AT91_RTC_IMR);	/* flush */
+
+	iounmap(base);
+}
+
+void __init at91_sysirq_mask_rtt(u32 rtt_base)
+{
+	void __iomem *base;
+	void __iomem *reg;
+	u32 mode;
+
+	base = ioremap(rtt_base, 16);
+	if (!base)
+		return;
+
+	reg = base + AT91_RTT_MR;
+
+	mode = readl_relaxed(reg);
+	if (mode & (AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN)) {
+		pr_info("AT91: Disabling rtt irq\n");
+		mode &= ~(AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN);
+		writel_relaxed(mode, reg);
+		(void)readl_relaxed(reg);			/* flush */
+	}
+
+	iounmap(base);
+}
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index b13cc74114db..8a53f346cdb3 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -116,7 +116,7 @@ static void __init ebsa110_map_io(void)
 	iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
 }
 
-static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+static void __iomem *ebsa110_ioremap_caller(phys_addr_t cookie, size_t size,
 					    unsigned int flags, void *caller)
 {
 	return (void __iomem *)cookie;
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
index 753b94f3fca7..d88234e14f96 100644
--- a/arch/arm/mach-exynos/mach-exynos5-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -14,6 +14,7 @@
 #include <linux/memblock.h>
 #include <linux/io.h>
 #include <linux/clocksource.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/mach/arch.h>
 #include <mach/regs-pmu.h>
@@ -23,11 +24,31 @@
 
 #include "common.h"
 
+static u64 dma_mask64 = DMA_BIT_MASK(64);
+
 static void __init exynos5_dt_map_io(void)
 {
 	exynos_init_io(NULL, 0);
 }
 
+static int exynos5250_platform_notifier(struct notifier_block *nb,
+				  unsigned long event, void *__dev)
+{
+	struct device *dev = __dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	dev->dma_mask = &dma_mask64;
+	dev->coherent_dma_mask = DMA_BIT_MASK(64);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block exynos5250_platform_nb = {
+	.notifier_call = exynos5250_platform_notifier,
+};
+
 static void __init exynos5_dt_machine_init(void)
 {
 	struct device_node *i2c_np;
@@ -52,6 +73,11 @@ static void __init exynos5_dt_machine_init(void)
 		}
 	}
 
+	if (config_enabled(CONFIG_ARM_LPAE) &&
+			of_machine_is_compatible("samsung,exynos5250"))
+		bus_register_notifier(&platform_bus_type,
+				&exynos5250_platform_nb);
+
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index a42b369bc439..95d0b6e6438b 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <video/vga.h>
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -196,6 +197,8 @@ void __init footbridge_map_io(void)
 		iotable_init(ebsa285_host_io_desc, ARRAY_SIZE(ebsa285_host_io_desc));
 		pci_map_io_early(__phys_to_pfn(DC21285_PCI_IO));
 	}
+
+	vga_base = PCIMEM_BASE;
 }
 
 void footbridge_restart(char mode, const char *cmd)
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 9ee78f7b4990..782f6c71fa0a 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -96,11 +96,12 @@ static struct irqaction footbridge_timer_irq = {
 void __init footbridge_timer_init(void)
 {
 	struct clock_event_device *ce = &ckevt_dc21285;
+	unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16);
 
-	clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16);
+	clocksource_register_hz(&cksrc_dc21285, rate);
 
 	setup_irq(ce->irq, &footbridge_timer_irq);
 
 	ce->cpumask = cpumask_of(smp_processor_id());
-	clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff);
+	clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
 }
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 3490a24f969e..7c2fdae9a38b 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
-#include <video/vga.h>
 
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
@@ -291,7 +290,6 @@ void __init dc21285_preinit(void)
 	int cfn_mode;
 
 	pcibios_min_mem = 0x81000000;
-	vga_base = PCIMEM_BASE;
 
 	mem_size = (unsigned int)high_memory - PAGE_OFFSET;
 	for (mem_mask = 0x00100000; mem_mask < 0x10000000; mem_mask <<= 1)
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index b08243500e2e..1a7235fb52ac 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -30,21 +30,24 @@ static const struct {
 	const char *name;
 	const char *trigger;
 } ebsa285_leds[] = {
-	{ "ebsa285:amber", "heartbeat", },
-	{ "ebsa285:green", "cpu0", },
+	{ "ebsa285:amber", "cpu0", },
+	{ "ebsa285:green", "heartbeat", },
 	{ "ebsa285:red",},
 };
 
+static unsigned char hw_led_state;
+
 static void ebsa285_led_set(struct led_classdev *cdev,
 		enum led_brightness b)
 {
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	if (b != LED_OFF)
-		*XBUS_LEDS |= led->mask;
+	if (b == LED_OFF)
+		hw_led_state |= led->mask;
 	else
-		*XBUS_LEDS &= ~led->mask;
+		hw_led_state &= ~led->mask;
+	*XBUS_LEDS = hw_led_state;
 }
 
 static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
@@ -52,18 +55,19 @@ static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	return (*XBUS_LEDS & led->mask) ? LED_FULL : LED_OFF;
+	return hw_led_state & led->mask ? LED_OFF : LED_FULL;
 }
 
 static int __init ebsa285_leds_init(void)
 {
 	int i;
 
-	if (machine_is_ebsa285())
+	if (!machine_is_ebsa285())
 		return -ENODEV;
 
-	/* 3 LEDS All ON */
-	*XBUS_LEDS |= XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	/* 3 LEDS all off */
+	hw_led_state = XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	*XBUS_LEDS = hw_led_state;
 
 	for (i = 0; i < ARRAY_SIZE(ebsa285_leds); i++) {
 		struct ebsa285_led *led;
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index cd9fcb1cd7ab..b8466fb00f55 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -2,6 +2,7 @@ config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7
 	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_AMBA
 	select ARM_GIC
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index e7df2dd43a40..c37d31e15a06 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
+#include <linux/pl320-ipc.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
@@ -65,13 +66,12 @@ void highbank_set_cpu_jump(int cpu, void *jump_addr)
 			  HB_JUMP_TABLE_PHYS(cpu) + 15);
 }
 
-#ifdef CONFIG_CACHE_L2X0
 static void highbank_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	highbank_smc1(0x102, 0x0);
 }
-#endif
 
 static void __init highbank_init_irq(void)
 {
@@ -80,12 +80,13 @@ static void __init highbank_init_irq(void)
 	if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9"))
 		highbank_scu_map_io();
 
-#ifdef CONFIG_CACHE_L2X0
 	/* Enable PL310 L2 Cache controller */
-	highbank_smc1(0x102, 0x1);
-	l2x0_of_init(0, ~0UL);
-	outer_cache.disable = highbank_l2x0_disable;
-#endif
+	if (IS_ENABLED(CONFIG_CACHE_L2X0) &&
+	    of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) {
+		highbank_smc1(0x102, 0x1);
+		l2x0_of_init(0, ~0UL);
+		outer_cache.disable = highbank_l2x0_disable;
+	}
 }
 
 static void __init highbank_timer_init(void)
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 4e3148ce852d..0b9e437719bd 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -424,7 +424,7 @@ int __init mx6q_clocks_init(void)
 	clk[asrc_podf]        = imx_clk_divider("asrc_podf",        "asrc_pred",         base + 0x30, 9,  3);
 	clk[spdif_pred]       = imx_clk_divider("spdif_pred",       "spdif_sel",         base + 0x30, 25, 3);
 	clk[spdif_podf]       = imx_clk_divider("spdif_podf",       "spdif_pred",        base + 0x30, 22, 3);
-	clk[can_root]         = imx_clk_divider("can_root",         "pll3_usb_otg",      base + 0x20, 2,  6);
+	clk[can_root]         = imx_clk_divider("can_root",         "pll3_60m",          base + 0x20, 2,  6);
 	clk[ecspi_root]       = imx_clk_divider("ecspi_root",       "pll3_60m",          base + 0x38, 19, 6);
 	clk[gpu2d_core_podf]  = imx_clk_divider("gpu2d_core_podf",  "gpu2d_core_sel",    base + 0x18, 23, 3);
 	clk[gpu3d_core_podf]  = imx_clk_divider("gpu3d_core_podf",  "gpu3d_core_sel",    base + 0x18, 26, 3);
diff --git a/arch/arm/mach-imx/devices/platform-ipu-core.c b/arch/arm/mach-imx/devices/platform-ipu-core.c
index fc4dd7cedc11..6bd7c3f37ac0 100644
--- a/arch/arm/mach-imx/devices/platform-ipu-core.c
+++ b/arch/arm/mach-imx/devices/platform-ipu-core.c
@@ -77,7 +77,7 @@ struct platform_device *__init imx_alloc_mx3_camera(
 
 	pdev = platform_device_alloc("mx3-camera", 0);
 	if (!pdev)
-		goto err;
+		return ERR_PTR(-ENOMEM);
 
 	pdev->dev.dma_mask = kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL);
 	if (!pdev->dev.dma_mask)
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index e0e69a682174..eed32ca0b8ab 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -65,7 +65,7 @@ static void imx3_idle(void)
 		: "=r" (reg));
 }
 
-static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+static void __iomem *imx3_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					 unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 8c60fcb08a98..2f4c92486cfa 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -199,7 +199,8 @@ static struct mmci_platform_data mmc_data = {
 static void cp_clcd_enable(struct clcd_fb *fb)
 {
 	struct fb_var_screeninfo *var = &fb->fb.var;
-	u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2;
+	u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2
+			| CM_CTRL_LCDEN0 | CM_CTRL_LCDEN1;
 
 	if (var->bits_per_pixel <= 8 ||
 	    (var->bits_per_pixel == 16 && var->green.length == 5))
diff --git a/arch/arm/mach-iop13xx/io.c b/arch/arm/mach-iop13xx/io.c
index 183dc8b5511b..faaf7d4482c5 100644
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@@ -23,7 +23,7 @@
 
 #include "pci.h"
 
-static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+static void __iomem *__iop13xx_ioremap_caller(phys_addr_t cookie,
 	size_t size, unsigned int mtype, void *caller)
 {
 	void __iomem * retval;
diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig
index 73a2d905af8a..72de05f09cb8 100644
--- a/arch/arm/mach-ixp4xx/Kconfig
+++ b/arch/arm/mach-ixp4xx/Kconfig
@@ -1,9 +1,5 @@
 if ARCH_IXP4XX
 
-config ARCH_SUPPORTS_BIG_ENDIAN
-	bool
-	default y
-
 menu "Intel IXP4xx Implementation Options"
 
 comment "IXP4xx Platforms"
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 6600cff6bd92..d7223b3b81f3 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -559,7 +559,7 @@ void ixp4xx_restart(char mode, const char *cmd)
  * fallback to the default.
  */
 
-static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+static void __iomem *ixp4xx_ioremap_caller(phys_addr_t addr, size_t size,
 					   unsigned int mtype, void *caller)
 {
 	if (!is_pci_memory(addr))
diff --git a/arch/arm/mach-msm/common.h b/arch/arm/mach-msm/common.h
index ce8215a269e5..421cf7751a80 100644
--- a/arch/arm/mach-msm/common.h
+++ b/arch/arm/mach-msm/common.h
@@ -23,7 +23,7 @@ extern void msm_map_msm8x60_io(void);
 extern void msm_map_msm8960_io(void);
 extern void msm_map_qsd8x50_io(void);
 
-extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					  unsigned int mtype, void *caller);
 
 extern struct smp_operations msm_smp_ops;
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 123ef9cbce1b..fd65b6d42cde 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -172,7 +172,7 @@ void __init msm_map_msm7x30_io(void)
 }
 #endif /* CONFIG_ARCH_MSM7X30 */
 
-void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 80a8bcacd9d5..317cdb800099 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -1,5 +1,6 @@
 config ARCH_MVEBU
 	bool "Marvell SOCs with Device Tree support" if ARCH_MULTI_V7
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_MMIO
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 8278960066c3..3ee701f1d38e 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -141,6 +141,29 @@ int __init coherency_init(void)
 {
 	struct device_node *np;
 
+	/*
+	 * The coherency fabric is needed:
+	 * - For coherency between processors on Armada XP, so only
+	 *   when SMP is enabled.
+	 * - For coherency between the processor and I/O devices, but
+	 *   this coherency requires many pre-requisites (write
+	 *   allocate cache policy, shareable pages, SMP bit set) that
+	 *   are only meant in SMP situations.
+	 *
+	 * Note that this means that on Armada 370, there is currently
+	 * no way to use hardware I/O coherency, because even when
+	 * CONFIG_SMP is enabled, is_smp() returns false due to the
+	 * Armada 370 being a single-core processor. To lift this
+	 * limitation, we would have to find a way to make the cache
+	 * policy set to write-allocate (on all Armada SoCs), and to
+	 * set the shareable attribute in page tables (on all Armada
+	 * SoCs except the Armada 370). Unfortunately, such decisions
+	 * are taken very early in the kernel boot process, at a point
+	 * where we don't know yet on which SoC we are running.
+	 */
+	if (!is_smp())
+		return 0;
+
 	np = of_find_matching_node(NULL, of_coherency_table);
 	if (np) {
 		pr_info("Initializing Coherency fabric\n");
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 5476669ba905..ee7598fe75db 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -20,6 +20,8 @@
 #define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
 #define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
 
+#include <asm/assembler.h>
+
 	.text
 /*
  * r0: Coherency fabric base register address
@@ -29,6 +31,7 @@ ENTRY(ll_set_cpu_coherent)
 	/* Create bit by cpu index */
 	mov	r3, #(1 << 24)
 	lsl	r1, r3, r1
+ARM_BE8(rev	r1, r1)
 
 	/* Add CPU to SMP group - Atomic */
 	add	r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S
index a06e0ede8c08..458ed3fb2626 100644
--- a/arch/arm/mach-mvebu/headsmp.S
+++ b/arch/arm/mach-mvebu/headsmp.S
@@ -21,6 +21,8 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
+#include <asm/assembler.h>
+
 /*
  * At this stage the secondary CPUs don't have acces yet to the MMU, so
  * we have to provide physical addresses
@@ -35,6 +37,7 @@
  * startup
  */
 ENTRY(armada_xp_secondary_startup)
+ ARM_BE8(setend	be )			@ go BE8 if entered LE
 
 	/* Read CPU id */
 	mrc     p15, 0, r1, c0, c0, 5
diff --git a/arch/arm/mach-mxs/pm.h b/arch/arm/mach-mxs/pm.h
index f57e7cdece2e..09d77b00a96b 100644
--- a/arch/arm/mach-mxs/pm.h
+++ b/arch/arm/mach-mxs/pm.h
@@ -9,6 +9,10 @@
 #ifndef __ARCH_MXS_PM_H
 #define __ARCH_MXS_PM_H
 
+#ifdef CONFIG_PM
 void mxs_pm_init(void);
+#else
+#define mxs_pm_init NULL
+#endif
 
 #endif
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index 0dac3d239e32..d712c5172237 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -379,7 +379,7 @@ static struct omap_usb_config h2_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg		= 2,
 
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode	= 19,	/* 0:host(off) 1:dev|otg 2:disabled */
 	/* .hmc_mode	= 21,*/	/* 0:host(off) 1:dev(loopback) 2:host(loopback) */
 #elif	defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 816ecd13f81e..bfed4f928663 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -366,7 +366,7 @@ static struct omap_usb_config h3_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg	    = 2,
 
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode       = 19,   /* 0:host(off) 1:dev|otg 2:disabled */
 #elif  defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	/* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index bd5f02e9c354..c49ce83cc1eb 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -312,7 +312,7 @@ static struct omap_usb_config h2_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg		= 2,
 
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode	= 19,	/* 0:host(off) 1:dev|otg 2:disabled */
 	/* .hmc_mode	= 21,*/	/* 0:host(off) 1:dev(loopback) 2:host(loopback) */
 #elif	defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index a7ce69286688..006fbb5f9654 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -280,7 +280,7 @@ static struct omap_usb_config osk_usb_config __initdata = {
 	 * be used, with a NONSTANDARD gender-bending cable/dongle, as
 	 * a peripheral.
 	 */
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.register_dev	= 1,
 	.hmc_mode	= 0,
 #else
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index f49cd51e162a..42afc6682d10 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -394,14 +394,6 @@ config MACH_OMAP4_PANDA
 	select OMAP_PACKAGE_CBS
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
-config OMAP3_EMU
-	bool "OMAP3 debugging peripherals"
-	depends on ARCH_OMAP3
-	select ARM_AMBA
-	select OC_ETM
-	help
-	  Say Y here to enable debugging hardware of omap3
-
 config OMAP3_SDRC_AC_TIMING
 	bool "Enable SDRC AC timing register changes"
 	depends on ARCH_OMAP3
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 55a9d6777683..e2f7210a8eab 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -200,7 +200,6 @@ obj-$(CONFIG_SOC_AM33XX)		+= omap_hwmod_33xx_data.o
 obj-$(CONFIG_ARCH_OMAP4)		+= omap_hwmod_44xx_data.o
 
 # EMU peripherals
-obj-$(CONFIG_OMAP3_EMU)			+= emu.o
 obj-$(CONFIG_HW_PERF_EVENTS)		+= pmu.o
 
 obj-$(CONFIG_OMAP_MBOX_FWK)		+= mailbox_mach.o
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 45cd26430d1f..da6d407c21cd 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -418,7 +418,8 @@ static struct clk_hw_omap dpll4_m5x2_ck_hw = {
 	.clkdm_name	= "dpll4_clkdm",
 };
 
-DEFINE_STRUCT_CLK(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, dpll4_m5x2_ck_ops);
+DEFINE_STRUCT_CLK_FLAGS(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names,
+			dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT);
 
 static struct clk dpll4_m5x2_ck_3630 = {
 	.name		= "dpll4_m5x2_ck",
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 2adb2683f074..6124da1a07d4 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -323,7 +323,8 @@ void omap3_save_scratchpad_contents(void)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore_3630);
 	else if (omap_rev() != OMAP3430_REV_ES3_0 &&
-					omap_rev() != OMAP3430_REV_ES3_1)
+					omap_rev() != OMAP3430_REV_ES3_1 &&
+					omap_rev() != OMAP3430_REV_ES3_1_2)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore);
 	else
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index c443f2e97e10..f98410a257e3 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -14,6 +14,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/export.h>
+#include <linux/clockchips.h>
 
 #include <asm/cpuidle.h>
 #include <asm/proc-fns.h>
@@ -80,6 +81,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 			int index)
 {
 	struct idle_statedata *cx = state_ptr + index;
+	int cpu_id = smp_processor_id();
 
 	/*
 	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -104,6 +106,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 		}
 	}
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+
 	/*
 	 * Call idle CPU PM enter notifier chain so that
 	 * VFP and per CPU interrupt context is saved.
@@ -147,6 +151,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 		(cx->mpu_logic_state == PWRDM_POWER_OFF))
 		cpu_cluster_pm_exit();
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
 	cpu_done[dev->cpu] = false;
@@ -154,6 +160,16 @@ fail:
 	return index;
 }
 
+/*
+ * For each cpu, setup the broadcast timer because local timers
+ * stops for the states above C1.
+ */
+static void omap_setup_broadcast_timer(void *arg)
+{
+	int cpu = smp_processor_id();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
 static struct cpuidle_driver omap4_idle_driver = {
 	.name				= "omap4_idle",
 	.owner				= THIS_MODULE,
@@ -171,8 +187,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C2",
 			.desc = "CPUx OFF, MPUSS CSWR",
@@ -181,8 +196,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C3",
 			.desc = "CPUx OFF, MPUSS OSWR",
@@ -213,5 +227,8 @@ int __init omap4_idle_init(void)
 	if (!cpu_clkdm[0] || !cpu_clkdm[1])
 		return -ENODEV;
 
+	/* Configure the broadcast timer on each cpu */
+	on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
+
 	return cpuidle_register(&omap4_idle_driver, cpu_online_mask);
 }
diff --git a/arch/arm/mach-omap2/emu.c b/arch/arm/mach-omap2/emu.c
deleted file mode 100644
index cbeaca2d7695..000000000000
--- a/arch/arm/mach-omap2/emu.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * emu.c
- *
- * ETM and ETB CoreSight components' resources as found in OMAP3xxx.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/amba/bus.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-
-#include "soc.h"
-#include "iomap.h"
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/* Cortex CoreSight components within omap3xxx EMU */
-#define ETM_BASE	(L4_EMU_34XX_PHYS + 0x10000)
-#define DBG_BASE	(L4_EMU_34XX_PHYS + 0x11000)
-#define ETB_BASE	(L4_EMU_34XX_PHYS + 0x1b000)
-#define DAPCTL		(L4_EMU_34XX_PHYS + 0x1d000)
-
-static AMBA_APB_DEVICE(omap3_etb, "etb", 0x000bb907, ETB_BASE, { }, NULL);
-static AMBA_APB_DEVICE(omap3_etm, "etm", 0x102bb921, ETM_BASE, { }, NULL);
-
-static int __init emu_init(void)
-{
-	if (!cpu_is_omap34xx())
-		return -ENODEV;
-
-	amba_device_register(&omap3_etb_device, &iomem_resource);
-	amba_device_register(&omap3_etm_device, &iomem_resource);
-
-	return 0;
-}
-
-omap_subsys_initcall(emu_init);
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 6c4da1254f53..55bcb77c623e 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1335,7 +1335,7 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np,
 		of_property_read_bool(np, "gpmc,time-para-granularity");
 }
 
-#ifdef CONFIG_MTD_NAND
+#if IS_ENABLED(CONFIG_MTD_NAND)
 
 static const char * const nand_ecc_opts[] = {
 	[OMAP_ECC_HAMMING_CODE_DEFAULT]		= "sw",
@@ -1391,7 +1391,7 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 }
 #endif
 
-#ifdef CONFIG_MTD_ONENAND
+#if IS_ENABLED(CONFIG_MTD_ONENAND)
 static int gpmc_probe_onenand_child(struct platform_device *pdev,
 				 struct device_node *child)
 {
diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c
index 3926f370448f..6037a9a01ed5 100644
--- a/arch/arm/mach-omap2/irq.c
+++ b/arch/arm/mach-omap2/irq.c
@@ -222,6 +222,7 @@ void __init ti81xx_init_irq(void)
 static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs *regs)
 {
 	u32 irqnr;
+	int handled_irq = 0;
 
 	do {
 		irqnr = readl_relaxed(base_addr + 0x98);
@@ -233,7 +234,7 @@ static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs
 			goto out;
 
 		irqnr = readl_relaxed(base_addr + 0xd8);
-#ifdef CONFIG_SOC_TI81XX
+#if IS_ENABLED(CONFIG_SOC_TI81XX) || IS_ENABLED(CONFIG_SOC_AM33XX)
 		if (irqnr)
 			goto out;
 		irqnr = readl_relaxed(base_addr + 0xf8);
@@ -249,8 +250,15 @@ out:
 		if (irqnr) {
 			irqnr = irq_find_mapping(domain, irqnr);
 			handle_IRQ(irqnr, regs);
+			handled_irq = 1;
 		}
 	} while (irqnr);
+
+	/* If an irq is masked or deasserted while active, we will
+	 * keep ending up here with no irq handled. So remove it from
+	 * the INTC with an ack.*/
+	if (!handled_irq)
+		omap_ack_irq(NULL);
 }
 
 asmlinkage void __exception_irq_entry omap2_intc_handle_irq(struct pt_regs *regs)
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index f82cf878d6af..94c2f6d17dae 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -183,8 +183,10 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition,
 		m0_entry = mux->muxnames[0];
 
 		/* First check for full name in mode0.muxmode format */
-		if (mode0_len && strncmp(muxname, m0_entry, mode0_len))
-			continue;
+		if (mode0_len)
+			if (strncmp(muxname, m0_entry, mode0_len) ||
+			    (strlen(m0_entry) != mode0_len))
+				continue;
 
 		/* Then check for muxmode only */
 		for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 13b27ffaf45e..ab99ab8fce8a 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -162,6 +162,7 @@ void __iomem *omap4_get_l2cache_base(void)
 
 static void omap4_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	omap_smc1(0x102, 0x0);
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 7341eff63f56..62e40a9fffa9 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -399,7 +399,7 @@ static int _set_clockactivity(struct omap_hwmod *oh, u8 clockact, u32 *v)
 }
 
 /**
- * _set_softreset: set OCP_SYSCONFIG.CLOCKACTIVITY bits in @v
+ * _set_softreset: set OCP_SYSCONFIG.SOFTRESET bit in @v
  * @oh: struct omap_hwmod *
  * @v: pointer to register contents to modify
  *
@@ -427,6 +427,36 @@ static int _set_softreset(struct omap_hwmod *oh, u32 *v)
 }
 
 /**
+ * _clear_softreset: clear OCP_SYSCONFIG.SOFTRESET bit in @v
+ * @oh: struct omap_hwmod *
+ * @v: pointer to register contents to modify
+ *
+ * Clear the SOFTRESET bit in @v for hwmod @oh.  Returns -EINVAL upon
+ * error or 0 upon success.
+ */
+static int _clear_softreset(struct omap_hwmod *oh, u32 *v)
+{
+	u32 softrst_mask;
+
+	if (!oh->class->sysc ||
+	    !(oh->class->sysc->sysc_flags & SYSC_HAS_SOFTRESET))
+		return -EINVAL;
+
+	if (!oh->class->sysc->sysc_fields) {
+		WARN(1,
+		     "omap_hwmod: %s: sysc_fields absent for sysconfig class\n",
+		     oh->name);
+		return -EINVAL;
+	}
+
+	softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift);
+
+	*v &= ~softrst_mask;
+
+	return 0;
+}
+
+/**
  * _wait_softreset_complete - wait for an OCP softreset to complete
  * @oh: struct omap_hwmod * to wait on
  *
@@ -1909,6 +1939,12 @@ static int _ocp_softreset(struct omap_hwmod *oh)
 	ret = _set_softreset(oh, &v);
 	if (ret)
 		goto dis_opt_clks;
+
+	_write_sysconfig(v, oh);
+	ret = _clear_softreset(oh, &v);
+	if (ret)
+		goto dis_opt_clks;
+
 	_write_sysconfig(v, oh);
 
 	if (oh->class->sysc->srst_udelay)
@@ -2141,6 +2177,8 @@ static int _enable(struct omap_hwmod *oh)
 			 oh->mux->pads_dynamic))) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	_add_initiator_dep(oh, mpu_oh);
@@ -2247,6 +2285,8 @@ static int _idle(struct omap_hwmod *oh)
 	if (oh->mux && oh->mux->pads_dynamic) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	oh->_state = _HWMOD_STATE_IDLE;
@@ -3148,6 +3188,11 @@ int omap_hwmod_softreset(struct omap_hwmod *oh)
 		goto error;
 	_write_sysconfig(v, oh);
 
+	ret = _clear_softreset(oh, &v);
+	if (ret)
+		goto error;
+	_write_sysconfig(v, oh);
+
 error:
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index d05fc7b54567..83735b72895d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -796,7 +796,7 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = {
 
 /* gpmc */
 static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -841,7 +841,7 @@ static struct omap_hwmod_class omap2_rng_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = {
-	{ .irq = 52 },
+	{ .irq = 52 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 31c7126eb3bb..8691c8cbe2c7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1930,7 +1930,8 @@ static struct omap_hwmod_class_sysconfig omap3xxx_usb_host_hs_sysc = {
 	.syss_offs	= 0x0014,
 	.sysc_flags	= (SYSC_HAS_MIDLEMODE | SYSC_HAS_CLOCKACTIVITY |
 			   SYSC_HAS_SIDLEMODE | SYSC_HAS_ENAWAKEUP |
-			   SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE),
+			   SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE |
+			   SYSS_HAS_RESET_STATUS),
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
 			   MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
@@ -1954,7 +1955,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_host_hs_irqs[] = {
 static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = {
 	.name		= "usb_host_hs",
 	.class		= &omap3xxx_usb_host_hs_hwmod_class,
-	.clkdm_name	= "l3_init_clkdm",
+	.clkdm_name	= "usbhost_clkdm",
 	.mpu_irqs	= omap3xxx_usb_host_hs_irqs,
 	.main_clk	= "usbhost_48m_fck",
 	.prcm = {
@@ -2008,15 +2009,7 @@ static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = {
 	 * hence HWMOD_SWSUP_MSTANDBY
 	 */
 
-	/*
-	 * During system boot; If the hwmod framework resets the module
-	 * the module will have smart idle settings; which can lead to deadlock
-	 * (above Errata Id:i660); so, dont reset the module during boot;
-	 * Use HWMOD_INIT_NO_RESET.
-	 */
-
-	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY |
-			  HWMOD_INIT_NO_RESET,
+	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
 };
 
 /*
@@ -2047,7 +2040,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_tll_hs_irqs[] = {
 static struct omap_hwmod omap3xxx_usb_tll_hs_hwmod = {
 	.name		= "usb_tll_hs",
 	.class		= &omap3xxx_usb_tll_hs_hwmod_class,
-	.clkdm_name	= "l3_init_clkdm",
+	.clkdm_name	= "core_l4_clkdm",
 	.mpu_irqs	= omap3xxx_usb_tll_hs_irqs,
 	.main_clk	= "usbtll_fck",
 	.prcm = {
@@ -2159,7 +2152,7 @@ static struct omap_hwmod_class omap3xxx_gpmc_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -2993,7 +2986,7 @@ static struct omap_mmu_dev_attr mmu_isp_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_isp_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = {
-	{ .irq = 24 },
+	{ .irq = 24 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -3035,7 +3028,7 @@ static struct omap_mmu_dev_attr mmu_iva_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_iva_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = {
-	{ .irq = 28 },
+	{ .irq = 28 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 7bdd22afce69..d4d0fce325c7 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -103,7 +103,7 @@ static inline void enable_omap3630_toggle_l2_on_restore(void) { }
 
 #define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD	(1 << 0)
 
-#if defined(CONFIG_ARCH_OMAP4)
+#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
 extern u16 pm44xx_errata;
 #define IS_PM44XX_ERRATUM(id)		(pm44xx_errata & (id))
 #else
diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c
index 3fab583755d4..0616390b857f 100644
--- a/arch/arm/mach-pxa/reset.c
+++ b/arch/arm/mach-pxa/reset.c
@@ -13,6 +13,7 @@
 
 #include <mach/regs-ost.h>
 #include <mach/reset.h>
+#include <mach/smemc.h>
 
 unsigned int reset_status;
 EXPORT_SYMBOL(reset_status);
@@ -81,6 +82,12 @@ static void do_hw_reset(void)
 	writel_relaxed(OSSR_M3, OSSR);
 	/* ... in 100 ms */
 	writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3);
+	/*
+	 * SDRAM hangs on watchdog reset on Marvell PXA270 (erratum 71)
+	 * we put SDRAM into self-refresh to prevent that
+	 */
+	while (1)
+		writel_relaxed(MDREFR_SLFRSH, MDREFR);
 }
 
 void pxa_restart(char mode, const char *cmd)
@@ -104,4 +111,3 @@ void pxa_restart(char mode, const char *cmd)
 		break;
 	}
 }
-
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 3d91d2e5bf3a..d91fcf403cee 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -424,57 +424,57 @@ static struct platform_device tosa_power_device = {
  * Tosa Keyboard
  */
 static const uint32_t tosakbd_keymap[] = {
-	KEY(0, 2, KEY_W),
-	KEY(0, 6, KEY_K),
-	KEY(0, 7, KEY_BACKSPACE),
-	KEY(0, 8, KEY_P),
-	KEY(1, 1, KEY_Q),
-	KEY(1, 2, KEY_E),
-	KEY(1, 3, KEY_T),
-	KEY(1, 4, KEY_Y),
-	KEY(1, 6, KEY_O),
-	KEY(1, 7, KEY_I),
-	KEY(1, 8, KEY_COMMA),
-	KEY(2, 1, KEY_A),
-	KEY(2, 2, KEY_D),
-	KEY(2, 3, KEY_G),
-	KEY(2, 4, KEY_U),
-	KEY(2, 6, KEY_L),
-	KEY(2, 7, KEY_ENTER),
-	KEY(2, 8, KEY_DOT),
-	KEY(3, 1, KEY_Z),
-	KEY(3, 2, KEY_C),
-	KEY(3, 3, KEY_V),
-	KEY(3, 4, KEY_J),
-	KEY(3, 5, TOSA_KEY_ADDRESSBOOK),
-	KEY(3, 6, TOSA_KEY_CANCEL),
-	KEY(3, 7, TOSA_KEY_CENTER),
-	KEY(3, 8, TOSA_KEY_OK),
-	KEY(3, 9, KEY_LEFTSHIFT),
-	KEY(4, 1, KEY_S),
-	KEY(4, 2, KEY_R),
-	KEY(4, 3, KEY_B),
-	KEY(4, 4, KEY_N),
-	KEY(4, 5, TOSA_KEY_CALENDAR),
-	KEY(4, 6, TOSA_KEY_HOMEPAGE),
-	KEY(4, 7, KEY_LEFTCTRL),
-	KEY(4, 8, TOSA_KEY_LIGHT),
-	KEY(4, 10, KEY_RIGHTSHIFT),
-	KEY(5, 1, KEY_TAB),
-	KEY(5, 2, KEY_SLASH),
-	KEY(5, 3, KEY_H),
-	KEY(5, 4, KEY_M),
-	KEY(5, 5, TOSA_KEY_MENU),
-	KEY(5, 7, KEY_UP),
-	KEY(5, 11, TOSA_KEY_FN),
-	KEY(6, 1, KEY_X),
-	KEY(6, 2, KEY_F),
-	KEY(6, 3, KEY_SPACE),
-	KEY(6, 4, KEY_APOSTROPHE),
-	KEY(6, 5, TOSA_KEY_MAIL),
-	KEY(6, 6, KEY_LEFT),
-	KEY(6, 7, KEY_DOWN),
-	KEY(6, 8, KEY_RIGHT),
+	KEY(0, 1, KEY_W),
+	KEY(0, 5, KEY_K),
+	KEY(0, 6, KEY_BACKSPACE),
+	KEY(0, 7, KEY_P),
+	KEY(1, 0, KEY_Q),
+	KEY(1, 1, KEY_E),
+	KEY(1, 2, KEY_T),
+	KEY(1, 3, KEY_Y),
+	KEY(1, 5, KEY_O),
+	KEY(1, 6, KEY_I),
+	KEY(1, 7, KEY_COMMA),
+	KEY(2, 0, KEY_A),
+	KEY(2, 1, KEY_D),
+	KEY(2, 2, KEY_G),
+	KEY(2, 3, KEY_U),
+	KEY(2, 5, KEY_L),
+	KEY(2, 6, KEY_ENTER),
+	KEY(2, 7, KEY_DOT),
+	KEY(3, 0, KEY_Z),
+	KEY(3, 1, KEY_C),
+	KEY(3, 2, KEY_V),
+	KEY(3, 3, KEY_J),
+	KEY(3, 4, TOSA_KEY_ADDRESSBOOK),
+	KEY(3, 5, TOSA_KEY_CANCEL),
+	KEY(3, 6, TOSA_KEY_CENTER),
+	KEY(3, 7, TOSA_KEY_OK),
+	KEY(3, 8, KEY_LEFTSHIFT),
+	KEY(4, 0, KEY_S),
+	KEY(4, 1, KEY_R),
+	KEY(4, 2, KEY_B),
+	KEY(4, 3, KEY_N),
+	KEY(4, 4, TOSA_KEY_CALENDAR),
+	KEY(4, 5, TOSA_KEY_HOMEPAGE),
+	KEY(4, 6, KEY_LEFTCTRL),
+	KEY(4, 7, TOSA_KEY_LIGHT),
+	KEY(4, 9, KEY_RIGHTSHIFT),
+	KEY(5, 0, KEY_TAB),
+	KEY(5, 1, KEY_SLASH),
+	KEY(5, 2, KEY_H),
+	KEY(5, 3, KEY_M),
+	KEY(5, 4, TOSA_KEY_MENU),
+	KEY(5, 6, KEY_UP),
+	KEY(5, 10, TOSA_KEY_FN),
+	KEY(6, 0, KEY_X),
+	KEY(6, 1, KEY_F),
+	KEY(6, 2, KEY_SPACE),
+	KEY(6, 3, KEY_APOSTROPHE),
+	KEY(6, 4, TOSA_KEY_MAIL),
+	KEY(6, 5, KEY_LEFT),
+	KEY(6, 6, KEY_DOWN),
+	KEY(6, 7, KEY_RIGHT),
 };
 
 static struct matrix_keymap_data tosakbd_keymap_data = {
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index e838ba27e443..c9808c684152 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -512,6 +512,9 @@ static void __init assabet_map_io(void)
 	 * Its called GPCLKR0 in my SA1110 manual.
 	 */
 	Ser1SDCR0 |= SDCR0_SUS;
+	MSC1 = (MSC1 & ~0xffff) |
+		MSC_NonBrst | MSC_32BitStMem |
+		MSC_RdAcc(2) | MSC_WrAcc(2) | MSC_Rec(0);
 
 	if (!machine_has_neponset())
 		sa1100_register_uart_fns(&assabet_port_fns);
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d2d3ee..50e1d850ee2e 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+#include "hardware.h" /* Gives GPIO_MAX */
+
 extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE	(GPIO_MAX + 1)
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index b85b2882dbd0..803c9fcfb359 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -437,7 +437,7 @@ static struct platform_device lcdc0_device = {
 	.id		= 0,
 	.dev	= {
 		.platform_data	= &lcdc0_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -534,7 +534,7 @@ static struct platform_device hdmi_lcdc_device = {
 	.id		= 1,
 	.dev	= {
 		.platform_data	= &hdmi_lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index e6b775a10aad..4d610e6ea987 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -332,7 +332,7 @@ static struct platform_device lcdc_device = {
 	.resource	= lcdc_resources,
 	.dev	= {
 		.platform_data	= &lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index fa3407da682a..3b917bc76a49 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -421,7 +421,7 @@ static struct platform_device lcdc_device = {
 	.resource	= lcdc_resources,
 	.dev	= {
 		.platform_data	= &lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -497,7 +497,7 @@ static struct platform_device hdmi_lcdc_device = {
 	.id		= 1,
 	.dev	= {
 		.platform_data	= &hdmi_lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c
index 9f852c6fe5b9..d5ebcd0bb622 100644
--- a/arch/arm/mach-tegra/common.c
+++ b/arch/arm/mach-tegra/common.c
@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/of.h>
 #include <linux/irqchip.h>
 #include <linux/clk/tegra.h>
 
@@ -80,10 +81,20 @@ void tegra_assert_system_reset(char mode, const char *cmd)
 static void __init tegra_init_cache(void)
 {
 #ifdef CONFIG_CACHE_L2X0
+	static const struct of_device_id pl310_ids[] __initconst = {
+		{ .compatible = "arm,pl310-cache",  },
+		{}
+	};
+
+	struct device_node *np;
 	int ret;
 	void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000;
 	u32 aux_ctrl, cache_type;
 
+	np = of_find_matching_node(NULL, pl310_ids);
+	if (!np)
+		return;
+
 	cache_type = readl(p + L2X0_CACHE_TYPE);
 	aux_ctrl = (cache_type & 0x700) << (17-8);
 	aux_ctrl |= 0x7C400001;
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 5907e10c37fd..39858ba03084 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,6 +1,9 @@
 config ARCH_VEXPRESS
 	bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
+	select ARCH_HAS_CPUFREQ
+	select ARCH_HAS_OPP
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_GIC
 	select ARM_TIMER_SP804
@@ -56,5 +59,23 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 
 config ARCH_VEXPRESS_CA9X4
 	bool "Versatile Express Cortex-A9x4 tile"
+	select ARM_ERRATA_643719
+
+config ARCH_VEXPRESS_DCSCB
+	bool "Dual Cluster System Control Block (DCSCB) support"
+	depends on MCPM
+	select ARM_CCI
+	help
+	  Support for the Dual Cluster System Configuration Block (DCSCB).
+	  This is needed to provide CPU and cluster power management
+	  on RTSM implementing big.LITTLE.
+
+config ARCH_VEXPRESS_TC2
+	bool "TC2 cluster management"
+	depends on MCPM
+	select VEXPRESS_SPC
+	select ARM_CCI
+	help
+	  Support for CPU and cluster power management on TC2.
 
 endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 42703e8b4d3b..14193dc7e6e8 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -6,5 +6,13 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 
 obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
+obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
+CFLAGS_REMOVE_dcscb.o			= -pg
+obj-$(CONFIG_ARCH_VEXPRESS_TC2)		+= tc2_pm.o tc2_pm_setup.o
+CFLAGS_REMOVE_tc2_pm.o			= -pg
+ifeq ($(CONFIG_ARCH_VEXPRESS_TC2),y)
+obj-$(CONFIG_ARM_PSCI)			+= tc2_pm_psci.o
+CFLAGS_REMOVE_tc2_pm_psci.o		= -pg
+endif
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index f134cd4a85f1..bde4374ab6d5 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -6,6 +6,8 @@
 
 void vexpress_dt_smp_map_io(void);
 
+bool vexpress_smp_init_ops(void);
+
 extern struct smp_operations	vexpress_smp_ops;
 
 extern void vexpress_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
new file mode 100644
index 000000000000..b35700f8e01f
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -0,0 +1,236 @@
+/*
+ * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block
+ *
+ * Created by:	Nicolas Pitre, May 2012
+ * Copyright:	(C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/of_address.h>
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+
+#define RST_HOLD0	0x0
+#define RST_HOLD1	0x4
+#define SYS_SWRESET	0x8
+#define RST_STAT0	0xc
+#define RST_STAT1	0x10
+#define EAG_CFG_R	0x20
+#define EAG_CFG_W	0x24
+#define KFC_CFG_R	0x28
+#define KFC_CFG_W	0x2c
+#define DCS_CFG_R	0x30
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() while its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static void __iomem *dcscb_base;
+static int dcscb_use_count[4][2];
+static int dcscb_allcpus_mask[2];
+
+static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int rst_hold, cpumask = (1 << cpu);
+	unsigned int all_mask = dcscb_allcpus_mask[cluster];
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cpu >= 4 || cluster >= 2)
+		return -EINVAL;
+
+	/*
+	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+	 * variant exists, we need to disable IRQs manually here.
+	 */
+	local_irq_disable();
+	arch_spin_lock(&dcscb_lock);
+
+	dcscb_use_count[cpu][cluster]++;
+	if (dcscb_use_count[cpu][cluster] == 1) {
+		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+		if (rst_hold & (1 << 8)) {
+			/* remove cluster reset and add individual CPU's reset */
+			rst_hold &= ~(1 << 8);
+			rst_hold |= all_mask;
+		}
+		rst_hold &= ~(cpumask | (cpumask << 4));
+		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+	} else if (dcscb_use_count[cpu][cluster] != 2) {
+		/*
+		 * The only possible values are:
+		 * 0 = CPU down
+		 * 1 = CPU (still) up
+		 * 2 = CPU requested to be up before it had a chance
+		 *     to actually make itself down.
+		 * Any other value is a bug.
+		 */
+		BUG();
+	}
+
+	arch_spin_unlock(&dcscb_lock);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void dcscb_power_down(void)
+{
+	unsigned int mpidr, cpu, cluster, rst_hold, cpumask, all_mask;
+	bool last_man = false, skip_wfi = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	cpumask = (1 << cpu);
+	all_mask = dcscb_allcpus_mask[cluster];
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cpu >= 4 || cluster >= 2);
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	arch_spin_lock(&dcscb_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	dcscb_use_count[cpu][cluster]--;
+	if (dcscb_use_count[cpu][cluster] == 0) {
+		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+		rst_hold |= cpumask;
+		if (((rst_hold | (rst_hold >> 4)) & all_mask) == all_mask) {
+			rst_hold |= (1 << 8);
+			last_man = true;
+		}
+		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+	} else if (dcscb_use_count[cpu][cluster] == 1) {
+		/*
+		 * A power_up request went ahead of us.
+		 * Even if we do not want to shut this CPU down,
+		 * the caller expects a certain state as if the WFI
+		 * was aborted.  So let's continue with cache cleaning.
+		 */
+		skip_wfi = true;
+	} else
+		BUG();
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		arch_spin_unlock(&dcscb_lock);
+
+		/* Flush all cache levels for this cluster. */
+		v7_exit_coherency_flush(all);
+
+		/*
+		 * This is a harmless no-op.  On platforms with a real
+		 * outer cache this might either be needed or not,
+		 * depending on where the outer cache sits.
+		 */
+		outer_flush_all();
+
+		/*
+		 * Disable cluster-level coherency by masking
+		 * incoming snoops and DVM messages:
+		 */
+		cci_disable_port_by_cpu(mpidr);
+
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		arch_spin_unlock(&dcscb_lock);
+
+		/* Disable and flush the local CPU cache. */
+		v7_exit_coherency_flush(louis);
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	dsb();
+	if (!skip_wfi)
+		wfi();
+
+	/* Not dead at this point?  Let our caller cope. */
+}
+
+static const struct mcpm_platform_ops dcscb_power_ops = {
+	.power_up	= dcscb_power_up,
+	.power_down	= dcscb_power_down,
+};
+
+static void __init dcscb_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cpu >= 4 || cluster >= 2);
+	dcscb_use_count[cpu][cluster] = 1;
+}
+
+extern void dcscb_power_up_setup(unsigned int affinity_level);
+
+static int __init dcscb_init(void)
+{
+	struct device_node *node;
+	unsigned int cfg;
+	int ret;
+
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
+	if (!cci_probed())
+		return -ENODEV;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb");
+	if (!node)
+		return -ENODEV;
+	dcscb_base = of_iomap(node, 0);
+	if (!dcscb_base)
+		return -EADDRNOTAVAIL;
+	cfg = readl_relaxed(dcscb_base + DCS_CFG_R);
+	dcscb_allcpus_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1;
+	dcscb_allcpus_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1;
+	dcscb_usage_count_init();
+
+	ret = mcpm_platform_register(&dcscb_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(dcscb_power_up_setup);
+	if (ret) {
+		iounmap(dcscb_base);
+		return ret;
+	}
+
+	pr_info("VExpress DCSCB support installed\n");
+
+	/*
+	 * Future entries into the kernel can now go
+	 * through the cluster entry vectors.
+	 */
+	vexpress_flags_set(virt_to_phys(mcpm_entry_point));
+
+	return 0;
+}
+
+early_initcall(dcscb_init);
diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S
new file mode 100644
index 000000000000..4bb7fbe0f621
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb_setup.S
@@ -0,0 +1,38 @@
+/*
+ * arch/arm/include/asm/dcscb_setup.S
+ *
+ * Created by:  Dave Martin, 2012-06-22
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+
+ENTRY(dcscb_power_up_setup)
+
+	cmp	r0, #0			@ check affinity level
+	beq	2f
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ *
+ * A15/A7 may not require explicit L2 invalidation on reset, dependent
+ * on hardware integration decisions.
+ * For now, this code assumes that L2 is either already invalidated,
+ * or invalidation is not required.
+ */
+
+	b	cci_enable_port_for_self
+
+2:	@ Implementation-specific local CPU setup operations should go here,
+	@ if any.  In this case, there is nothing to do.
+
+	bx	lr
+
+ENDPROC(dcscb_power_up_setup)
diff --git a/arch/arm/mach-vexpress/include/mach/tc2.h b/arch/arm/mach-vexpress/include/mach/tc2.h
new file mode 100644
index 000000000000..d3b5a2225a0e
--- /dev/null
+++ b/arch/arm/mach-vexpress/include/mach/tc2.h
@@ -0,0 +1,10 @@
+#ifndef __MACH_TC2_H
+#define __MACH_TC2_H
+
+/*
+ * cpu and cluster limits
+ */
+#define TC2_MAX_CPUS		3
+#define TC2_MAX_CLUSTERS	2
+
+#endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 84bd6fde7a7c..b4a5f0d8390d 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -12,9 +12,11 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/vexpress.h>
 
+#include <asm/mcpm.h>
 #include <asm/smp_scu.h>
 #include <asm/mach/map.h>
 
@@ -203,3 +205,21 @@ struct smp_operations __initdata vexpress_smp_ops = {
 	.cpu_die		= vexpress_cpu_die,
 #endif
 };
+
+bool __init vexpress_smp_init_ops(void)
+{
+#ifdef CONFIG_MCPM
+	/*
+	 * The best way to detect a multi-cluster configuration at the moment
+	 * is to look for the presence of a CCI in the system.
+	 * Override the default vexpress_smp_ops if so.
+	 */
+	struct device_node *node;
+	node = of_find_compatible_node(NULL, NULL, "arm,cci-400");
+	if (node && of_device_is_available(node)) {
+		mcpm_smp_set_ops();
+		return true;
+	}
+#endif
+	return false;
+}
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
new file mode 100644
index 000000000000..9fc264a3bade
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -0,0 +1,277 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
+ *
+ * Created by:	Nicolas Pitre, October 2012
+ * Copyright:	(C) 2012  Linaro Limited
+ *
+ * Some portions of this file were originally written by Achin Gupta
+ * Copyright:   (C) 2012  ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() after its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static int tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+{
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cluster >= TC2_MAX_CLUSTERS ||
+	    cpu >= vexpress_spc_get_nb_cpus(cluster))
+		return -EINVAL;
+
+	/*
+	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+	 * variant exists, we need to disable IRQs manually here.
+	 */
+	local_irq_disable();
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (!tc2_pm_use_count[0][cluster] &&
+	    !tc2_pm_use_count[1][cluster] &&
+	    !tc2_pm_use_count[2][cluster])
+		vexpress_spc_powerdown_enable(cluster, 0);
+
+	tc2_pm_use_count[cpu][cluster]++;
+	if (tc2_pm_use_count[cpu][cluster] == 1) {
+		vexpress_spc_write_resume_reg(cluster, cpu,
+					      virt_to_phys(mcpm_entry_point));
+		vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+	} else if (tc2_pm_use_count[cpu][cluster] != 2) {
+		/*
+		 * The only possible values are:
+		 * 0 = CPU down
+		 * 1 = CPU (still) up
+		 * 2 = CPU requested to be up before it had a chance
+		 *     to actually make itself down.
+		 * Any other value is a bug.
+		 */
+		BUG();
+	}
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void tc2_pm_down(u64 residency)
+{
+	unsigned int mpidr, cpu, cluster;
+	bool last_man = false, skip_wfi = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+	       cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	arch_spin_lock(&tc2_pm_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	tc2_pm_use_count[cpu][cluster]--;
+	if (tc2_pm_use_count[cpu][cluster] == 0) {
+		vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+		if (!tc2_pm_use_count[0][cluster] &&
+		    !tc2_pm_use_count[1][cluster] &&
+		    !tc2_pm_use_count[2][cluster] &&
+		    (!residency || residency > 5000)) {
+			vexpress_spc_powerdown_enable(cluster, 1);
+			vexpress_spc_set_global_wakeup_intr(1);
+			last_man = true;
+		}
+	} else if (tc2_pm_use_count[cpu][cluster] == 1) {
+		/*
+		 * A power_up request went ahead of us.
+		 * Even if we do not want to shut this CPU down,
+		 * the caller expects a certain state as if the WFI
+		 * was aborted.  So let's continue with cache cleaning.
+		 */
+		skip_wfi = true;
+	} else
+		BUG();
+
+	/*
+	 * If the CPU is committed to power down, make sure
+	 * the power controller will be in charge of waking it
+	 * up upon IRQ, ie IRQ lines are cut from GIC CPU IF
+	 * to the CPU by disabling the GIC CPU IF to prevent wfi
+	 * from completing execution behind power controller back
+	 */
+	if (!skip_wfi)
+		gic_cpu_if_down();
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		arch_spin_unlock(&tc2_pm_lock);
+
+		if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
+			/*
+			 * On the Cortex-A15 we need to disable
+			 * L2 prefetching before flushing the cache.
+			 */
+			asm volatile(
+			"mcr	p15, 1, %0, c15, c0, 3 \n\t"
+			"isb	\n\t"
+			"dsb	"
+			: : "r" (0x400) );
+		}
+
+		v7_exit_coherency_flush(all);
+
+		cci_disable_port_by_cpu(mpidr);
+
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		/*
+		 * If last man then undo any setup done previously.
+		 */
+		if (last_man) {
+			vexpress_spc_powerdown_enable(cluster, 0);
+			vexpress_spc_set_global_wakeup_intr(0);
+		}
+
+		arch_spin_unlock(&tc2_pm_lock);
+
+		v7_exit_coherency_flush(louis);
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	if (!skip_wfi)
+		wfi();
+
+	/* Not dead at this point?  Let our caller cope. */
+}
+
+static void tc2_pm_power_down(void)
+{
+	tc2_pm_down(0);
+}
+
+static void tc2_pm_suspend(u64 residency)
+{
+	extern void tc2_resume(void);
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	vexpress_spc_write_resume_reg(cluster, cpu,
+				      virt_to_phys(tc2_resume));
+
+	tc2_pm_down(residency);
+}
+
+static void tc2_pm_powered_up(void)
+{
+	unsigned int mpidr, cpu, cluster;
+	unsigned long flags;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+	       cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	local_irq_save(flags);
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (!tc2_pm_use_count[0][cluster] &&
+	    !tc2_pm_use_count[1][cluster] &&
+	    !tc2_pm_use_count[2][cluster]) {
+		vexpress_spc_powerdown_enable(cluster, 0);
+		vexpress_spc_set_global_wakeup_intr(0);
+	}
+
+	if (!tc2_pm_use_count[cpu][cluster])
+		tc2_pm_use_count[cpu][cluster] = 1;
+
+	vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0);
+	vexpress_spc_write_resume_reg(cluster, cpu, 0);
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_restore(flags);
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up	= tc2_pm_power_up,
+	.power_down	= tc2_pm_power_down,
+	.suspend	= tc2_pm_suspend,
+	.powered_up	= tc2_pm_powered_up,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+	       cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	tc2_pm_use_count[cpu][cluster] = 1;
+}
+
+extern void tc2_pm_power_up_setup(unsigned int affinity_level);
+
+static int __init tc2_pm_init(void)
+{
+	int ret;
+
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
+	if (!vexpress_spc_check_loaded())
+		return -ENODEV;
+
+	tc2_pm_usage_count_init();
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(tc2_pm_power_up_setup);
+	if (!ret)
+		pr_info("TC2 power management initialized\n");
+	return ret;
+}
+
+early_initcall(tc2_pm_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c
new file mode 100644
index 000000000000..c2fdc22e4c06
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_psci.c
@@ -0,0 +1,173 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support
+ *
+ * Created by: Achin Gupta, December 2012
+ * Copyright:  (C) 2012  ARM Limited
+ *
+ * Some portions of this file were originally written by Nicolas Pitre
+ * Copyright:   (C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/psci.h>
+#include <asm/atomic.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+
+/*
+ * Platform specific state id understood by the firmware and used to
+ * program the power controller
+ */
+#define PSCI_POWER_STATE_ID           0
+
+static atomic_t tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int mpidr = (cluster << 8) | cpu;
+	int ret = 0;
+
+	BUG_ON(!psci_ops.cpu_on);
+
+	switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * This is a request to power up a cpu that linux thinks has
+		 * been powered down. Retries are needed if the firmware has
+		 * seen the power down request as yet.
+		 */
+		do
+			ret = psci_ops.cpu_on(mpidr,
+					      virt_to_phys(mcpm_entry_point));
+		while (ret == -EAGAIN);
+
+		return ret;
+	case 2:
+		/* This power up request has overtaken a power down request */
+		return ret;
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_power_down(void)
+{
+	struct psci_power_state power_state;
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	BUG_ON(!psci_ops.cpu_off);
+
+	switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * Overtaken by a power up. Flush caches, exit coherency,
+		 * return & fake a reset
+		 */
+		set_cr(get_cr() & ~CR_C);
+
+		flush_cache_louis();
+
+		asm volatile ("clrex");
+		set_auxcr(get_auxcr() & ~(1 << 6));
+
+		return;
+	case 0:
+		/* A normal request to possibly power down the cluster */
+		power_state.id = PSCI_POWER_STATE_ID;
+		power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+		power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+		psci_ops.cpu_off(power_state);
+
+		/* On success this function never returns */
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_suspend(u64 unused)
+{
+	struct psci_power_state power_state;
+
+	BUG_ON(!psci_ops.cpu_suspend);
+
+	/* On TC2 always attempt to power down the cluster */
+	power_state.id = PSCI_POWER_STATE_ID;
+	power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+	power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+	psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point));
+
+	/* On success this function never returns */
+	BUG();
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up      = tc2_pm_psci_power_up,
+	.power_down    = tc2_pm_psci_power_down,
+	.suspend       = tc2_pm_psci_suspend,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+	       cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	atomic_set(&tc2_pm_use_count[cpu][cluster], 1);
+}
+
+static int __init tc2_pm_psci_init(void)
+{
+	int ret;
+
+	ret = psci_probe();
+	if (ret) {
+		pr_debug("psci not found. Aborting psci init\n");
+		return -ENODEV;
+	}
+
+	if (!vexpress_spc_check_loaded()) {
+		pr_debug("spc not found. Aborting psci init\n");
+		return -ENODEV;
+	}
+
+	tc2_pm_usage_count_init();
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(NULL);
+	if (!ret)
+		pr_info("TC2 power management initialized\n");
+	return ret;
+}
+
+early_initcall(tc2_pm_psci_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S
new file mode 100644
index 000000000000..a18dafeeb0ee
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_setup.S
@@ -0,0 +1,68 @@
+/*
+ * arch/arm/include/asm/tc2_pm_setup.S
+ *
+ * Created by: Nicolas Pitre, October 2012
+ (             (based on dcscb_setup.S by Dave Martin)
+ * Copyright:  (C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/linkage.h>
+#include <asm/mcpm.h>
+
+
+#define SPC_PHYS_BASE		0x7FFF0000
+#define SPC_WAKE_INT_STAT	0xb2c
+
+#define SNOOP_CTL_A15		0x404
+#define SNOOP_CTL_A7		0x504
+
+#define A15_SNOOP_MASK		(0x3 << 7)
+#define A7_SNOOP_MASK		(0x1 << 13)
+
+#define A15_BX_ADDR0		0xB68
+
+
+ENTRY(tc2_resume)
+	mrc	p15, 0, r0, c0, c0, 5
+	ubfx	r1, r0, #0, #4		@ r1 = cpu
+	ubfx	r2, r0, #8, #4		@ r2 = cluster
+	add	r1, r1, r2, lsl #2	@ r1 = index of CPU in WAKE_INT_STAT
+	ldr	r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT
+	ldr	r3, [r3]
+	lsr	r3, r1
+	tst	r3, #1
+	wfieq				@ if no pending IRQ reenters wfi
+	b	mcpm_entry_point
+ENDPROC(tc2_resume)
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ */
+
+ENTRY(tc2_pm_power_up_setup)
+
+	cmp	r0, #0
+	beq	2f
+
+	b cci_enable_port_for_self
+
+2:	@ Clear the BX addr register
+	ldr	r3, =SPC_PHYS_BASE + A15_BX_ADDR0
+	mrc	p15, 0, r0, c0, c0, 5	@ MPIDR
+	ubfx	r1, r0, #8, #4		@ cluster
+	ubfx	r0, r0, #0, #4		@ cpu
+	add	r3, r3, r1, lsl #4
+	mov	r1, #0
+	str	r1, [r3, r0, lsl #2]
+	dsb
+
+	bx	lr
+
+ENDPROC(tc2_pm_power_up_setup)
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 8802030df98d..057f99b62eaf 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -10,6 +10,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
+#include <linux/memblock.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/of_irq.h>
@@ -373,6 +374,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
 	.init_machine	= v2m_init,
 MACHINE_END
 
+static void __init v2m_dt_hdlcd_init(void)
+{
+	struct device_node *node;
+	int len, na, ns;
+	const __be32 *prop;
+	phys_addr_t fb_base, fb_size;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,hdlcd");
+	if (!node)
+		return;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	prop = of_get_property(node, "framebuffer", &len);
+	if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+		return;
+
+	fb_base = of_read_number(prop, na);
+	fb_size = of_read_number(prop + na, ns);
+
+	if (WARN_ON(memblock_remove(fb_base, fb_size)))
+		return;
+};
+
 static struct map_desc v2m_rs1_io_desc __initdata = {
 	.virtual	= V2M_PERIPH,
 	.pfn		= __phys_to_pfn(0x1c000000),
@@ -423,6 +449,8 @@ void __init v2m_dt_init_early(void)
 			pr_warning("vexpress: DT HBI (%x) is not matching "
 					"hardware (%x)!\n", dt_hbi, hbi);
 	}
+
+	v2m_dt_hdlcd_init();
 }
 
 static void __init v2m_dt_timer_init(void)
@@ -456,6 +484,7 @@ static const char * const v2m_dt_match[] __initconst = {
 DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
 	.dt_compat	= v2m_dt_match,
 	.smp		= smp_ops(vexpress_smp_ops),
+	.smp_init	= smp_init_ops(vexpress_smp_init_ops),
 	.map_io		= v2m_dt_map_io,
 	.init_early	= v2m_dt_init_early,
 	.init_irq	= irqchip_init,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 08c9fe917d1f..2e719593c5cb 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -436,7 +436,6 @@ config CPU_32v5
 
 config CPU_32v6
 	bool
-	select CPU_USE_DOMAINS if CPU_V6 && MMU
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
 
 config CPU_32v6K
@@ -651,7 +650,7 @@ config ARM_VIRT_EXT
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7
+	depends on CPU_V7
 	default y if SMP
 	select HAVE_PROC_CPU if PROC_FS
 	help
@@ -779,6 +778,7 @@ config NEED_KUSER_HELPERS
 
 config KUSER_HELPERS
 	bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+	depends on MMU
 	default y
 	help
 	  Warning: disabling this option may break user programs.
@@ -932,3 +932,9 @@ config ARCH_HAS_BARRIERS
 	help
 	  This option allows the use of custom mandatory barriers
 	  included via the mach/barriers.h file.
+
+config ARCH_SUPPORTS_BIG_ENDIAN
+	bool
+	help
+	  This option specifies the architecture can support big endian
+	  operation.
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 9e51be96f635..224a9cc09877 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_MODULES)		+= proc-syms.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 
 obj-$(CONFIG_CPU_ABRT_NOMMU)	+= abort-nommu.o
 obj-$(CONFIG_CPU_ABRT_EV4)	+= abort-ev4.o
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 80741992a9fc..8c48c5c22a33 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -17,12 +17,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
-	sub	r1, sp, #4			@ Get unused stack location
-	strex	r0, r1, [r1]			@ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
@@ -38,9 +32,8 @@ ENTRY(v6_early_abort)
 	bne	do_DataAbort
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r3, r3
-#endif
+ ARM_BE8(rev	r3, r3)
+
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 703375277ba6..4812ad054214 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -13,12 +13,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f4585b89078..d301662b7b32 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -25,6 +25,7 @@
 #include <asm/cp15.h>
 #include <asm/system_info.h>
 #include <asm/unaligned.h>
+#include <asm/opcodes.h>
 
 #include "fault.h"
 
@@ -39,6 +40,7 @@
  * This code is not portable to processors with late data abort handling.
  */
 #define CODING_BITS(i)	(i & 0x0e000000)
+#define COND_BITS(i)	(i & 0xf0000000)
 
 #define LDST_I_BIT(i)	(i & (1 << 26))		/* Immediate constant	*/
 #define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
@@ -762,21 +764,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
 		fault = probe_kernel_address(ptr, tinstr);
+		tinstr = __mem_to_opcode_thumb16(tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
 				fault = probe_kernel_address(ptr + 1, tinst2);
-				instr = (tinstr << 16) | tinst2;
+				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
 				isize = 2;
 				instr = thumb2arm(tinstr);
 			}
 		}
-	} else
+	} else {
 		fault = probe_kernel_address(instrptr, instr);
+		instr = __mem_to_opcode_arm(instr);
+	}
 
 	if (fault) {
 		type = TYPE_FAULT;
@@ -812,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		break;
 
 	case 0x04000000:	/* ldr or str immediate */
+		if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+			goto bad;
 		offset.un = OFFSET_BITS(instr);
 		handler = do_alignment_ldrstr;
 		break;
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 515b00064da8..a84e0536ce74 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -146,18 +146,18 @@ flush_levels:
 	ldr	r7, =0x7fff
 	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
 loop1:
-	mov	r9, r4				@ create working copy of max way size
+	mov	r9, r7				@ create working copy of max index
 loop2:
- ARM(	orr	r11, r10, r9, lsl r5	)	@ factor way and cache number into r11
- THUMB(	lsl	r6, r9, r5		)
+ ARM(	orr	r11, r10, r4, lsl r5	)	@ factor way and cache number into r11
+ THUMB(	lsl	r6, r4, r5		)
  THUMB(	orr	r11, r10, r6		)	@ factor way and cache number into r11
- ARM(	orr	r11, r11, r7, lsl r2	)	@ factor index number into r11
- THUMB(	lsl	r6, r7, r2		)
+ ARM(	orr	r11, r11, r9, lsl r2	)	@ factor index number into r11
+ THUMB(	lsl	r6, r9, r2		)
  THUMB(	orr	r11, r11, r6		)	@ factor index number into r11
 	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
-	subs	r9, r9, #1			@ decrement the way
+	subs	r9, r9, #1			@ decrement the index
 	bge	loop2
-	subs	r7, r7, #1			@ decrement the index
+	subs	r4, r4, #1			@ decrement the way
 	bge	loop1
 skip:
 	add	r10, r10, #2			@ increment cache number
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 9c52fef44d7f..19cab5318d08 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -250,7 +250,7 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 #ifdef CONFIG_MMU
 #ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
 #endif
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
@@ -1272,7 +1272,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (gfp & GFP_ATOMIC)
+	if (!(gfp & __GFP_WAIT))
 		return __iommu_alloc_atomic(dev, size, handle);
 
 	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c
index 9d285626bc7d..312e15e6d00b 100644
--- a/arch/arm/mm/extable.c
+++ b/arch/arm/mm/extable.c
@@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
+	if (fixup) {
 		regs->ARM_pc = fixup->fixup;
+#ifdef CONFIG_THUMB2_KERNEL
+		/* Clear the IT state to avoid nasty surprises in the fixup */
+		regs->ARM_cpsr &= ~PSR_IT_MASK;
+#endif
+	}
 
 	return fixup != NULL;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5dbf13f954f6..54fcddafec15 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	int write = fsr & FSR_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, fsr))
 		return 0;
@@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (fsr & FSR_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -349,6 +352,13 @@ retry:
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we
+	 * have no context to handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -359,13 +369,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to
@@ -446,8 +449,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 
 	if (pud_none(*pud_k))
 		goto bad_area;
-	if (!pud_present(*pud))
+	if (!pud_present(*pud)) {
 		set_pud(pud, *pud_k);
+		/*
+		 * There is a small window during free_pgtables() where the
+		 * user *pud entry is 0 but the TLB has not been invalidated
+		 * and we get a level 2 (pmd) translation fault caused by the
+		 * intermediate TLB caching of the old level 1 (pud) entry.
+		 */
+		flush_tlb_kernel_page(addr);
+	}
 
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);
@@ -470,8 +481,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 #endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;
+	if (!pmd_present(pmd[index]))
+		copy_pmd(pmd, pmd_k);
 
-	copy_pmd(pmd, pmd_k);
 	return 0;
 
 bad_area:
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 32aa5861119f..c9e37aac450b 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
 #include <asm/highmem.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
+#include <linux/hugetlb.h>
 
 #include "mm.h"
 
@@ -168,19 +169,23 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+		size_t page_size = PAGE_SIZE << compound_order(page);
+		__cpuc_flush_dcache_area(page_address(page), page_size);
 	} else {
-		void *addr;
-
+		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			addr = kmap_atomic(page);
-			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_atomic(addr);
-		} else {
-			addr = kmap_high_get(page);
-			if (addr) {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_atomic(page);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-				kunmap_high(page);
+				kunmap_atomic(addr);
+			}
+		} else {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_high_get(page);
+				if (addr) {
+					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+					kunmap_high(page);
+				}
 			}
 		}
 	}
diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c
index 05a4e9431836..ab4409a2307e 100644
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@@ -9,11 +9,11 @@ static struct fsr_info fsr_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
new file mode 100644
index 000000000000..3d1e4a205b0b
--- /dev/null
+++ b/arch/arm/mm/hugetlbpage.c
@@ -0,0 +1,101 @@
+/*
+ * arch/arm/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+/*
+ * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot
+ * of type casting from pmd_t * to pte_t *.
+ */
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_present(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (pud_present(*pud))
+			pmd = pmd_offset(pud, addr);
+	}
+
+	return (pte_t *)pmd;
+}
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+			      int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	return 0;
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pte_t *pte = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud)
+		pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
+	return pte;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pmd);
+	if (page)
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index c0a1e48f6733..990837379112 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -25,6 +25,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 04d9006eab1f..f123d6eb074b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -331,10 +331,10 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	return (void __iomem *) (offset + addr);
 }
 
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 	unsigned int mtype, void *caller)
 {
-	unsigned long last_addr;
+	phys_addr_t last_addr;
  	unsigned long offset = phys_addr & ~PAGE_MASK;
  	unsigned long pfn = __phys_to_pfn(phys_addr);
 
@@ -367,12 +367,12 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
 void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
 {
 	return arch_ioremap_caller(phys_addr, size, mtype,
 		__builtin_return_address(0));
@@ -387,7 +387,7 @@ EXPORT_SYMBOL(__arm_ioremap);
  * CONFIG_GENERIC_ALLOCATOR for allocating external memory.
  */
 void __iomem *
-__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 {
 	unsigned int mtype;
 
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 10062ceadd1c..5ef506c6f492 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = FIRST_USER_ADDRESS;
 	info.high_limit = mm->mmap_base;
 	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
@@ -204,13 +204,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size)
 }
 
 /*
- * We don't use supersection mappings for mmap() on /dev/mem, which
- * means that we can't map the memory area above the 4G barrier into
- * userspace.
+ * Do not allow /dev/mem mappings beyond the supported physical range.
  */
 int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 {
-	return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
+	return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
 }
 
 #ifdef CONFIG_STRICT_DEVMEM
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index daf336fe0be8..fb3c446af9e5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -459,6 +459,16 @@ static void __init build_mem_type_table(void)
 	hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte;
 
 	/*
+	 * We don't use domains on ARMv6 (since this causes problems with
+	 * v6/v7 kernels), so we must use a separate memory type for user
+	 * r/o, kernel r/w to map the vectors page.
+	 */
+#ifndef CONFIG_ARM_LPAE
+	if (cpu_arch == CPU_ARCH_ARMv6)
+		vecs_pgprot |= L_PTE_MT_VECTORS;
+#endif
+
+	/*
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index eb5293a69a84..7fe0524a5449 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -87,16 +87,16 @@ void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
 	return __arm_ioremap_pfn(pfn, offset, size, mtype);
 }
 
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
 			    unsigned int mtype)
 {
 	return (void __iomem *)phys_addr;
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
 
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 0acb089d0f70..1046b373d1ae 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
-		set_pte_ext(new_pte, *init_pte, 0);
+		set_pte_ext(new_pte + 0, init_pte[0], 0);
+		set_pte_ext(new_pte + 1, init_pte[1], 0);
 		pte_unmap(init_pte);
 		pte_unmap(new_pte);
 	}
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e3c48a3fe063..ee1d80593958 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -112,13 +112,9 @@
  *  100x   1   0   1	r/o	no acc
  *  10x0   1   0   1	r/o	no acc
  *  1011   0   0   1	r/w	no acc
- *  110x   0   1   0	r/w	r/o
- *  11x0   0   1   0	r/w	r/o
- *  1111   0   1   1	r/w	r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
  *  110x   1   1   1	r/o	r/o
  *  11x0   1   1   1	r/o	r/o
+ *  1111   0   1   1	r/w	r/w
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -137,7 +133,7 @@
 	.long	PTE_EXT_TEX(2)					@ L_PTE_MT_DEV_NONSHARED
 	.long	0x00						@ unused
 	.long	0x00						@ unused
-	.long	0x00						@ unused
+	.long	PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX	@ L_PTE_MT_VECTORS
 	.endm
 
 	.macro	armv6_set_pte_ext pfx
@@ -158,24 +154,21 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+	@ user read-only -> kernel read-only
+	bicne	r3, r3, #PTE_EXT_AP0
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
-	orr	r3, r3, r2
+	eor	r3, r3, r2
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
-#ifndef CONFIG_CPU_USE_DOMAINS
 	tstne	r1, #L_PTE_NONE
 	movne	r3, #0
-#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 919405e20b80..b96c6e64943e 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -206,7 +206,6 @@ __v6_setup:
 	mcr	p15, 0, r0, c7, c14, 0		@ clean+invalidate D cache
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, r0, c7, c15, 0		@ clean+invalidate cache
-	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
@@ -216,11 +215,11 @@ __v6_setup:
 	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
 	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
+	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer and
+						@ complete invalidations
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index b3997c70af32..bb20ba0f7bc7 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -90,21 +90,14 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_VALID
-#ifndef CONFIG_CPU_USE_DOMAINS
 	eorne	r1, r1, #L_PTE_NONE
 	tstne	r1, #L_PTE_NONE
-#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 6ba4bd9118f2..6f3b0476b729 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -56,6 +56,14 @@ ENTRY(cpu_v7_switch_mm)
 	mov	pc, lr
 ENDPROC(cpu_v7_switch_mm)
 
+#ifdef __ARMEB__
+#define rl r3
+#define rh r2
+#else
+#define rl r2
+#define rh r3
+#endif
+
 /*
  * cpu_v7_set_pte_ext(ptep, pte)
  *
@@ -65,13 +73,13 @@ ENDPROC(cpu_v7_switch_mm)
  */
 ENTRY(cpu_v7_set_pte_ext)
 #ifdef CONFIG_MMU
-	tst	r2, #L_PTE_VALID
+	tst	rl, #L_PTE_VALID
 	beq	1f
-	tst	r3, #1 << (57 - 32)		@ L_PTE_NONE
-	bicne	r2, #L_PTE_VALID
+	tst	rh, #1 << (57 - 32)		@ L_PTE_NONE
+	bicne	rl, #L_PTE_VALID
 	bne	1f
-	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
-	orreq	r2, #L_PTE_RDONLY
+	tst	rh, #1 << (55 - 32)		@ L_PTE_DIRTY
+	orreq	rl, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
 	ALT_SMP(W(nop))
 	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 5fbccee5f644..50c9943ca60d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -201,7 +201,6 @@ __v7_pj4b_setup:
 /* Auxiliary Debug Modes Control 1 Register */
 #define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
 #define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
-#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
 #define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
 
 /* Auxiliary Debug Modes Control 2 Register */
@@ -224,7 +223,6 @@ __v7_pj4b_setup:
 	/* Auxiliary Debug Modes Control 1 Register */
 	mrc	p15, 1,	r0, c15, c1, 1
 	orr     r0, r0, #PJ4B_CLEAN_LINE
-	orr     r0, r0, #PJ4B_BCK_OFF_STREX
 	orr     r0, r0, #PJ4B_INTER_PARITY
 	bic	r0, r0, #PJ4B_STATIC_BP
 	mcr	p15, 1,	r0, c15, c1, 1
@@ -329,7 +327,6 @@ __v7_setup:
 
 3:	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
-	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
@@ -338,6 +335,7 @@ __v7_setup:
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
+	dsb					@ Complete invalidations
 #ifndef CONFIG_ARM_THUMBEE
 	mrc	p15, 0, r0, c0, c1, 0		@ read ID_PFR0 for ThumbEE
 	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field
@@ -352,9 +350,7 @@ __v7_setup:
 #endif
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 #ifdef CONFIG_SWP_EMULATE
 	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
 	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index e766f889bfd6..08b51b7dbf69 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -535,7 +535,7 @@ ENTRY(cpu_xscale_do_suspend)
 	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mrc	p15, 0, r6, c13, c0, 0	@ PID
 	mrc	p15, 0, r7, c3, c0, 0	@ domain ID
-	mrc	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mrc	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
 	mrc	p15, 0, r9, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
 	stmia	r0, {r4 - r9}		@ store cp regs
@@ -552,7 +552,7 @@ ENTRY(cpu_xscale_do_resume)
 	mcr	p15, 0, r6, c13, c0, 0	@ PID
 	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
 	mcr	p15, 0, r1, c2, c0, 0	@ translation table base addr
-	mcr	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mcr	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
 	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_xscale_do_resume)
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 1a643ee8e082..78351ca8d51e 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -19,6 +19,7 @@
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
+#include <asm/opcodes.h>
 
 #include "bpf_jit_32.h"
 
@@ -113,8 +114,11 @@ static u32 jit_udiv(u32 dividend, u32 divisor)
 
 static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
 {
+	inst |= (cond << 28);
+	inst = __opcode_to_mem_arm(inst);
+
 	if (ctx->target != NULL)
-		ctx->target[ctx->idx] = inst | (cond << 28);
+		ctx->target[ctx->idx] = inst;
 
 	ctx->idx++;
 }
@@ -637,10 +641,10 @@ load_ind:
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
 		case BPF_S_ALU_DIV_K:
-			/* current k == reciprocal_value(userspace k) */
+			if (k == 1)
+				break;
 			emit_mov_i(r_scratch, k, ctx);
-			/* A = top 32 bits of the product */
-			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
 		case BPF_S_ALU_DIV_X:
 			update_on_xread(ctx);
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index b178d44e9eaa..40f27e52de75 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -10,8 +10,7 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
-
-	__INIT
+#include <asm/assembler.h>
 
 /*
  * Realview/Versatile Express specific entry point for secondary CPUs.
@@ -19,6 +18,7 @@
  * until we're ready for them to initialise.
  */
 ENTRY(versatile_secondary_startup)
+ ARM_BE8(setend	be)
 	mrc	p15, 0, r0, c0, c0, 5
 	bic	r0, #0xff000000
 	adr	r4, 1f
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index d185ea209ef1..2cf752060a41 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -3,18 +3,25 @@ config ARM64
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_OPP
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_HAS_OPP
+	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
+	select ARM_GIC_V3
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
@@ -24,21 +31,30 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
+	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS
+	select HAVE_DYNAMIC_FTRACE
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
@@ -148,6 +164,11 @@ config ARM64_64K_PAGES
 	  look-up. AArch32 emulation is not available when this feature
 	  is enabled.
 
+config CPU_BIG_ENDIAN
+       bool "Build big-endian kernel"
+       help
+         Say Y if you plan on running a kernel in big-endian mode.
+
 config SMP
 	bool "Symmetric Multi-Processing"
 	select USE_GENERIC_SMP_HELPERS
@@ -162,6 +183,118 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on SMP
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on SMP
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+	bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+	help
+	  Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the thresholds and load average
+	  period value for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  and the thresholds used for HMP migration.
+	  The load_avg_period_ms is the time in ms to reach a load average of
+	  0.5 for an idle task of 0 load average ratio that start a busy loop.
+	  The up_threshold and down_threshold is the value to go to a faster
+	  CPU or to go back to a slower cpu.
+	  The {up,down}_threshold are devided by 1024 before being compared
+	  to the load average.
+	  For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on HMP_VARIABLE_SCALE && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
@@ -245,6 +378,20 @@ config CMDLINE_FORCE
 	  This is useful if you cannot or don't want to change the
 	  command-line options your boot loader passes to the kernel.
 
+config EFI
+	bool "UEFI runtime support"
+	depends on OF && !CPU_BIG_ENDIAN
+	select LIBFDT
+	select UCS2_STRING
+	select EFI_PARAMS_FROM_FDT
+	default y
+	help
+	  This option provides support for runtime services provided
+	  by UEFI firmware (such as non-volatile variables, realtime
+          clock, and platform reset). A UEFI stub is also provided to
+	  allow the kernel to be booted as an EFI application. This
+	  is only useful on systems that have UEFI firmware.
+
 endmenu
 
 menu "Userspace binary formats"
@@ -272,10 +419,31 @@ config SYSVIPC_COMPAT
 
 endmenu
 
+menu "Power management options"
+
+source "kernel/power/Kconfig"
+
+source "drivers/cpufreq/Kconfig"
+config ARCH_SUSPEND_POSSIBLE
+	def_bool y
+
+config ARM64_CPU_SUSPEND
+	def_bool PM_SLEEP
+
+endmenu
+
+menu "CPU Power Management"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
 
+source "drivers/firmware/Kconfig"
+
 source "fs/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
@@ -285,5 +453,8 @@ source "arch/arm64/Kconfig.debug"
 source "security/Kconfig"
 
 source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
 
 source "lib/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index a5004a5b7aa4..3e7882c4e034 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -20,9 +20,15 @@ LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 KBUILD_DEFCONFIG := defconfig
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+KBUILD_CPPFLAGS	+= -mbig-endian
+AS		+= -EB
+LD		+= -EB
+else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 AS		+= -EL
 LD		+= -EL
+endif
 
 comma = ,
 
@@ -42,6 +48,7 @@ export	TEXT_OFFSET GZFLAGS
 
 core-y		+= arch/arm64/kernel/ arch/arm64/mm/
 core-$(CONFIG_KVM) += arch/arm64/kvm/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
 libs-y		:= arch/arm64/lib/ $(libs-y)
 libs-y		+= $(LIBGCC)
 
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index c52bdb051f66..ef388176116d 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,4 +1,6 @@
-dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb \
+				fvp-base-gicv2-psci.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb
 dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
 
 targets += dtbs
diff --git a/arch/arm64/boot/dts/clcd-panels.dtsi b/arch/arm64/boot/dts/clcd-panels.dtsi
new file mode 100644
index 000000000000..0b0ff6ead4b2
--- /dev/null
+++ b/arch/arm64/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "VGA";
+			refresh		= <60>;
+			xres		= <640>;
+			yres		= <480>;
+			pixclock	= <39721>;
+			left_margin	= <40>;
+			right_margin	= <24>;
+			upper_margin	= <32>;
+			lower_margin	= <11>;
+			hsync_len	= <96>;
+			vsync_len	= <2>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+
+		panel@1 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
new file mode 100644
index 000000000000..ed55571e06dd
--- /dev/null
+++ b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
@@ -0,0 +1,294 @@
+/*
+ * Copyright (c) 2013, ARM Limited. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * Neither the name of ARM nor the names of its contributors may be used
+ * to endorse or promote products derived from this software without specific
+ * prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+};
+
+/ {
+	model = "FVP Base";
+	compatible = "arm,vfp-base", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		cpu_suspend = <0x84000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xc4000003>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				entry-method-param = <0x0010000>;
+				entry-latency-us = <40>;
+				exit-latency-us = <100>;
+				min-residency-us = <150>;
+			};
+
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				entry-method-param = <0x1010000>;
+				entry-latency-us = <500>;
+				exit-latency-us = <1000>;
+				min-residency-us = <2500>;
+			};
+		};
+
+		big0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		big1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		big2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		big3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		little0: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		little1: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		little2: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+		little3: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&big0>;
+				};
+				core1 {
+					cpu = <&big1>;
+				};
+				core2 {
+					cpu = <&big2>;
+				};
+				core3 {
+					cpu = <&big3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&little0>;
+				};
+				core1 {
+					cpu = <&little1>;
+				};
+				core2 {
+					cpu = <&little2>;
+				};
+				core3 {
+					cpu = <&little3>;
+				};
+			};
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0 0x80000000>,
+		      <0x00000008 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2f000000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2f000000 0 0x10000>,
+		      <0x0 0x2c000000 0 0x2000>,
+		      <0x0 0x2c010000 0 0x2000>,
+		      <0x0 0x2c02F000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 13 0xff01>,
+			     <1 14 0xff01>,
+			     <1 11 0xff01>,
+			     <1 10 0xff01>;
+		clock-frequency = <100000000>;
+	};
+
+	timer@2a810000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0x0 0x2a810000 0x0 0x10000>;
+			clock-frequency = <100000000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			frame@2a820000 {
+				frame-number = <0>;
+				interrupts = <0 25 4>;
+				reg = <0x0 0x2a820000 0x0 0x10000>;
+			};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <0 60 4>,
+			     <0 61 4>,
+			     <0 62 4>,
+			     <0 63 4>;
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/juno.dts b/arch/arm64/boot/dts/juno.dts
new file mode 100644
index 000000000000..f260d702041c
--- /dev/null
+++ b/arch/arm64/boot/dts/juno.dts
@@ -0,0 +1,498 @@
+/*
+ * ARM Ltd. Juno Plaform
+ *
+ * Fast Models FVP v2 support
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "Juno";
+	compatible = "arm,juno", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &soc_uart0;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+		};
+
+		cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+		};
+
+		cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+		};
+
+		cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+		};
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0x0 0x7f000000>,
+		      <0x00000008 0x80000000 0x1 0x80000000>;
+	};
+
+	/* memory@14000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x14000000 0x0 0x02000000>;
+	}; */
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2c010000 0 0x1000>,
+		      <0x0 0x2c02f000 0 0x1000>,
+		      <0x0 0x2c04f000 0 0x2000>,
+		      <0x0 0x2c06f000 0 0x2000>;
+		interrupts = <GIC_PPI 9 0xf04>;
+	};
+
+	msi0: msi@2c1c0000 {
+		compatible = "arm,gic-msi";
+		reg = <0x0 0x2c1c0000 0 0x10000
+		       0x0 0x2c1d0000 0 0x10000
+		       0x0 0x2c1e0000 0 0x10000
+		       0x0 0x2c1f0000 0 0x10000>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 0xff01>,
+			     <GIC_PPI 14 0xff01>,
+			     <GIC_PPI 11 0xff01>,
+			     <GIC_PPI 10 0xff01>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 60 4>,
+			     <GIC_SPI 61 4>,
+			     <GIC_SPI 62 4>,
+			     <GIC_SPI 63 4>;
+	};
+
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		cpu_suspend = <0xC4000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xC4000003>;
+		migrate = <0xC4000005>;
+	};
+
+	pci0: pci@30000000 {
+		compatible = "arm,pcie-xr3";
+		device_type = "pci";
+		reg = <0 0x7ff30000 0 0x1000
+		       0 0x7ff20000 0 0x10000
+		       0 0x40000000 0 0x10000000>;
+		bus-range = <0 255>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges = <0x01000000 0x0 0x00000000 0x00 0x5ff00000 0x0 0x00100000
+		          0x02000000 0x0 0x00000000 0x40 0x00000000 0x0 0x80000000
+			  0x42000000 0x0 0x80000000 0x40 0x80000000 0x0 0x80000000>;
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &gic 0 136 4
+			         0 0 0 2 &gic 0 137 4
+				 0 0 0 3 &gic 0 138 4
+				 0 0 0 4 &gic 0 139 4>;
+	};
+
+	scpi: scpi@2b1f0000 {
+		compatible = "arm,scpi-mhu";
+		reg = <0x0 0x2b1f0000 0x0 0x10000>,   /* MHU registers */
+		      <0x0 0x2e000000 0x0 0x10000>;   /* Payload area */
+		interrupts = <0 36 4>,   /* low priority interrupt */
+			     <0 35 4>,   /* high priority interrupt */
+			     <0 37 4>;   /* secure channel interrupt */
+		#clock-cells = <1>;
+		clock-output-names = "a57", "a53", "gpu", "hdlcd0", "hdlcd1";
+	};
+
+	hdlcd0_osc: scpi_osc@3 {
+		compatible = "arm,scpi-osc";
+		#clock-cells = <0>;
+		clocks = <&scpi 3>;
+		frequency-range = <23000000 210000000>;
+		clock-output-names = "pxlclk0";
+	};
+
+	hdlcd1_osc: scpi_osc@4 {
+		compatible = "arm,scpi-osc";
+		#clock-cells = <0>;
+		clocks = <&scpi 4>;
+		frequency-range = <23000000 210000000>;
+		clock-output-names = "pxlclk1";
+	};
+
+	soc_uartclk: refclk72738khz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <7273800>;
+		clock-output-names = "juno:uartclk";
+	};
+
+	soc_refclk24mhz: clk24mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "juno:clk24mhz";
+	};
+
+	mb_eth25mhz: clk25mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+		clock-output-names = "ethclk25mhz";
+	};
+
+	soc_usb48mhz: clk48mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <48000000>;
+		clock-output-names = "clk48mhz";
+	};
+
+	soc_smc50mhz: clk50mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "smc_clk";
+	};
+
+	soc_refclk100mhz: refclk100mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "apb_pclk";
+	};
+
+	soc_faxiclk: refclk533mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <533000000>;
+		clock-output-names = "faxi_clk";
+	};
+
+	soc_fixed_3v3: fixedregulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	memory-controller@7ffd0000 {
+		compatible = "arm,pl354", "arm,primecell";
+		reg = <0 0x7ffd0000 0 0x1000>;
+		interrupts = <0 86 4>,
+			     <0 87 4>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		chip5-memwidth = <16>;
+	};
+
+	dma0: dma@0x7ff00000 {
+		compatible = "arm,pl330", "arm,primecell";
+		reg = <0x0 0x7ff00000 0 0x1000>;
+		interrupts = <0 95 4>,
+			     <0 88 4>,
+			     <0 89 4>,
+			     <0 90 4>,
+			     <0 91 4>,
+			     <0 108 4>,
+			     <0 109 4>,
+			     <0 110 4>,
+			     <0 111 4>;
+		#dma-cells = <1>;
+		#dma-channels = <8>;
+		#dma-requests = <32>;
+		clocks = <&soc_faxiclk>;
+		clock-names = "apb_pclk";
+	};
+
+	soc_uart0: uart@7ff80000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0x0 0x7ff80000 0x0 0x1000>;
+		interrupts = <0 83 4>;
+		clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+		clock-names = "uartclk", "apb_pclk";
+		dmas = <&dma0 1
+			&dma0 2>;
+		dma-names = "rx", "tx";
+	};
+
+	/* this UART is reserved for secure software.
+	soc_uart1: uart@7ff70000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0x0 0x7ff70000 0x0 0x1000>;
+		interrupts = <0 84 4>;
+		clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+		clock-names = "uartclk", "apb_pclk";
+	}; */
+
+	ulpi_phy: phy@0 {
+		compatible = "phy-ulpi-generic";
+		reg = <0x0 0x94 0x0 0x4>;
+		phy-id = <0>;
+	};
+
+	ehci@7ffc0000 {
+		compatible = "snps,ehci-h20ahb";
+		/* compatible = "arm,h20ahb-ehci"; */
+		reg = <0x0 0x7ffc0000 0x0 0x10000>;
+		interrupts = <0 117 4>;
+		clocks = <&soc_usb48mhz>;
+		clock-names = "otg";
+		phys = <&ulpi_phy>;
+	};
+
+	ohci@0x7ffb0000 {
+		compatible = "generic-ohci";
+		reg = <0x0 0x7ffb0000 0x0 0x10000>;
+		interrupts = <0 116 4>;
+		clocks = <&soc_usb48mhz>;
+		clock-names = "otg";
+	};
+
+	i2c@0x7ffa0000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "snps,designware-i2c";
+		reg = <0x0 0x7ffa0000 0x0 0x1000>;
+		interrupts = <0 104 4>;
+		clock-frequency = <400000>;
+		i2c-sda-hold-time-ns = <500>;
+		clocks = <&soc_smc50mhz>;
+
+		dvi0: dvi-transmitter@70 {
+			compatible = "nxp,tda998x";
+			reg = <0x70>;
+		};
+
+		dvi1: dvi-transmitter@71 {
+			compatible = "nxp,tda998x";
+			reg = <0x71>;
+		};
+	};
+
+	/* mmci@1c050000 {
+		compatible = "arm,pl180", "arm,primecell";
+		reg = <0x0 0x1c050000 0x0 0x1000>;
+		interrupts = <0 73 4>,
+			     <0 74 4>;
+		max-frequency = <12000000>;
+		vmmc-supply = <&soc_fixed_3v3>;
+		clocks = <&soc_refclk24mhz>, <&soc_refclk100mhz>;
+		clock-names = "mclk", "apb_pclk";
+	}; */
+
+	hdlcd@7ff60000 {
+		compatible = "arm,hdlcd";
+		reg = <0 0x7ff60000 0 0x1000>;
+		interrupts = <0 85 4>;
+		clocks = <&hdlcd0_osc>;
+		clock-names = "pxlclk";
+		i2c-slave = <&dvi0>;
+
+		/* display-timings {
+			native-mode = <&timing0>;
+			timing0: timing@0 {
+				/* 1024 x 768 framebufer, standard VGA timings * /
+				clock-frequency = <65000>;
+				hactive = <1024>;
+				vactive = <768>;
+				hfront-porch = <24>;
+				hback-porch = <160>;
+				hsync-len = <136>;
+				vfront-porch = <3>;
+				vback-porch = <29>;
+				vsync-len = <6>;
+			};
+		}; */
+	};
+
+	hdlcd@7ff50000 {
+		compatible = "arm,hdlcd";
+		reg = <0 0x7ff50000 0 0x1000>;
+		interrupts = <0 93 4>;
+		clocks = <&hdlcd1_osc>;
+		clock-names = "pxlclk";
+		i2c-slave = <&dvi1>;
+
+		display-timings {
+			native-mode = <&timing1>;
+			timing1: timing@1 {
+				/* 1024 x 768 framebufer, standard VGA timings */
+				clock-frequency = <65000>;
+				hactive = <1024>;
+				vactive = <768>;
+				hfront-porch = <24>;
+				hback-porch = <160>;
+				hsync-len = <136>;
+				vfront-porch = <3>;
+				vback-porch = <29>;
+				vsync-len = <6>;
+			};
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 15>;
+		interrupt-map = <0 0  0 &gic 0  68 4>,
+				<0 0  1 &gic 0  69 4>,
+				<0 0  2 &gic 0  70 4>,
+				<0 0  3 &gic 0 160 4>,
+				<0 0  4 &gic 0 161 4>,
+				<0 0  5 &gic 0 162 4>,
+				<0 0  6 &gic 0 163 4>,
+				<0 0  7 &gic 0 164 4>,
+				<0 0  8 &gic 0 165 4>,
+				<0 0  9 &gic 0 166 4>,
+				<0 0 10 &gic 0 167 4>,
+				<0 0 11 &gic 0 168 4>,
+				<0 0 12 &gic 0 169 4>;
+
+		motherboard {
+			model = "V2M-Juno";
+			arm,hbi = <0x252>;
+			arm,vexpress,site = <0>;
+			arm,v2m-memory-map = "rs1";
+			compatible = "arm,vexpress,v2p-p1", "simple-bus";
+			#address-cells = <2>;  /* SMB chipselect number and offset */
+			#size-cells = <1>;
+			#interrupt-cells = <1>;
+			ranges;
+
+			usb@5,00000000 {
+				compatible = "nxp,usb-isp1763";
+				reg = <5 0x00000000 0x20000>;
+				bus-width = <16>;
+				interrupts = <4>;
+			};
+
+			ethernet@2,00000000 {
+				compatible = "smsc,lan9118", "smsc,lan9115";
+				reg = <2 0x00000000 0x10000>;
+				interrupts = <3>;
+				phy-mode = "mii";
+				reg-io-width = <4>;
+				smsc,irq-active-high;
+				smsc,irq-push-pull;
+				clocks = <&mb_eth25mhz>;
+				vdd33a-supply = <&soc_fixed_3v3>; /* change this */
+				vddvario-supply = <&soc_fixed_3v3>; /* and this */
+			};
+
+			iofpga@3,00000000 {
+				compatible = "arm,amba-bus", "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 3 0 0x200000>;
+
+				kmi@060000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x060000 0x1000>;
+					interrupts = <8>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				kmi@070000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x070000 0x1000>;
+					interrupts = <8>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				wdt@0f0000 {
+					compatible = "arm,sp805", "arm,primecell";
+					reg = <0x0f0000 0x10000>;
+					interrupts = <7>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "wdogclk", "apb_pclk";
+				};
+
+				v2m_timer01: timer@110000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x110000 0x10000>;
+					interrupts = <9>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				v2m_timer23: timer@120000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x120000 0x10000>;
+					interrupts = <9>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				rtc@170000 {
+					compatible = "arm,pl031", "arm,primecell";
+					reg = <0x170000 0x10000>;
+					interrupts = <0>;
+					clocks = <&soc_smc50mhz>;
+					clock-names = "apb_pclk";
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
index 572005ea2217..28ed4ba3391a 100644
--- a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
+++ b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
@@ -27,37 +27,70 @@
 		serial3 = &v2m_serial3;
 	};
 
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		/*
+		 * Function IDs usage and compliancy with PSCI v0.2 still
+		 * under discussion.  Current IDs should be considered
+		 * temporary for demonstration purposes.
+		 */
+		cpu_suspend = <0x84000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0x84000003>;
+	};
+
 	cpus {
 		#address-cells = <2>;
 		#size-cells = <0>;
 
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				entry-method-param = <0x0010000>;
+				entry-latency-us = <40>;
+				exit-latency-us = <100>;
+				min-residency-us = <150>;
+			};
+
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				entry-method-param = <0x1010000>;
+				entry-latency-us = <500>;
+				exit-latency-us = <1000>;
+				min-residency-us = <2500>;
+			};
+		};
+
 		cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,armv8";
 			reg = <0x0 0x0>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 		cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,armv8";
 			reg = <0x0 0x1>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 		cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,armv8";
 			reg = <0x0 0x2>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 		cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,armv8";
 			reg = <0x0 0x3>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 	};
 
@@ -157,3 +190,5 @@
 		/include/ "rtsm_ve-motherboard.dtsi"
 	};
 };
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
index b45e5f39f577..b683d4703582 100644
--- a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
@@ -182,6 +182,15 @@
 				interrupts = <14>;
 				clocks = <&v2m_oscclk1>, <&v2m_clk24mhz>;
 				clock-names = "clcdclk", "apb_pclk";
+				mode = "XVGA";
+				use_dma = <0>;
+				framebuffer = <0x18000000 0x00180000>;
+			};
+
+			virtio_block@0130000 {
+				compatible = "virtio,mmio";
+				reg = <0x130000 0x200>;
+				interrupts = <42>;
 			};
 		};
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 6d48a72419b4..8e323147c375 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -102,3 +102,4 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO=y
 # CONFIG_FTRACE is not set
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_DMA_CMA=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 000000000000..5562652c5316
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,53 @@
+
+menuconfig ARM64_CRYPTO
+	bool "ARM64 Accelerated Cryptographic Algorithms"
+	depends on ARM64
+	help
+	  Say Y here to choose from a selection of cryptographic algorithms
+	  implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+	tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_SHA2_ARM64_CE
+	tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_GHASH_ARM64_CE
+	tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64_CE
+	tristate "AES core cipher using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+
+config CRYPTO_AES_ARM64_CE_CCM
+	tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+	select CRYPTO_AEAD
+
+config CRYPTO_AES_ARM64_CE_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+config CRYPTO_AES_ARM64_NEON_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000000..2070a56ecc46
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,38 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+AFLAGS_aes-ce.o		:= -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
+
+CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+	$(call if_changed_dep,cc_o_c)
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 000000000000..432e4841cd81
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,222 @@
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.arch	armv8-a+crypto
+
+	/*
+	 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+	 *			     u32 *macp, u8 const rk[], u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_auth_data)
+	ldr	w8, [x3]			/* leftover from prev round? */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cbz	w8, 1f
+	sub	w8, w8, #16
+	eor	v1.16b, v1.16b, v1.16b
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
+	ins	v1.b[0], w7
+	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
+	beq	8f				/* out of input? */
+	cbnz	w8, 0b
+	eor	v0.16b, v0.16b, v1.16b
+1:	ld1	{v3.2d}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
+	bmi	2f
+	bne	5f
+	mov	v5.16b, v3.16b
+	b	4f
+2:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+3:	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	bpl	3b
+	aese	v0.16b, v4.16b
+	subs	w2, w2, #16			/* last data? */
+	eor	v0.16b, v0.16b, v5.16b		/* final round */
+	bmi	6f
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
+	bne	1b
+6:	st1	{v0.2d}, [x0]			/* store mac */
+	beq	10f
+	adds	w2, w2, #16
+	beq	10f
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
+	umov	w6, v0.b[0]
+	eor	w6, w6, w7
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
+	beq	10f
+	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
+	b	7b
+8:	mov	w7, w8
+	add	w8, w8, #16
+9:	ext	v1.16b, v1.16b, v1.16b, #1
+	adds	w7, w7, #1
+	bne	9b
+	eor	v0.16b, v0.16b, v1.16b
+	st1	{v0.2d}, [x0]
+10:	str	w8, [x3]
+	ret
+ENDPROC(ce_aes_ccm_auth_data)
+
+	/*
+	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+	 * 			 u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_final)
+	ld1	{v3.2d}, [x2], #16		/* load first round key */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cmp	w3, #12				/* which key size? */
+	sub	w3, w3, #2			/* modified # of rounds */
+	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	bmi	0f
+	bne	3f
+	mov	v5.16b, v3.16b
+	b	2f
+0:	mov	v4.16b, v3.16b
+1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+	subs	w3, w3, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	bpl	1b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	/* final round key cancels out */
+	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
+	st1	{v0.2d}, [x0]			/* store result */
+	ret
+ENDPROC(ce_aes_ccm_final)
+
+	.macro	aes_ccm_do_crypt,enc
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.2d}, [x5]			/* load mac */
+	rev	x8, x8				/* keep swabbed ctr in reg */
+0:	/* outer loop */
+	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
+	ins	v1.d[1], x9			/* no carry in lower ctr */
+	ld1	{v3.2d}, [x3]			/* load first round key */
+	add	x10, x3, #16
+	bmi	1f
+	bne	4f
+	mov	v5.16b, v3.16b
+	b	3f
+1:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+2:	/* inner loop: 3 rounds, 2x interleaved */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	bpl	2b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
+	.if	\enc == 1
+	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
+	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
+	.else
+	eor	v2.16b, v2.16b, v1.16b		/* xor with crypted ctr */
+	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
+	.endif
+	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+	rev	x8, x8
+	st1	{v0.2d}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+	st1	{v0.2d}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
+	umov	w6, v1.b[0]			/* get top crypted ctr byte */
+	umov	w7, v0.b[0]			/* get top mac byte */
+	.if	\enc == 1
+	eor	w7, w7, w9
+	eor	w9, w9, w6
+	.else
+	eor	w9, w9, w6
+	eor	w7, w7, w9
+	.endif
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
+	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
+	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
+	b	7b
+	.endm
+
+	/*
+	 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 */
+ENTRY(ce_aes_ccm_encrypt)
+	aes_ccm_do_crypt	1
+ENDPROC(ce_aes_ccm_encrypt)
+
+ENTRY(ce_aes_ccm_decrypt)
+	aes_ccm_do_crypt	0
+ENDPROC(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 000000000000..9e6cdde9b43d
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,297 @@
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+				     u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+				 u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+		      unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	if ((authsize & 1) || authsize < 4)
+		return -EINVAL;
+	return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	__be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+	u32 l = req->iv[0] + 1;
+
+	/* verify that CCM dimension 'L' is set correctly in the IV */
+	if (l < 2 || l > 8)
+		return -EINVAL;
+
+	/* verify that msglen can in fact be represented in L bytes */
+	if (l < 4 && msglen >> (8 * l))
+		return -EOVERFLOW;
+
+	/*
+	 * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+	 * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+	 */
+	n[0] = 0;
+	n[1] = cpu_to_be32(msglen);
+
+	memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+	/*
+	 * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+	 * - bits 0..2	: max # of bytes required to represent msglen, minus 1
+	 *                (already set by caller)
+	 * - bits 3..5	: size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+	 * - bit 6	: indicates presence of authenticate-only data
+	 */
+	maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+	if (req->assoclen)
+		maciv[0] |= 0x40;
+
+	memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+	return 0;
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+	struct scatter_walk walk;
+	u32 len = req->assoclen;
+	u32 macp = 0;
+
+	/* prepend the AAD with a length tag */
+	if (len < 0xff00) {
+		ltag.l = cpu_to_be16(len);
+		ltag.len = 2;
+	} else  {
+		ltag.l = cpu_to_be16(0xfffe);
+		put_unaligned_be32(len, &ltag.h);
+		ltag.len = 6;
+	}
+
+	ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
+			     num_rounds(ctx));
+	scatterwalk_start(&walk, req->assoc);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+		p = scatterwalk_map(&walk);
+		ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
+				     num_rounds(ctx));
+		len -= n;
+
+		scatterwalk_unmap(p);
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen - authsize;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* compare calculated auth tag with the stored one */
+	scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+				 authsize, 0);
+
+	if (memcmp(mac, buf, authsize))
+		return -EBADMSG;
+	return 0;
+}
+
+static struct crypto_alg ccm_aes_alg = {
+	.cra_name		= "ccm(aes)",
+	.cra_driver_name	= "ccm-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_aead_type,
+	.cra_module		= THIS_MODULE,
+	.cra_aead = {
+		.ivsize		= AES_BLOCK_SIZE,
+		.maxauthsize	= AES_BLOCK_SIZE,
+		.setkey		= ccm_setkey,
+		.setauthsize	= ccm_setauthsize,
+		.encrypt	= ccm_encrypt,
+		.decrypt	= ccm_decrypt,
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_AES))
+		return -ENODEV;
+	return crypto_register_alg(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 000000000000..2075e1acae6b
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,155 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aese	v0.16b, v2.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aese	v0.16b, v3.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aese	v0.16b, v1.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aese	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_enc),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aesd	v0.16b, v2.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aesd	v0.16b, v3.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aesd	v0.16b, v1.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aesd	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_dec),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_cipher = {
+		.cia_min_keysize	= AES_MIN_KEY_SIZE,
+		.cia_max_keysize	= AES_MAX_KEY_SIZE,
+		.cia_setkey		= crypto_aes_set_key,
+		.cia_encrypt		= aes_cipher_encrypt,
+		.cia_decrypt		= aes_cipher_decrypt
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 000000000000..685a18f731eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,133 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ *                                    Crypto Extensions
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(ce_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
+
+	.arch		armv8-a+crypto
+
+	/* preload all round keys */
+	.macro		load_round_keys, rounds, rk
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	ld1		{v17.16b-v18.16b}, [\rk], #32
+1111:	ld1		{v19.16b-v20.16b}, [\rk], #32
+2222:	ld1		{v21.16b-v24.16b}, [\rk], #64
+	ld1		{v25.16b-v28.16b}, [\rk], #64
+	ld1		{v29.16b-v31.16b}, [\rk]
+	.endm
+
+	/* prepare for encryption with key in rk[] */
+	.macro		enc_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for encryption (again) but with new key in rk[] */
+	.macro		enc_switch_key, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for decryption with key in rk[] */
+	.macro		dec_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	aes\mc		\i0\().16b, \i0\().16b
+	.ifnb		\i1
+	aes\mc		\i1\().16b, \i1\().16b
+	.ifnb		\i3
+	aes\mc		\i2\().16b, \i2\().16b
+	aes\mc		\i3\().16b, \i3\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved encryption rounds with the same round key */
+	.macro		round_Nx, enc, k, i0, i1, i2, i3
+	.ifc		\enc, e
+	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3
+	.else
+	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3
+	.endif
+	.endm
+
+	/* up to 4 interleaved final rounds */
+	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	eor		\i0\().16b, \i0\().16b, \k2\().16b
+	.ifnb		\i1
+	eor		\i1\().16b, \i1\().16b, \k2\().16b
+	.ifnb		\i3
+	eor		\i2\().16b, \i2\().16b, \k2\().16b
+	eor		\i3\().16b, \i3\().16b, \k2\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved blocks */
+	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	round_Nx	\enc, v17, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v18, \i0, \i1, \i2, \i3
+1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v20, \i0, \i1, \i2, \i3
+2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+	round_Nx	\enc, \key, \i0, \i1, \i2, \i3
+	.endr
+	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		encrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \in
+	.endm
+
+	.macro		encrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1
+	.endm
+
+	.macro		encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		decrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \in
+	.endm
+
+	.macro		decrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1
+	.endm
+
+	.macro		decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 000000000000..60f2f4c12256
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,446 @@
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE			"ce"
+#define PRIO			300
+#define aes_ecb_encrypt		ce_aes_ecb_encrypt
+#define aes_ecb_decrypt		ce_aes_ecb_decrypt
+#define aes_cbc_encrypt		ce_aes_cbc_encrypt
+#define aes_cbc_decrypt		ce_aes_cbc_decrypt
+#define aes_ctr_encrypt		ce_aes_ctr_encrypt
+#define aes_xts_encrypt		ce_aes_xts_encrypt
+#define aes_xts_decrypt		ce_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE			"neon"
+#define PRIO			200
+#define aes_ecb_encrypt		neon_aes_ecb_encrypt
+#define aes_ecb_decrypt		neon_aes_ecb_decrypt
+#define aes_cbc_encrypt		neon_aes_cbc_encrypt
+#define aes_cbc_decrypt		neon_aes_cbc_decrypt
+#define aes_ctr_encrypt		neon_aes_ctr_encrypt
+#define aes_xts_encrypt		neon_aes_xts_encrypt
+#define aes_xts_decrypt		neon_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+MODULE_ALIAS("ecb(aes)");
+MODULE_ALIAS("cbc(aes)");
+MODULE_ALIAS("ctr(aes)");
+MODULE_ALIAS("xts(aes)");
+#endif
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 ctr[], int first);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+
+struct crypto_aes_xts_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2);
+	if (!ret)
+		ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2],
+					    key_len / 2);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+	first = 1;
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		first = 0;
+		nbytes -= blocks * AES_BLOCK_SIZE;
+		if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+			break;
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	if (nbytes) {
+		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+		/*
+		 * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+		 * to tell aes_ctr_encrypt() to only read half a block.
+		 */
+		blocks = (nbytes <= 8) ? -1 : 1;
+
+		aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+				blocks, walk.iv, first);
+		memcpy(tdst, tail, nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_enc, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_dec, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+	.cra_name		= "__ecb-aes-" MODE,
+	.cra_driver_name	= "__driver-ecb-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ecb_encrypt,
+		.decrypt	= ecb_decrypt,
+	},
+}, {
+	.cra_name		= "__cbc-aes-" MODE,
+	.cra_driver_name	= "__driver-cbc-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= cbc_encrypt,
+		.decrypt	= cbc_decrypt,
+	},
+}, {
+	.cra_name		= "__ctr-aes-" MODE,
+	.cra_driver_name	= "__driver-ctr-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ctr_encrypt,
+		.decrypt	= ctr_encrypt,
+	},
+}, {
+	.cra_name		= "__xts-aes-" MODE,
+	.cra_driver_name	= "__driver-xts-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= xts_set_key,
+		.encrypt	= xts_encrypt,
+		.decrypt	= xts_decrypt,
+	},
+}, {
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "ecb-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "cbc-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "ctr-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "xts(aes)",
+	.cra_driver_name	= "xts-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+} };
+
+static int __init aes_init(void)
+{
+	return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+	crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 000000000000..f6e372c528eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,532 @@
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+	.text
+	.align		4
+
+/*
+ * There are several ways to instantiate this code:
+ * - no interleave, all inline
+ * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
+ * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
+ * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
+ * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
+ *
+ * Macros imported by this code:
+ * - enc_prepare	- setup NEON registers for encryption
+ * - dec_prepare	- setup NEON registers for decryption
+ * - enc_switch_key	- change to new key after having prepared for encryption
+ * - encrypt_block	- encrypt a single block
+ * - decrypt block	- decrypt a single block
+ * - encrypt_block2x	- encrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - decrypt_block2x	- decrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - encrypt_block4x	- encrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ * - decrypt_block4x	- decrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ */
+
+#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
+#define FRAME_PUSH	stp x29, x30, [sp,#-16]! ; mov x29, sp
+#define FRAME_POP	ldp x29, x30, [sp],#16
+
+#if INTERLEAVE == 2
+
+aes_encrypt_block2x:
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block2x)
+
+aes_decrypt_block2x:
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block2x)
+
+#elif INTERLEAVE == 4
+
+aes_encrypt_block4x:
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block4x)
+
+aes_decrypt_block4x:
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block4x)
+
+#else
+#error INTERLEAVE should equal 2 or 4
+#endif
+
+	.macro		do_encrypt_block2x
+	bl		aes_encrypt_block2x
+	.endm
+
+	.macro		do_decrypt_block2x
+	bl		aes_decrypt_block2x
+	.endm
+
+	.macro		do_encrypt_block4x
+	bl		aes_encrypt_block4x
+	.endm
+
+	.macro		do_decrypt_block4x
+	bl		aes_decrypt_block4x
+	.endm
+
+#else
+#define FRAME_PUSH
+#define FRAME_POP
+
+	.macro		do_encrypt_block2x
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block2x
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_encrypt_block4x
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block4x
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+#endif
+
+	/*
+	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 */
+
+AES_ENTRY(aes_ecb_encrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbencloopNx
+
+	enc_prepare	w3, x2, x5
+
+.LecbencloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	do_encrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	do_encrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbencloopNx
+.Lecbenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbencout
+#endif
+.Lecbencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbencloop
+.Lecbencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_encrypt)
+
+
+AES_ENTRY(aes_ecb_decrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbdecloopNx
+
+	dec_prepare	w3, x2, x5
+
+.LecbdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	do_decrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	do_decrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbdecloopNx
+.Lecbdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbdecout
+#endif
+.Lecbdecloop:
+	ld1		{v0.16b}, [x1], #16		/* get next ct block */
+	decrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbdecloop
+.Lecbdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_decrypt)
+
+
+	/*
+	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 */
+
+AES_ENTRY(aes_cbc_encrypt)
+	cbz		w6, .Lcbcencloop
+
+	ld1		{v0.16b}, [x5]			/* get iv */
+	enc_prepare	w3, x2, x5
+
+.Lcbcencloop:
+	ld1		{v1.16b}, [x1], #16		/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcencloop
+	ret
+AES_ENDPROC(aes_cbc_encrypt)
+
+
+AES_ENTRY(aes_cbc_decrypt)
+	FRAME_PUSH
+	cbz		w6, .LcbcdecloopNx
+
+	ld1		{v7.16b}, [x5]			/* get iv */
+	dec_prepare	w3, x2, x5
+
+.LcbcdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lcbcdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	mov		v2.16b, v0.16b
+	mov		v3.16b, v1.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v2.16b
+	mov		v7.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	mov		v4.16b, v0.16b
+	mov		v5.16b, v1.16b
+	mov		v6.16b, v2.16b
+	do_decrypt_block4x
+	sub		x1, x1, #16
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v4.16b
+	ld1		{v7.16b}, [x1], #16		/* reload 1 ct block */
+	eor		v2.16b, v2.16b, v5.16b
+	eor		v3.16b, v3.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LcbcdecloopNx
+.Lcbcdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lcbcdecout
+#endif
+.Lcbcdecloop:
+	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	mov		v0.16b, v1.16b			/* ...and copy to v0 */
+	decrypt_block	v0, w3, x2, x5, w6
+	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
+	mov		v7.16b, v1.16b			/* ct is next iv */
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcdecloop
+.Lcbcdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_cbc_decrypt)
+
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 ctr[], int first)
+	 */
+
+AES_ENTRY(aes_ctr_encrypt)
+	FRAME_PUSH
+	cbnz		w6, .Lctrfirst		/* 1st time around? */
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrinc
+	add		x5, x5, #1		/* increment BE ctr */
+	b		.LctrincNx
+#else
+	b		.Lctrinc
+#endif
+.Lctrfirst:
+	enc_prepare	w3, x2, x6
+	ld1		{v4.16b}, [x5]
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrloop
+.LctrloopNx:
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lctr1x
+#if INTERLEAVE == 2
+	mov		v0.8b, v4.8b
+	mov		v1.8b, v4.8b
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v0.d[1], x7
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v1.d[1], x7
+	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v2.16b
+	eor		v1.16b, v1.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
+	dup		v7.4s, w5
+	mov		v0.16b, v4.16b
+	add		v7.4s, v7.4s, v8.4s
+	mov		v1.16b, v4.16b
+	rev32		v8.16b, v7.16b
+	mov		v2.16b, v4.16b
+	mov		v3.16b, v4.16b
+	mov		v1.s[3], v8.s[0]
+	mov		v2.s[3], v8.s[1]
+	mov		v3.s[3], v8.s[2]
+	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	do_encrypt_block4x
+	eor		v0.16b, v5.16b, v0.16b
+	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
+	eor		v1.16b, v6.16b, v1.16b
+	eor		v2.16b, v7.16b, v2.16b
+	eor		v3.16b, v5.16b, v3.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	add		x5, x5, #INTERLEAVE
+#endif
+	cbz		w4, .LctroutNx
+.LctrincNx:
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.LctrloopNx
+.LctroutNx:
+	sub		x5, x5, #1
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.Lctrout
+.Lctr1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lctrout
+#endif
+.Lctrloop:
+	mov		v0.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	subs		w4, w4, #1
+	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
+	ld1		{v3.16b}, [x1], #16
+	eor		v3.16b, v0.16b, v3.16b
+	st1		{v3.16b}, [x0], #16
+	beq		.Lctrout
+.Lctrinc:
+	adds		x5, x5, #1		/* increment BE ctr */
+	rev		x7, x5
+	ins		v4.d[1], x7
+	bcc		.Lctrloop		/* no overflow? */
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrloop
+.Lctrhalfblock:
+	ld1		{v3.8b}, [x1]
+	eor		v3.8b, v0.8b, v3.8b
+	st1		{v3.8b}, [x0]
+.Lctrout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ctr_encrypt)
+	.ltorg
+
+
+	/*
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 */
+
+	.macro		next_tweak, out, in, const, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, \const\().16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+.Lxts_mul_x:
+	.word		1, 0, 0x87, 0
+
+AES_ENTRY(aes_xts_encrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsencloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	enc_switch_key	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsencNx
+
+.LxtsencloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsencNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsencoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsencNx
+.LxtsencoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsencout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_encrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsencout
+	b		.LxtsencloopNx
+#endif
+.Lxtsenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsencout
+#endif
+.Lxtsencloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsencout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsencloop
+.Lxtsencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_encrypt)
+
+
+AES_ENTRY(aes_xts_decrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsdecloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	dec_prepare	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsdecNx
+
+.LxtsdecloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsdecNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsdecoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsdecNx
+.LxtsdecoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsdecout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_decrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsdecout
+	b		.LxtsdecloopNx
+#endif
+.Lxtsdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsdecout
+#endif
+.Lxtsdecloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	decrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsdecout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsdecloop
+.Lxtsdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 000000000000..b93170e1cc93
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(neon_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
+
+	/* multiply by polynomial 'x' in GF(2^8) */
+	.macro		mul_by_x, out, in, temp, const
+	sshr		\temp, \in, #7
+	add		\out, \in, \in
+	and		\temp, \temp, \const
+	eor		\out, \out, \temp
+	.endm
+
+	/* preload the entire Sbox */
+	.macro		prepare, sbox, shiftrows, temp
+	adr		\temp, \sbox
+	movi		v12.16b, #0x40
+	ldr		q13, \shiftrows
+	movi		v14.16b, #0x1b
+	ld1		{v16.16b-v19.16b}, [\temp], #64
+	ld1		{v20.16b-v23.16b}, [\temp], #64
+	ld1		{v24.16b-v27.16b}, [\temp], #64
+	ld1		{v28.16b-v31.16b}, [\temp]
+	.endm
+
+	/* do preload for encryption */
+	.macro		enc_prepare, ignore0, ignore1, temp
+	prepare		.LForward_Sbox, .LForward_ShiftRows, \temp
+	.endm
+
+	.macro		enc_switch_key, ignore0, ignore1, temp
+	/* do nothing */
+	.endm
+
+	/* do preload for decryption */
+	.macro		dec_prepare, ignore0, ignore1, temp
+	prepare		.LReverse_Sbox, .LReverse_ShiftRows, \temp
+	.endm
+
+	/* apply SubBytes transformation using the the preloaded Sbox */
+	.macro		sub_bytes, in
+	sub		v9.16b, \in\().16b, v12.16b
+	tbl		\in\().16b, {v16.16b-v19.16b}, \in\().16b
+	sub		v10.16b, v9.16b, v12.16b
+	tbx		\in\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v11.16b, v10.16b, v12.16b
+	tbx		\in\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	/* apply MixColumns transformation */
+	.macro		mix_columns, in
+	mul_by_x	v10.16b, \in\().16b, v9.16b, v14.16b
+	rev32		v8.8h, \in\().8h
+	eor		\in\().16b, v10.16b, \in\().16b
+	shl		v9.4s, v8.4s, #24
+	shl		v11.4s, \in\().4s, #24
+	sri		v9.4s, v8.4s, #8
+	sri		v11.4s, \in\().4s, #8
+	eor		v9.16b, v9.16b, v8.16b
+	eor		v10.16b, v10.16b, v9.16b
+	eor		\in\().16b, v10.16b, v11.16b
+	.endm
+
+	/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+	.macro		inv_mix_columns, in
+	mul_by_x	v11.16b, \in\().16b, v10.16b, v14.16b
+	mul_by_x	v11.16b, v11.16b, v10.16b, v14.16b
+	eor		\in\().16b, \in\().16b, v11.16b
+	rev32		v11.8h, v11.8h
+	eor		\in\().16b, \in\().16b, v11.16b
+	mix_columns	\in
+	.endm
+
+	.macro		do_block, enc, in, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
+	sub_bytes	\in
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns	\in
+	.else
+	inv_mix_columns	\in
+	.endif
+	b		1111b
+2222:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	.endm
+
+	.macro		encrypt_block, in, rounds, rk, rkp, i
+	do_block	1, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block, in, rounds, rk, rkp, i
+	do_block	0, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	/*
+	 * Interleaved versions: functionally equivalent to the
+	 * ones above, but applied to 2 or 4 AES states in parallel.
+	 */
+
+	.macro		sub_bytes_2x, in0, in1
+	sub		v8.16b, \in0\().16b, v12.16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, v8.16b, v12.16b
+	sub		v11.16b, v9.16b, v12.16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v10.16b, v12.16b
+	sub		v9.16b, v11.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v11.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	.endm
+
+	.macro		sub_bytes_4x, in0, in1, in2, in3
+	sub		v8.16b, \in0\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, \in2\().16b, v12.16b
+	tbl		\in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+	sub		v11.16b, \in3\().16b, v12.16b
+	tbl		\in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v20.16b-v23.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v20.16b-v23.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v24.16b-v27.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v24.16b-v27.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	tbx		\in2\().16b, {v28.16b-v31.16b}, v10.16b
+	tbx		\in3\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	.macro		mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+	sshr		\tmp0\().16b, \in0\().16b,  #7
+	add		\out0\().16b, \in0\().16b,  \in0\().16b
+	sshr		\tmp1\().16b, \in1\().16b,  #7
+	and		\tmp0\().16b, \tmp0\().16b, \const\().16b
+	add		\out1\().16b, \in1\().16b,  \in1\().16b
+	and		\tmp1\().16b, \tmp1\().16b, \const\().16b
+	eor		\out0\().16b, \out0\().16b, \tmp0\().16b
+	eor		\out1\().16b, \out1\().16b, \tmp1\().16b
+	.endm
+
+	.macro		mix_columns_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	rev32		v10.8h, \in0\().8h
+	rev32		v11.8h, \in1\().8h
+	eor		\in0\().16b, v8.16b, \in0\().16b
+	eor		\in1\().16b, v9.16b, \in1\().16b
+	shl		v12.4s, v10.4s, #24
+	shl		v13.4s, v11.4s, #24
+	eor		v8.16b, v8.16b, v10.16b
+	sri		v12.4s, v10.4s, #8
+	shl		v10.4s, \in0\().4s, #24
+	eor		v9.16b, v9.16b, v11.16b
+	sri		v13.4s, v11.4s, #8
+	shl		v11.4s, \in1\().4s, #24
+	sri		v10.4s, \in0\().4s, #8
+	eor		\in0\().16b, v8.16b, v12.16b
+	sri		v11.4s, \in1\().4s, #8
+	eor		\in1\().16b, v9.16b, v13.16b
+	eor		\in0\().16b, v10.16b, \in0\().16b
+	eor		\in1\().16b, v11.16b, \in1\().16b
+	.endm
+
+	.macro		inv_mix_cols_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v8, v9, v8, v9, v10, v11, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	mix_columns_2x	\in0, \in1
+	.endm
+
+	.macro		inv_mix_cols_4x, in0, in1, in2, in3
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v10, v11, \in2, \in3, v12, v13, v14
+	mul_by_x_2x	v8, v9, v8, v9, v12, v13, v14
+	mul_by_x_2x	v10, v11, v10, v11, v12, v13, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	rev32		v10.8h, v10.8h
+	rev32		v11.8h, v11.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	.endm
+
+	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	sub_bytes_2x	\in0, \in1
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_2x	\in0, \in1
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	sub_bytes_4x	\in0, \in1, \in2, \in3
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_4x	\in0, \in1, \in2, \in3
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		encrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	1, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	0, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+#include "aes-modes.S"
+
+	.text
+	.align		4
+.LForward_ShiftRows:
+	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
+	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+
+.LReverse_ShiftRows:
+	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
+	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+
+.LForward_Sbox:
+	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+	.byte		0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+	.byte		0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+	.byte		0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+	.byte		0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+	.byte		0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+	.byte		0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+	.byte		0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+	.byte		0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+	.byte		0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+	.byte		0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+	.byte		0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+	.byte		0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+	.byte		0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+	.byte		0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+	.byte		0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+	.byte		0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+	.byte		0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+	.byte		0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+	.byte		0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+	.byte		0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+	.byte		0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+	.byte		0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+	.byte		0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+	.byte		0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+	.byte		0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+	.byte		0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+	.byte		0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+	.byte		0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+	.byte		0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+	.byte		0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+	.byte		0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.LReverse_Sbox:
+	.byte		0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+	.byte		0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+	.byte		0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+	.byte		0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+	.byte		0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+	.byte		0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+	.byte		0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+	.byte		0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+	.byte		0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+	.byte		0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+	.byte		0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+	.byte		0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+	.byte		0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+	.byte		0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+	.byte		0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+	.byte		0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+	.byte		0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+	.byte		0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+	.byte		0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+	.byte		0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+	.byte		0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+	.byte		0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+	.byte		0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+	.byte		0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+	.byte		0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+	.byte		0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+	.byte		0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+	.byte		0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+	.byte		0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+	.byte		0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 000000000000..b9e6eaf41c9b
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,95 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
+ *
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *           Vinodh Gopal
+ *           Erdinc Ozturk
+ *           Deniz Karakoyunlu
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	DATA	.req	v0
+	SHASH	.req	v1
+	IN1	.req	v2
+	T1	.req	v2
+	T2	.req	v3
+	T3	.req	v4
+	VZR	.req	v5
+
+	.text
+	.arch		armv8-a+crypto
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+ENTRY(pmull_ghash_update)
+	ld1		{DATA.16b}, [x1]
+	ld1		{SHASH.16b}, [x3]
+	eor		VZR.16b, VZR.16b, VZR.16b
+
+	/* do the head block first, if supplied */
+	cbz		x4, 0f
+	ld1		{IN1.2d}, [x4]
+	b		1f
+
+0:	ld1		{IN1.2d}, [x2], #16
+	sub		w0, w0, #1
+1:	ext		IN1.16b, IN1.16b, IN1.16b, #8
+CPU_LE(	rev64		IN1.16b, IN1.16b	)
+	eor		DATA.16b, DATA.16b, IN1.16b
+
+	/* multiply DATA by SHASH in GF(2^128) */
+	ext		T2.16b, DATA.16b, DATA.16b, #8
+	ext		T3.16b, SHASH.16b, SHASH.16b, #8
+	eor		T2.16b, T2.16b, DATA.16b
+	eor		T3.16b, T3.16b, SHASH.16b
+
+	pmull2		T1.1q, SHASH.2d, DATA.2d	// a1 * b1
+	pmull		DATA.1q, SHASH.1d, DATA.1d	// a0 * b0
+	pmull		T2.1q, T2.1d, T3.1d		// (a1 + a0)(b1 + b0)
+	eor		T2.16b, T2.16b, T1.16b		// (a0 * b1) + (a1 * b0)
+	eor		T2.16b, T2.16b, DATA.16b
+
+	ext		T3.16b, VZR.16b, T2.16b, #8
+	ext		T2.16b, T2.16b, VZR.16b, #8
+	eor		DATA.16b, DATA.16b, T3.16b
+	eor		T1.16b, T1.16b, T2.16b	// <T1:DATA> is result of
+						// carry-less multiplication
+
+	/* first phase of the reduction */
+	shl		T3.2d, DATA.2d, #1
+	eor		T3.16b, T3.16b, DATA.16b
+	shl		T3.2d, T3.2d, #5
+	eor		T3.16b, T3.16b, DATA.16b
+	shl		T3.2d, T3.2d, #57
+	ext		T2.16b, VZR.16b, T3.16b, #8
+	ext		T3.16b, T3.16b, VZR.16b, #8
+	eor		DATA.16b, DATA.16b, T2.16b
+	eor		T1.16b, T1.16b, T3.16b
+
+	/* second phase of the reduction */
+	ushr		T2.2d, DATA.2d, #5
+	eor		T2.16b, T2.16b, DATA.16b
+	ushr		T2.2d, T2.2d, #1
+	eor		T2.16b, T2.16b, DATA.16b
+	ushr		T2.2d, T2.2d, #1
+	eor		T1.16b, T1.16b, T2.16b
+	eor		DATA.16b, DATA.16b, T1.16b
+
+	cbnz		w0, 0b
+
+	st1		{DATA.16b}, [x1]
+	ret
+ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 000000000000..b92baf3f68c7
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,155 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+struct ghash_key {
+	u64 a;
+	u64 b;
+};
+
+struct ghash_desc_ctx {
+	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+	u8 buf[GHASH_BLOCK_SIZE];
+	u32 count;
+};
+
+asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+				   struct ghash_key const *k, const char *head);
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	ctx->count += len;
+
+	if ((partial + len) >= GHASH_BLOCK_SIZE) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+		int blocks;
+
+		if (partial) {
+			int p = GHASH_BLOCK_SIZE - partial;
+
+			memcpy(ctx->buf + partial, src, p);
+			src += p;
+			len -= p;
+		}
+
+		blocks = len / GHASH_BLOCK_SIZE;
+		len %= GHASH_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(6);
+		pmull_ghash_update(blocks, ctx->digest, src, key,
+				   partial ? ctx->buf : NULL);
+		kernel_neon_end();
+		src += blocks * GHASH_BLOCK_SIZE;
+	}
+	if (len)
+		memcpy(ctx->buf + partial, src, len);
+	return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	if (partial) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+		kernel_neon_begin_partial(6);
+		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
+		kernel_neon_end();
+	}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *inkey, unsigned int keylen)
+{
+	struct ghash_key *key = crypto_shash_ctx(tfm);
+	u64 a, b;
+
+	if (keylen != GHASH_BLOCK_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* perform multiplication by 'x' in GF(2^128) */
+	b = get_unaligned_be64(inkey);
+	a = get_unaligned_be64(inkey + 8);
+
+	key->a = (a << 1) | (b >> 63);
+	key->b = (b << 1) | (a >> 63);
+
+	if (b >> 63)
+		key->b ^= 0xc200000000000000UL;
+
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.digestsize	= GHASH_DIGEST_SIZE,
+	.init		= ghash_init,
+	.update		= ghash_update,
+	.final		= ghash_final,
+	.setkey		= ghash_setkey,
+	.descsize	= sizeof(struct ghash_desc_ctx),
+	.base		= {
+		.cra_name		= "ghash",
+		.cra_driver_name	= "ghash-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= GHASH_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct ghash_key),
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+	return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+	crypto_unregister_shash(&ghash_alg);
+}
+
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 000000000000..09d57d98609c
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	k0		.req	v0
+	k1		.req	v1
+	k2		.req	v2
+	k3		.req	v3
+
+	t0		.req	v4
+	t1		.req	v5
+
+	dga		.req	q6
+	dgav		.req	v6
+	dgb		.req	s7
+	dgbv		.req	v7
+
+	dg0q		.req	q12
+	dg0s		.req	s12
+	dg0v		.req	v12
+	dg1s		.req	s13
+	dg1v		.req	v13
+	dg2s		.req	s14
+
+	.macro		add_only, op, ev, rc, s0, dg1
+	.ifc		\ev, ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha1h		dg2s, dg0s
+	.ifnb		\dg1
+	sha1\op		dg0q, \dg1, t0.4s
+	.else
+	sha1\op		dg0q, dg1s, t0.4s
+	.endif
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha1h		dg1s, dg0s
+	sha1\op		dg0q, dg2s, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, op, ev, rc, s0, s1, s2, s3, dg1
+	sha1su0		v\s0\().4s, v\s1\().4s, v\s2\().4s
+	add_only	\op, \ev, \rc, \s1, \dg1
+	sha1su1		v\s0\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA1 round constants
+	 */
+	.align		4
+.Lsha1_rcon:
+	.word		0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+	/*
+	 * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+	 * 			  u8 *head, long bytes)
+	 */
+ENTRY(sha1_ce_transform)
+	/* load round constants */
+	adr		x6, .Lsha1_rcon
+	ld1r		{k0.4s}, [x6], #4
+	ld1r		{k1.4s}, [x6], #4
+	ld1r		{k2.4s}, [x6], #4
+	ld1r		{k3.4s}, [x6]
+
+	/* load state */
+	ldr		dga, [x2]
+	ldr		dgb, [x2, #16]
+
+	/* load partial state (if supplied) */
+	cbz		x3, 0f
+	ld1		{v8.4s-v11.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v8.4s-v11.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v8.16b, v8.16b		)
+CPU_LE(	rev32		v9.16b, v9.16b		)
+CPU_LE(	rev32		v10.16b, v10.16b	)
+CPU_LE(	rev32		v11.16b, v11.16b	)
+
+2:	add		t0.4s, v8.4s, k0.4s
+	mov		dg0v.16b, dgav.16b
+
+	add_update	c, ev, k0,  8,  9, 10, 11, dgb
+	add_update	c, od, k0,  9, 10, 11,  8
+	add_update	c, ev, k0, 10, 11,  8,  9
+	add_update	c, od, k0, 11,  8,  9, 10
+	add_update	c, ev, k1,  8,  9, 10, 11
+
+	add_update	p, od, k1,  9, 10, 11,  8
+	add_update	p, ev, k1, 10, 11,  8,  9
+	add_update	p, od, k1, 11,  8,  9, 10
+	add_update	p, ev, k1,  8,  9, 10, 11
+	add_update	p, od, k2,  9, 10, 11,  8
+
+	add_update	m, ev, k2, 10, 11,  8,  9
+	add_update	m, od, k2, 11,  8,  9, 10
+	add_update	m, ev, k2,  8,  9, 10, 11
+	add_update	m, od, k2,  9, 10, 11,  8
+	add_update	m, ev, k3, 10, 11,  8,  9
+
+	add_update	p, od, k3, 11,  8,  9, 10
+	add_only	p, ev, k3,  9
+	add_only	p, od, k3, 10
+	add_only	p, ev, k3, 11
+	add_only	p, od
+
+	/* update state */
+	add		dgbv.2s, dgbv.2s, dg1v.2s
+	add		dgav.4s, dgav.4s, dg0v.4s
+
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v9.2d, #0
+	mov		x8, #0x80000000
+	movi		v10.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d8, x8
+	mov		x4, #0
+	mov		v11.d[0], xzr
+	mov		v11.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	str		dga, [x2]
+	str		dgb, [x2, #16]
+	ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 000000000000..6fe83f37a750
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+				  u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+	return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA1_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA1_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buffer + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA1_BLOCK_SIZE;
+		len %= SHA1_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(16);
+		sha1_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buffer : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA1_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buffer + partial, data, len);
+	return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	u32 padlen = SHA1_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+	sha1_update(desc, padding, padlen);
+	sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+		      unsigned int len, u8 *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int blocks;
+	int i;
+
+	if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+		sha1_update(desc, data, len);
+		return sha1_final(desc, out);
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha1_ce_transform()
+	 */
+	blocks = len / SHA1_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(16);
+	sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.init			= sha1_init,
+	.update			= sha1_update,
+	.final			= sha1_final,
+	.finup			= sha1_finup,
+	.export			= sha1_export,
+	.import			= sha1_import,
+	.descsize		= sizeof(struct sha1_state),
+	.digestsize		= SHA1_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha1_state),
+	.base			= {
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 000000000000..7f29fc031ea8
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,156 @@
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	dga		.req	q20
+	dgav		.req	v20
+	dgb		.req	q21
+	dgbv		.req	v21
+
+	t0		.req	v22
+	t1		.req	v23
+
+	dg0q		.req	q24
+	dg0v		.req	v24
+	dg1q		.req	q25
+	dg1v		.req	v25
+	dg2q		.req	q26
+	dg2v		.req	v26
+
+	.macro		add_only, ev, rc, s0
+	mov		dg2v.16b, dg0v.16b
+	.ifeq		\ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha256h		dg0q, dg1q, t0.4s
+	sha256h2	dg1q, dg2q, t0.4s
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha256h		dg0q, dg1q, t1.4s
+	sha256h2	dg1q, dg2q, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, ev, rc, s0, s1, s2, s3
+	sha256su0	v\s0\().4s, v\s1\().4s
+	add_only	\ev, \rc, \s1
+	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA-256 round constants
+	 */
+	.align		4
+.Lsha2_rcon:
+	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+	/*
+	 * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+	 *                        u8 *head, long bytes)
+	 */
+ENTRY(sha2_ce_transform)
+	/* load round constants */
+	adr		x8, .Lsha2_rcon
+	ld1		{ v0.4s- v3.4s}, [x8], #64
+	ld1		{ v4.4s- v7.4s}, [x8], #64
+	ld1		{ v8.4s-v11.4s}, [x8], #64
+	ld1		{v12.4s-v15.4s}, [x8]
+
+	/* load state */
+	ldp		dga, dgb, [x2]
+
+	/* load partial input (if supplied) */
+	cbz		x3, 0f
+	ld1		{v16.4s-v19.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v16.16b, v16.16b	)
+CPU_LE(	rev32		v17.16b, v17.16b	)
+CPU_LE(	rev32		v18.16b, v18.16b	)
+CPU_LE(	rev32		v19.16b, v19.16b	)
+
+2:	add		t0.4s, v16.4s, v0.4s
+	mov		dg0v.16b, dgav.16b
+	mov		dg1v.16b, dgbv.16b
+
+	add_update	0,  v1, 16, 17, 18, 19
+	add_update	1,  v2, 17, 18, 19, 16
+	add_update	0,  v3, 18, 19, 16, 17
+	add_update	1,  v4, 19, 16, 17, 18
+
+	add_update	0,  v5, 16, 17, 18, 19
+	add_update	1,  v6, 17, 18, 19, 16
+	add_update	0,  v7, 18, 19, 16, 17
+	add_update	1,  v8, 19, 16, 17, 18
+
+	add_update	0,  v9, 16, 17, 18, 19
+	add_update	1, v10, 17, 18, 19, 16
+	add_update	0, v11, 18, 19, 16, 17
+	add_update	1, v12, 19, 16, 17, 18
+
+	add_only	0, v13, 17
+	add_only	1, v14, 18
+	add_only	0, v15, 19
+	add_only	1
+
+	/* update state */
+	add		dgav.4s, dgav.4s, dg0v.4s
+	add		dgbv.4s, dgbv.4s, dg1v.4s
+
+	/* handled all input blocks? */
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v17.2d, #0
+	mov		x8, #0x80000000
+	movi		v18.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d16, x8
+	mov		x4, #0
+	mov		v19.d[0], xzr
+	mov		v19.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	stp		dga, dgb, [x2]
+	ret
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 000000000000..c294e67d3925
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,255 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+				 u8 *head, long bytes);
+
+static int sha224_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+			SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+			SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA256_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA256_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buf + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA256_BLOCK_SIZE;
+		len %= SHA256_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(28);
+		sha2_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buf : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA256_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buf + partial, data, len);
+	return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	u32 padlen = SHA256_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+	sha2_update(desc, padding, padlen);
+	sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static void sha2_finup(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	int blocks;
+
+	if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
+		sha2_update(desc, data, len);
+		sha2_final(desc);
+		return;
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha2_ce_transform()
+	 */
+	blocks = len / SHA256_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(28);
+	sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+	data += blocks * SHA256_BLOCK_SIZE;
+}
+
+static int sha224_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha224_init,
+	.update			= sha2_update,
+	.final			= sha224_final,
+	.finup			= sha224_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha224",
+		.cra_driver_name	= "sha224-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+}, {
+	.init			= sha256_init,
+	.update			= sha2_update,
+	.final			= sha256_final,
+	.finup			= sha256_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha256",
+		.cra_driver_name	= "sha256-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index bc5da00f8d84..cfe9860b2076 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -37,6 +37,7 @@ generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index d56ed11ba9a3..be56d33c5dbf 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -26,7 +26,13 @@
 
 #include <clocksource/arm_arch_timer.h>
 
-static inline void arch_timer_reg_write(int access, int reg, u32 val)
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code.
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
@@ -36,8 +42,6 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
@@ -47,17 +51,14 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
-	} else {
-		BUILD_BUG();
 	}
 
 	isb();
 }
 
-static inline u32 arch_timer_reg_read(int access, int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
 	u32 val;
 
@@ -69,8 +70,6 @@ static inline u32 arch_timer_reg_read(int access, int reg)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
@@ -80,11 +79,7 @@ static inline u32 arch_timer_reg_read(int access, int reg)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
-	} else {
-		BUILD_BUG();
 	}
 
 	return val;
@@ -97,19 +92,49 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
-static inline void __cpuinit arch_counter_set_user_access(void)
+static inline u32 arch_timer_get_cntkctl(void)
 {
 	u32 cntkctl;
-
-	/* Disable user access to the timers and the physical counter. */
 	asm volatile("mrs	%0, cntkctl_el1" : "=r" (cntkctl));
-	cntkctl &= ~((3 << 8) | (1 << 0));
+	return cntkctl;
+}
 
-	/* Enable user access to the virtual counter and frequency. */
-	cntkctl |= (1 << 1);
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
+static inline void __cpuinit arch_counter_set_user_access(void)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	/* Disable user access to the timers and the physical counter */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+
+	/* Enable user access to the virtual counter */
+	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+	arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+	/* Set the divider and enable virtual event stream */
+	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+			| ARCH_TIMER_VIRT_EVT_EN;
+	arch_timer_set_cntkctl(cntkctl);
+	elf_hwcap |= HWCAP_EVTSTRM;
+#ifdef CONFIG_COMPAT
+	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
+#endif
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 5aceb83b3f5c..fd3e3924041b 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -115,3 +115,34 @@ lr	.req	x30		// link register
 	.align	7
 	b	\label
 	.endm
+
+/*
+ * Select code when configured for BE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_BE(code...) code
+#else
+#define CPU_BE(code...)
+#endif
+
+/*
+ * Select code when configured for LE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+/*
+ * Define a macro that constructs a 64-bit value by concatenating two
+ * 32-bit registers. Note that on big endian systems the order of the
+ * registers is swapped.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	.macro	regs_to_64, rd, lbits, hbits
+#else
+	.macro	regs_to_64, rd, hbits, lbits
+#endif
+	orr	\rd, \lbits, \hbits, lsl #32
+	.endm
diff --git a/arch/arm64/include/asm/bL_switcher.h b/arch/arm64/include/asm/bL_switcher.h
new file mode 100644
index 000000000000..2bee500b7f54
--- /dev/null
+++ b/arch/arm64/include/asm/bL_switcher.h
@@ -0,0 +1,54 @@
+/*
+ * Based on the stubs for the ARM implementation which is:
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+static inline int bL_switch_request(unsigned int cpu,
+				    unsigned int new_cluster_id)
+{
+	return -ENOTSUPP;
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+
+#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index d3d4089d9fc3..a84d4c8acbbe 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -164,17 +164,23 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	return ret;
 }
 
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
-
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg((ptr),				\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n) \
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+	__cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
+		sizeof(*(ptr))); \
+	__ret; \
+})
+
+#define cmpxchg_local(ptr, o, n) \
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+	__cmpxchg((ptr), (unsigned long)(o), \
+		(unsigned long)(n), sizeof(*(ptr))); \
+	__ret; \
+})
 
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 899af807ef0f..56de5aadede2 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -26,15 +26,19 @@
 #include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __AARCH64EB__
+#define COMPAT_UTS_MACHINE	"armv8b\0\0"
+#else
 #define COMPAT_UTS_MACHINE	"armv8l\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
 typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
-typedef u32		__compat_uid_t;
-typedef u32		__compat_gid_t;
+typedef u16		__compat_uid_t;
+typedef u16		__compat_gid_t;
 typedef u16		__compat_uid16_t;
 typedef u16		__compat_gid16_t;
 typedef u32		__compat_uid32_t;
@@ -73,13 +77,23 @@ struct compat_timeval {
 };
 
 struct compat_stat {
+#ifdef __AARCH64EB__
+	short		st_dev;
+	short		__pad1;
+#else
 	compat_dev_t	st_dev;
+#endif
 	compat_ino_t	st_ino;
 	compat_mode_t	st_mode;
 	compat_ushort_t	st_nlink;
 	__compat_uid16_t	st_uid;
 	__compat_gid16_t	st_gid;
+#ifdef __AARCH64EB__
+	short		st_rdev;
+	short		__pad2;
+#else
 	compat_dev_t	st_rdev;
+#endif
 	compat_off_t	st_size;
 	compat_off_t	st_blksize;
 	compat_off_t	st_blocks;
@@ -214,7 +228,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
@@ -291,11 +305,6 @@ static inline int is_compat_thread(struct thread_info *thread)
 
 #else /* !CONFIG_COMPAT */
 
-static inline int is_compat_task(void)
-{
-	return 0;
-}
-
 static inline int is_compat_thread(struct thread_info *thread)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 27207fee2521..47dfa31ad71a 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -28,6 +28,8 @@ struct device_node;
  *		enable-method property.
  * @cpu_init:	Reads any data necessary for a specific enable-method from the
  *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -40,10 +42,14 @@ struct device_node;
  * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
  *		cpu being killed.
  * @cpu_kill:  Ensures a cpu has left the kernel. Called from another cpu.
+ * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
+ *               to wrong parameters or error conditions. Called from the
+ *               CPU being suspended. Must be called with IRQs disabled.
  */
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
@@ -52,6 +58,9 @@ struct cpu_operations {
 	void		(*cpu_die)(unsigned int cpu);
 	int		(*cpu_kill)(unsigned int cpu);
 #endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+	int		(*cpu_suspend)(unsigned long);
+#endif
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 000000000000..cd4ac0516488
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
+#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
new file mode 100644
index 000000000000..b52a9932e2b1
--- /dev/null
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int cpu_init_idle(unsigned int cpu);
+#else
+static inline int cpu_init_idle(unsigned int cpu)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 632298c2d951..ec5e41c23429 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -16,23 +16,23 @@
 #ifndef __ASM_CPUTYPE_H
 #define __ASM_CPUTYPE_H
 
-#define ID_MIDR_EL1		"midr_el1"
-#define ID_MPIDR_EL1		"mpidr_el1"
-#define ID_CTR_EL0		"ctr_el0"
-
-#define ID_AA64PFR0_EL1		"id_aa64pfr0_el1"
-#define ID_AA64DFR0_EL1		"id_aa64dfr0_el1"
-#define ID_AA64AFR0_EL1		"id_aa64afr0_el1"
-#define ID_AA64ISAR0_EL1	"id_aa64isar0_el1"
-#define ID_AA64MMFR0_EL1	"id_aa64mmfr0_el1"
-
 #define INVALID_HWID		ULONG_MAX
 
 #define MPIDR_HWID_BITMASK	0xff00ffffff
 
+#define MPIDR_LEVEL_BITS_SHIFT	3
+#define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)
+#define MPIDR_LEVEL_MASK	((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_LEVEL_SHIFT(level) \
+	(((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
+
 #define read_cpuid(reg) ({						\
 	u64 __val;							\
-	asm("mrs	%0, " reg : "=r" (__val));			\
+	asm("mrs	%0, " #reg : "=r" (__val));			\
 	__val;								\
 })
 
@@ -74,12 +74,12 @@
  */
 static inline u32 __attribute_const__ read_cpuid_id(void)
 {
-	return read_cpuid(ID_MIDR_EL1);
+	return read_cpuid(MIDR_EL1);
 }
 
 static inline u64 __attribute_const__ read_cpuid_mpidr(void)
 {
-	return read_cpuid(ID_MPIDR_EL1);
+	return read_cpuid(MPIDR_EL1);
 }
 
 static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
@@ -94,7 +94,7 @@ static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
 
 static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 {
-	return read_cpuid(ID_CTR_EL0);
+	return read_cpuid(CTR_EL0);
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
new file mode 100644
index 000000000000..5a46c4e7f539
--- /dev/null
+++ b/arch/arm64/include/asm/efi.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_EFI_H
+#define _ASM_EFI_H
+
+#include <asm/io.h>
+
+#ifdef CONFIG_EFI
+extern void efi_init(void);
+extern void efi_idmap_init(void);
+#else
+#define efi_init()
+#define efi_idmap_init()
+#endif
+
+#endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index e7fa87f9201b..01d3aab64b79 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -90,11 +90,24 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  * These are used to set parameters in the core dumps.
  */
 #define ELF_CLASS	ELFCLASS64
+#ifdef __AARCH64EB__
+#define ELF_DATA	ELFDATA2MSB
+#else
 #define ELF_DATA	ELFDATA2LSB
+#endif
 #define ELF_ARCH	EM_AARCH64
 
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
 #define ELF_PLATFORM_SIZE	16
+#ifdef __AARCH64EB__
+#define ELF_PLATFORM		("aarch64_be")
+#else
 #define ELF_PLATFORM		("aarch64")
+#endif
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
@@ -149,7 +162,12 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
+
+#ifdef __AARCH64EB__
+#define COMPAT_ELF_PLATFORM		("v8b")
+#else
 #define COMPAT_ELF_PLATFORM		("v8l")
+#endif
 
 #define COMPAT_ELF_ET_DYN_BASE		(randomize_et_dyn(2 * TASK_SIZE_32 / 3))
 
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
new file mode 100644
index 000000000000..c5534facf941
--- /dev/null
+++ b/arch/arm64/include/asm/ftrace.h
@@ -0,0 +1,59 @@
+/*
+ * arch/arm64/include/asm/ftrace.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_FTRACE_H
+#define __ASM_FTRACE_H
+
+#include <asm/insn.h>
+
+#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
+
+#ifndef __ASSEMBLY__
+#include <linux/compat.h>
+
+extern void _mcount(unsigned long);
+extern void *return_address(unsigned int);
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for arm64 */
+};
+
+extern unsigned long ftrace_graph_call;
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
+	 */
+	return addr;
+}
+
+#define ftrace_return_address(n) return_address(n)
+
+/*
+ * Because AArch32 mode does not share the same syscall table with AArch64,
+ * tracing compat syscalls may result in reporting bogus syscalls or even
+ * hang-up, so just do not trace them.
+ * See kernel/trace/trace_syscalls.c
+ *
+ * x86 code says:
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+	return is_compat_task();
+}
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 990c051e7829..ae4801d77514 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	4
+#define NR_IPI	5
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index e2950b098e76..024c46183c3c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,13 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_EVTSTRM	(1 << 21)
+
+#define COMPAT_HWCAP2_AES	(1 << 0)
+#define COMPAT_HWCAP2_PMULL	(1 << 1)
+#define COMPAT_HWCAP2_SHA1	(1 << 2)
+#define COMPAT_HWCAP2_SHA2	(1 << 3)
+#define COMPAT_HWCAP2_CRC32	(1 << 4)
 
 #ifndef __ASSEMBLY__
 /*
@@ -37,11 +44,12 @@
  * instruction set this cpu supports.
  */
 #define ELF_HWCAP		(elf_hwcap)
-#define COMPAT_ELF_HWCAP	(COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
-				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
-				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
-				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
+#define COMPAT_ELF_HWCAP2	(compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
+#endif
 
 extern unsigned long elf_hwcap;
 #endif
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
new file mode 100644
index 000000000000..62e7b8bcd2dc
--- /dev/null
+++ b/arch/arm64/include/asm/insn.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef	__ASM_INSN_H
+#define	__ASM_INSN_H
+
+#include <linux/types.h>
+
+/* A64 instructions are always 32 bits. */
+#define	AARCH64_INSN_SIZE		4
+
+#ifndef __ASSEMBLY__
+
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section C3.1 "A64 instruction index by encoding":
+ * AArch64 main encoding table
+ *  Bit position
+ *   28 27 26 25	Encoding Group
+ *   0  0  -  -		Unallocated
+ *   1  0  0  -		Data processing, immediate
+ *   1  0  1  -		Branch, exception generation and system instructions
+ *   -  1  -  0		Loads and stores
+ *   -  1  0  1		Data processing - register
+ *   0  1  1  1		Data processing - SIMD and floating point
+ *   1  1  1  1		Data processing - SIMD and floating point
+ * "-" means "don't care"
+ */
+enum aarch64_insn_encoding_class {
+	AARCH64_INSN_CLS_UNKNOWN,	/* UNALLOCATED */
+	AARCH64_INSN_CLS_DP_IMM,	/* Data processing - immediate */
+	AARCH64_INSN_CLS_DP_REG,	/* Data processing - register */
+	AARCH64_INSN_CLS_DP_FPSIMD,	/* Data processing - SIMD and FP */
+	AARCH64_INSN_CLS_LDST,		/* Loads and stores */
+	AARCH64_INSN_CLS_BR_SYS,	/* Branch, exception generation and
+					 * system instructions */
+};
+
+enum aarch64_insn_hint_op {
+	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
+	AARCH64_INSN_HINT_YIELD	= 0x1 << 5,
+	AARCH64_INSN_HINT_WFE	= 0x2 << 5,
+	AARCH64_INSN_HINT_WFI	= 0x3 << 5,
+	AARCH64_INSN_HINT_SEV	= 0x4 << 5,
+	AARCH64_INSN_HINT_SEVL	= 0x5 << 5,
+};
+
+enum aarch64_insn_imm_type {
+	AARCH64_INSN_IMM_ADR,
+	AARCH64_INSN_IMM_26,
+	AARCH64_INSN_IMM_19,
+	AARCH64_INSN_IMM_16,
+	AARCH64_INSN_IMM_14,
+	AARCH64_INSN_IMM_12,
+	AARCH64_INSN_IMM_9,
+	AARCH64_INSN_IMM_MAX
+};
+
+enum aarch64_insn_branch_type {
+	AARCH64_INSN_BRANCH_NOLINK,
+	AARCH64_INSN_BRANCH_LINK,
+};
+
+#define	__AARCH64_INSN_FUNCS(abbr, mask, val)	\
+static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
+{ return (code & (mask)) == (val); } \
+static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
+{ return (val); }
+
+__AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
+__AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
+__AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
+__AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
+__AARCH64_INSN_FUNCS(smc,	0xFFE0001F, 0xD4000003)
+__AARCH64_INSN_FUNCS(brk,	0xFFE0001F, 0xD4200000)
+__AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
+
+#undef	__AARCH64_INSN_FUNCS
+
+bool aarch64_insn_is_nop(u32 insn);
+
+int aarch64_insn_read(void *addr, u32 *insnp);
+int aarch64_insn_write(void *addr, u32 insn);
+enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
+u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+				  u32 insn, u64 imm);
+u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+				enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op);
+u32 aarch64_insn_gen_nop(void);
+
+bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
+
+int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
+int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
+int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+#endif  /* __ASSEMBLY__ */
+
+#endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
new file mode 100644
index 000000000000..076a1c714049
--- /dev/null
+++ b/arch/arm64/include/asm/jump_label.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Based on arch/arm/include/asm/jump_label.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_JUMP_LABEL_H
+#define __ASM_JUMP_LABEL_H
+#include <linux/types.h>
+#include <asm/insn.h>
+
+#ifdef __KERNEL__
+
+#define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
+
+static __always_inline bool arch_static_branch(struct static_key *key)
+{
+	asm goto("1: nop\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align 3\n\t"
+		 ".quad 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 :  :  "i"(key) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u64 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif	/* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h
index 4489615f14a9..4e94424938a4 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-3level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
 #define __ASM_PGTABLE_3LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pmdval_t;
 typedef u64 pgdval_t;
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index a496aa6ff7ef..0d3b0b17e927 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -26,11 +26,14 @@
 #include <asm/page.h>
 
 struct mm_struct;
+struct cpu_suspend_ctx;
 
 extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
+extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 void cpu_soft_restart(phys_addr_t cpu_reset,
 		unsigned long addr) __attribute__((noreturn));
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 3b7bb031f98f..001b764fffa1 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -107,6 +107,11 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->pstate = COMPAT_PSR_MODE_USR;
 	if (pc & 1)
 		regs->pstate |= COMPAT_PSR_T_BIT;
+
+#ifdef __AARCH64EB__
+	regs->pstate |= COMPAT_PSR_E_BIT;
+#endif
+
 	regs->compat_sp = sp;
 }
 #endif
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 2e9ddd71b24a..5db016e6d065 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -42,6 +42,7 @@
 #define COMPAT_PSR_MODE_UND	0x0000001b
 #define COMPAT_PSR_MODE_SYS	0x0000001f
 #define COMPAT_PSR_T_BIT	0x00000020
+#define COMPAT_PSR_E_BIT	0x00000200
 #define COMPAT_PSR_F_BIT	0x00000040
 #define COMPAT_PSR_I_BIT	0x00000080
 #define COMPAT_PSR_A_BIT	0x00000100
@@ -67,6 +68,7 @@
 
 /* Architecturally defined mapping between AArch32 and AArch64 registers */
 #define compat_usr(x)	regs[(x)]
+#define compat_fp	regs[11]
 #define compat_sp	regs[13]
 #define compat_lr	regs[14]
 #define compat_sp_hyp	regs[15]
@@ -131,7 +133,12 @@ struct pt_regs {
 	(!((regs)->pstate & PSR_F_BIT))
 
 #define user_stack_pointer(regs) \
-	((regs)->sp)
+	(!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->regs[0];
+}
 
 /*
  * Are the current registers suitable for user mode? (used to maintain
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index ed43a0d2b1b2..59e282311b58 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -21,6 +21,19 @@
 
 #include <asm/types.h>
 
+struct mpidr_hash {
+	u64	mask;
+	u32	shift_aff[4];
+	u32	bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+	return 1 << mpidr_hash.bits;
+}
+
 /*
  * Logical CPU mapping.
  */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
new file mode 100644
index 000000000000..e9c149c042e0
--- /dev/null
+++ b/arch/arm64/include/asm/suspend.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_SUSPEND_H
+#define __ASM_SUSPEND_H
+
+#define NR_CTX_REGS 11
+
+/*
+ * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on
+ * the stack, which must be 16-byte aligned on v8
+ */
+struct cpu_suspend_ctx {
+	/*
+	 * This struct must be kept in sync with
+	 * cpu_do_{suspend/resume} in mm/proc.S
+	 */
+	u64 ctx_regs[NR_CTX_REGS];
+	u64 sp;
+} __aligned(16);
+
+struct sleep_save_sp {
+	phys_addr_t *save_ptr_stash;
+	phys_addr_t save_ptr_stash_phys;
+};
+
+extern void cpu_resume(void);
+extern int cpu_suspend(unsigned long);
+
+#endif
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 70ba9d4ee978..383771eb0b87 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -18,6 +18,7 @@
 
 #include <linux/err.h>
 
+extern const void *sys_call_table[];
 
 static inline int syscall_get_nr(struct task_struct *task,
 				 struct pt_regs *regs)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 000000000000..5c89df0acbcb
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,60 @@
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	.equ	__reg_num_x\num, \num
+	.endr
+	.equ	__reg_num_xzr, 31
+
+	.macro	mrs_s, rt, sreg
+	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+	.macro	msr_s, sreg, rt
+	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+#else
+
+asm(
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
+"	.equ	__reg_num_x\\num, \\num\n"
+"	.endr\n"
+"	.equ	__reg_num_xzr, 31\n"
+"\n"
+"	.macro	mrs_s, rt, sreg\n"
+"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+"\n"
+"	.macro	msr_s, sreg, rt\n"
+"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+);
+
+#endif
+
+#endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index d971013f73c1..70dd1ac01f16 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -102,6 +102,9 @@ static inline struct thread_info *current_thread_info(void)
 /*
  * thread information flags:
  *  TIF_SYSCALL_TRACE	- syscall trace active
+ *  TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace
+ *  TIF_SYSCALL_AUDIT	- syscall auditing
+ *  TIF_SECOMP		- syscall secure computing
  *  TIF_SIGPENDING	- signal pending
  *  TIF_NEED_RESCHED	- rescheduling necessary
  *  TIF_NOTIFY_RESUME	- callback before returning to user
@@ -112,6 +115,9 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_SYSCALL_TRACE	8
+#define TIF_SYSCALL_AUDIT	9
+#define TIF_SYSCALL_TRACEPOINT	10
+#define TIF_SECCOMP		11
 #define TIF_POLLING_NRFLAG	16
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
@@ -123,10 +129,17 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME)
 
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 000000000000..e0171b393a14
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+	int thread_id;
+	int core_id;
+	int cluster_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].cluster_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 0,					\
+	.wake_idx		= 0,					\
+	.forkexec_idx		= 0,					\
+									\
+	.flags			= 0*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_BALANCE_WAKE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				,					\
+	.last_balance		 = jiffies,				\
+	.balance_interval	= 1,					\
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217e94cf..c335479c2638 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -28,3 +28,5 @@
 #endif
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index e4b78bdca19e..942376d37d22 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -9,6 +9,7 @@ header-y += byteorder.h
 header-y += fcntl.h
 header-y += hwcap.h
 header-y += kvm_para.h
+header-y += perf_regs.h
 header-y += param.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm64/include/uapi/asm/byteorder.h b/arch/arm64/include/uapi/asm/byteorder.h
index 2b92046aafc5..dc19e9537f0d 100644
--- a/arch/arm64/include/uapi/asm/byteorder.h
+++ b/arch/arm64/include/uapi/asm/byteorder.h
@@ -16,6 +16,10 @@
 #ifndef __ASM_BYTEORDER_H
 #define __ASM_BYTEORDER_H
 
+#ifdef __AARCH64EB__
+#include <linux/byteorder/big_endian.h>
+#else
 #include <linux/byteorder/little_endian.h>
+#endif
 
 #endif	/* __ASM_BYTEORDER_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index eea497578b87..73cf0f54d57c 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -21,6 +21,11 @@
  */
 #define HWCAP_FP		(1 << 0)
 #define HWCAP_ASIMD		(1 << 1)
-
+#define HWCAP_EVTSTRM		(1 << 2)
+#define HWCAP_AES		(1 << 3)
+#define HWCAP_PMULL		(1 << 4)
+#define HWCAP_SHA1		(1 << 5)
+#define HWCAP_SHA2		(1 << 6)
+#define HWCAP_CRC32		(1 << 7)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..172b8317ee49
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM64_X0,
+	PERF_REG_ARM64_X1,
+	PERF_REG_ARM64_X2,
+	PERF_REG_ARM64_X3,
+	PERF_REG_ARM64_X4,
+	PERF_REG_ARM64_X5,
+	PERF_REG_ARM64_X6,
+	PERF_REG_ARM64_X7,
+	PERF_REG_ARM64_X8,
+	PERF_REG_ARM64_X9,
+	PERF_REG_ARM64_X10,
+	PERF_REG_ARM64_X11,
+	PERF_REG_ARM64_X12,
+	PERF_REG_ARM64_X13,
+	PERF_REG_ARM64_X14,
+	PERF_REG_ARM64_X15,
+	PERF_REG_ARM64_X16,
+	PERF_REG_ARM64_X17,
+	PERF_REG_ARM64_X18,
+	PERF_REG_ARM64_X19,
+	PERF_REG_ARM64_X20,
+	PERF_REG_ARM64_X21,
+	PERF_REG_ARM64_X22,
+	PERF_REG_ARM64_X23,
+	PERF_REG_ARM64_X24,
+	PERF_REG_ARM64_X25,
+	PERF_REG_ARM64_X26,
+	PERF_REG_ARM64_X27,
+	PERF_REG_ARM64_X28,
+	PERF_REG_ARM64_X29,
+	PERF_REG_ARM64_LR,
+	PERF_REG_ARM64_SP,
+	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index b9b87fa61bac..a8ad571c4758 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -4,21 +4,35 @@
 
 CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
+CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET) \
+			   -I$(src)/../../../scripts/dtc/libfdt
+
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_return_address.o = -pg
 
 # Object file lists.
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o
+			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
+arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
+arm64-obj-$(CONFIG_SMP)			+= topology.o
+arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
+arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
+arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
+arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 1edc792b4a1f..a85843ddbde8 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -61,3 +61,7 @@ EXPORT_SYMBOL(clear_bit);
 EXPORT_SYMBOL(test_and_clear_bit);
 EXPORT_SYMBOL(change_bit);
 EXPORT_SYMBOL(test_and_change_bit);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 825d76c21d84..9a9fce090d58 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -25,6 +25,8 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/cputable.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
 
@@ -150,5 +152,14 @@ int main(void)
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
 #endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+  DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));
+  DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
+  DEFINE(MPIDR_HASH_MASK,	offsetof(struct mpidr_hash, mask));
+  DEFINE(MPIDR_HASH_SHIFTS,	offsetof(struct mpidr_hash, shift_aff));
+  DEFINE(SLEEP_SAVE_SP_SZ,	sizeof(struct sleep_save_sp));
+  DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
+  DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
+#endif
   return 0;
 }
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
new file mode 100644
index 000000000000..19d17f51db37
--- /dev/null
+++ b/arch/arm64/kernel/cpuidle.c
@@ -0,0 +1,31 @@
+/*
+ * ARM64 CPU idle arch support
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include <asm/cpuidle.h>
+#include <asm/cpu_ops.h>
+
+int cpu_init_idle(unsigned int cpu)
+{
+	int ret = -EOPNOTSUPP;
+	struct device_node *cpu_node = of_cpu_device_node_get(cpu);
+
+	if (!cpu_node)
+		return -ENODEV;
+
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
+		ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+
+	of_node_put(cpu_node);
+	return ret;
+}
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
new file mode 100644
index 000000000000..66716c9b9e5f
--- /dev/null
+++ b/arch/arm64/kernel/efi-entry.S
@@ -0,0 +1,109 @@
+/*
+ * EFI entry point.
+ *
+ * Copyright (C) 2013, 2014 Red Hat, Inc.
+ * Author: Mark Salter <msalter@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+#include <asm/assembler.h>
+
+#define EFI_LOAD_ERROR 0x8000000000000001
+
+	__INIT
+
+	/*
+	 * We arrive here from the EFI boot manager with:
+	 *
+	 *    * CPU in little-endian mode
+	 *    * MMU on with identity-mapped RAM
+	 *    * Icache and Dcache on
+	 *
+	 * We will most likely be running from some place other than where
+	 * we want to be. The kernel image wants to be placed at TEXT_OFFSET
+	 * from start of RAM.
+	 */
+ENTRY(efi_stub_entry)
+	/*
+	 * Create a stack frame to save FP/LR with extra space
+	 * for image_addr variable passed to efi_entry().
+	 */
+	stp	x29, x30, [sp, #-32]!
+
+	/*
+	 * Call efi_entry to do the real work.
+	 * x0 and x1 are already set up by firmware. Current runtime
+	 * address of image is calculated and passed via *image_addr.
+	 *
+	 * unsigned long efi_entry(void *handle,
+	 *                         efi_system_table_t *sys_table,
+	 *                         unsigned long *image_addr) ;
+	 */
+	adrp	x8, _text
+	add	x8, x8, #:lo12:_text
+	add	x2, sp, 16
+	str	x8, [x2]
+	bl	efi_entry
+	cmn	x0, #1
+	b.eq	efi_load_fail
+
+	/*
+	 * efi_entry() will have relocated the kernel image if necessary
+	 * and we return here with device tree address in x0 and the kernel
+	 * entry point stored at *image_addr. Save those values in registers
+	 * which are callee preserved.
+	 */
+	mov	x20, x0		// DTB address
+	ldr	x0, [sp, #16]	// relocated _text address
+	mov	x21, x0
+
+	/*
+	 * Flush dcache covering current runtime addresses
+	 * of kernel text/data. Then flush all of icache.
+	 */
+	adrp	x1, _text
+	add	x1, x1, #:lo12:_text
+	adrp	x2, _edata
+	add	x2, x2, #:lo12:_edata
+	sub	x1, x2, x1
+
+	bl	__flush_dcache_area
+	ic	ialluis
+
+	/* Turn off Dcache and MMU */
+	mrs	x0, CurrentEL
+	cmp	x0, #PSR_MODE_EL2t
+	ccmp	x0, #PSR_MODE_EL2h, #0x4, ne
+	b.ne	1f
+	mrs	x0, sctlr_el2
+	bic	x0, x0, #1 << 0	// clear SCTLR.M
+	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	msr	sctlr_el2, x0
+	isb
+	b	2f
+1:
+	mrs	x0, sctlr_el1
+	bic	x0, x0, #1 << 0	// clear SCTLR.M
+	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	msr	sctlr_el1, x0
+	isb
+2:
+	/* Jump to kernel entry point */
+	mov	x0, x20
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	br	x21
+
+efi_load_fail:
+	mov	x0, #EFI_LOAD_ERROR
+	ldp	x29, x30, [sp], #32
+	ret
+
+ENDPROC(efi_stub_entry)
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
new file mode 100644
index 000000000000..e786e6cdc400
--- /dev/null
+++ b/arch/arm64/kernel/efi-stub.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2013, 2014 Linaro Ltd;  <roy.franz@linaro.org>
+ *
+ * This file implements the EFI boot stub for the arm64 kernel.
+ * Adapted from ARM version by Mark Salter <msalter@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/efi.h>
+#include <linux/libfdt.h>
+#include <asm/sections.h>
+
+/*
+ * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
+ * start of kernel and may not cross a 2MiB boundary. We set alignment to
+ * 2MiB so we know it won't cross a 2MiB boundary.
+ */
+#define EFI_FDT_ALIGN	SZ_2M   /* used by allocate_new_fdt_and_exit_boot() */
+#define MAX_FDT_OFFSET	SZ_512M
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
+static void efi_char16_printk(efi_system_table_t *sys_table_arg,
+			      efi_char16_t *str);
+
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table,
+				    void *__image, void **__fh);
+static efi_status_t efi_file_close(void *handle);
+
+static efi_status_t
+efi_file_read(void *handle, unsigned long *size, void *addr);
+
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table, void *__fh,
+	      efi_char16_t *filename_16, void **handle, u64 *file_sz);
+
+/* Include shared EFI stub code */
+#include "../../../drivers/firmware/efi/efi-stub-helper.c"
+#include "../../../drivers/firmware/efi/fdt.c"
+#include "../../../drivers/firmware/efi/arm-stub.c"
+
+
+static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+					unsigned long *image_addr,
+					unsigned long *image_size,
+					unsigned long *reserve_addr,
+					unsigned long *reserve_size,
+					unsigned long dram_base,
+					efi_loaded_image_t *image)
+{
+	efi_status_t status;
+	unsigned long kernel_size, kernel_memsize = 0;
+
+	/* Relocate the image, if required. */
+	kernel_size = _edata - _text;
+	if (*image_addr != (dram_base + TEXT_OFFSET)) {
+		kernel_memsize = kernel_size + (_end - _edata);
+		status = efi_relocate_kernel(sys_table, image_addr,
+					     kernel_size, kernel_memsize,
+					     dram_base + TEXT_OFFSET,
+					     PAGE_SIZE);
+		if (status != EFI_SUCCESS) {
+			pr_efi_err(sys_table, "Failed to relocate kernel\n");
+			return status;
+		}
+		if (*image_addr != (dram_base + TEXT_OFFSET)) {
+			pr_efi_err(sys_table, "Failed to alloc kernel memory\n");
+			efi_free(sys_table, kernel_memsize, *image_addr);
+			return EFI_ERROR;
+		}
+		*image_size = kernel_memsize;
+	}
+
+
+	return EFI_SUCCESS;
+}
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
new file mode 100644
index 000000000000..14db1f6e8d7f
--- /dev/null
+++ b/arch/arm64/kernel/efi.c
@@ -0,0 +1,469 @@
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013, 2014 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cacheflush.h>
+#include <asm/efi.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+
+struct efi_memory_map memmap;
+
+static efi_runtime_services_t *runtime;
+
+static u64 efi_system_table;
+
+static int uefi_debug __initdata;
+static int __init uefi_debug_setup(char *str)
+{
+	uefi_debug = 1;
+
+	return 0;
+}
+early_param("uefi_debug", uefi_debug_setup);
+
+static int __init is_normal_ram(efi_memory_desc_t *md)
+{
+	if (md->attribute & EFI_MEMORY_WB)
+		return 1;
+	return 0;
+}
+
+static void __init efi_setup_idmap(void)
+{
+	struct memblock_region *r;
+	efi_memory_desc_t *md;
+	u64 paddr, npages, size;
+
+	for_each_memblock(memory, r)
+		create_id_mapping(r->base, r->size, 0);
+
+	/* map runtime io spaces */
+	for_each_efi_memory_desc(&memmap, md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) || is_normal_ram(md))
+			continue;
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+		create_id_mapping(paddr, size, 1);
+	}
+}
+
+static int __init uefi_init(void)
+{
+	efi_char16_t *c16;
+	char vendor[100] = "unknown";
+	int i, retval;
+
+	efi.systab = early_memremap(efi_system_table,
+				    sizeof(efi_system_table_t));
+	if (efi.systab == NULL) {
+		pr_warn("Unable to map EFI system table.\n");
+		return -ENOMEM;
+	}
+
+	set_bit(EFI_BOOT, &efi.flags);
+	set_bit(EFI_64BIT, &efi.flags);
+
+	/*
+	 * Verify the EFI Table
+	 */
+	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
+		pr_err("System table signature incorrect\n");
+		return -EINVAL;
+	}
+	if ((efi.systab->hdr.revision >> 16) < 2)
+		pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n",
+			efi.systab->hdr.revision >> 16,
+			efi.systab->hdr.revision & 0xffff);
+
+	/* Show what we know for posterity */
+	c16 = early_memremap(efi.systab->fw_vendor,
+			     sizeof(vendor));
+	if (c16) {
+		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
+			vendor[i] = c16[i];
+		vendor[i] = '\0';
+	}
+
+	pr_info("EFI v%u.%.02u by %s\n",
+		efi.systab->hdr.revision >> 16,
+		efi.systab->hdr.revision & 0xffff, vendor);
+
+	retval = efi_config_init(NULL);
+	if (retval == 0)
+		set_bit(EFI_CONFIG_TABLES, &efi.flags);
+
+	early_memunmap(c16, sizeof(vendor));
+	early_memunmap(efi.systab,  sizeof(efi_system_table_t));
+
+	return retval;
+}
+
+static __initdata char memory_type_name[][32] = {
+	{"Reserved"},
+	{"Loader Code"},
+	{"Loader Data"},
+	{"Boot Code"},
+	{"Boot Data"},
+	{"Runtime Code"},
+	{"Runtime Data"},
+	{"Conventional Memory"},
+	{"Unusable Memory"},
+	{"ACPI Reclaim Memory"},
+	{"ACPI Memory NVS"},
+	{"Memory Mapped I/O"},
+	{"MMIO Port Space"},
+	{"PAL Code"},
+};
+
+/*
+ * Return true for RAM regions we want to permanently reserve.
+ */
+static __init int is_reserve_region(efi_memory_desc_t *md)
+{
+	if (!is_normal_ram(md))
+		return 0;
+
+	if (md->attribute & EFI_MEMORY_RUNTIME)
+		return 1;
+
+	if (md->type == EFI_ACPI_RECLAIM_MEMORY ||
+	    md->type == EFI_RESERVED_TYPE)
+		return 1;
+
+	return 0;
+}
+
+static __init void reserve_regions(void)
+{
+	efi_memory_desc_t *md;
+	u64 paddr, npages, size;
+
+	if (uefi_debug)
+		pr_info("Processing EFI memory map:\n");
+
+	for_each_efi_memory_desc(&memmap, md) {
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+
+		if (uefi_debug)
+			pr_info("  0x%012llx-0x%012llx [%s]",
+				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
+				memory_type_name[md->type]);
+
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+
+		if (is_normal_ram(md))
+			early_init_dt_add_memory_arch(paddr, size);
+
+		if (is_reserve_region(md) ||
+		    md->type == EFI_BOOT_SERVICES_CODE ||
+		    md->type == EFI_BOOT_SERVICES_DATA) {
+			memblock_reserve(paddr, size);
+			if (uefi_debug)
+				pr_cont("*");
+		}
+
+		if (uefi_debug)
+			pr_cont("\n");
+	}
+}
+
+
+static u64 __init free_one_region(u64 start, u64 end)
+{
+	u64 size = end - start;
+
+	if (uefi_debug)
+		pr_info("  EFI freeing: 0x%012llx-0x%012llx\n",	start, end - 1);
+
+	free_bootmem_late(start, size);
+	return size;
+}
+
+static u64 __init free_region(u64 start, u64 end)
+{
+	u64 map_start, map_end, total = 0;
+
+	if (end <= start)
+		return total;
+
+	map_start = (u64)memmap.phys_map;
+	map_end = PAGE_ALIGN(map_start + (memmap.map_end - memmap.map));
+	map_start &= PAGE_MASK;
+
+	if (start < map_end && end > map_start) {
+		/* region overlaps UEFI memmap */
+		if (start < map_start)
+			total += free_one_region(start, map_start);
+
+		if (map_end < end)
+			total += free_one_region(map_end, end);
+	} else
+		total += free_one_region(start, end);
+
+	return total;
+}
+
+static void __init free_boot_services(void)
+{
+	u64 total_freed = 0;
+	u64 keep_end, free_start, free_end;
+	efi_memory_desc_t *md;
+
+	/*
+	 * If kernel uses larger pages than UEFI, we have to be careful
+	 * not to inadvertantly free memory we want to keep if there is
+	 * overlap at the kernel page size alignment. We do not want to
+	 * free is_reserve_region() memory nor the UEFI memmap itself.
+	 *
+	 * The memory map is sorted, so we keep track of the end of
+	 * any previous region we want to keep, remember any region
+	 * we want to free and defer freeing it until we encounter
+	 * the next region we want to keep. This way, before freeing
+	 * it, we can clip it as needed to avoid freeing memory we
+	 * want to keep for UEFI.
+	 */
+
+	keep_end = 0;
+	free_start = 0;
+
+	for_each_efi_memory_desc(&memmap, md) {
+		u64 paddr, npages, size;
+
+		if (is_reserve_region(md)) {
+			/*
+			 * We don't want to free any memory from this region.
+			 */
+			if (free_start) {
+				/* adjust free_end then free region */
+				if (free_end > md->phys_addr)
+					free_end -= PAGE_SIZE;
+				total_freed += free_region(free_start, free_end);
+				free_start = 0;
+			}
+			keep_end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+			continue;
+		}
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA) {
+			/* no need to free this region */
+			continue;
+		}
+
+		/*
+		 * We want to free memory from this region.
+		 */
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+
+		if (free_start) {
+			if (paddr <= free_end)
+				free_end = paddr + size;
+			else {
+				total_freed += free_region(free_start, free_end);
+				free_start = paddr;
+				free_end = paddr + size;
+			}
+		} else {
+			free_start = paddr;
+			free_end = paddr + size;
+		}
+		if (free_start < keep_end) {
+			free_start += PAGE_SIZE;
+			if (free_start >= free_end)
+				free_start = 0;
+		}
+	}
+	if (free_start)
+		total_freed += free_region(free_start, free_end);
+
+	if (total_freed)
+		pr_info("Freed 0x%llx bytes of EFI boot services memory",
+			total_freed);
+}
+
+void __init efi_init(void)
+{
+	struct efi_fdt_params params;
+
+	/* Grab UEFI information placed in FDT by stub */
+	if (!efi_get_fdt_params(&params, uefi_debug))
+		return;
+
+	efi_system_table = params.system_table;
+
+	memblock_reserve(params.mmap & PAGE_MASK,
+			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
+	memmap.phys_map = (void *)params.mmap;
+	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	memmap.map_end = memmap.map + params.mmap_size;
+	memmap.desc_size = params.desc_size;
+	memmap.desc_version = params.desc_ver;
+
+	if (uefi_init() < 0)
+		return;
+
+	reserve_regions();
+}
+
+void __init efi_idmap_init(void)
+{
+	if (!efi_enabled(EFI_BOOT))
+		return;
+
+	/* boot time idmap_pg_dir is incomplete, so fill in missing parts */
+	efi_setup_idmap();
+}
+
+static int __init remap_region(efi_memory_desc_t *md, void **new)
+{
+	u64 paddr, vaddr, npages, size;
+
+	paddr = md->phys_addr;
+	npages = md->num_pages;
+	memrange_efi_to_native(&paddr, &npages);
+	size = npages << PAGE_SHIFT;
+
+	if (is_normal_ram(md))
+		vaddr = (__force u64)ioremap_cache(paddr, size);
+	else
+		vaddr = (__force u64)ioremap(paddr, size);
+
+	if (!vaddr) {
+		pr_err("Unable to remap 0x%llx pages @ %p\n",
+		       npages, (void *)paddr);
+		return 0;
+	}
+
+	/* adjust for any rounding when EFI and system pagesize differs */
+	md->virt_addr = vaddr + (md->phys_addr - paddr);
+
+	if (uefi_debug)
+		pr_info("  EFI remap 0x%012llx => %p\n",
+			md->phys_addr, (void *)md->virt_addr);
+
+	memcpy(*new, md, memmap.desc_size);
+	*new += memmap.desc_size;
+
+	return 1;
+}
+
+/*
+ * Switch UEFI from an identity map to a kernel virtual map
+ */
+static int __init arm64_enter_virtual_mode(void)
+{
+	efi_memory_desc_t *md;
+	phys_addr_t virtmap_phys;
+	void *virtmap, *virt_md;
+	efi_status_t status;
+	u64 mapsize;
+	int count = 0;
+	unsigned long flags;
+
+	if (!efi_enabled(EFI_BOOT)) {
+		pr_info("EFI services will not be available.\n");
+		return -1;
+	}
+
+	pr_info("Remapping and enabling EFI services.\n");
+
+	/* replace early memmap mapping with permanent mapping */
+	mapsize = memmap.map_end - memmap.map;
+	early_memunmap(memmap.map, mapsize);
+	memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map,
+						   mapsize);
+	memmap.map_end = memmap.map + mapsize;
+
+	efi.memmap = &memmap;
+
+	/* Map the runtime regions */
+	virtmap = kmalloc(mapsize, GFP_KERNEL);
+	if (!virtmap) {
+		pr_err("Failed to allocate EFI virtual memmap\n");
+		return -1;
+	}
+	virtmap_phys = virt_to_phys(virtmap);
+	virt_md = virtmap;
+
+	for_each_efi_memory_desc(&memmap, md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (remap_region(md, &virt_md))
+			++count;
+	}
+
+	efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table);
+	if (efi.systab)
+		set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+	local_irq_save(flags);
+	cpu_switch_mm(idmap_pg_dir, &init_mm);
+
+	/* Call SetVirtualAddressMap with the physical address of the map */
+	runtime = efi.systab->runtime;
+	efi.set_virtual_address_map = runtime->set_virtual_address_map;
+
+	status = efi.set_virtual_address_map(count * memmap.desc_size,
+					     memmap.desc_size,
+					     memmap.desc_version,
+					     (efi_memory_desc_t *)virtmap_phys);
+	cpu_set_reserved_ttbr0();
+	flush_tlb_all();
+	local_irq_restore(flags);
+
+	kfree(virtmap);
+
+	free_boot_services();
+
+	if (status != EFI_SUCCESS) {
+		pr_err("Failed to set EFI virtual address map! [%lx]\n",
+			status);
+		return -1;
+	}
+
+	/* Set up runtime services function pointers */
+	runtime = efi.systab->runtime;
+	efi.get_time = runtime->get_time;
+	efi.set_time = runtime->set_time;
+	efi.get_wakeup_time = runtime->get_wakeup_time;
+	efi.set_wakeup_time = runtime->set_wakeup_time;
+	efi.get_variable = runtime->get_variable;
+	efi.get_next_variable = runtime->get_next_variable;
+	efi.set_variable = runtime->set_variable;
+	efi.query_variable_info = runtime->query_variable_info;
+	efi.update_capsule = runtime->update_capsule;
+	efi.query_capsule_caps = runtime->query_capsule_caps;
+	efi.get_next_high_mono_count = runtime->get_next_high_mono_count;
+	efi.reset_system = runtime->reset_system;
+
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+	return 0;
+}
+early_initcall(arm64_enter_virtual_mode);
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
new file mode 100644
index 000000000000..b051871f2965
--- /dev/null
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -0,0 +1,218 @@
+/*
+ * arch/arm64/kernel/entry-ftrace.S
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+/*
+ * Gcc with -pg will put the following code in the beginning of each function:
+ *      mov x0, x30
+ *      bl _mcount
+ *	[function's body ...]
+ * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
+ * ftrace is enabled.
+ *
+ * Please note that x0 as an argument will not be used here because we can
+ * get lr(x30) of instrumented function at any time by winding up call stack
+ * as long as the kernel is compiled without -fomit-frame-pointer.
+ * (or CONFIG_FRAME_POINTER, this is forced on arm64)
+ *
+ * stack layout after mcount_enter in _mcount():
+ *
+ * current sp/fp =>  0:+-----+
+ * in _mcount()        | x29 | -> instrumented function's fp
+ *                     +-----+
+ *                     | x30 | -> _mcount()'s lr (= instrumented function's pc)
+ * old sp       => +16:+-----+
+ * when instrumented   |     |
+ * function calls      | ... |
+ * _mcount()           |     |
+ *                     |     |
+ * instrumented => +xx:+-----+
+ * function's fp       | x29 | -> parent's fp
+ *                     +-----+
+ *                     | x30 | -> instrumented function's lr (= parent's pc)
+ *                     +-----+
+ *                     | ... |
+ */
+
+	.macro mcount_enter
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+	.endm
+
+	.macro mcount_exit
+	ldp	x29, x30, [sp], #16
+	ret
+	.endm
+
+	.macro mcount_adjust_addr rd, rn
+	sub	\rd, \rn, #AARCH64_INSN_SIZE
+	.endm
+
+	/* for instrumented function's parent */
+	.macro mcount_get_parent_fp reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg]
+	.endm
+
+	/* for instrumented function */
+	.macro mcount_get_pc0 reg
+	mcount_adjust_addr	\reg, x30
+	.endm
+
+	.macro mcount_get_pc reg
+	ldr	\reg, [x29, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr_addr reg
+	ldr	\reg, [x29]
+	add	\reg, \reg, #8
+	.endm
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+/*
+ * void _mcount(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function makes calls, if enabled, to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(_mcount)
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	ldr	x0, =ftrace_trace_stop
+	ldr	x0, [x0]		// if ftrace_trace_stop
+	ret				//   return;
+#endif
+	mcount_enter
+
+	ldr	x0, =ftrace_trace_function
+	ldr	x2, [x0]
+	adr	x0, ftrace_stub
+	cmp	x0, x2			// if (ftrace_trace_function
+	b.eq	skip_ftrace_call	//     != ftrace_stub) {
+
+	mcount_get_pc	x0		//       function's pc
+	mcount_get_lr	x1		//       function's lr (= parent's pc)
+	blr	x2			//   (*ftrace_trace_function)(pc, lr);
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace_call:			//   return;
+	mcount_exit			// }
+#else
+	mcount_exit			//   return;
+					// }
+skip_ftrace_call:
+	ldr	x1, =ftrace_graph_return
+	ldr	x2, [x1]		//   if ((ftrace_graph_return
+	cmp	x0, x2			//        != ftrace_stub)
+	b.ne	ftrace_graph_caller
+
+	ldr	x1, =ftrace_graph_entry	//     || (ftrace_graph_entry
+	ldr	x2, [x1]		//        != ftrace_graph_entry_stub))
+	ldr	x0, =ftrace_graph_entry_stub
+	cmp	x0, x2
+	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
+
+	mcount_exit
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ENDPROC(_mcount)
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+/*
+ * _mcount() is used to build the kernel with -pg option, but all the branch
+ * instructions to _mcount() are replaced to NOP initially at kernel start up,
+ * and later on, NOP to branch to ftrace_caller() when enabled or branch to
+ * NOP when disabled per-function base.
+ */
+ENTRY(_mcount)
+	ret
+ENDPROC(_mcount)
+
+/*
+ * void ftrace_caller(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function is a counterpart of _mcount() in 'static' ftrace, and
+ * makes calls to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(ftrace_caller)
+	mcount_enter
+
+	mcount_get_pc0	x0		//     function's pc
+	mcount_get_lr	x1		//     function's lr
+
+	.global ftrace_call
+ftrace_call:				// tracer(pc, lr);
+	nop				// This will be replaced with "bl xxx"
+					// where xxx can be any kind of tracer.
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.global ftrace_graph_call
+ftrace_graph_call:			// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+	mcount_exit
+ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * void ftrace_graph_caller(void)
+ *
+ * Called from _mcount() or ftrace_caller() when function_graph tracer is
+ * selected.
+ * This function w/ prepare_ftrace_return() fakes link register's value on
+ * the call stack in order to intercept instrumented function's return path
+ * and run return_to_handler() later on its exit.
+ */
+ENTRY(ftrace_graph_caller)
+	mcount_get_lr_addr	  x0	//     pointer to function's saved lr
+	mcount_get_pc		  x1	//     function's pc
+	mcount_get_parent_fp	  x2	//     parent's fp
+	bl	prepare_ftrace_return	// prepare_ftrace_return(&lr, pc, fp)
+
+	mcount_exit
+ENDPROC(ftrace_graph_caller)
+
+/*
+ * void return_to_handler(void)
+ *
+ * Run ftrace_return_to_handler() before going back to parent.
+ * @fp is checked against the value passed by ftrace_graph_caller()
+ * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ */
+ENTRY(return_to_handler)
+	str	x0, [sp, #-16]!
+	mov	x0, x29			//     parent's fp
+	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
+	mov	x30, x0			// restore the original return address
+	ldr	x0, [sp], #16
+	ret
+END(return_to_handler)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 0aca56ac8a32..56ef569b2b62 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -275,7 +275,6 @@ el1_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:
@@ -646,8 +645,9 @@ el0_svc_naked:					// compat entry point
 	enable_irq
 
 	get_thread_info tsk
-	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall tracing
-	tbnz	x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls?
+	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
+	tst	x16, #_TIF_SYSCALL_WORK
+	b.ne	__sys_trace
 	adr	lr, ret_fast_syscall		// return address
 	cmp     scno, sc_nr                     // check upper syscall limit
 	b.hs	ni_sys
@@ -663,9 +663,8 @@ ENDPROC(el0_svc)
 	 * switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	x1, sp
-	mov	w0, #0				// trace entry
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_enter
 	adr	lr, __sys_trace_return		// return address
 	uxtw	scno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
@@ -680,9 +679,8 @@ __sys_trace:
 
 __sys_trace_return:
 	str	x0, [sp]			// save returned x0
-	mov	x1, sp
-	mov	w0, #1				// trace exit
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_exit
 	b	ret_to_user
 
 /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 2fa308e4a1fa..522df9c7f3a4 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -85,6 +86,66 @@ void fpsimd_flush_thread(void)
 	preempt_enable();
 }
 
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+	/* Avoid using the NEON in interrupt context */
+	BUG_ON(in_interrupt());
+	preempt_disable();
+
+	if (current->mm)
+		fpsimd_save_state(&current->thread.fpsimd_state);
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+	if (current->mm)
+		fpsimd_load_state(&current->thread.fpsimd_state);
+
+	preempt_enable();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
+#ifdef CONFIG_CPU_PM
+static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
+				  unsigned long cmd, void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		if (current->mm)
+			fpsimd_save_state(&current->thread.fpsimd_state);
+		break;
+	case CPU_PM_EXIT:
+		if (current->mm)
+			fpsimd_load_state(&current->thread.fpsimd_state);
+		break;
+	case CPU_PM_ENTER_FAILED:
+	default:
+		return NOTIFY_DONE;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_pm_notifier_block = {
+	.notifier_call = fpsimd_cpu_pm_notifier,
+};
+
+static void fpsimd_pm_init(void)
+{
+	cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
+}
+
+#else
+static inline void fpsimd_pm_init(void) { }
+#endif /* CONFIG_CPU_PM */
+
 /*
  * FP/SIMD support code initialisation.
  */
@@ -103,6 +164,8 @@ static int __init fpsimd_init(void)
 	else
 		elf_hwcap |= HWCAP_ASIMD;
 
+	fpsimd_pm_init();
+
 	return 0;
 }
 late_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
new file mode 100644
index 000000000000..649890a3ac4e
--- /dev/null
+++ b/arch/arm64/kernel/ftrace.c
@@ -0,0 +1,177 @@
+/*
+ * arch/arm64/kernel/ftrace.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/swab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Replace a single instruction, which may be a branch or NOP.
+ * If @validate == true, a replaced instruction is checked against 'old'.
+ */
+static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
+			      bool validate)
+{
+	u32 replaced;
+
+	/*
+	 * Note:
+	 * Due to modules and __init, code can disappear and change,
+	 * we need to protect against faulting as well as code changing.
+	 * We do this by aarch64_insn_*() which use the probe_kernel_*().
+	 *
+	 * No lock is held here because all the modifications are run
+	 * through stop_machine().
+	 */
+	if (validate) {
+		if (aarch64_insn_read((void *)pc, &replaced))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
+	if (aarch64_insn_patch_text_nosync((void *)pc, new))
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * Replace tracer function in ftrace_caller()
+ */
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long pc;
+	u32 new;
+
+	pc = (unsigned long)&ftrace_call;
+	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true);
+
+	return ftrace_modify_code(pc, 0, new, false);
+}
+
+/*
+ * Turn on the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_branch_imm(pc, addr, true);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * Turn off the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, addr, true);
+	new = aarch64_insn_gen_nop();
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	*(unsigned long *)data = 0;
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * function_graph tracer expects ftrace_return_to_handler() to be called
+ * on the way back to parent. For this purpose, this function is called
+ * in _mcount() or ftrace_caller() to replace return address (*parent) on
+ * the call stack to return_to_handler.
+ *
+ * Note that @frame_pointer is used only for sanity check later.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * Note:
+	 * No protection against faulting at *parent, which may be seen
+	 * on other archs. It's unlikely on AArch64.
+	 */
+	old = *parent;
+	*parent = return_hooker;
+
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		*parent = old;
+		return;
+	}
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer);
+	if (err == -EBUSY) {
+		*parent = old;
+		return;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
+ * depending on @enable.
+ */
+static int ftrace_modify_graph_caller(bool enable)
+{
+	unsigned long pc = (unsigned long)&ftrace_graph_call;
+	u32 branch, nop;
+
+	branch = aarch64_insn_gen_branch_imm(pc,
+			(unsigned long)ftrace_graph_caller, false);
+	nop = aarch64_insn_gen_nop();
+
+	if (enable)
+		return ftrace_modify_code(pc, nop, branch, true);
+	else
+		return ftrace_modify_code(pc, branch, nop, true);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b7f76fff32a6..6254f4a28eed 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -22,6 +22,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
@@ -100,8 +101,18 @@
 	/*
 	 * DO NOT MODIFY. Image header expected by Linux boot-loaders.
 	 */
+#ifdef CONFIG_EFI
+efi_head:
+	/*
+	 * This add instruction has no meaningful effect except that
+	 * its opcode forms the magic "MZ" signature required by UEFI.
+	 */
+	add	x13, x18, #0x16
+	b	stext
+#else
 	b	stext				// branch to kernel start, magic
 	.long	0				// reserved
+#endif
 	.quad	TEXT_OFFSET			// Image load offset from start of RAM
 	.quad	0				// reserved
 	.quad	0				// reserved
@@ -112,7 +123,109 @@
 	.byte	0x52
 	.byte	0x4d
 	.byte	0x64
+#ifdef CONFIG_EFI
+	.long	pe_header - efi_head		// Offset to the PE header.
+#else
 	.word	0				// reserved
+#endif
+
+#ifdef CONFIG_EFI
+	.align 3
+pe_header:
+	.ascii	"PE"
+	.short 	0
+coff_header:
+	.short	0xaa64				// AArch64
+	.short	2				// nr_sections
+	.long	0 				// TimeDateStamp
+	.long	0				// PointerToSymbolTable
+	.long	1				// NumberOfSymbols
+	.short	section_table - optional_header	// SizeOfOptionalHeader
+	.short	0x206				// Characteristics.
+						// IMAGE_FILE_DEBUG_STRIPPED |
+						// IMAGE_FILE_EXECUTABLE_IMAGE |
+						// IMAGE_FILE_LINE_NUMS_STRIPPED
+optional_header:
+	.short	0x20b				// PE32+ format
+	.byte	0x02				// MajorLinkerVersion
+	.byte	0x14				// MinorLinkerVersion
+	.long	_edata - stext			// SizeOfCode
+	.long	0				// SizeOfInitializedData
+	.long	0				// SizeOfUninitializedData
+	.long	efi_stub_entry - efi_head	// AddressOfEntryPoint
+	.long	stext - efi_head		// BaseOfCode
+
+extra_header_fields:
+	.quad	0				// ImageBase
+	.long	0x20				// SectionAlignment
+	.long	0x8				// FileAlignment
+	.short	0				// MajorOperatingSystemVersion
+	.short	0				// MinorOperatingSystemVersion
+	.short	0				// MajorImageVersion
+	.short	0				// MinorImageVersion
+	.short	0				// MajorSubsystemVersion
+	.short	0				// MinorSubsystemVersion
+	.long	0				// Win32VersionValue
+
+	.long	_edata - efi_head		// SizeOfImage
+
+	// Everything before the kernel image is considered part of the header
+	.long	stext - efi_head		// SizeOfHeaders
+	.long	0				// CheckSum
+	.short	0xa				// Subsystem (EFI application)
+	.short	0				// DllCharacteristics
+	.quad	0				// SizeOfStackReserve
+	.quad	0				// SizeOfStackCommit
+	.quad	0				// SizeOfHeapReserve
+	.quad	0				// SizeOfHeapCommit
+	.long	0				// LoaderFlags
+	.long	0x6				// NumberOfRvaAndSizes
+
+	.quad	0				// ExportTable
+	.quad	0				// ImportTable
+	.quad	0				// ResourceTable
+	.quad	0				// ExceptionTable
+	.quad	0				// CertificationTable
+	.quad	0				// BaseRelocationTable
+
+	// Section table
+section_table:
+
+	/*
+	 * The EFI application loader requires a relocation section
+	 * because EFI applications must be relocatable.  This is a
+	 * dummy section as far as we are concerned.
+	 */
+	.ascii	".reloc"
+	.byte	0
+	.byte	0			// end of 0 padding of section name
+	.long	0
+	.long	0
+	.long	0			// SizeOfRawData
+	.long	0			// PointerToRawData
+	.long	0			// PointerToRelocations
+	.long	0			// PointerToLineNumbers
+	.short	0			// NumberOfRelocations
+	.short	0			// NumberOfLineNumbers
+	.long	0x42100040		// Characteristics (section flags)
+
+
+	.ascii	".text"
+	.byte	0
+	.byte	0
+	.byte	0        		// end of 0 padding of section name
+	.long	_edata - stext		// VirtualSize
+	.long	stext - efi_head	// VirtualAddress
+	.long	_edata - stext		// SizeOfRawData
+	.long	stext - efi_head	// PointerToRawData
+
+	.long	0		// PointerToRelocations (0 for executables)
+	.long	0		// PointerToLineNumbers (0 for executables)
+	.short	0		// NumberOfRelocations  (0 for executables)
+	.short	0		// NumberOfLineNumbers  (0 for executables)
+	.long	0xe0500020	// Characteristics (section flags)
+	.align 5
+#endif
 
 ENTRY(stext)
 	mov	x21, x0				// x21=FDT
@@ -152,12 +265,22 @@ ENTRY(el2_setup)
 	mrs	x0, CurrentEL
 	cmp	x0, #PSR_MODE_EL2t
 	ccmp	x0, #PSR_MODE_EL2h, #0x4, ne
-	b.eq	1f
+	b.ne	1f
+	mrs	x0, sctlr_el2
+CPU_BE(	orr	x0, x0, #(1 << 25)	)	// Set the EE bit for EL2
+CPU_LE(	bic	x0, x0, #(1 << 25)	)	// Clear the EE bit for EL2
+	msr	sctlr_el2, x0
+	b	2f
+1:	mrs	x0, sctlr_el1
+CPU_BE(	orr	x0, x0, #(3 << 24)	)	// Set the EE and E0E bits for EL1
+CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
+	msr	sctlr_el1, x0
 	mov	w20, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
+	isb
 	ret
 
 	/* Hyp configuration. */
-1:	mov	x0, #(1 << 31)			// 64-bit EL1
+2:	mov	x0, #(1 << 31)			// 64-bit EL1
 	msr	hcr_el2, x0
 
 	/* Generic timers. */
@@ -166,6 +289,23 @@ ENTRY(el2_setup)
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 
+#ifdef CONFIG_ARM_GIC_V3
+	/* GICv3 system register access */
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #24, #4
+	cmp	x0, #1
+	b.ne	3f
+
+	mrs_s	x0, ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+
+3:
+#endif
+
 	/* Populate ID registers. */
 	mrs	x0, midr_el1
 	mrs	x1, mpidr_el1
@@ -174,7 +314,8 @@ ENTRY(el2_setup)
 
 	/* sctlr_el1 */
 	mov	x0, #0x0800			// Set/clear RES{1,0} bits
-	movk	x0, #0x30d0, lsl #16
+CPU_BE(	movk	x0, #0x33d0, lsl #16	)	// Set EE and E0E on BE systems
+CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	msr	sctlr_el1, x0
 
 	/* Coprocessor traps. */
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 5ab825c59db9..6de3460ede4c 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,13 +20,14 @@
 
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
+#include <linux/compat.h>
+#include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/smp.h>
 
-#include <asm/compat.h>
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
@@ -169,15 +170,68 @@ static enum debug_el debug_exception_level(int privilege)
 	}
 }
 
-/*
- * Install a perf counter breakpoint.
+enum hw_breakpoint_ops {
+	HW_BREAKPOINT_INSTALL,
+	HW_BREAKPOINT_UNINSTALL,
+	HW_BREAKPOINT_RESTORE
+};
+
+/**
+ * hw_breakpoint_slot_setup - Find and setup a perf slot according to
+ *			      operations
+ *
+ * @slots: pointer to array of slots
+ * @max_slots: max number of slots
+ * @bp: perf_event to setup
+ * @ops: operation to be carried out on the slot
+ *
+ * Return:
+ *	slot index on success
+ *	-ENOSPC if no slot is available/matches
+ *	-EINVAL on wrong operations parameter
  */
-int arch_install_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots,
+				    struct perf_event *bp,
+				    enum hw_breakpoint_ops ops)
+{
+	int i;
+	struct perf_event **slot;
+
+	for (i = 0; i < max_slots; ++i) {
+		slot = &slots[i];
+		switch (ops) {
+		case HW_BREAKPOINT_INSTALL:
+			if (!*slot) {
+				*slot = bp;
+				return i;
+			}
+			break;
+		case HW_BREAKPOINT_UNINSTALL:
+			if (*slot == bp) {
+				*slot = NULL;
+				return i;
+			}
+			break;
+		case HW_BREAKPOINT_RESTORE:
+			if (*slot == bp)
+				return i;
+			break;
+		default:
+			pr_warn_once("Unhandled hw breakpoint ops %d\n", ops);
+			return -EINVAL;
+		}
+	}
+	return -ENOSPC;
+}
+
+static int hw_breakpoint_control(struct perf_event *bp,
+				 enum hw_breakpoint_ops ops)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot, **slots;
+	struct perf_event **slots;
 	struct debug_info *debug_info = &current->thread.debug;
 	int i, max_slots, ctrl_reg, val_reg, reg_enable;
+	enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege);
 	u32 ctrl;
 
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
@@ -196,67 +250,54 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		reg_enable = !debug_info->wps_disabled;
 	}
 
-	for (i = 0; i < max_slots; ++i) {
-		slot = &slots[i];
-
-		if (!*slot) {
-			*slot = bp;
-			break;
-		}
-	}
-
-	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
-		return -ENOSPC;
+	i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops);
 
-	/* Ensure debug monitors are enabled at the correct exception level.  */
-	enable_debug_monitors(debug_exception_level(info->ctrl.privilege));
+	if (WARN_ONCE(i < 0, "Can't find any breakpoint slot"))
+		return i;
 
-	/* Setup the address register. */
-	write_wb_reg(val_reg, i, info->address);
+	switch (ops) {
+	case HW_BREAKPOINT_INSTALL:
+		/*
+		 * Ensure debug monitors are enabled at the correct exception
+		 * level.
+		 */
+		enable_debug_monitors(dbg_el);
+		/* Fall through */
+	case HW_BREAKPOINT_RESTORE:
+		/* Setup the address register. */
+		write_wb_reg(val_reg, i, info->address);
+
+		/* Setup the control register. */
+		ctrl = encode_ctrl_reg(info->ctrl);
+		write_wb_reg(ctrl_reg, i,
+			     reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
+		break;
+	case HW_BREAKPOINT_UNINSTALL:
+		/* Reset the control register. */
+		write_wb_reg(ctrl_reg, i, 0);
 
-	/* Setup the control register. */
-	ctrl = encode_ctrl_reg(info->ctrl);
-	write_wb_reg(ctrl_reg, i, reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
+		/*
+		 * Release the debug monitors for the correct exception
+		 * level.
+		 */
+		disable_debug_monitors(dbg_el);
+		break;
+	}
 
 	return 0;
 }
 
-void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+/*
+ * Install a perf counter breakpoint.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot, **slots;
-	int i, max_slots, base;
-
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
-		/* Breakpoint */
-		base = AARCH64_DBG_REG_BCR;
-		slots = __get_cpu_var(bp_on_reg);
-		max_slots = core_num_brps;
-	} else {
-		/* Watchpoint */
-		base = AARCH64_DBG_REG_WCR;
-		slots = __get_cpu_var(wp_on_reg);
-		max_slots = core_num_wrps;
-	}
-
-	/* Remove the breakpoint. */
-	for (i = 0; i < max_slots; ++i) {
-		slot = &slots[i];
-
-		if (*slot == bp) {
-			*slot = NULL;
-			break;
-		}
-	}
-
-	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
-		return;
-
-	/* Reset the control register. */
-	write_wb_reg(base, i, 0);
+	return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL);
+}
 
-	/* Release the debug monitors for the correct exception level.  */
-	disable_debug_monitors(debug_exception_level(info->ctrl.privilege));
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+	hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL);
 }
 
 static int get_hbp_len(u8 hbp_len)
@@ -806,18 +847,36 @@ void hw_breakpoint_thread_switch(struct task_struct *next)
 /*
  * CPU initialisation.
  */
-static void reset_ctrl_regs(void *unused)
+static void hw_breakpoint_reset(void *unused)
 {
 	int i;
-
-	for (i = 0; i < core_num_brps; ++i) {
-		write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
-		write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+	struct perf_event **slots;
+	/*
+	 * When a CPU goes through cold-boot, it does not have any installed
+	 * slot, so it is safe to share the same function for restoring and
+	 * resetting breakpoints; when a CPU is hotplugged in, it goes
+	 * through the slots, which are all empty, hence it just resets control
+	 * and value for debug registers.
+	 * When this function is triggered on warm-boot through a CPU PM
+	 * notifier some slots might be initialized; if so they are
+	 * reprogrammed according to the debug slots content.
+	 */
+	for (slots = __get_cpu_var(bp_on_reg), i = 0; i < core_num_brps; ++i) {
+		if (slots[i]) {
+			hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+		} else {
+			write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
+			write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+		}
 	}
 
-	for (i = 0; i < core_num_wrps; ++i) {
-		write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
-		write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+	for (slots = __get_cpu_var(wp_on_reg), i = 0; i < core_num_wrps; ++i) {
+		if (slots[i]) {
+			hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+		} else {
+			write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
+			write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+		}
 	}
 }
 
@@ -827,7 +886,7 @@ static int __cpuinit hw_breakpoint_reset_notify(struct notifier_block *self,
 {
 	int cpu = (long)hcpu;
 	if (action == CPU_ONLINE)
-		smp_call_function_single(cpu, reset_ctrl_regs, NULL, 1);
+		smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1);
 	return NOTIFY_OK;
 }
 
@@ -835,6 +894,14 @@ static struct notifier_block __cpuinitdata hw_breakpoint_reset_nb = {
 	.notifier_call = hw_breakpoint_reset_notify,
 };
 
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
+#else
+static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+{
+}
+#endif
+
 /*
  * One-time initialisation.
  */
@@ -850,8 +917,8 @@ static int __init arch_hw_breakpoint_init(void)
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	smp_call_function(reset_ctrl_regs, NULL, 1);
-	reset_ctrl_regs(NULL);
+	smp_call_function(hw_breakpoint_reset, NULL, 1);
+	hw_breakpoint_reset(NULL);
 
 	/* Register debug fault handlers. */
 	hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
@@ -861,6 +928,8 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Register hotplug notifier. */
 	register_cpu_notifier(&hw_breakpoint_reset_nb);
+	/* Register cpu_suspend hw breakpoint restore hook */
+	cpu_suspend_set_dbg_restorer(hw_breakpoint_reset);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 0959611d9ff1..a272f335c289 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -19,6 +19,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
new file mode 100644
index 000000000000..92f36835486b
--- /dev/null
+++ b/arch/arm64/kernel/insn.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/stop_machine.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/insn.h>
+
+static int aarch64_insn_encoding_class[] = {
+	AARCH64_INSN_CLS_UNKNOWN,
+	AARCH64_INSN_CLS_UNKNOWN,
+	AARCH64_INSN_CLS_UNKNOWN,
+	AARCH64_INSN_CLS_UNKNOWN,
+	AARCH64_INSN_CLS_LDST,
+	AARCH64_INSN_CLS_DP_REG,
+	AARCH64_INSN_CLS_LDST,
+	AARCH64_INSN_CLS_DP_FPSIMD,
+	AARCH64_INSN_CLS_DP_IMM,
+	AARCH64_INSN_CLS_DP_IMM,
+	AARCH64_INSN_CLS_BR_SYS,
+	AARCH64_INSN_CLS_BR_SYS,
+	AARCH64_INSN_CLS_LDST,
+	AARCH64_INSN_CLS_DP_REG,
+	AARCH64_INSN_CLS_LDST,
+	AARCH64_INSN_CLS_DP_FPSIMD,
+};
+
+enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn)
+{
+	return aarch64_insn_encoding_class[(insn >> 25) & 0xf];
+}
+
+/* NOP is an alias of HINT */
+bool __kprobes aarch64_insn_is_nop(u32 insn)
+{
+	if (!aarch64_insn_is_hint(insn))
+		return false;
+
+	switch (insn & 0xFE0) {
+	case AARCH64_INSN_HINT_YIELD:
+	case AARCH64_INSN_HINT_WFE:
+	case AARCH64_INSN_HINT_WFI:
+	case AARCH64_INSN_HINT_SEV:
+	case AARCH64_INSN_HINT_SEVL:
+		return false;
+	default:
+		return true;
+	}
+}
+
+/*
+ * In ARMv8-A, A64 instructions have a fixed length of 32 bits and are always
+ * little-endian.
+ */
+int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
+{
+	int ret;
+	u32 val;
+
+	ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
+	if (!ret)
+		*insnp = le32_to_cpu(val);
+
+	return ret;
+}
+
+int __kprobes aarch64_insn_write(void *addr, u32 insn)
+{
+	insn = cpu_to_le32(insn);
+	return probe_kernel_write(addr, &insn, AARCH64_INSN_SIZE);
+}
+
+static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
+{
+	if (aarch64_get_insn_class(insn) != AARCH64_INSN_CLS_BR_SYS)
+		return false;
+
+	return	aarch64_insn_is_b(insn) ||
+		aarch64_insn_is_bl(insn) ||
+		aarch64_insn_is_svc(insn) ||
+		aarch64_insn_is_hvc(insn) ||
+		aarch64_insn_is_smc(insn) ||
+		aarch64_insn_is_brk(insn) ||
+		aarch64_insn_is_nop(insn);
+}
+
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section B2.6.5 "Concurrent modification and execution of instructions":
+ * Concurrent modification and execution of instructions can lead to the
+ * resulting instruction performing any behavior that can be achieved by
+ * executing any sequence of instructions that can be executed from the
+ * same Exception level, except where the instruction before modification
+ * and the instruction after modification is a B, BL, NOP, BKPT, SVC, HVC,
+ * or SMC instruction.
+ */
+bool __kprobes aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn)
+{
+	return __aarch64_insn_hotpatch_safe(old_insn) &&
+	       __aarch64_insn_hotpatch_safe(new_insn);
+}
+
+int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
+{
+	u32 *tp = addr;
+	int ret;
+
+	/* A64 instructions must be word aligned */
+	if ((uintptr_t)tp & 0x3)
+		return -EINVAL;
+
+	ret = aarch64_insn_write(tp, insn);
+	if (ret == 0)
+		flush_icache_range((uintptr_t)tp,
+				   (uintptr_t)tp + AARCH64_INSN_SIZE);
+
+	return ret;
+}
+
+struct aarch64_insn_patch {
+	void		**text_addrs;
+	u32		*new_insns;
+	int		insn_cnt;
+	atomic_t	cpu_count;
+};
+
+static int __kprobes aarch64_insn_patch_text_cb(void *arg)
+{
+	int i, ret = 0;
+	struct aarch64_insn_patch *pp = arg;
+
+	/* The first CPU becomes master */
+	if (atomic_inc_return(&pp->cpu_count) == 1) {
+		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
+			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
+							     pp->new_insns[i]);
+		/*
+		 * aarch64_insn_patch_text_nosync() calls flush_icache_range(),
+		 * which ends with "dsb; isb" pair guaranteeing global
+		 * visibility.
+		 */
+		atomic_set(&pp->cpu_count, -1);
+	} else {
+		while (atomic_read(&pp->cpu_count) != -1)
+			cpu_relax();
+		isb();
+	}
+
+	return ret;
+}
+
+int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
+{
+	struct aarch64_insn_patch patch = {
+		.text_addrs = addrs,
+		.new_insns = insns,
+		.insn_cnt = cnt,
+		.cpu_count = ATOMIC_INIT(0),
+	};
+
+	if (cnt <= 0)
+		return -EINVAL;
+
+	return stop_machine(aarch64_insn_patch_text_cb, &patch,
+			    cpu_online_mask);
+}
+
+int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
+{
+	int ret;
+	u32 insn;
+
+	/* Unsafe to patch multiple instructions without synchronizaiton */
+	if (cnt == 1) {
+		ret = aarch64_insn_read(addrs[0], &insn);
+		if (ret)
+			return ret;
+
+		if (aarch64_insn_hotpatch_safe(insn, insns[0])) {
+			/*
+			 * ARMv8 architecture doesn't guarantee all CPUs see
+			 * the new instruction after returning from function
+			 * aarch64_insn_patch_text_nosync(). So send IPIs to
+			 * all other CPUs to achieve instruction
+			 * synchronization.
+			 */
+			ret = aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
+			kick_all_cpus_sync();
+			return ret;
+		}
+	}
+
+	return aarch64_insn_patch_text_sync(addrs, insns, cnt);
+}
+
+u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+				  u32 insn, u64 imm)
+{
+	u32 immlo, immhi, lomask, himask, mask;
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_IMM_ADR:
+		lomask = 0x3;
+		himask = 0x7ffff;
+		immlo = imm & lomask;
+		imm >>= 2;
+		immhi = imm & himask;
+		imm = (immlo << 24) | (immhi);
+		mask = (lomask << 24) | (himask);
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_26:
+		mask = BIT(26) - 1;
+		shift = 0;
+		break;
+	case AARCH64_INSN_IMM_19:
+		mask = BIT(19) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_16:
+		mask = BIT(16) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_14:
+		mask = BIT(14) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_12:
+		mask = BIT(12) - 1;
+		shift = 10;
+		break;
+	case AARCH64_INSN_IMM_9:
+		mask = BIT(9) - 1;
+		shift = 12;
+		break;
+	default:
+		pr_err("aarch64_insn_encode_immediate: unknown immediate encoding %d\n",
+			type);
+		return 0;
+	}
+
+	/* Update the immediate field. */
+	insn &= ~(mask << shift);
+	insn |= (imm & mask) << shift;
+
+	return insn;
+}
+
+u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+					  enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+	long offset;
+
+	/*
+	 * PC: A 64-bit Program Counter holding the address of the current
+	 * instruction. A64 instructions must be word-aligned.
+	 */
+	BUG_ON((pc & 0x3) || (addr & 0x3));
+
+	/*
+	 * B/BL support [-128M, 128M) offset
+	 * ARM64 virtual address arrangement guarantees all kernel and module
+	 * texts are within +/-128M.
+	 */
+	offset = ((long)addr - (long)pc);
+	BUG_ON(offset < -SZ_128M || offset >= SZ_128M);
+
+	if (type == AARCH64_INSN_BRANCH_LINK)
+		insn = aarch64_insn_get_bl_value();
+	else
+		insn = aarch64_insn_get_b_value();
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+					     offset >> 2);
+}
+
+u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_op op)
+{
+	return aarch64_insn_get_hint_value() | op;
+}
+
+u32 __kprobes aarch64_insn_gen_nop(void)
+{
+	return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
+}
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
new file mode 100644
index 000000000000..263a166291fb
--- /dev/null
+++ b/arch/arm64/kernel/jump_label.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Based on arch/arm/kernel/jump_label.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <asm/insn.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+					enum jump_label_type type,
+					bool is_static)
+{
+	void *addr = (void *)entry->code;
+	u32 insn;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		insn = aarch64_insn_gen_branch_imm(entry->code,
+						   entry->target,
+						   AARCH64_INSN_BRANCH_NOLINK);
+	} else {
+		insn = aarch64_insn_gen_nop();
+	}
+
+	if (is_static)
+		aarch64_insn_patch_text_nosync(addr, insn);
+	else
+		aarch64_insn_patch_text(&addr, &insn, 1);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, true);
+}
+
+#endif	/* HAVE_JUMP_LABEL */
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 87542397b3ac..7787208e8cc6 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -27,6 +27,9 @@
  *
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
+
+#include <asm/unistd32.h>
+
 	.align	5
 	.globl	__kuser_helper_start
 __kuser_helper_start:
@@ -74,3 +77,42 @@ __kuser_helper_version:			// 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
+
+/*
+ * AArch32 sigreturn code
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index ca0e3d55da99..df08a6e0287d 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -25,6 +25,10 @@
 #include <linux/mm.h>
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
+#include <asm/insn.h>
+
+#define	AARCH64_INSN_IMM_MOVNZ		AARCH64_INSN_IMM_MAX
+#define	AARCH64_INSN_IMM_MOVK		AARCH64_INSN_IMM_16
 
 void *module_alloc(unsigned long size)
 {
@@ -94,25 +98,18 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len)
 	return 0;
 }
 
-enum aarch64_imm_type {
-	INSN_IMM_MOVNZ,
-	INSN_IMM_MOVK,
-	INSN_IMM_ADR,
-	INSN_IMM_26,
-	INSN_IMM_19,
-	INSN_IMM_16,
-	INSN_IMM_14,
-	INSN_IMM_12,
-	INSN_IMM_9,
-};
-
-static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm)
+static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
+			   int lsb, enum aarch64_insn_imm_type imm_type)
 {
-	u32 immlo, immhi, lomask, himask, mask;
-	int shift;
+	u64 imm, limit = 0;
+	s64 sval;
+	u32 insn = le32_to_cpu(*(u32 *)place);
+
+	sval = do_reloc(op, place, val);
+	sval >>= lsb;
+	imm = sval & 0xffff;
 
-	switch (type) {
-	case INSN_IMM_MOVNZ:
+	if (imm_type == AARCH64_INSN_IMM_MOVNZ) {
 		/*
 		 * For signed MOVW relocations, we have to manipulate the
 		 * instruction encoding depending on whether or not the
@@ -131,70 +128,12 @@ static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm)
 			 */
 			imm = ~imm;
 		}
-	case INSN_IMM_MOVK:
-		mask = BIT(16) - 1;
-		shift = 5;
-		break;
-	case INSN_IMM_ADR:
-		lomask = 0x3;
-		himask = 0x7ffff;
-		immlo = imm & lomask;
-		imm >>= 2;
-		immhi = imm & himask;
-		imm = (immlo << 24) | (immhi);
-		mask = (lomask << 24) | (himask);
-		shift = 5;
-		break;
-	case INSN_IMM_26:
-		mask = BIT(26) - 1;
-		shift = 0;
-		break;
-	case INSN_IMM_19:
-		mask = BIT(19) - 1;
-		shift = 5;
-		break;
-	case INSN_IMM_16:
-		mask = BIT(16) - 1;
-		shift = 5;
-		break;
-	case INSN_IMM_14:
-		mask = BIT(14) - 1;
-		shift = 5;
-		break;
-	case INSN_IMM_12:
-		mask = BIT(12) - 1;
-		shift = 10;
-		break;
-	case INSN_IMM_9:
-		mask = BIT(9) - 1;
-		shift = 12;
-		break;
-	default:
-		pr_err("encode_insn_immediate: unknown immediate encoding %d\n",
-			type);
-		return 0;
+		imm_type = AARCH64_INSN_IMM_MOVK;
 	}
 
-	/* Update the immediate field. */
-	insn &= ~(mask << shift);
-	insn |= (imm & mask) << shift;
-
-	return insn;
-}
-
-static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
-			   int lsb, enum aarch64_imm_type imm_type)
-{
-	u64 imm, limit = 0;
-	s64 sval;
-	u32 insn = *(u32 *)place;
-
-	sval = do_reloc(op, place, val);
-	sval >>= lsb;
-	imm = sval & 0xffff;
-
 	/* Update the instruction with the new encoding. */
-	*(u32 *)place = encode_insn_immediate(imm_type, insn, imm);
+	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+	*(u32 *)place = cpu_to_le32(insn);
 
 	/* Shift out the immediate field. */
 	sval >>= 16;
@@ -203,9 +142,9 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 	 * For unsigned immediates, the overflow check is straightforward.
 	 * For signed immediates, the sign bit is actually the bit past the
 	 * most significant bit of the field.
-	 * The INSN_IMM_16 immediate type is unsigned.
+	 * The AARCH64_INSN_IMM_16 immediate type is unsigned.
 	 */
-	if (imm_type != INSN_IMM_16) {
+	if (imm_type != AARCH64_INSN_IMM_16) {
 		sval++;
 		limit++;
 	}
@@ -218,11 +157,11 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 }
 
 static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
-			  int lsb, int len, enum aarch64_imm_type imm_type)
+			  int lsb, int len, enum aarch64_insn_imm_type imm_type)
 {
 	u64 imm, imm_mask;
 	s64 sval;
-	u32 insn = *(u32 *)place;
+	u32 insn = le32_to_cpu(*(u32 *)place);
 
 	/* Calculate the relocation value. */
 	sval = do_reloc(op, place, val);
@@ -233,7 +172,8 @@ static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
 	imm = sval & imm_mask;
 
 	/* Update the instruction's immediate field. */
-	*(u32 *)place = encode_insn_immediate(imm_type, insn, imm);
+	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+	*(u32 *)place = cpu_to_le32(insn);
 
 	/*
 	 * Extract the upper value bits (including the sign bit) and
@@ -315,125 +255,125 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      INSN_IMM_16);
+					      AARCH64_INSN_IMM_16);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      INSN_IMM_16);
+					      AARCH64_INSN_IMM_16);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      INSN_IMM_16);
+					      AARCH64_INSN_IMM_16);
 			break;
 		case R_AARCH64_MOVW_UABS_G3:
 			/* We're using the top bits so we can't overflow. */
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
-					      INSN_IMM_16);
+					      AARCH64_INSN_IMM_16);
 			break;
 		case R_AARCH64_MOVW_SABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_SABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_SABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G0_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVK);
 			break;
 		case R_AARCH64_MOVW_PREL_G0:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G1_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVK);
 			break;
 		case R_AARCH64_MOVW_PREL_G1:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G2_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVK);
 			break;
 		case R_AARCH64_MOVW_PREL_G2:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G3:
 			/* We're using the top bits so we can't overflow. */
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 48,
-					      INSN_IMM_MOVNZ);
+					      AARCH64_INSN_IMM_MOVNZ);
 			break;
 
 		/* Immediate instruction relocations. */
 		case R_AARCH64_LD_PREL_LO19:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
-					     INSN_IMM_19);
+					     AARCH64_INSN_IMM_19);
 			break;
 		case R_AARCH64_ADR_PREL_LO21:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
-					     INSN_IMM_ADR);
+					     AARCH64_INSN_IMM_ADR);
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
-					     INSN_IMM_ADR);
+					     AARCH64_INSN_IMM_ADR);
 			break;
 		case R_AARCH64_ADD_ABS_LO12_NC:
 		case R_AARCH64_LDST8_ABS_LO12_NC:
 			overflow_check = false;
 			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 0, 12,
-					     INSN_IMM_12);
+					     AARCH64_INSN_IMM_12);
 			break;
 		case R_AARCH64_LDST16_ABS_LO12_NC:
 			overflow_check = false;
 			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 1, 11,
-					     INSN_IMM_12);
+					     AARCH64_INSN_IMM_12);
 			break;
 		case R_AARCH64_LDST32_ABS_LO12_NC:
 			overflow_check = false;
 			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 2, 10,
-					     INSN_IMM_12);
+					     AARCH64_INSN_IMM_12);
 			break;
 		case R_AARCH64_LDST64_ABS_LO12_NC:
 			overflow_check = false;
 			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 3, 9,
-					     INSN_IMM_12);
+					     AARCH64_INSN_IMM_12);
 			break;
 		case R_AARCH64_LDST128_ABS_LO12_NC:
 			overflow_check = false;
 			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 4, 8,
-					     INSN_IMM_12);
+					     AARCH64_INSN_IMM_12);
 			break;
 		case R_AARCH64_TSTBR14:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 14,
-					     INSN_IMM_14);
+					     AARCH64_INSN_IMM_14);
 			break;
 		case R_AARCH64_CONDBR19:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
-					     INSN_IMM_19);
+					     AARCH64_INSN_IMM_19);
 			break;
 		case R_AARCH64_JUMP26:
 		case R_AARCH64_CALL26:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
-					     INSN_IMM_26);
+					     AARCH64_INSN_IMM_26);
 			break;
 
 		default:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cea1594ff933..dfcd8fadde3c 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -22,6 +22,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/perf_event.h>
@@ -363,26 +364,53 @@ validate_group(struct perf_event *event)
 }
 
 static void
+armpmu_disable_percpu_irq(void *data)
+{
+	unsigned int irq = *(unsigned int *)data;
+	disable_percpu_irq(irq);
+}
+
+static void
 armpmu_release_hardware(struct arm_pmu *armpmu)
 {
-	int i, irq, irqs;
+	int irq;
+	unsigned int i, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (!irqs)
+		return;
 
-	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
-			continue;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, armpmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq <= 0)
+		return;
+
+	if (irq_is_percpu(irq)) {
+		on_each_cpu(armpmu_disable_percpu_irq, &irq, 1);
+		free_percpu_irq(irq, &cpu_hw_events);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq > 0)
+				free_irq(irq, armpmu);
+		}
 	}
 }
 
+static void
+armpmu_enable_percpu_irq(void *data)
+{
+	unsigned int irq = *(unsigned int *)data;
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+}
+
 static int
 armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
-	int i, err, irq, irqs;
+	int err, irq;
+	unsigned int i, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
 	if (!pmu_device) {
@@ -391,39 +419,59 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 	}
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
-	if (irqs < 1) {
+	if (!irqs) {
 		pr_err("no irqs for PMUs defined\n");
 		return -ENODEV;
 	}
 
-	for (i = 0; i < irqs; ++i) {
-		err = 0;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq < 0)
-			continue;
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq <= 0) {
+		pr_err("failed to get valid irq for PMU device\n");
+		return -ENODEV;
+	}
 
-		/*
-		 * If we have a single PMU interrupt that we can't shift,
-		 * assume that we're running on a uniprocessor machine and
-		 * continue. Otherwise, continue without this interrupt.
-		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
-			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-				    irq, i);
-			continue;
-		}
+	if (irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, armpmu->handle_irq,
+				"arm-pmu", &cpu_hw_events);
 
-		err = request_irq(irq, armpmu->handle_irq,
-				  IRQF_NOBALANCING,
-				  "arm-pmu", armpmu);
 		if (err) {
-			pr_err("unable to request IRQ%d for ARM PMU counters\n",
-				irq);
+			pr_err("unable to request percpu IRQ%d for ARM PMU counters\n",
+					irq);
 			armpmu_release_hardware(armpmu);
 			return err;
 		}
 
-		cpumask_set_cpu(i, &armpmu->active_irqs);
+		on_each_cpu(armpmu_enable_percpu_irq, &irq, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq <= 0)
+				continue;
+
+			/*
+			 * If we have a single PMU interrupt that we can't shift,
+			 * assume that we're running on a uniprocessor machine and
+			 * continue. Otherwise, continue without this interrupt.
+			 */
+			if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+				pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+						irq, i);
+				continue;
+			}
+
+			err = request_irq(irq, armpmu->handle_irq,
+					IRQF_NOBALANCING,
+					"arm-pmu", armpmu);
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+						irq);
+				armpmu_release_hardware(armpmu);
+				return err;
+			}
+
+			cpumask_set_cpu(i, &armpmu->active_irqs);
+		}
 	}
 
 	return 0;
@@ -1299,8 +1347,8 @@ early_initcall(init_hw_perf_events);
  * Callchain handling code.
  */
 struct frame_tail {
-	struct frame_tail   __user *fp;
-	unsigned long	    lr;
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
 } __attribute__((packed));
 
 /*
@@ -1337,22 +1385,84 @@ user_backtrace(struct frame_tail __user *tail,
 	return buftail.fp;
 }
 
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+		      struct perf_callchain_entry *entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
 void perf_callchain_user(struct perf_callchain_entry *entry,
 			 struct pt_regs *regs)
 {
-	struct frame_tail __user *tail;
-
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
 
 	perf_callchain_store(entry, regs->pc);
-	tail = (struct frame_tail __user *)regs->regs[29];
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH &&
-	       tail && !((unsigned long)tail & 0xf))
-		tail = user_backtrace(tail, entry);
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+
+		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		       tail && !((unsigned long)tail & 0xf))
+			tail = user_backtrace(tail, entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+			tail && !((unsigned long)tail & 0x3))
+			tail = compat_user_backtrace(tail, entry);
+#endif
+	}
 }
 
 /*
@@ -1380,6 +1490,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+
 	walk_stackframe(&frame, callchain_trace, entry);
 }
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
new file mode 100644
index 000000000000..422ebd63b619
--- /dev/null
+++ b/arch/arm64/kernel/perf_regs.c
@@ -0,0 +1,46 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+
+#include <asm/compat.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+		return 0;
+
+	/*
+	 * Compat (i.e. 32 bit) mode:
+	 * - PC has been set in the pt_regs struct in kernel_entry,
+	 * - Handle SP and LR here.
+	 */
+	if (compat_user_mode(regs)) {
+		if ((u32)idx == PERF_REG_ARM64_SP)
+			return regs->compat_sp;
+		if ((u32)idx == PERF_REG_ARM64_LR)
+			return regs->compat_lr;
+	}
+
+	return regs->regs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM64_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	if (is_compat_thread(task_thread_info(task)))
+		return PERF_SAMPLE_REGS_ABI_32;
+	else
+		return PERF_SAMPLE_REGS_ABI_64;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f38f224b04bb..a82af49bcc51 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -20,6 +20,7 @@
 
 #include <stdarg.h>
 
+#include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -33,6 +34,7 @@
 #include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -87,8 +89,10 @@ void arch_cpu_idle(void)
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	cpu_do_idle();
-	local_irq_enable();
+	if (cpuidle_idle_call()) {
+		cpu_do_idle();
+		local_irq_enable();
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -179,9 +183,27 @@ void exit_thread(void)
 {
 }
 
+static void tls_thread_flush(void)
+{
+	asm ("msr tpidr_el0, xzr");
+
+	if (is_compat_task()) {
+		current->thread.tp_value = 0;
+
+		/*
+		 * We need to ensure ordering between the shadow state and the
+		 * hardware state, so that we don't corrupt the hardware state
+		 * with a stale shadow state during context switch.
+		 */
+		barrier();
+		asm ("msr tpidrro_el0, xzr");
+	}
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
+	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 }
 
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 553954771a67..4d827dd62199 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -15,9 +15,11 @@
 
 #define pr_fmt(fmt) "psci: " fmt
 
+#include <linux/cpuidle.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/reboot.h>
 #include <linux/pm.h>
 #include <linux/delay.h>
@@ -28,6 +30,7 @@
 #include <asm/errno.h>
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
+#include <asm/suspend.h>
 #include <asm/system_misc.h>
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
@@ -65,6 +68,8 @@ enum psci_function {
 	PSCI_FN_MAX,
 };
 
+static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+
 static u32 psci_function_id[PSCI_FN_MAX];
 
 static int psci_to_linux_errno(int errno)
@@ -93,6 +98,17 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
+static void psci_power_state_unpack(u32 power_state,
+				    struct psci_power_state *state)
+{
+	state->id = (power_state >> PSCI_0_2_POWER_STATE_ID_SHIFT)
+			& PSCI_0_2_POWER_STATE_ID_MASK;
+	state->type = (power_state >> PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+			& PSCI_0_2_POWER_STATE_TYPE_MASK;
+	state->affinity_level = (power_state >> PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+			& PSCI_0_2_POWER_STATE_AFFL_MASK;
+}
+
 /*
  * The following two functions are invoked via the invoke_psci_fn pointer
  * and will not be inlined, allowing us to piggyback on the AAPCS.
@@ -221,7 +237,7 @@ static int get_set_conduit_method(struct device_node *np)
 	return 0;
 }
 
-static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+static void psci_sys_reset(char str, const char *cmd)
 {
 	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
 }
@@ -436,6 +452,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 #endif
 #endif
 
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+static int cpu_psci_cpu_suspend(unsigned long index)
+{
+	struct psci_power_state *state = __get_cpu_var(psci_power_state);
+
+	if (!state)
+		return -EOPNOTSUPP;
+
+	return psci_ops.cpu_suspend(state[index], virt_to_phys(cpu_resume));
+}
+#endif
+
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
 #ifdef CONFIG_SMP
@@ -448,5 +476,8 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_kill	= cpu_psci_cpu_kill,
 #endif
 #endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+	.cpu_suspend	= cpu_psci_cpu_suspend,
+#endif
 };
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 2b453624d5ad..5cafe0e40cfa 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,6 +19,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -41,6 +42,9 @@
 #include <asm/traps.h>
 #include <asm/system_misc.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 /*
  * TODO: does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
@@ -635,20 +639,20 @@ static int compat_gpr_get(struct task_struct *target,
 
 	for (i = 0; i < num_regs; ++i) {
 		unsigned int idx = start + i;
-		void *reg;
+		compat_ulong_t reg;
 
 		switch (idx) {
 		case 15:
-			reg = (void *)&task_pt_regs(target)->pc;
+			reg = task_pt_regs(target)->pc;
 			break;
 		case 16:
-			reg = (void *)&task_pt_regs(target)->pstate;
+			reg = task_pt_regs(target)->pstate;
 			break;
 		case 17:
-			reg = (void *)&task_pt_regs(target)->orig_x0;
+			reg = task_pt_regs(target)->orig_x0;
 			break;
 		default:
-			reg = (void *)&task_pt_regs(target)->regs[idx];
+			reg = task_pt_regs(target)->regs[idx];
 		}
 
 		if (kbuf) {
@@ -707,24 +711,18 @@ static int compat_gpr_set(struct task_struct *target,
 
 		switch (idx) {
 		case 15:
-			reg = (void *)&newregs.pc;
+			newregs.pc = reg;
 			break;
 		case 16:
-			reg = (void *)&newregs.pstate;
+			newregs.pstate = reg;
 			break;
 		case 17:
-			reg = (void *)&newregs.orig_x0;
+			newregs.orig_x0 = reg;
 			break;
 		default:
-			reg = (void *)&newregs.regs[idx];
+			newregs.regs[idx] = reg;
 		}
 
-		ret = copy_from_user(reg, ubuf, sizeof(compat_ulong_t));
-
-		if (ret)
-			goto out;
-		else
-			ubuf += sizeof(compat_ulong_t);
 	}
 
 	if (valid_user_regs(&newregs.user_regs))
@@ -732,7 +730,6 @@ static int compat_gpr_set(struct task_struct *target,
 	else
 		ret = -EINVAL;
 
-out:
 	return ret;
 }
 
@@ -1084,35 +1081,49 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ptrace_request(child, request, addr, data);
 }
 
-asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
+enum ptrace_syscall_dir {
+	PTRACE_SYSCALL_ENTER = 0,
+	PTRACE_SYSCALL_EXIT,
+};
+
+static void tracehook_report_syscall(struct pt_regs *regs,
+				     enum ptrace_syscall_dir dir)
 {
+	int regno;
 	unsigned long saved_reg;
 
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return regs->syscallno;
-
-	if (is_compat_task()) {
-		/* AArch32 uses ip (r12) for scratch */
-		saved_reg = regs->regs[12];
-		regs->regs[12] = dir;
-	} else {
-		/*
-		 * Save X7. X7 is used to denote syscall entry/exit:
-		 *   X7 = 0 -> entry, = 1 -> exit
-		 */
-		saved_reg = regs->regs[7];
-		regs->regs[7] = dir;
-	}
+	/*
+	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
+	 * used to denote syscall entry/exit:
+	 */
+	regno = (is_compat_task() ? 12 : 7);
+	saved_reg = regs->regs[regno];
+	regs->regs[regno] = dir;
 
-	if (dir)
+	if (dir == PTRACE_SYSCALL_EXIT)
 		tracehook_report_syscall_exit(regs, 0);
 	else if (tracehook_report_syscall_entry(regs))
 		regs->syscallno = ~0UL;
 
-	if (is_compat_task())
-		regs->regs[12] = saved_reg;
-	else
-		regs->regs[7] = saved_reg;
+	regs->regs[regno] = saved_reg;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, regs->syscallno);
 
 	return regs->syscallno;
 }
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, regs_return_value(regs));
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
new file mode 100644
index 000000000000..89102a6ffad5
--- /dev/null
+++ b/arch/arm64/kernel/return_address.c
@@ -0,0 +1,55 @@
+/*
+ * arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/ftrace.h>
+
+#include <asm/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static int save_return_addr(struct stackframe *frame, void *d)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)frame->pc;
+		return 1;
+	} else {
+		--data->level;
+		return 0;
+	}
+}
+
+void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+	struct stackframe frame;
+	register unsigned long current_sp asm ("sp");
+
+	data.level = level + 2;
+	data.addr = NULL;
+
+	frame.fp = (unsigned long)__builtin_frame_address(0);
+	frame.sp = current_sp;
+	frame.pc = (unsigned long)return_address; /* dummy */
+
+	walk_stackframe(&frame, save_return_addr, &data);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 5fdfc0255953..e87b5fd07b8c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -41,6 +41,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
+#include <linux/efi.h>
 
 #include <asm/fixmap.h>
 #include <asm/cputype.h>
@@ -55,6 +56,7 @@
 #include <asm/traps.h>
 #include <asm/memblock.h>
 #include <asm/psci.h>
+#include <asm/efi.h>
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -62,6 +64,17 @@ EXPORT_SYMBOL(processor_id);
 unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
 
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP_DEFAULT	\
+				(COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
+				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
+				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
+				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
+				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
+#endif
+
 static const char *cpu_name;
 static const char *machine_name;
 phys_addr_t __fdt_pointer __initdata;
@@ -114,9 +127,79 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 	return phys_id == cpu_logical_map(cpu);
 }
 
+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ *			  level in order to build a linear index from an
+ *			  MPIDR value. Resulting algorithm is a collision
+ *			  free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+	u32 i, affinity, fs[4], bits[4], ls;
+	u64 mask = 0;
+	/*
+	 * Pre-scan the list of MPIDRS and filter out bits that do
+	 * not contribute to affinity levels, ie they never toggle.
+	 */
+	for_each_possible_cpu(i)
+		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+	pr_debug("mask of set bits %#llx\n", mask);
+	/*
+	 * Find and stash the last and first bit set at all affinity levels to
+	 * check how many bits are required to represent them.
+	 */
+	for (i = 0; i < 4; i++) {
+		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+		/*
+		 * Find the MSB bit and LSB bits position
+		 * to determine how many bits are required
+		 * to express the affinity level.
+		 */
+		ls = fls(affinity);
+		fs[i] = affinity ? ffs(affinity) - 1 : 0;
+		bits[i] = ls - fs[i];
+	}
+	/*
+	 * An index can be created from the MPIDR_EL1 by isolating the
+	 * significant bits at each affinity level and by shifting
+	 * them in order to compress the 32 bits values space to a
+	 * compressed set of values. This is equivalent to hashing
+	 * the MPIDR_EL1 through shifting and ORing. It is a collision free
+	 * hash though not minimal since some levels might contain a number
+	 * of CPUs that is not an exact power of 2 and their bit
+	 * representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
+	 */
+	mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
+	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
+	mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
+						(bits[1] + bits[0]);
+	mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
+				  fs[3] - (bits[2] + bits[1] + bits[0]);
+	mpidr_hash.mask = mask;
+	mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
+	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
+		mpidr_hash.shift_aff[0],
+		mpidr_hash.shift_aff[1],
+		mpidr_hash.shift_aff[2],
+		mpidr_hash.shift_aff[3],
+		mpidr_hash.mask,
+		mpidr_hash.bits);
+	/*
+	 * 4x is an arbitrary value used to warn on a hash table much bigger
+	 * than expected on most systems.
+	 */
+	if (mpidr_hash_size() > 4 * num_possible_cpus())
+		pr_warn("Large number of MPIDR hash buckets detected\n");
+	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
+}
+#endif
+
 static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
+	u64 features, block;
 
 	cpu_info = lookup_processor_type(read_cpuid_id());
 	if (!cpu_info) {
@@ -130,8 +213,71 @@ static void __init setup_processor(void)
 	printk("CPU: %s [%08x] revision %d\n",
 	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15);
 
-	sprintf(init_utsname()->machine, "aarch64");
+	sprintf(init_utsname()->machine, ELF_PLATFORM);
 	elf_hwcap = 0;
+
+	/*
+	 * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
+	 * The blocks we test below represent incremental functionality
+	 * for non-negative values. Negative values are reserved.
+	 */
+	features = read_cpuid(ID_AA64ISAR0_EL1);
+	block = (features >> 4) & 0xf;
+	if (!(block & 0x8)) {
+		switch (block) {
+		default:
+		case 2:
+			elf_hwcap |= HWCAP_PMULL;
+		case 1:
+			elf_hwcap |= HWCAP_AES;
+		case 0:
+			break;
+		}
+	}
+
+	block = (features >> 8) & 0xf;
+	if (block && !(block & 0x8))
+		elf_hwcap |= HWCAP_SHA1;
+
+	block = (features >> 12) & 0xf;
+	if (block && !(block & 0x8))
+		elf_hwcap |= HWCAP_SHA2;
+
+	block = (features >> 16) & 0xf;
+	if (block && !(block & 0x8))
+		elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+	 * the Aarch32 32-bit execution state.
+	 */
+	features = read_cpuid(ID_ISAR5_EL1);
+	block = (features >> 4) & 0xf;
+	if (!(block & 0x8)) {
+		switch (block) {
+		default:
+		case 2:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+		case 1:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+		case 0:
+			break;
+		}
+	}
+
+	block = (features >> 8) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+	block = (features >> 12) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+	block = (features >> 16) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
@@ -273,11 +419,14 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	efi_init();
 	arm64_memblock_init();
 
 	paging_init();
 	request_standard_resources();
 
+	efi_idmap_init();
+
 	unflatten_device_tree();
 
 	psci_init();
@@ -286,6 +435,7 @@ void __init setup_arch(char **cmdline_p)
 	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
 	smp_init_cpus();
+	smp_build_mpidr_hash();
 #endif
 
 #ifdef CONFIG_VT
@@ -324,6 +474,12 @@ subsys_initcall(topology_init);
 static const char *hwcap_str[] = {
 	"fp",
 	"asimd",
+	"evtstrm",
+	"aes",
+	"pmull",
+	"sha1",
+	"sha2",
+	"crc32",
 	NULL
 };
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 7ff2eee96c6b..e3cf09626245 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
@@ -25,7 +26,6 @@
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
 
-#include <asm/compat.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 3edf7f48c54b..e51bbe79f5b5 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -100,34 +100,6 @@ struct compat_rt_sigframe {
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-/*
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- */
-#define MOV_R7_NR_SIGRETURN	(0xe3a07000 | __NR_compat_sigreturn)
-#define SVC_SYS_SIGRETURN	(0xef000000 | __NR_compat_sigreturn)
-#define MOV_R7_NR_RT_SIGRETURN	(0xe3a07000 | __NR_compat_rt_sigreturn)
-#define SVC_SYS_RT_SIGRETURN	(0xef000000 | __NR_compat_rt_sigreturn)
-
-/*
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-#define SVC_THUMB_SIGRETURN	(((0xdf00 | __NR_compat_sigreturn) << 16) | \
-				   0x2700 | __NR_compat_sigreturn)
-#define SVC_THUMB_RT_SIGRETURN	(((0xdf00 | __NR_compat_rt_sigreturn) << 16) | \
-				   0x2700 | __NR_compat_rt_sigreturn)
-
-const compat_ulong_t aarch32_sigret_code[6] = {
-	/*
-	 * AArch32 sigreturn code.
-	 * We don't construct an OABI SWI - instead we just set the imm24 field
-	 * to the EABI syscall number so that we create a sane disassembly.
-	 */
-	MOV_R7_NR_SIGRETURN,    SVC_SYS_SIGRETURN,    SVC_THUMB_SIGRETURN,
-	MOV_R7_NR_RT_SIGRETURN, SVC_SYS_RT_SIGRETURN, SVC_THUMB_RT_SIGRETURN,
-};
-
 static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
 {
 	compat_sigset_t	cset;
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
new file mode 100644
index 000000000000..b1925729c692
--- /dev/null
+++ b/arch/arm64/kernel/sleep.S
@@ -0,0 +1,184 @@
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+	.text
+/*
+ * Implementation of MPIDR_EL1 hash algorithm through shifting
+ * and OR'ing.
+ *
+ * @dst: register containing hash result
+ * @rs0: register containing affinity level 0 bit shift
+ * @rs1: register containing affinity level 1 bit shift
+ * @rs2: register containing affinity level 2 bit shift
+ * @rs3: register containing affinity level 3 bit shift
+ * @mpidr: register containing MPIDR_EL1 value
+ * @mask: register containing MPIDR mask
+ *
+ * Pseudo C-code:
+ *
+ *u32 dst;
+ *
+ *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 rs3, u64 mpidr, u64 mask) {
+ *	u32 aff0, aff1, aff2, aff3;
+ *	u64 mpidr_masked = mpidr & mask;
+ *	aff0 = mpidr_masked & 0xff;
+ *	aff1 = mpidr_masked & 0xff00;
+ *	aff2 = mpidr_masked & 0xff0000;
+ *	aff2 = mpidr_masked & 0xff00000000;
+ *	dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
+ *}
+ * Input registers: rs0, rs1, rs2, rs3, mpidr, mask
+ * Output register: dst
+ * Note: input and output registers must be disjoint register sets
+         (eg: a macro instance with mpidr = x1 and dst = x1 is invalid)
+ */
+	.macro compute_mpidr_hash dst, rs0, rs1, rs2, rs3, mpidr, mask
+	and	\mpidr, \mpidr, \mask		// mask out MPIDR bits
+	and	\dst, \mpidr, #0xff		// mask=aff0
+	lsr	\dst ,\dst, \rs0		// dst=aff0>>rs0
+	and	\mask, \mpidr, #0xff00		// mask = aff1
+	lsr	\mask ,\mask, \rs1
+	orr	\dst, \dst, \mask		// dst|=(aff1>>rs1)
+	and	\mask, \mpidr, #0xff0000	// mask = aff2
+	lsr	\mask ,\mask, \rs2
+	orr	\dst, \dst, \mask		// dst|=(aff2>>rs2)
+	and	\mask, \mpidr, #0xff00000000	// mask = aff3
+	lsr	\mask ,\mask, \rs3
+	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
+	.endm
+/*
+ * Save CPU state for a suspend.  This saves callee registers, and allocates
+ * space on the kernel stack to save the CPU specific registers + some
+ * other data for resume.
+ *
+ *  x0 = suspend finisher argument
+ */
+ENTRY(__cpu_suspend)
+	stp	x29, lr, [sp, #-96]!
+	stp	x19, x20, [sp,#16]
+	stp	x21, x22, [sp,#32]
+	stp	x23, x24, [sp,#48]
+	stp	x25, x26, [sp,#64]
+	stp	x27, x28, [sp,#80]
+	mov	x2, sp
+	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
+	mov	x1, sp
+	/*
+	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 */
+	str	x2, [x1, #CPU_CTX_SP]
+	ldr	x2, =sleep_save_sp
+	ldr	x2, [x2, #SLEEP_SAVE_SP_VIRT]
+#ifdef CONFIG_SMP
+	mrs	x7, mpidr_el1
+	ldr	x9, =mpidr_hash
+	ldr	x10, [x9, #MPIDR_HASH_MASK]
+	/*
+	 * Following code relies on the struct mpidr_hash
+	 * members size.
+	 */
+	ldp	w3, w4, [x9, #MPIDR_HASH_SHIFTS]
+	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
+	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
+	add	x2, x2, x8, lsl #3
+#endif
+	bl	__cpu_suspend_finisher
+        /*
+	 * Never gets here, unless suspend fails.
+	 * Successful cpu_suspend should return from cpu_resume, returning
+	 * through this code path is considered an error
+	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
+	 * to make sure a proper error condition is propagated
+	 */
+	cmp	x0, #0
+	mov	x3, #-EOPNOTSUPP
+	csel	x0, x3, x0, eq
+	add	sp, sp, #CPU_SUSPEND_SZ	// rewind stack pointer
+	ldp	x19, x20, [sp, #16]
+	ldp	x21, x22, [sp, #32]
+	ldp	x23, x24, [sp, #48]
+	ldp	x25, x26, [sp, #64]
+	ldp	x27, x28, [sp, #80]
+	ldp	x29, lr, [sp], #96
+	ret
+ENDPROC(__cpu_suspend)
+	.ltorg
+
+/*
+ * x0 must contain the sctlr value retrieved from restored context
+ */
+ENTRY(cpu_resume_mmu)
+	ldr	x3, =cpu_resume_after_mmu
+	msr	sctlr_el1, x0		// restore sctlr_el1
+	isb
+	br	x3			// global jump to virtual address
+ENDPROC(cpu_resume_mmu)
+cpu_resume_after_mmu:
+	mov	x0, #0			// return zero on success
+	ldp	x19, x20, [sp, #16]
+	ldp	x21, x22, [sp, #32]
+	ldp	x23, x24, [sp, #48]
+	ldp	x25, x26, [sp, #64]
+	ldp	x27, x28, [sp, #80]
+	ldp	x29, lr, [sp], #96
+	ret
+ENDPROC(cpu_resume_after_mmu)
+
+	.data
+ENTRY(cpu_resume)
+	bl	el2_setup		// if in EL2 drop to EL1 cleanly
+#ifdef CONFIG_SMP
+	mrs	x1, mpidr_el1
+	adr	x4, mpidr_hash_ptr
+	ldr	x5, [x4]
+	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+        /* retrieve mpidr_hash members to compute the hash */
+	ldr	x2, [x8, #MPIDR_HASH_MASK]
+	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
+	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
+	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
+        /* x7 contains hash index, let's use it to grab context pointer */
+#else
+	mov	x7, xzr
+#endif
+	adr	x0, sleep_save_sp
+	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
+	ldr	x0, [x0, x7, lsl #3]
+	/* load sp from context */
+	ldr	x2, [x0, #CPU_CTX_SP]
+	adr	x1, sleep_idmap_phys
+	/* load physical address of identity map page table in x1 */
+	ldr	x1, [x1]
+	mov	sp, x2
+	/*
+	 * cpu_do_resume expects x0 to contain context physical address
+	 * pointer and x1 to contain physical address of 1:1 page tables
+	 */
+	bl	cpu_do_resume		// PC relative jump, MMU off
+	b	cpu_resume_mmu		// Resume MMU, never returns
+ENDPROC(cpu_resume)
+
+	.align 3
+mpidr_hash_ptr:
+	/*
+	 * offset of mpidr_hash symbol from current location
+	 * used to obtain run-time mpidr_hash address with MMU off
+         */
+	.quad	mpidr_hash - .
+/*
+ * physical address of identity mapped page tables
+ */
+	.type	sleep_idmap_phys, #object
+ENTRY(sleep_idmap_phys)
+	.quad	0
+/*
+ * struct sleep_save_sp {
+ *	phys_addr_t *save_ptr_stash;
+ *	phys_addr_t save_ptr_stash_phys;
+ * };
+ */
+	.type	sleep_save_sp, #object
+ENTRY(sleep_save_sp)
+	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 8fbefa6e97a5..0ac31a581f02 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -49,6 +49,9 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/arm-ipi.h>
+
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
  * so we need some other way of telling a new secondary core
@@ -61,6 +64,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
+	IPI_TIMER,
 };
 
 /*
@@ -113,6 +117,11 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -147,6 +156,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 		cpu_ops[cpu]->cpu_postboot();
 
 	/*
+	 * Enable GIC and timers.
+	 */
+	notify_cpu_starting(cpu);
+
+	smp_store_cpu_info(cpu);
+
+	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
 	 * before we continue.
@@ -154,11 +170,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	/*
-	 * Enable GIC and timers.
-	 */
-	notify_cpu_starting(cpu);
-
 	local_dbg_enable();
 	local_irq_enable();
 	local_fiq_enable();
@@ -416,6 +427,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	int err;
 	unsigned int cpu, ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
 	/*
 	 * are we trying to boot more cores than exist?
 	 */
@@ -475,6 +490,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_TIMER, "Timer broadcast interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -560,6 +576,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	case IPI_TIMER:
+		irq_enter();
+		tick_receive_broadcast();
+		irq_exit();
+		break;
+#endif
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
 		break;
@@ -572,6 +596,13 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+	smp_cross_call(mask, IPI_TIMER);
+}
+#endif
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index e3e5755f61bb..0347d38eea29 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -71,7 +71,16 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 		return -ENODEV;
 
 	release_addr = __va(cpu_release_addr[cpu]);
-	release_addr[0] = (void *)__pa(secondary_holding_pen);
+
+	/*
+	 * We write the release address as LE regardless of the native
+	 * endianess of the kernel. Therefore, any boot-loaders that
+	 * read this address need to convert this address to the
+	 * boot-loader's endianess before jumping. This is mandated by
+	 * the boot protocol.
+	 */
+	release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
+
 	__flush_dcache_area(release_addr, sizeof(release_addr[0]));
 
 	/*
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 6f44bf97e4cf..407991bf79f5 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -35,7 +35,7 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
-int unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
new file mode 100644
index 000000000000..1fa9ce4afd8f
--- /dev/null
+++ b/arch/arm64/kernel/suspend.c
@@ -0,0 +1,140 @@
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/debug-monitors.h>
+#include <asm/pgtable.h>
+#include <asm/memory.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+extern int __cpu_suspend(unsigned long);
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ *
+ * @arg: Argument to pass to suspend operations
+ * @ptr: CPU context virtual address
+ * @save_ptr: address of the location where the context physical address
+ *            must be saved
+ */
+int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
+			   phys_addr_t *save_ptr)
+{
+	int cpu = smp_processor_id();
+
+	*save_ptr = virt_to_phys(ptr);
+
+	cpu_do_suspend(ptr);
+	/*
+	 * Only flush the context that must be retrieved with the MMU
+	 * off. VA primitives ensure the flush is applied to all
+	 * cache levels so context is pushed to DRAM.
+	 */
+	__flush_dcache_area(ptr, sizeof(*ptr));
+	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
+
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * This hook is provided so that cpu_suspend code can restore HW
+ * breakpoints as early as possible in the resume path, before reenabling
+ * debug exceptions. Code cannot be run from a CPU PM notifier since by the
+ * time the notifier runs debug exceptions might have been enabled already,
+ * with HW breakpoints registers content still in an unknown state.
+ */
+void (*hw_breakpoint_restore)(void *);
+void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+{
+	/* Prevent multiple restore hook initializations */
+	if (WARN_ON(hw_breakpoint_restore))
+		return;
+	hw_breakpoint_restore = hw_bp_restore;
+}
+
+/**
+ * cpu_suspend
+ *
+ * @arg: argument to pass to the finisher function
+ */
+int cpu_suspend(unsigned long arg)
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret, cpu = smp_processor_id();
+	unsigned long flags;
+
+	/*
+	 * If cpu_ops have not been registered or suspend
+	 * has not been initialized, cpu_suspend call fails early.
+	 */
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
+		return -EOPNOTSUPP;
+
+	/*
+	 * From this point debug exceptions are disabled to prevent
+	 * updates to mdscr register (saved and restored along with
+	 * general purpose registers) from kernel debuggers.
+	 */
+	local_dbg_save(flags);
+
+	/*
+	 * mm context saved on the stack, it will be restored when
+	 * the cpu comes out of reset through the identity mapped
+	 * page tables, so that the thread address space is properly
+	 * set-up on function return.
+	 */
+	ret = __cpu_suspend(arg);
+	if (ret == 0) {
+		cpu_switch_mm(mm->pgd, mm);
+		flush_tlb_all();
+
+		/*
+		 * Restore per-cpu offset before any kernel
+		 * subsystem relying on it has a chance to run.
+		 */
+		set_my_cpu_offset(per_cpu_offset(cpu));
+
+		/*
+		 * Restore HW breakpoint registers to sane values
+		 * before debug exceptions are possibly reenabled
+		 * through local_dbg_restore.
+		 */
+		if (hw_breakpoint_restore)
+			hw_breakpoint_restore(NULL);
+	}
+
+	/*
+	 * Restore pstate flags. OS lock and mdscr have been already
+	 * restored, so from this point onwards, debugging is fully
+	 * renabled if it was enabled when core started shutdown.
+	 */
+	local_dbg_restore(flags);
+
+	return ret;
+}
+
+extern struct sleep_save_sp sleep_save_sp;
+extern phys_addr_t sleep_idmap_phys;
+
+static int cpu_suspend_init(void)
+{
+	void *ctx_ptr;
+
+	/* ctx_ptr is an array of physical addresses */
+	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL);
+
+	if (WARN_ON(!ctx_ptr))
+		return -ENOMEM;
+
+	sleep_save_sp.save_ptr_stash = ctx_ptr;
+	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
+	sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
+	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
+	__flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
+
+	return 0;
+}
+early_initcall(cpu_suspend_init);
diff --git a/arch/arm64/kernel/sys32.S b/arch/arm64/kernel/sys32.S
index a1b19ed7467c..423a5b3fc2be 100644
--- a/arch/arm64/kernel/sys32.S
+++ b/arch/arm64/kernel/sys32.S
@@ -59,48 +59,48 @@ ENDPROC(compat_sys_fstatfs64_wrapper)
  * extension.
  */
 compat_sys_pread64_wrapper:
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x3, x4, x5
 	b	sys_pread64
 ENDPROC(compat_sys_pread64_wrapper)
 
 compat_sys_pwrite64_wrapper:
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x3, x4, x5
 	b	sys_pwrite64
 ENDPROC(compat_sys_pwrite64_wrapper)
 
 compat_sys_truncate64_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	b	sys_truncate
 ENDPROC(compat_sys_truncate64_wrapper)
 
 compat_sys_ftruncate64_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	b	sys_ftruncate
 ENDPROC(compat_sys_ftruncate64_wrapper)
 
 compat_sys_readahead_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	mov	w2, w4
 	b	sys_readahead
 ENDPROC(compat_sys_readahead_wrapper)
 
 compat_sys_fadvise64_64_wrapper:
 	mov	w6, w1
-	orr	x1, x2, x3, lsl #32
-	orr	x2, x4, x5, lsl #32
+	regs_to_64	x1, x2, x3
+	regs_to_64	x2, x4, x5
 	mov	w3, w6
 	b	sys_fadvise64_64
 ENDPROC(compat_sys_fadvise64_64_wrapper)
 
 compat_sys_sync_file_range2_wrapper:
-	orr	x2, x2, x3, lsl #32
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x2, x2, x3
+	regs_to_64	x3, x4, x5
 	b	sys_sync_file_range2
 ENDPROC(compat_sys_sync_file_range2_wrapper)
 
 compat_sys_fallocate_wrapper:
-	orr	x2, x2, x3, lsl #32
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x2, x2, x3
+	regs_to_64	x3, x4, x5
 	b	sys_fallocate
 ENDPROC(compat_sys_fallocate_wrapper)
 
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 26e9c4eeaba8..78039927c807 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs)
 
 	case __ARM_NR_compat_set_tls:
 		current->thread.tp_value = regs->regs[0];
+
+		/*
+		 * Protect against register corruption from context switch.
+		 * See comment in tls_thread_flush.
+		 */
+		barrier();
 		asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
 		return 0;
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 000000000000..db8bb29c3852
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,590 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013,2014 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+#include <asm/smp_plat.h>
+
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node)
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			of_node_put(cpu_node);
+			return cpu;
+		}
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+
+	of_node_put(cpu_node);
+	return -1;
+}
+
+static int __init parse_core(struct device_node *core, int cluster_id,
+			     int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				cpu_topology[cpu].cluster_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+				of_node_put(t);
+				return -EINVAL;
+			}
+			of_node_put(t);
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return -EINVAL;
+		}
+
+		cpu_topology[cpu].cluster_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int cluster_id __initdata;
+	int core_id = 0;
+	int i, ret;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			leaf = false;
+			ret = parse_cluster(c, depth + 1);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0) {
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+				of_node_put(c);
+				return -EINVAL;
+			}
+
+			if (leaf) {
+				ret = parse_core(c, cluster_id, core_id++);
+			} else {
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+				ret = -EINVAL;
+			}
+
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+
+	return 0;
+}
+
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static int __init parse_dt_topology(void)
+{
+	struct device_node *cn, *map;
+	int ret = 0;
+	int cpu;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return 0;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	map = of_get_child_by_name(cn, "cpu-map");
+	if (!map)
+		goto out;
+
+	ret = parse_cluster(map, 0);
+	if (ret != 0)
+		goto out_map;
+
+	/*
+	 * Check that all cores are in the topology; the SMP code will
+	 * only mark cores described in the DT as possible.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (cpu_topology[cpu].cluster_id == -1) {
+			pr_err("CPU%d: No topology information specified\n",
+			       cpu);
+			ret = -EINVAL;
+		}
+	}
+
+out_map:
+	of_node_put(map);
+out:
+	of_node_put(cn);
+	return ret;
+}
+
+static void __init parse_dt_cpu_power(void)
+{
+	const struct cpu_efficiency *cpu_eff;
+	struct device_node *cn;
+	unsigned long min_capacity = ULONG_MAX;
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int cpu;
+
+	__cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+				 GFP_NOWAIT);
+
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
+		int len;
+
+		/* Too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("Missing device node for CPU %d\n", cpu);
+			continue;
+		}
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL) {
+			pr_warn("%s: Unknown CPU type\n", cn->full_name);
+			continue;
+		}
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s: Missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity(cpu) = capacity;
+	}
+
+	/* If min and max capacities are equal we bypass the update of the
+	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
+	 * compute a middle_capacity factor that will ensure that the capacity
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		return;
+	else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+	if (!cpu_capacity(cpu))
+		return;
+
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+	pr_info("CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	if (cpuid_topo->cluster_id == -1) {
+		/*
+		 * DT does not contain topology information for this cpu.
+		 */
+		pr_debug("CPU%u: No topology information configured\n", cpuid);
+		return;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+}
+
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+	"arm,cortex-a53",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 8) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr+1));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr+1));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu) {
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	update_siblings_masks(cpuid);
+	update_cpu_power(cpuid);
+}
+
+static void __init reset_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id = 0;
+		cpu_topo->cluster_id = -1;
+
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+	}
+}
+
+static void __init reset_cpu_power(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		set_power_scale(cpu, SCHED_POWER_SCALE);
+}
+
+void __init init_cpu_topology(void)
+{
+	reset_cpu_topology();
+
+	/*
+	 * Discard anything that was parsed if we hit an error so we
+	 * don't use partial information.
+	 */
+	if (parse_dt_topology())
+		reset_cpu_topology();
+
+	reset_cpu_power();
+	parse_dt_cpu_power();
+}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 40ba5dea2ed7..84cafbc3eb54 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -58,7 +58,10 @@ static struct page *vectors_page[1];
 static int alloc_vectors_page(void)
 {
 	extern char __kuser_helper_start[], __kuser_helper_end[];
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
 	unsigned long vpage;
 
 	vpage = get_zeroed_page(GFP_ATOMIC);
@@ -72,7 +75,7 @@ static int alloc_vectors_page(void)
 
 	/* sigreturn code */
 	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-		aarch32_sigret_code, sizeof(aarch32_sigret_code));
+               __aarch32_sigret_code_start, sigret_sz);
 
 	flush_icache_range(vpage, vpage + PAGE_SIZE);
 	vectors_page[0] = virt_to_page(vpage);
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 6e0ed93d51fe..c17967fdf5f6 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -46,7 +46,7 @@ USER(9f, strh	wzr, [x0], #2	)
 	sub	x1, x1, #2
 4:	adds	x1, x1, #1
 	b.mi	5f
-	strb	wzr, [x0]
+USER(9f, strb	wzr, [x0]	)
 5:	mov	x0, #0
 	ret
 ENDPROC(__clear_user)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index df4f2fd187c3..c23751b06120 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (esr & ESR_LNX_EXEC) {
-		vm_flags = VM_EXEC;
-	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
-		vm_flags = VM_WRITE;
-		mm_flags |= FAULT_FLAG_WRITE;
-	}
-
 	tsk = current;
 	mm  = tsk->mm;
 
@@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		mm_flags |= FAULT_FLAG_USER;
+
+	if (esr & ESR_LNX_EXEC) {
+		vm_flags = VM_EXEC;
+	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+		vm_flags = VM_WRITE;
+		mm_flags |= FAULT_FLAG_WRITE;
+	}
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -288,6 +291,13 @@ retry:
 			      VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we have no context to
+	 * handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -298,13 +308,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we have no context to
-	 * handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to successfully fix up
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 639dca61ad7a..a2155ca6921c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -168,7 +168,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 			    PMD_ATTRINDX(MT_DEVICE_nGnRE);
 		prot_pte = __pgprot(PROT_DEVICE_nGnRE);
 	} else {
-		prot_sect = prot_sect_kernel;
+		prot_sect = PROT_SECT_NORMAL_EXEC;
 		prot_pte = PAGE_KERNEL_EXEC;
 	}
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cc65d201cd9d..c133ae53ed86 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -95,6 +95,75 @@ ENTRY(cpu_do_idle)
 	ret
 ENDPROC(cpu_do_idle)
 
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+/**
+ * cpu_do_suspend - save CPU registers context
+ *
+ * x0: virtual address of context pointer
+ */
+ENTRY(cpu_do_suspend)
+	mrs	x2, tpidr_el0
+	mrs	x3, tpidrro_el0
+	mrs	x4, contextidr_el1
+	mrs	x5, mair_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, ttbr1_el1
+	mrs	x8, tcr_el1
+	mrs	x9, vbar_el1
+	mrs	x10, mdscr_el1
+	mrs	x11, oslsr_el1
+	mrs	x12, sctlr_el1
+	stp	x2, x3, [x0]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	str	x12, [x0, #80]
+	ret
+ENDPROC(cpu_do_suspend)
+
+/**
+ * cpu_do_resume - restore CPU register context
+ *
+ * x0: Physical address of context pointer
+ * x1: ttbr0_el1 to be restored
+ *
+ * Returns:
+ *	sctlr_el1 value in x0
+ */
+ENTRY(cpu_do_resume)
+	/*
+	 * Invalidate local tlb entries before turning on MMU
+	 */
+	tlbi	vmalle1
+	ldp	x2, x3, [x0]
+	ldp	x4, x5, [x0, #16]
+	ldp	x6, x7, [x0, #32]
+	ldp	x8, x9, [x0, #48]
+	ldp	x10, x11, [x0, #64]
+	ldr	x12, [x0, #80]
+	msr	tpidr_el0, x2
+	msr	tpidrro_el0, x3
+	msr	contextidr_el1, x4
+	msr	mair_el1, x5
+	msr	cpacr_el1, x6
+	msr	ttbr0_el1, x1
+	msr	ttbr1_el1, x7
+	msr	tcr_el1, x8
+	msr	vbar_el1, x9
+	msr	mdscr_el1, x10
+	/*
+	 * Restore oslsr_el1 by writing oslar_el1
+	 */
+	ubfx	x11, x11, #1, #1
+	msr	oslar_el1, x11
+	mov	x0, x12
+	dsb	nsh		// Make sure local tlb invalidation completed
+	isb
+	ret
+ENDPROC(cpu_do_resume)
+#endif
+
 /*
  *	cpu_do_switch_mm(pgd_phys, tsk)
  *
@@ -177,9 +246,9 @@ ENDPROC(__cpu_setup)
 	 *       CE0      XWHW CZ     ME TEEA S
 	 * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
 	 * 0011 0... 1101 ..0. ..0. 10.. .... .... < hardware reserved
-	 * .... .100 .... 01.1 11.1 ..01 0001 1101 < software settings
+	 * .... .1.. .... 01.1 11.1 ..01 0001 1101 < software settings
 	 */
 	.type	crval, #object
 crval:
-	.word	0x030802e2			// clear
+	.word	0x000802e2			// clear
 	.word	0x0405d11d			// set
diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile
index 22fb66590dcd..dba48a5d5bb9 100644
--- a/arch/avr32/Makefile
+++ b/arch/avr32/Makefile
@@ -11,7 +11,7 @@ all: uImage vmlinux.elf
 
 KBUILD_DEFCONFIG	:= atstk1002_defconfig
 
-KBUILD_CFLAGS	+= -pipe -fno-builtin -mno-pic
+KBUILD_CFLAGS	+= -pipe -fno-builtin -mno-pic -D__linux__
 KBUILD_AFLAGS	+= -mrelax -mno-pic
 KBUILD_CFLAGS_MODULE += -mno-relax
 LDFLAGS_vmlinux	+= --relax
diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c
index 9764a1a1073e..c1466a872b9c 100644
--- a/arch/avr32/boards/mimc200/fram.c
+++ b/arch/avr32/boards/mimc200/fram.c
@@ -11,6 +11,7 @@
 #define FRAM_VERSION	"1.0"
 
 #include <linux/miscdevice.h>
+#include <linux/module.h>
 #include <linux/proc_fs.h>
 #include <linux/mm.h>
 #include <linux/io.h>
diff --git a/arch/avr32/boot/u-boot/head.S b/arch/avr32/boot/u-boot/head.S
index 4488fa27fe94..2ffc298f061b 100644
--- a/arch/avr32/boot/u-boot/head.S
+++ b/arch/avr32/boot/u-boot/head.S
@@ -8,6 +8,8 @@
  * published by the Free Software Foundation.
  */
 #include <asm/setup.h>
+#include <asm/thread_info.h>
+#include <asm/sysreg.h>
 
 	/*
 	 * The kernel is loaded where we want it to be and all caches
@@ -20,11 +22,6 @@
 	.section .init.text,"ax"
 	.global _start
 _start:
-	/* Check if the boot loader actually provided a tag table */
-	lddpc	r0, magic_number
-	cp.w	r12, r0
-	brne	no_tag_table
-
 	/* Initialize .bss */
 	lddpc	r2, bss_start_addr
 	lddpc   r3, end_addr
@@ -34,6 +31,25 @@ _start:
 	cp      r2, r3
 	brlo    1b
 
+	/* Initialize status register */
+	lddpc	r0, init_sr
+	mtsr	SYSREG_SR, r0
+
+	/* Set initial stack pointer */
+	lddpc	sp, stack_addr
+	sub	sp, -THREAD_SIZE
+
+#ifdef CONFIG_FRAME_POINTER
+	/* Mark last stack frame */
+	mov	lr, 0
+	mov	r7, 0
+#endif
+
+	/* Check if the boot loader actually provided a tag table */
+	lddpc	r0, magic_number
+	cp.w	r12, r0
+	brne	no_tag_table
+
 	/*
 	 * Save the tag table address for later use. This must be done
 	 * _after_ .bss has been initialized...
@@ -53,8 +69,15 @@ bss_start_addr:
 	.long   __bss_start
 end_addr:
 	.long   _end
+init_sr:
+	.long	0x007f0000	/* Supervisor mode, everything masked */
+stack_addr:
+	.long	init_thread_union
+panic_addr:
+	.long	panic
 
 no_tag_table:
 	sub	r12, pc, (. - 2f)
-	bral	panic
+	/* branch to panic() which can be far away with that construct */
+	lddpc	pc, panic_addr
 2:	.asciz	"Boot loader didn't provide correct magic number\n"
diff --git a/arch/avr32/kernel/entry-avr32b.S b/arch/avr32/kernel/entry-avr32b.S
index 9899d3cc6f03..7301f4806bbe 100644
--- a/arch/avr32/kernel/entry-avr32b.S
+++ b/arch/avr32/kernel/entry-avr32b.S
@@ -401,9 +401,10 @@ handle_critical:
 	/* We should never get here... */
 bad_return:
 	sub	r12, pc, (. - 1f)
-	bral	panic
+	lddpc	pc, 2f
 	.align	2
 1:	.asciz	"Return from critical exception!"
+2:	.long	panic
 
 	.align	1
 do_bus_error_write:
diff --git a/arch/avr32/kernel/head.S b/arch/avr32/kernel/head.S
index 6163bd0acb95..59eae6dfbed2 100644
--- a/arch/avr32/kernel/head.S
+++ b/arch/avr32/kernel/head.S
@@ -10,33 +10,13 @@
 #include <linux/linkage.h>
 
 #include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/sysreg.h>
 
 	.section .init.text,"ax"
 	.global kernel_entry
 kernel_entry:
-	/* Initialize status register */
-	lddpc   r0, init_sr
-	mtsr	SYSREG_SR, r0
-
-	/* Set initial stack pointer */
-	lddpc   sp, stack_addr
-	sub	sp, -THREAD_SIZE
-
-#ifdef CONFIG_FRAME_POINTER
-	/* Mark last stack frame */
-	mov	lr, 0
-	mov	r7, 0
-#endif
-
 	/* Start the show */
 	lddpc   pc, kernel_start_addr
 
 	.align  2
-init_sr:
-	.long   0x007f0000	/* Supervisor mode, everything masked */
-stack_addr:
-	.long   init_thread_union
 kernel_start_addr:
 	.long   start_kernel
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index 869a1c6ffeee..12f828ad5058 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -98,7 +98,14 @@ static void comparator_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		sysreg_write(COMPARE, 0);
 		pr_debug("%s: stop\n", evdev->name);
-		cpu_idle_poll_ctrl(false);
+		if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
+		    evdev->mode == CLOCK_EVT_MODE_RESUME) {
+			/*
+			 * Only disable idle poll if we have forced that
+			 * in a previous call.
+			 */
+			cpu_idle_poll_ctrl(false);
+		}
 		break;
 	default:
 		BUG();
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index b2f2d2d66849..0eca93327195 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 
 	local_irq_enable();
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
@@ -228,9 +230,9 @@ no_context:
 	 */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	pagefault_out_of_memory();
 	if (!user_mode(regs))
 		goto no_context;
+	pagefault_out_of_memory();
 	return;
 
 do_sigbus:
diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h
index 8a029505d7b7..2f1c3c2657ad 100644
--- a/arch/blackfin/include/asm/ftrace.h
+++ b/arch/blackfin/include/asm/ftrace.h
@@ -66,16 +66,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif /* CONFIG_FRAME_POINTER */
 
-#define HAVE_ARCH_CALLER_ADDR
-
-/* inline function or macro may lead to unexpected result */
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/cris/include/asm/io.h b/arch/cris/include/asm/io.h
index ac12ae2b9286..db9a16c704f3 100644
--- a/arch/cris/include/asm/io.h
+++ b/arch/cris/include/asm/io.h
@@ -3,6 +3,7 @@
 
 #include <asm/page.h>   /* for __va, __pa */
 #include <arch/io.h>
+#include <asm-generic/iomap.h>
 #include <linux/kernel.h>
 
 struct cris_io_operations
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab6c696..1790f22e71a2 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	struct vm_area_struct * vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	D(printk(KERN_DEBUG
 		 "Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -155,6 +156,7 @@ retry:
 	} else if (writeaccess == 1) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2cfb67..9a66372fc7c7 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long _pme, lrai, lrad, fixup;
+	unsigned long flags = 0;
 	siginfo_t info;
 	pgd_t *pge;
 	pud_t *pue;
 	pte_t *pte;
-	int write;
 	int fault;
 
 #if 0
@@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(__frame))
+		flags |= FAULT_FLAG_USER;
+
 	down_read(&mm->mmap_sem);
 
 	vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
  */
  good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (esr0 & ESR0_ATXC) {
 	default:
 		/* handle write to write protected page */
@@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 #endif
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
-		write = 1;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 
 		 /* handle read from protected page */
@@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, ear0, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276dbec7d..8704c9320032 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 	int si_code = SEGV_MAPERR;
 	int fault;
 	const struct exception_table_entry *fixup;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 (cause > 0 ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/*
 	 * If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	local_irq_enable();
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -96,6 +97,7 @@ good_area:
 	case FLT_STORE:
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 	}
 
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index e0a899a1a8a6..5a84b3a50741 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -319,7 +319,7 @@ struct thread_struct {
 	regs->loadrs = 0;									\
 	regs->r8 = get_dumpable(current->mm);	/* set "don't zap registers" flag */		\
 	regs->r12 = new_sp - 16;	/* allocate 16 byte scratch area */			\
-	if (unlikely(!get_dumpable(current->mm))) {							\
+	if (unlikely(get_dumpable(current->mm) != SUID_DUMP_USER)) {	\
 		/*										\
 		 * Zap scratch regs to avoid leaking bits between processes with different	\
 		 * uid/privileges.								\
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index f034563aeae5..ff0968042829 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -44,10 +44,15 @@
 
 #define EFI_DEBUG	0
 
+static __initdata unsigned long palo_phys;
+
+static __initdata efi_config_table_type_t arch_tables[] = {
+	{PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys},
+	{NULL_GUID, NULL, 0},
+};
+
 extern efi_status_t efi_call_phys (void *, ...);
 
-struct efi efi;
-EXPORT_SYMBOL(efi);
 static efi_runtime_services_t *runtime;
 static u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL;
 
@@ -423,9 +428,9 @@ static u8 __init palo_checksum(u8 *buffer, u32 length)
  * Parse and handle PALO table which is published at:
  * http://www.dig64.org/home/DIG64_PALO_R1_0.pdf
  */
-static void __init handle_palo(unsigned long palo_phys)
+static void __init handle_palo(unsigned long phys_addr)
 {
-	struct palo_table *palo = __va(palo_phys);
+	struct palo_table *palo = __va(phys_addr);
 	u8  checksum;
 
 	if (strncmp(palo->signature, PALO_SIG, sizeof(PALO_SIG) - 1)) {
@@ -467,12 +472,13 @@ void __init
 efi_init (void)
 {
 	void *efi_map_start, *efi_map_end;
-	efi_config_table_t *config_tables;
 	efi_char16_t *c16;
 	u64 efi_desc_size;
 	char *cp, vendor[100] = "unknown";
 	int i;
-	unsigned long palo_phys;
+
+	set_bit(EFI_BOOT, &efi.flags);
+	set_bit(EFI_64BIT, &efi.flags);
 
 	/*
 	 * It's too early to be able to use the standard kernel command line
@@ -514,8 +520,6 @@ efi_init (void)
 		       efi.systab->hdr.revision >> 16,
 		       efi.systab->hdr.revision & 0xffff);
 
-	config_tables = __va(efi.systab->tables);
-
 	/* Show what we know for posterity */
 	c16 = __va(efi.systab->fw_vendor);
 	if (c16) {
@@ -528,43 +532,12 @@ efi_init (void)
 	       efi.systab->hdr.revision >> 16,
 	       efi.systab->hdr.revision & 0xffff, vendor);
 
-	efi.mps        = EFI_INVALID_TABLE_ADDR;
-	efi.acpi       = EFI_INVALID_TABLE_ADDR;
-	efi.acpi20     = EFI_INVALID_TABLE_ADDR;
-	efi.smbios     = EFI_INVALID_TABLE_ADDR;
-	efi.sal_systab = EFI_INVALID_TABLE_ADDR;
-	efi.boot_info  = EFI_INVALID_TABLE_ADDR;
-	efi.hcdp       = EFI_INVALID_TABLE_ADDR;
-	efi.uga        = EFI_INVALID_TABLE_ADDR;
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	palo_phys      = EFI_INVALID_TABLE_ADDR;
 
-	for (i = 0; i < (int) efi.systab->nr_tables; i++) {
-		if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
-			efi.mps = config_tables[i].table;
-			printk(" MPS=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) {
-			efi.acpi20 = config_tables[i].table;
-			printk(" ACPI 2.0=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) {
-			efi.acpi = config_tables[i].table;
-			printk(" ACPI=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) {
-			efi.smbios = config_tables[i].table;
-			printk(" SMBIOS=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) {
-			efi.sal_systab = config_tables[i].table;
-			printk(" SALsystab=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
-			efi.hcdp = config_tables[i].table;
-			printk(" HCDP=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid,
-			 PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID) == 0) {
-			palo_phys = config_tables[i].table;
-			printk(" PALO=0x%lx", config_tables[i].table);
-		}
-	}
-	printk("\n");
+	if (efi_config_init(arch_tables) != 0)
+		return;
 
 	if (palo_phys != EFI_INVALID_TABLE_ADDR)
 		handle_palo(palo_phys);
@@ -689,6 +662,8 @@ efi_enter_virtual_mode (void)
 		return;
 	}
 
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
 	/*
 	 * Now that EFI is in virtual mode, we call the EFI functions more
 	 * efficiently:
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341f978e..7225dad87094 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
 		| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
 
-	flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
 	/* mmap_sem is performance critical.... */
 	prefetchw(&mm->mmap_sem);
 
@@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	if (notify_page_fault(regs, TRAP_BRKPT))
 		return;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (mask & VM_WRITE)
+		flags |= FAULT_FLAG_WRITE;
 retry:
 	down_read(&mm->mmap_sem);
 
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c1d091..e9c6a8014bd6 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	unsigned long page, addr;
-	int write;
+	unsigned long flags = 0;
 	int fault;
 	siginfo_t info;
 
@@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (error_code & ACE_USERMODE)
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
  */
 good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
 		default:	/* 3: write, present */
 			/* fall through */
 		case ACE_WRITE:	/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto bad_area;
-			write++;
+			flags |= FAULT_FLAG_WRITE;
 			break;
 		case ACE_PROTECTION:	/* read, present */
 		case 0:		/* read, not present */
@@ -194,7 +196,7 @@ good_area:
 	 */
 	addr = (address & PAGE_MASK);
 	set_thread_fault_code(error_code);
-	fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, addr, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 821170e5f6ed..b969eea4e237 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -16,6 +16,7 @@ config M68K
 	select FPU if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
 	select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727806bf..eb1d61f68725 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c
index 2c7dde3c6430..2a5259fd23eb 100644
--- a/arch/m68k/mm/hwtest.c
+++ b/arch/m68k/mm/hwtest.c
@@ -28,9 +28,11 @@
 int hwreg_present( volatile void *regp )
 {
     int	ret = 0;
+    unsigned long flags;
     long	save_sp, save_vbr;
     long	tmp_vectors[3];
 
+    local_irq_save(flags);
     __asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr1,%4@(8)\n\t"
@@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors)
                 );
+    local_irq_restore(flags);
 
     return( ret );
 }
@@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present);
 int hwreg_write( volatile void *regp, unsigned short val )
 {
 	int		ret;
+	unsigned long flags;
 	long	save_sp, save_vbr;
 	long	tmp_vectors[3];
 
+	local_irq_save(flags);
 	__asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr2,%4@(8)\n\t"
@@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors), "g" (val)
 	);
+	local_irq_restore(flags);
 
 	return( ret );
 }
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index c90bfc6bf648..e355a4c10968 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -15,6 +15,7 @@ static inline void wr_fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 
 #else /* CONFIG_METAG_META21 */
@@ -35,6 +36,7 @@ static inline void wr_fence(void)
 	*flushptr = 0;
 	*flushptr = 0;
 	*flushptr = 0;
+	barrier();
 }
 
 #endif /* !CONFIG_METAG_META21 */
@@ -68,6 +70,7 @@ static inline void fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 #define smp_mb()        fence()
 #define smp_rmb()       fence()
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index 9b029a7911c3..579e3d93a5ca 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -22,6 +22,8 @@
 /* Add an extra page of padding at the top of the stack for the guard page. */
 #define STACK_TOP	(TASK_SIZE - PAGE_SIZE)
 #define STACK_TOP_MAX	STACK_TOP
+/* Maximum virtual space for stack */
+#define STACK_SIZE_MAX	(1 << 28)	/* 256 MB */
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2c75bf7357c5..332680e5ebf2 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct vm_area_struct *vma, *prev_vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write_access ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 
@@ -109,6 +108,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
@@ -121,6 +122,7 @@ good_area:
 	if (write_access) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
@@ -224,8 +226,10 @@ do_sigbus:
 	 */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (user_mode(regs))
-		do_group_exit(SIGKILL);
+	if (user_mode(regs)) {
+		pagefault_out_of_memory();
+		return 1;
+	}
 
 no_context:
 	/* Are we prepared to handle this kernel fault?  */
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739d17a1..fa4cf52aa7a6 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	int code = SEGV_MAPERR;
 	int is_write = error_code & ESR_S;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					 (is_write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	regs->ear = address;
 	regs->esr = error_code;
@@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -199,6 +201,7 @@ good_area:
 	if (unlikely(is_write)) {
 		if (unlikely(!(vma->vm_flags & VM_WRITE)))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index 2c9573098c0d..d498a1f9bccf 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 #include <asm/addrspace.h>
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index a22f06a6f7ca..45c1a6caa206 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -635,7 +635,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
 		cpumask_clear(&new_affinity);
 		cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity);
 	}
-	__irq_set_affinity_locked(data, &new_affinity);
+	irq_set_affinity_locked(data, &new_affinity, false);
 }
 
 static int octeon_irq_ciu_set_affinity(struct irq_data *data,
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 2a75ff249e71..6430e7acb1eb 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -463,6 +463,18 @@ static void octeon_halt(void)
 	octeon_kill_core(NULL);
 }
 
+static char __read_mostly octeon_system_type[80];
+
+static int __init init_octeon_system_type(void)
+{
+	snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)",
+		cvmx_board_type_to_string(octeon_bootinfo->board_type),
+		octeon_model_get_string(read_c0_prid()));
+
+	return 0;
+}
+early_initcall(init_octeon_system_type);
+
 /**
  * Handle all the error condition interrupts that might occur.
  *
@@ -482,11 +494,7 @@ static irqreturn_t octeon_rlm_interrupt(int cpl, void *dev_id)
  */
 const char *octeon_board_type_string(void)
 {
-	static char name[80];
-	sprintf(name, "%s (%s)",
-		cvmx_board_type_to_string(octeon_bootinfo->board_type),
-		octeon_model_get_string(read_c0_prid()));
-	return name;
+	return octeon_system_type;
 }
 
 const char *get_system_type(void)
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77ed9b9d..e194f957ca8c 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\tnop\n\t"
+	asm_volatile_goto("1:\tnop\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 87e6207b05e4..3d0074e10595 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -14,6 +14,7 @@
 #define _ASM_MIPSREGS_H
 
 #include <linux/linkage.h>
+#include <linux/types.h>
 #include <asm/hazards.h>
 #include <asm/war.h>
 
diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h
index 910e71a12466..b8343ccbc989 100644
--- a/arch/mips/include/asm/reg.h
+++ b/arch/mips/include/asm/reg.h
@@ -12,116 +12,194 @@
 #ifndef __ASM_MIPS_REG_H
 #define __ASM_MIPS_REG_H
 
-
-#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			6
-#define EF_R1			7
-#define EF_R2			8
-#define EF_R3			9
-#define EF_R4			10
-#define EF_R5			11
-#define EF_R6			12
-#define EF_R7			13
-#define EF_R8			14
-#define EF_R9			15
-#define EF_R10			16
-#define EF_R11			17
-#define EF_R12			18
-#define EF_R13			19
-#define EF_R14			20
-#define EF_R15			21
-#define EF_R16			22
-#define EF_R17			23
-#define EF_R18			24
-#define EF_R19			25
-#define EF_R20			26
-#define EF_R21			27
-#define EF_R22			28
-#define EF_R23			29
-#define EF_R24			30
-#define EF_R25			31
+#define MIPS32_EF_R0		6
+#define MIPS32_EF_R1		7
+#define MIPS32_EF_R2		8
+#define MIPS32_EF_R3		9
+#define MIPS32_EF_R4		10
+#define MIPS32_EF_R5		11
+#define MIPS32_EF_R6		12
+#define MIPS32_EF_R7		13
+#define MIPS32_EF_R8		14
+#define MIPS32_EF_R9		15
+#define MIPS32_EF_R10		16
+#define MIPS32_EF_R11		17
+#define MIPS32_EF_R12		18
+#define MIPS32_EF_R13		19
+#define MIPS32_EF_R14		20
+#define MIPS32_EF_R15		21
+#define MIPS32_EF_R16		22
+#define MIPS32_EF_R17		23
+#define MIPS32_EF_R18		24
+#define MIPS32_EF_R19		25
+#define MIPS32_EF_R20		26
+#define MIPS32_EF_R21		27
+#define MIPS32_EF_R22		28
+#define MIPS32_EF_R23		29
+#define MIPS32_EF_R24		30
+#define MIPS32_EF_R25		31
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			32
-#define EF_R27			33
+#define MIPS32_EF_R26		32
+#define MIPS32_EF_R27		33
 
-#define EF_R28			34
-#define EF_R29			35
-#define EF_R30			36
-#define EF_R31			37
+#define MIPS32_EF_R28		34
+#define MIPS32_EF_R29		35
+#define MIPS32_EF_R30		36
+#define MIPS32_EF_R31		37
 
 /*
  * Saved special registers
  */
-#define EF_LO			38
-#define EF_HI			39
-
-#define EF_CP0_EPC		40
-#define EF_CP0_BADVADDR		41
-#define EF_CP0_STATUS		42
-#define EF_CP0_CAUSE		43
-#define EF_UNUSED0		44
-
-#define EF_SIZE			180
-
-#endif
-
-#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			 0
-#define EF_R1			 1
-#define EF_R2			 2
-#define EF_R3			 3
-#define EF_R4			 4
-#define EF_R5			 5
-#define EF_R6			 6
-#define EF_R7			 7
-#define EF_R8			 8
-#define EF_R9			 9
-#define EF_R10			10
-#define EF_R11			11
-#define EF_R12			12
-#define EF_R13			13
-#define EF_R14			14
-#define EF_R15			15
-#define EF_R16			16
-#define EF_R17			17
-#define EF_R18			18
-#define EF_R19			19
-#define EF_R20			20
-#define EF_R21			21
-#define EF_R22			22
-#define EF_R23			23
-#define EF_R24			24
-#define EF_R25			25
+#define MIPS32_EF_LO		38
+#define MIPS32_EF_HI		39
+
+#define MIPS32_EF_CP0_EPC	40
+#define MIPS32_EF_CP0_BADVADDR	41
+#define MIPS32_EF_CP0_STATUS	42
+#define MIPS32_EF_CP0_CAUSE	43
+#define MIPS32_EF_UNUSED0	44
+
+#define MIPS32_EF_SIZE		180
+
+#define MIPS64_EF_R0		0
+#define MIPS64_EF_R1		1
+#define MIPS64_EF_R2		2
+#define MIPS64_EF_R3		3
+#define MIPS64_EF_R4		4
+#define MIPS64_EF_R5		5
+#define MIPS64_EF_R6		6
+#define MIPS64_EF_R7		7
+#define MIPS64_EF_R8		8
+#define MIPS64_EF_R9		9
+#define MIPS64_EF_R10		10
+#define MIPS64_EF_R11		11
+#define MIPS64_EF_R12		12
+#define MIPS64_EF_R13		13
+#define MIPS64_EF_R14		14
+#define MIPS64_EF_R15		15
+#define MIPS64_EF_R16		16
+#define MIPS64_EF_R17		17
+#define MIPS64_EF_R18		18
+#define MIPS64_EF_R19		19
+#define MIPS64_EF_R20		20
+#define MIPS64_EF_R21		21
+#define MIPS64_EF_R22		22
+#define MIPS64_EF_R23		23
+#define MIPS64_EF_R24		24
+#define MIPS64_EF_R25		25
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			26
-#define EF_R27			27
+#define MIPS64_EF_R26		26
+#define MIPS64_EF_R27		27
 
 
-#define EF_R28			28
-#define EF_R29			29
-#define EF_R30			30
-#define EF_R31			31
+#define MIPS64_EF_R28		28
+#define MIPS64_EF_R29		29
+#define MIPS64_EF_R30		30
+#define MIPS64_EF_R31		31
 
 /*
  * Saved special registers
  */
-#define EF_LO			32
-#define EF_HI			33
-
-#define EF_CP0_EPC		34
-#define EF_CP0_BADVADDR		35
-#define EF_CP0_STATUS		36
-#define EF_CP0_CAUSE		37
-
-#define EF_SIZE			304	/* size in bytes */
+#define MIPS64_EF_LO		32
+#define MIPS64_EF_HI		33
+
+#define MIPS64_EF_CP0_EPC	34
+#define MIPS64_EF_CP0_BADVADDR	35
+#define MIPS64_EF_CP0_STATUS	36
+#define MIPS64_EF_CP0_CAUSE	37
+
+#define MIPS64_EF_SIZE		304	/* size in bytes */
+
+#if defined(CONFIG_32BIT)
+
+#define EF_R0			MIPS32_EF_R0
+#define EF_R1			MIPS32_EF_R1
+#define EF_R2			MIPS32_EF_R2
+#define EF_R3			MIPS32_EF_R3
+#define EF_R4			MIPS32_EF_R4
+#define EF_R5			MIPS32_EF_R5
+#define EF_R6			MIPS32_EF_R6
+#define EF_R7			MIPS32_EF_R7
+#define EF_R8			MIPS32_EF_R8
+#define EF_R9			MIPS32_EF_R9
+#define EF_R10			MIPS32_EF_R10
+#define EF_R11			MIPS32_EF_R11
+#define EF_R12			MIPS32_EF_R12
+#define EF_R13			MIPS32_EF_R13
+#define EF_R14			MIPS32_EF_R14
+#define EF_R15			MIPS32_EF_R15
+#define EF_R16			MIPS32_EF_R16
+#define EF_R17			MIPS32_EF_R17
+#define EF_R18			MIPS32_EF_R18
+#define EF_R19			MIPS32_EF_R19
+#define EF_R20			MIPS32_EF_R20
+#define EF_R21			MIPS32_EF_R21
+#define EF_R22			MIPS32_EF_R22
+#define EF_R23			MIPS32_EF_R23
+#define EF_R24			MIPS32_EF_R24
+#define EF_R25			MIPS32_EF_R25
+#define EF_R26			MIPS32_EF_R26
+#define EF_R27			MIPS32_EF_R27
+#define EF_R28			MIPS32_EF_R28
+#define EF_R29			MIPS32_EF_R29
+#define EF_R30			MIPS32_EF_R30
+#define EF_R31			MIPS32_EF_R31
+#define EF_LO			MIPS32_EF_LO
+#define EF_HI			MIPS32_EF_HI
+#define EF_CP0_EPC		MIPS32_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS32_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS32_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS32_EF_CP0_CAUSE
+#define EF_UNUSED0		MIPS32_EF_UNUSED0
+#define EF_SIZE			MIPS32_EF_SIZE
+
+#elif defined(CONFIG_64BIT)
+
+#define EF_R0			MIPS64_EF_R0
+#define EF_R1			MIPS64_EF_R1
+#define EF_R2			MIPS64_EF_R2
+#define EF_R3			MIPS64_EF_R3
+#define EF_R4			MIPS64_EF_R4
+#define EF_R5			MIPS64_EF_R5
+#define EF_R6			MIPS64_EF_R6
+#define EF_R7			MIPS64_EF_R7
+#define EF_R8			MIPS64_EF_R8
+#define EF_R9			MIPS64_EF_R9
+#define EF_R10			MIPS64_EF_R10
+#define EF_R11			MIPS64_EF_R11
+#define EF_R12			MIPS64_EF_R12
+#define EF_R13			MIPS64_EF_R13
+#define EF_R14			MIPS64_EF_R14
+#define EF_R15			MIPS64_EF_R15
+#define EF_R16			MIPS64_EF_R16
+#define EF_R17			MIPS64_EF_R17
+#define EF_R18			MIPS64_EF_R18
+#define EF_R19			MIPS64_EF_R19
+#define EF_R20			MIPS64_EF_R20
+#define EF_R21			MIPS64_EF_R21
+#define EF_R22			MIPS64_EF_R22
+#define EF_R23			MIPS64_EF_R23
+#define EF_R24			MIPS64_EF_R24
+#define EF_R25			MIPS64_EF_R25
+#define EF_R26			MIPS64_EF_R26
+#define EF_R27			MIPS64_EF_R27
+#define EF_R28			MIPS64_EF_R28
+#define EF_R29			MIPS64_EF_R29
+#define EF_R30			MIPS64_EF_R30
+#define EF_R31			MIPS64_EF_R31
+#define EF_LO			MIPS64_EF_LO
+#define EF_HI			MIPS64_EF_HI
+#define EF_CP0_EPC		MIPS64_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS64_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS64_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS64_EF_CP0_CAUSE
+#define EF_SIZE			MIPS64_EF_SIZE
 
 #endif /* CONFIG_64BIT */
 
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 895320e25662..e6e5d9162213 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -131,6 +131,8 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_FPUBOUND		(1<<TIF_FPUBOUND)
 #define _TIF_LOAD_WATCH		(1<<TIF_LOAD_WATCH)
 
+#define _TIF_WORK_SYSCALL_ENTRY	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP)
+
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT)
 
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 202e581e6096..7fdf1de0447f 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -58,12 +58,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 #include <asm/processor.h>
 
-/*
- * When this file is selected, we are definitely running a 64bit kernel.
- * So using the right regs define in asm/reg.h
- */
-#define WANT_COMPAT_REG_H
-
 /* These MUST be defined before elf.h gets included */
 extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs);
 #define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs);
@@ -135,21 +129,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs)
 {
 	int i;
 
-	for (i = 0; i < EF_R0; i++)
+	for (i = 0; i < MIPS32_EF_R0; i++)
 		grp[i] = 0;
-	grp[EF_R0] = 0;
+	grp[MIPS32_EF_R0] = 0;
 	for (i = 1; i <= 31; i++)
-		grp[EF_R0 + i] = (elf_greg_t) regs->regs[i];
-	grp[EF_R26] = 0;
-	grp[EF_R27] = 0;
-	grp[EF_LO] = (elf_greg_t) regs->lo;
-	grp[EF_HI] = (elf_greg_t) regs->hi;
-	grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
-	grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
-	grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
-	grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
-#ifdef EF_UNUSED0
-	grp[EF_UNUSED0] = 0;
+		grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i];
+	grp[MIPS32_EF_R26] = 0;
+	grp[MIPS32_EF_R27] = 0;
+	grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo;
+	grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi;
+	grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
+	grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
+	grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
+	grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
+#ifdef MIPS32_EF_UNUSED0
+	grp[MIPS32_EF_UNUSED0] = 0;
 #endif
 }
 
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index c01b307317a9..bffbbc557879 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -256,11 +256,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu,
 
 	/* Setup Intr to Pin mapping */
 	if (pin & GIC_MAP_TO_NMI_MSK) {
+		int i;
+
 		GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
 		/* FIXME: hack to route NMI to all cpu's */
-		for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+		for (i = 0; i < NR_CPUS; i += 32) {
 			GICWRITE(GIC_REG_ADDR(SHARED,
-					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)),
 				 0xffffffff);
 		}
 	} else {
diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index fab40f7d2e03..ac9facc08694 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -131,7 +131,7 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma
 
 	board_bind_eic_interrupt = &msc_bind_eic_interrupt;
 
-	for (; nirq >= 0; nirq--, imp++) {
+	for (; nirq > 0; nirq--, imp++) {
 		int n = imp->im_irq;
 
 		switch (imp->im_type) {
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 33d067148e61..3efbf0b29c1b 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra)
 	 nop
 #endif
 	b	ftrace_stub
+#ifdef CONFIG_32BIT
+	 addiu sp, sp, 8
+#else
 	 nop
+#endif
 
 static_trace:
 	MCOUNT_SAVE_REGS
@@ -133,6 +137,9 @@ static_trace:
 	 move	a1, AT		/* arg2: parent's return address */
 
 	MCOUNT_RESTORE_REGS
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK
@@ -181,6 +188,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra)
 	jal	prepare_ftrace_return
 	 nop
 	MCOUNT_RESTORE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
+#endif
 	RETURN_BACK
 	END(ftrace_graph_caller)
 
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9c6299c733a3..1b95b2443221 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -161,6 +161,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 		__get_user(fregs[i], i + (__u64 __user *) data);
 
 	__get_user(child->thread.fpu.fcr31, data + 64);
+	child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
 
 	/* FIR may not be written.  */
 
@@ -451,7 +452,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
-			child->thread.fpu.fcr31 = data;
+			child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 9b36424b03c5..ed5bafb5d637 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -52,7 +52,7 @@ NESTED(handle_sys, PT_SIZE, sp)
 
 stack_done:
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
-	li	t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	and	t0, t1
 	bnez	t0, syscall_trace_entry # -> yes
 
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 97a5909a61cf..be6627ead619 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -54,7 +54,7 @@ NESTED(handle_sys64, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
-	li	t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
 	bnez	t0, syscall_trace_entry
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index edcb6594e7b5..cab150789c8d 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -47,7 +47,7 @@ NESTED(handle_sysn32, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
-	li	t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
 	bnez	t0, n32_syscall_trace_entry
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 74f485d3c0ef..37605dc8eef7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -81,7 +81,7 @@ NESTED(handle_sys, PT_SIZE, sp)
 	PTR	4b, bad_stack
 	.previous
 
-	li	t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
 	bnez	t0, trace_a_syscall
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 203d8857070d..2c81265bcf46 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -604,7 +604,6 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sdc1_op:
 		die_if_kernel("Unaligned FP access in kernel code", regs);
 		BUG_ON(!used_math());
-		BUG_ON(!is_fpu_owner());
 
 		lose_fpu(1);	/* Save FPU state for the emulator. */
 		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index 73b34827826c..5cd48572450e 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -149,9 +149,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm)
 		if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE)
 			kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]);
 	}
-
-	if (kvm->arch.guest_pmap)
-		kfree(kvm->arch.guest_pmap);
+	kfree(kvm->arch.guest_pmap);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		kvm_arch_vcpu_free(vcpu);
@@ -304,7 +302,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (cpu_has_veic || cpu_has_vint) {
 		size = 0x200 + VECTORSPACING * 64;
 	} else {
-		size = 0x200;
+		size = 0x4000;
 	}
 
 	/* Save Linux EBASE */
@@ -389,12 +387,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 
 	kvm_mips_dump_stats(vcpu);
 
-	if (vcpu->arch.guest_ebase)
-		kfree(vcpu->arch.guest_ebase);
-
-	if (vcpu->arch.kseg0_commpage)
-		kfree(vcpu->arch.kseg0_commpage);
-
+	kfree(vcpu->arch.guest_ebase);
+	kfree(vcpu->arch.kseg0_commpage);
+	kfree(vcpu);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c
index 4b6274b47f33..e75ef8219caf 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/kvm_mips_emul.c
@@ -1571,17 +1571,17 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 			arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0);
 #else
 			/* UserLocal not implemented */
-			er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
+			er = EMULATE_FAIL;
 #endif
 			break;
 
 		default:
-			printk("RDHWR not supported\n");
+			kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc);
 			er = EMULATE_FAIL;
 			break;
 		}
 	} else {
-		printk("Emulate RI not supported @ %p: %#x\n", opc, inst);
+		kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst);
 		er = EMULATE_FAIL;
 	}
 
@@ -1590,6 +1590,7 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	 */
 	if (er == EMULATE_FAIL) {
 		vcpu->arch.pc = curr_pc;
+		er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
 	}
 	return er;
 }
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/lantiq/dts/easy50712.dts
index fac1f5b178eb..143b8a37b5e4 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/lantiq/dts/easy50712.dts
@@ -8,6 +8,7 @@
 	};
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 4c57b3e5743f..33f76e658d19 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -10,7 +10,8 @@ obj-$(CONFIG_GPIOLIB) += gpio.o
 # Serial port support
 #
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-obj-$(CONFIG_SERIAL_8250) += serial.o
+loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
+obj-y += $(loongson-serial-m) $(loongson-serial-y)
 obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
 obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 21813beec7a5..c2ec87e5d1cc 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -12,6 +12,7 @@
 #include <linux/highmem.h>
 #include <linux/kernel.h>
 #include <linux/linkage.h>
+#include <linux/preempt.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
@@ -601,11 +602,13 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	/* Catch bad driver code */
 	BUG_ON(size == 0);
 
+	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size)
 			r4k_blast_scache();
 		else
 			blast_scache_range(addr, addr + size);
+		preempt_enable();
 		__sync();
 		return;
 	}
@@ -621,6 +624,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 		R4600_HIT_CACHEOP_WAR_IMPL;
 		blast_dcache_range(addr, addr + size);
 	}
+	preempt_enable();
 
 	bc_wback_inv(addr, size);
 	__sync();
@@ -631,6 +635,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	/* Catch bad driver code */
 	BUG_ON(size == 0);
 
+	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size)
 			r4k_blast_scache();
@@ -645,6 +650,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 			 */
 			blast_inv_scache_range(addr, addr + size);
 		}
+		preempt_enable();
 		__sync();
 		return;
 	}
@@ -655,6 +661,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		R4600_HIT_CACHEOP_WAR_IMPL;
 		blast_inv_dcache_range(addr, addr + size);
 	}
+	preempt_enable();
 
 	bc_inv(addr, size);
 	__sync();
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index caf92ecb37d6..23129d1005db 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -50,16 +50,20 @@ static inline struct page *dma_addr_to_page(struct device *dev,
 }
 
 /*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
+ * speculatively fill random cachelines with stale data at any time,
+ * requiring an extra flush post-DMA.
+ *
  * Warning on the terminology - Linux calls an uncached area coherent;
  * MIPS terminology calls memory areas with hardware maintained coherency
  * coherent.
  */
-
-static inline int cpu_is_noncoherent_r10000(struct device *dev)
+static inline int cpu_needs_post_dma_flush(struct device *dev)
 {
 	return !plat_device_is_coherent(dev) &&
 	       (current_cpu_type() == CPU_R10000 ||
-	       current_cpu_type() == CPU_R12000);
+		current_cpu_type() == CPU_R12000 ||
+		current_cpu_type() == CPU_BMIPS5000);
 }
 
 static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
@@ -230,7 +234,7 @@ static inline void __dma_sync(struct page *page,
 static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
 {
-	if (cpu_is_noncoherent_r10000(dev))
+	if (cpu_needs_post_dma_flush(dev))
 		__dma_sync(dma_addr_to_page(dev, dma_addr),
 			   dma_addr & ~PAGE_MASK, size, direction);
 
@@ -281,7 +285,7 @@ static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 static void mips_dma_sync_single_for_cpu(struct device *dev,
 	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
 {
-	if (cpu_is_noncoherent_r10000(dev))
+	if (cpu_needs_post_dma_flush(dev))
 		__dma_sync(dma_addr_to_page(dev, dma_handle),
 			   dma_handle & ~PAGE_MASK, size, direction);
 }
@@ -302,7 +306,7 @@ static void mips_dma_sync_sg_for_cpu(struct device *dev,
 
 	/* Make sure that gcc doesn't leave the empty loop body.  */
 	for (i = 0; i < nelems; i++, sg++) {
-		if (cpu_is_noncoherent_r10000(dev))
+		if (cpu_needs_post_dma_flush(dev))
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
 	}
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 0fead53d1c26..0214a43b9911 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -41,8 +41,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
 	const int field = sizeof(unsigned long) * 2;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-						 (write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 #if 0
 	printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -92,6 +91,8 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -113,6 +114,7 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (cpu_has_rixi) {
 			if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
@@ -240,6 +242,8 @@ out_of_memory:
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	up_read(&mm->mmap_sem);
+	if (!user_mode(regs))
+		goto no_context;
 	pagefault_out_of_memory();
 	return;
 
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index afeef93f81a7..a91a7a99f70f 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1091,6 +1091,7 @@ static void __cpuinit build_update_entries(u32 **p, unsigned int tmp,
 struct mips_huge_tlb_info {
 	int huge_pte;
 	int restore_scratch;
+	bool need_reload_pte;
 };
 
 static struct mips_huge_tlb_info __cpuinit
@@ -1105,6 +1106,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	rv.huge_pte = scratch;
 	rv.restore_scratch = 0;
+	rv.need_reload_pte = false;
 
 	if (check_for_high_segbits) {
 		UASM_i_MFC0(p, tmp, C0_BADVADDR);
@@ -1293,6 +1295,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	} else {
 		htlb_info.huge_pte = K0;
 		htlb_info.restore_scratch = 0;
+		htlb_info.need_reload_pte = true;
 		vmalloc_mode = refill_noscratch;
 		/*
 		 * create the plain linear handler
@@ -1329,6 +1332,8 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	}
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	uasm_l_tlb_huge_update(&l, p);
+	if (htlb_info.need_reload_pte)
+		UASM_i_LW(&p, htlb_info.huge_pte, 0, K1);
 	build_huge_update_entries(&p, htlb_info.huge_pte, K1);
 	build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
 				   htlb_info.restore_scratch);
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
index 6854ed5097d2..83a1dfd8f0e3 100644
--- a/arch/mips/oprofile/backtrace.c
+++ b/arch/mips/oprofile/backtrace.c
@@ -92,7 +92,7 @@ static inline int unwind_user_frame(struct stackframe *old_frame,
 				/* This marks the end of the previous function,
 				   which means we overran. */
 				break;
-			stack_size = (unsigned) stack_adjustment;
+			stack_size = (unsigned long) stack_adjustment;
 		} else if (is_ra_save_ins(&ip)) {
 			int ra_slot = ip.i_format.simmediate;
 			if (ra_slot < 0)
diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S
index 7e0277a1048f..32a7c828f073 100644
--- a/arch/mips/power/hibernate.S
+++ b/arch/mips/power/hibernate.S
@@ -43,6 +43,7 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
+	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/ralink/dts/mt7620a_eval.dts
index 35eb874ab7f1..709f58132f5c 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/ralink/dts/mt7620a_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink MT7620A evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/ralink/dts/rt2880_eval.dts
index 322d7002595b..0a685db093d4 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/ralink/dts/rt2880_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT2880 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x8000000 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts
index 0ac73ea28198..ec9e9a035541 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/ralink/dts/rt3052_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3052 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/ralink/dts/rt3883_eval.dts
index 2fa6b330bf4f..e8df21a5d10d 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/ralink/dts/rt3883_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3883 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index d48a84fd7fae..3516cbdf1ee9 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
@@ -345,9 +347,10 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	printk(KERN_ALERT "VM: killing process %s\n", tsk->comm);
-	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
-		do_exit(SIGKILL);
+	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
+		pagefault_out_of_memory();
+		return;
+	}
 	goto no_context;
 
 do_sigbus:
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index d8a455ede5a7..fec8bf97d806 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -853,37 +853,44 @@ UNHANDLED_EXCEPTION(_vector_0x1f00,0x1f00)
 
 /* ========================================================[ return ] === */
 
+_resume_userspace:
+	DISABLE_INTERRUPTS(r3,r4)
+	l.lwz	r4,TI_FLAGS(r10)
+	l.andi	r13,r4,_TIF_WORK_MASK
+	l.sfeqi	r13,0
+	l.bf	_restore_all
+	 l.nop
+
 _work_pending:
-	/*
-	 * if (current_thread_info->flags & _TIF_NEED_RESCHED)
-	 *     schedule();
-	 */
-	l.lwz   r5,TI_FLAGS(r10)
-	l.andi	r3,r5,_TIF_NEED_RESCHED
-	l.sfnei r3,0
-	l.bnf   _work_notifysig
+	l.lwz	r5,PT_ORIG_GPR11(r1)
+	l.sfltsi r5,0
+	l.bnf	1f
 	 l.nop
-	l.jal   schedule
+	l.andi	r5,r5,0
+1:
+	l.jal	do_work_pending
+	 l.ori	r3,r1,0			/* pt_regs */
+
+	l.sfeqi	r11,0
+	l.bf	_restore_all
 	 l.nop
-	l.j	_resume_userspace
+	l.sfltsi r11,0
+	l.bnf	1f
 	 l.nop
-
-/* Handle pending signals and notify-resume requests.
- * do_notify_resume must be passed the latest pushed pt_regs, not
- * necessarily the "userspace" ones.  Also, pt_regs->syscallno
- * must be set so that the syscall restart functionality works.
- */
-_work_notifysig:
-	l.jal	do_notify_resume
-	 l.ori	r3,r1,0		  /* pt_regs */
-
-_resume_userspace:
-	DISABLE_INTERRUPTS(r3,r4)
-	l.lwz	r3,TI_FLAGS(r10)
-	l.andi	r3,r3,_TIF_WORK_MASK
-	l.sfnei	r3,0
-	l.bf	_work_pending
+	l.and	r11,r11,r0
+	l.ori	r11,r11,__NR_restart_syscall
+	l.j	_syscall_check_trace_enter
 	 l.nop
+1:
+	l.lwz	r11,PT_ORIG_GPR11(r1)
+	/* Restore arg registers */
+	l.lwz	r3,PT_GPR3(r1)
+	l.lwz	r4,PT_GPR4(r1)
+	l.lwz	r5,PT_GPR5(r1)
+	l.lwz	r6,PT_GPR6(r1)
+	l.lwz	r7,PT_GPR7(r1)
+	l.j	_syscall_check_trace_enter
+	 l.lwz	r8,PT_GPR8(r1)
 
 _restore_all:
 	RESTORE_ALL
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index ae167f7e081a..c277ec82783d 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -28,24 +28,24 @@
 #include <linux/tracehook.h>
 
 #include <asm/processor.h>
+#include <asm/syscall.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 
 #define DEBUG_SIG 0
 
 struct rt_sigframe {
-	struct siginfo *pinfo;
-	void *puc;
 	struct siginfo info;
 	struct ucontext uc;
 	unsigned char retcode[16];	/* trampoline code */
 };
 
-static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc)
+static int restore_sigcontext(struct pt_regs *regs,
+			      struct sigcontext __user *sc)
 {
-	unsigned int err = 0;
+	int err = 0;
 
-	/* Alwys make any pending restarted system call return -EINTR */
+	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
 	/*
@@ -53,25 +53,21 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc)
 	 * (sc is already checked for VERIFY_READ since the sigframe was
 	 *  checked in sys_sigreturn previously)
 	 */
-	if (__copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long)))
-		goto badframe;
-	if (__copy_from_user(&regs->pc, &sc->regs.pc, sizeof(unsigned long)))
-		goto badframe;
-	if (__copy_from_user(&regs->sr, &sc->regs.sr, sizeof(unsigned long)))
-		goto badframe;
+	err |= __copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long));
+	err |= __copy_from_user(&regs->pc, &sc->regs.pc, sizeof(unsigned long));
+	err |= __copy_from_user(&regs->sr, &sc->regs.sr, sizeof(unsigned long));
 
 	/* make sure the SM-bit is cleared so user-mode cannot fool us */
 	regs->sr &= ~SPR_SR_SM;
 
+	regs->orig_gpr11 = -1;	/* Avoid syscall restart checks */
+
 	/* TODO: the other ports use regs->orig_XX to disable syscall checks
 	 * after this completes, but we don't use that mechanism. maybe we can
 	 * use it now ?
 	 */
 
 	return err;
-
-badframe:
-	return 1;
 }
 
 asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
@@ -111,21 +107,18 @@ badframe:
  * Set up a signal frame.
  */
 
-static int setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs,
-			    unsigned long mask)
+static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 {
 	int err = 0;
 
 	/* copy the regs */
-
+	/* There should be no need to save callee-saved registers here...
+	 * ...but we save them anyway.  Revisit this
+	 */
 	err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long));
 	err |= __copy_to_user(&sc->regs.pc, &regs->pc, sizeof(unsigned long));
 	err |= __copy_to_user(&sc->regs.sr, &regs->sr, sizeof(unsigned long));
 
-	/* then some other stuff */
-
-	err |= __put_user(mask, &sc->oldmask);
-
 	return err;
 }
 
@@ -181,24 +174,18 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	int err = 0;
 
 	frame = get_sigframe(ka, regs, sizeof(*frame));
-
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
 
-	err |= __put_user(&frame->info, &frame->pinfo);
-	err |= __put_user(&frame->uc, &frame->puc);
-
+	/* Create siginfo.  */
 	if (ka->sa.sa_flags & SA_SIGINFO)
 		err |= copy_siginfo_to_user(&frame->info, info);
-	if (err)
-		goto give_sigsegv;
 
-	/* Clear all the bits of the ucontext we don't use.  */
-	err |= __clear_user(&frame->uc, offsetof(struct ucontext, uc_mcontext));
+	/* Create the ucontext.  */
 	err |= __put_user(0, &frame->uc.uc_flags);
 	err |= __put_user(NULL, &frame->uc.uc_link);
 	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0]);
+	err |= setup_sigcontext(regs, &frame->uc.uc_mcontext);
 
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 
@@ -207,9 +194,12 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	/* trampoline - the desired return ip is the retcode itself */
 	return_ip = (unsigned long)&frame->retcode;
-	/* This is l.ori r11,r0,__NR_sigreturn, l.sys 1 */
-	err |= __put_user(0xa960, (short *)(frame->retcode + 0));
-	err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2));
+	/* This is:
+		l.ori r11,r0,__NR_sigreturn
+		l.sys 1
+	 */
+	err |= __put_user(0xa960,             (short *)(frame->retcode + 0));
+	err |= __put_user(__NR_rt_sigreturn,  (short *)(frame->retcode + 2));
 	err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4));
 	err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8));
 
@@ -262,82 +252,106 @@ handle_signal(unsigned long sig,
  * mode below.
  */
 
-void do_signal(struct pt_regs *regs)
+int do_signal(struct pt_regs *regs, int syscall)
 {
 	siginfo_t info;
 	int signr;
 	struct k_sigaction ka;
-
-	/*
-	 * We want the common case to go fast, which
-	 * is why we may in certain cases get here from
-	 * kernel mode. Just return without doing anything
-	 * if so.
-	 */
-	if (!user_mode(regs))
-		return;
-
-	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-
-	/* If we are coming out of a syscall then we need
-	 * to check if the syscall was interrupted and wants to be
-	 * restarted after handling the signal.  If so, the original
-	 * syscall number is put back into r11 and the PC rewound to
-	 * point at the l.sys instruction that resulted in the
-	 * original syscall.  Syscall results other than the four
-	 * below mean that the syscall executed to completion and no
-	 * restart is necessary.
-	 */
-	if (regs->orig_gpr11) {
-		int restart = 0;
-
-		switch (regs->gpr[11]) {
+	unsigned long continue_addr = 0;
+	unsigned long restart_addr = 0;
+	unsigned long retval = 0;
+	int restart = 0;
+
+	if (syscall) {
+		continue_addr = regs->pc;
+		restart_addr = continue_addr - 4;
+		retval = regs->gpr[11];
+
+		/*
+		 * Setup syscall restart here so that a debugger will
+		 * see the already changed PC.
+		 */
+		switch (retval) {
 		case -ERESTART_RESTARTBLOCK:
+			restart = -2;
+			/* Fall through */
 		case -ERESTARTNOHAND:
-			/* Restart if there is no signal handler */
-			restart = (signr <= 0);
-			break;
 		case -ERESTARTSYS:
-			/* Restart if there no signal handler or
-			 * SA_RESTART flag is set */
-			restart = (signr <= 0 || (ka.sa.sa_flags & SA_RESTART));
-			break;
 		case -ERESTARTNOINTR:
-			/* Always restart */
-			restart = 1;
+			restart++;
+			regs->gpr[11] = regs->orig_gpr11;
+			regs->pc = restart_addr;
 			break;
 		}
+	}
 
-		if (restart) {
-			if (regs->gpr[11] == -ERESTART_RESTARTBLOCK)
-				regs->gpr[11] = __NR_restart_syscall;
-			else
-				regs->gpr[11] = regs->orig_gpr11;
-			regs->pc -= 4;
-		} else {
-			regs->gpr[11] = -EINTR;
+	/*
+	 * Get the signal to deliver.  When running under ptrace, at this
+	 * point the debugger may change all our registers ...
+	 */
+	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+	/*
+	 * Depending on the signal settings we may need to revert the
+	 * decision to restart the system call.  But skip this if a
+	 * debugger has chosen to restart at a different PC.
+	 */
+	if (signr > 0) {
+		if (unlikely(restart) && regs->pc == restart_addr) {
+			if (retval == -ERESTARTNOHAND ||
+			    retval == -ERESTART_RESTARTBLOCK
+			    || (retval == -ERESTARTSYS
+			        && !(ka.sa.sa_flags & SA_RESTART))) {
+				/* No automatic restart */
+				regs->gpr[11] = -EINTR;
+				regs->pc = continue_addr;
+			}
 		}
-	}
 
-	if (signr <= 0) {
-		/* no signal to deliver so we just put the saved sigmask
-		 * back */
-		restore_saved_sigmask();
-	} else {		/* signr > 0 */
-		/* Whee!  Actually deliver the signal.  */
 		handle_signal(signr, &info, &ka, regs);
+	} else {
+		/* no handler */
+		restore_saved_sigmask();
+		/*
+		 * Restore pt_regs PC as syscall restart will be handled by
+		 * kernel without return to userspace
+		 */
+		if (unlikely(restart) && regs->pc == restart_addr) {
+			regs->pc = continue_addr;
+			return restart;
+		}
 	}
 
-	return;
+	return 0;
 }
 
-asmlinkage void do_notify_resume(struct pt_regs *regs)
+asmlinkage int
+do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
-	if (current_thread_info()->flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (current_thread_info()->flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
+	do {
+		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+			schedule();
+		} else {
+			if (unlikely(!user_mode(regs)))
+				return 0;
+			local_irq_enable();
+			if (thread_flags & _TIF_SIGPENDING) {
+				int restart = do_signal(regs, syscall);
+				if (unlikely(restart)) {
+					/*
+					 * Restart without handlers.
+					 * Deal with it without leaving
+					 * the kernel space.
+					 */
+					return restart;
+				}
+				syscall = 0;
+			} else {
+				clear_thread_flag(TIF_NOTIFY_RESUME);
+				tracehook_notify_resume(regs);
+			}
+		}
+		local_irq_disable();
+		thread_flags = current_thread_info()->flags;
+	} while (thread_flags & _TIF_WORK_MASK);
+	return 0;
 }
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e2bfafce66c5..0703acf7d327 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (user_mode(regs)) {
 		/* Exception was in userspace: reenable interrupts */
 		local_irq_enable();
+		flags |= FAULT_FLAG_USER;
 	} else {
 		/* If exception was in a syscall, then IRQ's may have
 		 * been enabled or disabled.  If they were enabled,
@@ -267,10 +268,10 @@ out_of_memory:
 	__asm__ __volatile__("l.nop 1");
 
 	up_read(&mm->mmap_sem);
-	printk("VM: killing process %s\n", tsk->comm);
-	if (user_mode(regs))
-		do_exit(SIGKILL);
-	goto no_context;
+	if (!user_mode(regs))
+		goto no_context;
+	pagefault_out_of_memory();
+	return;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 96ec3982be8d..94607bfa273d 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -46,7 +46,12 @@ cflags-y	:= -pipe
 
 # These flags should be implied by an hppa-linux configuration, but they
 # are not in gcc 3.2.
-cflags-y	+= -mno-space-regs -mfast-indirect-calls
+cflags-y	+= -mno-space-regs
+
+# -mfast-indirect-calls is only relevant for 32-bit kernels.
+ifndef CONFIG_64BIT
+cflags-y	+= -mfast-indirect-calls
+endif
 
 # Currently we save and restore fpregs on all kernel entry/interruption paths.
 # If that gets optimized, we might need to disable the use of fpregs in the
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index f0e2784e7cca..de65f66ea64e 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -125,15 +125,10 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma
 void mark_rodata_ro(void);
 #endif
 
-#ifdef CONFIG_PA8X00
-/* Only pa8800, pa8900 needs this */
-
 #include <asm/kmap_types.h>
 
 #define ARCH_HAS_KMAP
 
-void kunmap_parisc(void *addr);
-
 static inline void *kmap(struct page *page)
 {
 	might_sleep();
@@ -142,7 +137,7 @@ static inline void *kmap(struct page *page)
 
 static inline void kunmap(struct page *page)
 {
-	kunmap_parisc(page_address(page));
+	flush_kernel_dcache_page_addr(page_address(page));
 }
 
 static inline void *kmap_atomic(struct page *page)
@@ -153,14 +148,13 @@ static inline void *kmap_atomic(struct page *page)
 
 static inline void __kunmap_atomic(void *addr)
 {
-	kunmap_parisc(addr);
+	flush_kernel_dcache_page_addr(addr);
 	pagefault_enable();
 }
 
 #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
 #define kmap_atomic_to_page(ptr)	virt_to_page(ptr)
-#endif
 
 #endif /* _PARISC_CACHEFLUSH_H */
 
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
index 72c0fafaa039..544ed8ef87eb 100644
--- a/arch/parisc/include/asm/ftrace.h
+++ b/arch/parisc/include/asm/ftrace.h
@@ -24,15 +24,7 @@ extern void return_to_handler(void);
 
 extern unsigned long return_address(unsigned int);
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 return_address(1)
-#define CALLER_ADDR2 return_address(2)
-#define CALLER_ADDR3 return_address(3)
-#define CALLER_ADDR4 return_address(4)
-#define CALLER_ADDR5 return_address(5)
-#define CALLER_ADDR6 return_address(6)
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index b7adb2ac049c..637fe031aa84 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -28,9 +28,9 @@ struct page;
 
 void clear_page_asm(void *page);
 void copy_page_asm(void *to, void *from);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *pg);
+#define clear_user_page(vto, vaddr, page) clear_page_asm(vto)
 void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
-			   struct page *pg);
+			struct page *pg);
 
 /* #define CONFIG_PARISC_TMPALIAS */
 
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index cc2290a3cace..c6ee86542fec 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -53,6 +53,8 @@
 #define STACK_TOP	TASK_SIZE
 #define STACK_TOP_MAX	DEFAULT_TASK_SIZE
 
+#define STACK_SIZE_MAX	(1 << 30)	/* 1 GB */
+
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
new file mode 100644
index 000000000000..748016cb122d
--- /dev/null
+++ b/arch/parisc/include/asm/socket.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <uapi/asm/socket.h>
+
+/* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
+ * have to define SOCK_NONBLOCK to a different value here.
+ */
+#define SOCK_NONBLOCK	0x40000000
+
+#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index 0a3eada1863b..f395cde7b593 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -36,23 +36,16 @@ struct shmid64_ds {
 	unsigned int		__unused2;
 };
 
-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
 struct shminfo64 {
-	unsigned int	shmmax;
-	unsigned int	shmmin;
-	unsigned int	shmmni;
-	unsigned int	shmseg;
-	unsigned int	shmall;
-	unsigned int	__unused1;
-	unsigned int	__unused2;
-	unsigned int	__unused3;
-	unsigned int	__unused4;
+	unsigned long	shmmax;
+	unsigned long	shmmin;
+	unsigned long	shmmni;
+	unsigned long	shmseg;
+	unsigned long	shmall;
+	unsigned long	__unused1;
+	unsigned long	__unused2;
+	unsigned long	__unused3;
+	unsigned long	__unused4;
 };
 
 #endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index a2fa297196bc..f5645d6a89f2 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -69,8 +69,6 @@
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 70c512a386f7..4fecb26230e7 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
+#ifndef _UAPI_ASM_SOCKET_H
+#define _UAPI_ASM_SOCKET_H
 
 #include <asm/sockios.h>
 
@@ -73,9 +73,4 @@
 
 #define SO_SELECT_ERR_QUEUE	0x4026
 
-/* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
- * have to define SOCK_NONBLOCK to a different value here.
- */
-#define SOCK_NONBLOCK   0x40000000
-
-#endif /* _ASM_SOCKET_H */
+#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c035673209f7..ac87a40502e6 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -388,41 +388,20 @@ void flush_kernel_dcache_page_addr(void *addr)
 }
 EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
 
-void clear_user_page(void *vto, unsigned long vaddr, struct page *page)
-{
-	clear_page_asm(vto);
-	if (!parisc_requires_coherency())
-		flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(clear_user_page);
-
 void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
 	struct page *pg)
 {
-	/* Copy using kernel mapping.  No coherency is needed
-	   (all in kmap/kunmap) on machines that don't support
-	   non-equivalent aliasing.  However, the `from' page
-	   needs to be flushed before it can be accessed through
-	   the kernel mapping. */
+       /* Copy using kernel mapping.  No coherency is needed (all in
+	  kunmap) for the `to' page.  However, the `from' page needs to
+	  be flushed through a mapping equivalent to the user mapping
+	  before it can be accessed through the kernel mapping. */
 	preempt_disable();
 	flush_dcache_page_asm(__pa(vfrom), vaddr);
 	preempt_enable();
 	copy_page_asm(vto, vfrom);
-	if (!parisc_requires_coherency())
-		flush_kernel_dcache_page_asm(vto);
 }
 EXPORT_SYMBOL(copy_user_page);
 
-#ifdef CONFIG_PA8X00
-
-void kunmap_parisc(void *addr)
-{
-	if (parisc_requires_coherency())
-		flush_kernel_dcache_page_addr(addr);
-}
-EXPORT_SYMBOL(kunmap_parisc);
-#endif
-
 void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long flags;
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 872275659d98..c22c3d84e28b 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1205,7 +1205,8 @@ static struct hp_hardware hp_hardware_list[] = {
 	{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, 
 	{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, 
 	{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, 
-	{HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
+	{HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"},
+	{HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"},
 	{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, 
 	{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, 
 	{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, 
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index 37aabd772fbb..d2d58258aea6 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -195,6 +195,8 @@ common_stext:
 	ldw             MEM_PDC_HI(%r0),%r6
 	depd            %r6, 31, 32, %r3        /* move to upper word */
 
+	mfctl		%cr30,%r6		/* PCX-W2 firmware bug */
+
 	ldo             PDC_PSW(%r0),%arg0              /* 21 */
 	ldo             PDC_PSW_SET_DEFAULTS(%r0),%arg1 /* 2 */
 	ldo             PDC_PSW_WIDE_BIT(%r0),%arg2     /* 2 */
@@ -203,6 +205,8 @@ common_stext:
 	copy            %r0,%arg3
 
 stext_pdc_ret:
+	mtctl		%r6,%cr30		/* restore task thread info */
+
 	/* restore rfi target address*/
 	ldd             TI_TASK-THREAD_SZ_ALGN(%sp), %r10
 	tophys_r1       %r10
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 5dfd248e3f1a..0d3a9d4927b5 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -61,8 +61,15 @@ static int get_offset(struct address_space *mapping)
 	return (unsigned long) mapping >> 8;
 }
 
-static unsigned long get_shared_area(struct address_space *mapping,
-		unsigned long addr, unsigned long len, unsigned long pgoff)
+static unsigned long shared_align_offset(struct file *filp, unsigned long pgoff)
+{
+	struct address_space *mapping = filp ? filp->f_mapping : NULL;
+
+	return (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+}
+
+static unsigned long get_shared_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff)
 {
 	struct vm_unmapped_area_info info;
 
@@ -71,7 +78,7 @@ static unsigned long get_shared_area(struct address_space *mapping,
 	info.low_limit = PAGE_ALIGN(addr);
 	info.high_limit = TASK_SIZE;
 	info.align_mask = PAGE_MASK & (SHMLBA - 1);
-	info.align_offset = (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+	info.align_offset = shared_align_offset(filp, pgoff);
 	return vm_unmapped_area(&info);
 }
 
@@ -82,20 +89,18 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		return -ENOMEM;
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) &&
-		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+		    (addr - shared_align_offset(filp, pgoff)) & (SHMLBA - 1))
 			return -EINVAL;
 		return addr;
 	}
 	if (!addr)
 		addr = TASK_UNMAPPED_BASE;
 
-	if (filp) {
-		addr = get_shared_area(filp->f_mapping, addr, len, pgoff);
-	} else if(flags & MAP_SHARED) {
-		addr = get_shared_area(NULL, addr, len, pgoff);
-	} else {
+	if (filp || (flags & MAP_SHARED))
+		addr = get_shared_area(filp, addr, len, pgoff);
+	else
 		addr = get_unshared_area(addr, len);
-	}
+
 	return addr;
 }
 
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 0c9107285e66..b24732d1bdbf 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -286,11 +286,11 @@
 	ENTRY_COMP(msgsnd)
 	ENTRY_COMP(msgrcv)
 	ENTRY_SAME(msgget)		/* 190 */
-	ENTRY_SAME(msgctl)
-	ENTRY_SAME(shmat)
+	ENTRY_COMP(msgctl)
+	ENTRY_COMP(shmat)
 	ENTRY_SAME(shmdt)
 	ENTRY_SAME(shmget)
-	ENTRY_SAME(shmctl)		/* 195 */
+	ENTRY_COMP(shmctl)		/* 195 */
 	ENTRY_SAME(ni_syscall)		/* streams1 */
 	ENTRY_SAME(ni_syscall)		/* streams2 */
 	ENTRY_SAME(lstat64)
@@ -323,7 +323,7 @@
 	ENTRY_SAME(epoll_ctl)		/* 225 */
 	ENTRY_SAME(epoll_wait)
  	ENTRY_SAME(remap_file_pages)
-	ENTRY_SAME(semtimedop)
+	ENTRY_COMP(semtimedop)
 	ENTRY_COMP(mq_open)
 	ENTRY_SAME(mq_unlink)		/* 230 */
 	ENTRY_COMP(mq_timedsend)
@@ -392,7 +392,7 @@
 	ENTRY_COMP(vmsplice)
 	ENTRY_COMP(move_pages)		/* 295 */
 	ENTRY_SAME(getcpu)
-	ENTRY_SAME(epoll_pwait)
+	ENTRY_COMP(epoll_pwait)
 	ENTRY_COMP(statfs64)
 	ENTRY_COMP(fstatfs64)
 	ENTRY_COMP(kexec_load)		/* 300 */
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 04e47c6a4562..b3f87a3b4bce 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -805,14 +805,14 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	else {
 
 	    /*
-	     * The kernel should never fault on its own address space.
+	     * The kernel should never fault on its own address space,
+	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0) 
+	    if (fault_space == 0 && !in_atomic())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
-	
 	    }
 	}
 
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a3480e8e..d10d27a720c0 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -180,6 +180,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (acc_type & VM_WRITE)
+		flags |= FAULT_FLAG_WRITE;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma_prev(mm, address, &prev_vma);
@@ -203,8 +207,7 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address,
-			flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+	fault = handle_mm_fault(mm, vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fe404e77246e..7f656f119ea6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@ config PPC
 	select ARCH_USE_BUILTIN_BSWAP
 	select OLD_SIGSUSPEND
 	select OLD_SIGACTION if PPC32
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 967fd23ace78..56a4a5d205af 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -97,7 +97,9 @@ CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7)
 
 CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 
-KBUILD_CPPFLAGS	+= -Iarch/$(ARCH)
+asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
+
+KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
 KBUILD_AFLAGS	+= -Iarch/$(ARCH)
 KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf6857c31..ef22898daa93 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/sched.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __BIG_ENDIAN__
 #define COMPAT_UTS_MACHINE	"ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"ppcle\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 07ca627e52c0..e17d94d429a8 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -264,7 +264,7 @@ do_kvm_##n:								\
 	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
 	beq-	1f;							   \
 	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
-1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
+1:	cmpdi	cr1,r1,-INT_FRAME_SIZE;	/* check if r1 is in userspace	*/ \
 	blt+	cr1,3f;			/* abort if it is		*/ \
 	li	r1,(n);			/* will be reloaded later	*/ \
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c438f00..f016bb699b5f 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index f265049dd7d6..960bf64788a3 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -59,7 +59,7 @@ struct power_pmu {
 #define PPMU_SIAR_VALID		0x00000010 /* Processor has SIAR Valid bit */
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER		0x00000040 /* Has SIER */
-#define PPMU_BHRB		0x00000080 /* has BHRB feature enabled */
+#define PPMU_ARCH_207S		0x00000080 /* PMC is architecture v2.07S */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 27b2386f738a..842846c1b711 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -84,10 +84,8 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	struct page *page = page_address(table);
-
 	tlb_flush_pgtable(tlb, address);
-	pgtable_page_dtor(page);
-	pgtable_free_tlb(tlb, page, 0);
+	pgtable_page_dtor(table);
+	pgtable_free_tlb(tlb, page_address(table), 0);
 }
 #endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index b66ae722a8e9..64aaf016b478 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -144,11 +144,9 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	struct page *page = page_address(table);
-
 	tlb_flush_pgtable(tlb, address);
-	pgtable_page_dtor(page);
-	pgtable_free_tlb(tlb, page, 0);
+	pgtable_page_dtor(table);
+	pgtable_free_tlb(tlb, page_address(table), 0);
 }
 
 #else /* if CONFIG_PPC_64K_PAGES */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2f1b6c5f8174..22cee04a47fc 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -390,11 +390,16 @@ n:
  *      ld	rY,ADDROFF(name)(rX)
  */
 #ifdef __powerpc64__
+#ifdef HAVE_AS_ATHIGH
+#define __AS_ATHIGH high
+#else
+#define __AS_ATHIGH h
+#endif
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
 	lis     reg,(expr)@highest;		\
 	ori     reg,reg,(expr)@higher;	\
 	rldicr  reg,reg,32,31;		\
-	oris    reg,reg,(expr)@h;		\
+	oris    reg,reg,(expr)@__AS_ATHIGH;	\
 	ori     reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)			\
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68b..ac204e022922 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index d836d945068d..063fcadd1a00 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -40,17 +40,39 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>	/* for smp_rmb() */
+
 /*
  * With 64K pages on hash table, we have a special PTE format that
  * uses a second "half" of the page table to encode sub-page information
  * in order to deal with 64K made of 4K HW pages. Thus we override the
  * generic accessors and iterators here
  */
-#define __real_pte(e,p) 	((real_pte_t) { \
-			(e), (pte_val(e) & _PAGE_COMBO) ? \
-				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
-#define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
-        (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+	real_pte_t rpte;
+
+	rpte.pte = pte;
+	rpte.hidx = 0;
+	if (pte_val(pte) & _PAGE_COMBO) {
+		/*
+		 * Make sure we order the hidx load against the _PAGE_COMBO
+		 * check. The store side ordering is done in __hash_page_4K
+		 */
+		smp_rmb();
+		rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
+	}
+	return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	if ((pte_val(rpte.pte) & _PAGE_COMBO))
+		return (rpte.hidx >> (index<<2)) & 0xf;
+	return (pte_val(rpte.pte) >> 12) & 0xf;
+}
+
 #define __rpte_to_pte(r)	((r).pte)
 #define __rpte_sub_valid(rpte, index) \
 	(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e6a65c..637c97fcbeb5 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -35,6 +35,12 @@
 					STACK_FRAME_OVERHEAD + 288)
 #define STACK_FRAME_MARKER	12
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE	32
+#else
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
+#endif
+
 /* Size of dummy stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	128
 #define __SIGNAL_FRAMESIZE32	64
@@ -46,6 +52,7 @@
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
 #define STACK_FRAME_MARKER	2
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
 
 /* Size of stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	64
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e1fb161252ef..795f67792ea9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -208,6 +208,7 @@
 #define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_TFIAR	0x81	/* Transaction Failure Inst Addr   */
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
+#define   TEXASR_FS	__MASK(63-36)	/* Transaction Failure Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
 #define SPRN_CTRLF	0x088
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 43523fe0d8b4..05fcdd826829 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd)
 SYSCALL_SPU(capget)
 SYSCALL_SPU(capset)
 COMPAT_SYS(sigaltstack)
-COMPAT_SYS_SPU(sendfile)
+SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 PPC_SYS(vfork)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 161ab662843b..884b001bafcb 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -22,7 +22,15 @@ struct device_node;
 
 static inline int cpu_to_node(int cpu)
 {
-	return numa_cpu_lookup_table[cpu];
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * During early boot, the numa-cpu lookup table might not have been
+	 * setup for all CPUs yet. In such cases, default to node 0.
+	 */
+	return (nid < 0) ? 0 : nid;
 }
 
 #define parent_node(node)	(node)
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 5b7657959faa..de2c0e4ee1aa 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -41,5 +41,6 @@
 #define PPC_FEATURE2_EBB		0x10000000
 #define PPC_FEATURE2_ISEL		0x08000000
 #define PPC_FEATURE2_TAR		0x04000000
+#define PPC_FEATURE2_VEC_CRYPTO		0x02000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 92c6b008dd2b..b4437e8a7a8f 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -788,6 +788,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir)
 {
 	remove_index_dirs(cache_dir);
 
+	/* Remove cache dir from sysfs */
+	kobject_del(cache_dir->kobj);
+
 	kobject_put(cache_dir->kobj);
 
 	kfree(cache_dir);
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2a45d0f04385..b2dc45522850 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -105,7 +105,8 @@ extern void __restore_cpu_e6500(void);
 				 PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8	(PPC_FEATURE2_ARCH_2_07 | \
 				 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
-				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR)
+				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+				 PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T	(COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
 				 PPC_FEATURE_TRUE_LE | \
 				 PPC_FEATURE_HAS_ALTIVEC_COMP)
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 9ec3fe174cba..555ae67e4086 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -108,17 +108,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 			size_t csize, unsigned long offset, int userbuf)
 {
 	void  *vaddr;
+	phys_addr_t paddr;
 
 	if (!csize)
 		return 0;
 
 	csize = min_t(size_t, csize, PAGE_SIZE);
+	paddr = pfn << PAGE_SHIFT;
 
-	if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
-		vaddr = __va(pfn << PAGE_SHIFT);
+	if (memblock_is_region_memory(paddr, csize)) {
+		vaddr = __va(paddr);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
-		vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+		vaddr = __ioremap(paddr, PAGE_SIZE, 0);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 		iounmap(vaddr);
 	}
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b61363d557b5..192a3f562bdb 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -467,6 +467,7 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+.balign 8
 p_end:	.llong	_end - _stext
 
 4:	/* Now copy the rest of the kernel up to _end */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c0d0dbddfba1..93d8d96840b5 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -658,7 +658,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	/* number of bytes needed for the bitmap */
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
-	page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+	page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
 	if (!page)
 		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
 	tbl->it_map = page_address(page);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7baa27b7abbe..d55357ee9028 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -523,6 +523,31 @@ out_and_saveregs:
 	tm_save_sprs(thr);
 }
 
+extern void __tm_recheckpoint(struct thread_struct *thread,
+			      unsigned long orig_msr);
+
+void tm_recheckpoint(struct thread_struct *thread,
+		     unsigned long orig_msr)
+{
+	unsigned long flags;
+
+	/* We really can't be interrupted here as the TEXASR registers can't
+	 * change and later in the trecheckpoint code, we have a userspace R1.
+	 * So let's hard disable over this region.
+	 */
+	local_irq_save(flags);
+	hard_irq_disable();
+
+	/* The TM SPRs are restored here, so that TEXASR.FS can be set
+	 * before the trecheckpoint and no explosion occurs.
+	 */
+	tm_restore_sprs(thread);
+
+	__tm_recheckpoint(thread, orig_msr);
+
+	local_irq_restore(flags);
+}
+
 static inline void tm_recheckpoint_new_task(struct task_struct *new)
 {
 	unsigned long msr;
@@ -541,13 +566,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 	if (!new->thread.regs)
 		return;
 
-	/* The TM SPRs are restored here, so that TEXASR.FS can be set
-	 * before the trecheckpoint and no explosion occurs.
-	 */
-	tm_restore_sprs(&new->thread);
-
-	if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+	if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+		tm_restore_sprs(&new->thread);
 		return;
+	}
 	msr = new->thread.tm_orig_msr;
 	/* Recheckpoint to restore original checkpointed register state. */
 	TM_DEBUG("*** tm_recheckpoint of pid %d "
@@ -926,6 +948,16 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+	/*
+	* Flush TM state out so we can copy it.  __switch_to_tm() does this
+	* flush but it removes the checkpointed state from the current CPU and
+	* transitions the CPU out of TM mode.  Hence we need to call
+	* tm_recheckpoint_new_task() (on the same task) to restore the
+	* checkpointed state back and the TM mode.
+	*/
+	__switch_to_tm(src);
+	tm_recheckpoint_new_task(src);
+
 	*dst = *src;
 	return 0;
 }
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 2a954ab60839..fe0c17dcfbd7 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -827,49 +827,10 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	int hardid;
-	struct device_node *np;
-
-	hardid = get_hard_smp_processor_id(cpu);
-
-	for_each_node_by_type(np, "cpu") {
-		const u32 *intserv;
-		unsigned int plen, t;
-
-		/* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
-		 * fallback to "reg" property and assume no threads
-		 */
-		intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
-				&plen);
-		if (intserv == NULL) {
-			const u32 *reg = of_get_property(np, "reg", NULL);
-			if (reg == NULL)
-				continue;
-			if (*reg == hardid) {
-				if (thread)
-					*thread = 0;
-				return np;
-			}
-		} else {
-			plen /= sizeof(u32);
-			for (t = 0; t < plen; t++) {
-				if (hardid == intserv[t]) {
-					if (thread)
-						*thread = t;
-					return np;
-				}
-			}
-		}
-	}
-	return NULL;
+	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
-EXPORT_SYMBOL(of_get_cpu_node);
 
 #if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
 static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1ab001..c712ecec13ba 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@ _GLOBAL(relocate)
 
 6:	blr
 
+.balign 8
 p_dyn:	.llong	__dynamic_start - 0b
 p_rela:	.llong	__rela_dyn_start - 0b
 p_st:	.llong	_stext - 0b
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0f83122e6676..81f929f026f2 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -442,6 +442,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 #endif /* CONFIG_ALTIVEC */
 	if (copy_fpr_to_user(&frame->mc_fregs, current))
 		return 1;
+
+	/*
+	 * Clear the MSR VSX bit to indicate there is no valid state attached
+	 * to this context, except in the specific case below where we set it.
+	 */
+	msr &= ~MSR_VSX;
 #ifdef CONFIG_VSX
 	/*
 	 * Copy VSR 0-31 upper half from thread_struct to local
@@ -857,6 +863,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	 * transactional versions should be loaded.
 	 */
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 	/* Get the top half of the MSR */
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 887e99d85bc2..74d9615a6bb6 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -121,6 +121,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	flush_fp_to_thread(current);
 	/* copy fpr regs and fpscr */
 	err |= copy_fpr_to_user(&sc->fp_regs, current);
+
+	/*
+	 * Clear the MSR VSX bit to indicate there is no valid state attached
+	 * to this context, except in the specific case below where we set it.
+	 */
+	msr &= ~MSR_VSX;
 #ifdef CONFIG_VSX
 	/*
 	 * Copy VSX low doubleword to local buffer for formatting,
@@ -507,6 +513,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	}
 #endif
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index e68a84568b8b..a15fd1a0690c 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/firmware.h>
 
 #include "cacheinfo.h"
 
@@ -179,15 +180,25 @@ SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
 SYSFS_PMCSETUP(pir, SPRN_PIR);
 
+/*
+  Lets only enable read for phyp resources and
+  enable write when needed with a separate function.
+  Lets be conservative and default to pseries.
+*/
 static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-static DEVICE_ATTR(purr, 0600, show_purr, store_purr);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
 unsigned long dscr_default = 0;
 EXPORT_SYMBOL(dscr_default);
 
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+	attr->attr.mode |= 0200;
+}
+
 static ssize_t show_dscr_default(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -394,8 +405,11 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		device_create_file(s, &dev_attr_mmcra);
 
-	if (cpu_has_feature(CPU_FTR_PURR))
+	if (cpu_has_feature(CPU_FTR_PURR)) {
+		if (!firmware_has_feature(FW_FEATURE_LPAR))
+			add_write_permission_dev_attr(&dev_attr_purr);
 		device_create_file(s, &dev_attr_purr);
+	}
 
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		device_create_file(s, &dev_attr_spurr);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 5fc29ad7e26f..57fd5c1e8e89 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -512,7 +512,7 @@ void timer_interrupt(struct pt_regs * regs)
 
 	__get_cpu_var(irq_stat).timer_irqs++;
 
-#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 1edd6c2a168d..1e43ed404b95 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -79,6 +79,11 @@ _GLOBAL(tm_abort)
 	TABORT(R3)
 	blr
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
 
 /* void tm_reclaim(struct thread_struct *thread,
  *                 unsigned long orig_msr,
@@ -178,11 +183,18 @@ dont_backup_fp:
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
 
+	/* Store the PPR in r11 and reset to decent value */
+	std	r11, GPR11(r1)			/* Temporary stash */
+	mfspr	r11, SPRN_PPR
+	HMT_MEDIUM
+
 	/* Now get some more GPRS free */
 	std	r7, GPR7(r1)			/* Temporary stash */
 	std	r12, GPR12(r1)			/* ''   ''    ''   */
 	ld	r12, STACK_PARAM(0)(r1)		/* Param 0, thread_struct * */
 
+	std	r11, THREAD_TM_PPR(r12)		/* Store PPR and free r11 */
+
 	addi	r7, r12, PT_CKPT_REGS		/* Thread's ckpt_regs */
 
 	/* Make r7 look like an exception frame so that we
@@ -194,15 +206,19 @@ dont_backup_fp:
 	SAVE_GPR(0, r7)				/* user r0 */
 	SAVE_GPR(2, r7)			/* user r2 */
 	SAVE_4GPRS(3, r7)			/* user r3-r6 */
-	SAVE_4GPRS(8, r7)			/* user r8-r11 */
+	SAVE_GPR(8, r7)				/* user r8 */
+	SAVE_GPR(9, r7)				/* user r9 */
+	SAVE_GPR(10, r7)			/* user r10 */
 	ld	r3, PACATMSCRATCH(r13)		/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
-	ld	r5, GPR12(r1)			/* user r12 */
-	GET_SCRATCH0(6)				/* user r13 */
+	ld	r5, GPR11(r1)			/* user r11 */
+	ld	r6, GPR12(r1)			/* user r12 */
+	GET_SCRATCH0(8)				/* user r13 */
 	std	r3, GPR1(r7)
 	std	r4, GPR7(r7)
-	std	r5, GPR12(r7)
-	std	r6, GPR13(r7)
+	std	r5, GPR11(r7)
+	std	r6, GPR12(r7)
+	std	r8, GPR13(r7)
 
 	SAVE_NVGPRS(r7)				/* user r14-r31 */
 
@@ -225,14 +241,12 @@ dont_backup_fp:
 	std	r6, _XER(r7)
 
 
-	/* ******************** TAR, PPR, DSCR ********** */
+	/* ******************** TAR, DSCR ********** */
 	mfspr	r3, SPRN_TAR
-	mfspr	r4, SPRN_PPR
-	mfspr	r5, SPRN_DSCR
+	mfspr	r4, SPRN_DSCR
 
 	std	r3, THREAD_TM_TAR(r12)
-	std	r4, THREAD_TM_PPR(r12)
-	std	r5, THREAD_TM_DSCR(r12)
+	std	r4, THREAD_TM_DSCR(r12)
 
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
@@ -249,7 +263,7 @@ dont_backup_fp:
 	std	r3, THREAD_TM_TFHAR(r12)
 	std	r4, THREAD_TM_TFIAR(r12)
 
-	/* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+	/* AMR is checkpointed too, but is unsupported by Linux. */
 
 	/* Restore original MSR/IRQ state & clear TM mode */
 	ld	r14, TM_FRAME_L0(r1)		/* Orig MSR */
@@ -265,6 +279,12 @@ dont_backup_fp:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 
@@ -276,7 +296,7 @@ dont_backup_fp:
 	 *	Call with IRQs off, stacks get all out of sync for
 	 *	some periods in here!
 	 */
-_GLOBAL(tm_recheckpoint)
+_GLOBAL(__tm_recheckpoint)
 	mfcr	r5
 	mflr	r0
 	std	r5, 8(r1)
@@ -349,44 +369,50 @@ dont_restore_fp:
 
 restore_gprs:
 
-	/* ******************** TAR, PPR, DSCR ********** */
-	ld	r4, THREAD_TM_TAR(r3)
-	ld	r5, THREAD_TM_PPR(r3)
-	ld	r6, THREAD_TM_DSCR(r3)
+	/* ******************** CR,LR,CCR,MSR ********** */
+	ld	r4, _CTR(r7)
+	ld	r5, _LINK(r7)
+	ld	r6, _CCR(r7)
+	ld	r8, _XER(r7)
 
-	mtspr	SPRN_TAR,	r4
-	mtspr	SPRN_PPR,	r5
-	mtspr	SPRN_DSCR,	r6
+	mtctr	r4
+	mtlr	r5
+	mtcr	r6
+	mtxer	r8
 
-	/* ******************** CR,LR,CCR,MSR ********** */
-	ld	r3, _CTR(r7)
-	ld	r4, _LINK(r7)
-	ld	r5, _CCR(r7)
-	ld	r6, _XER(r7)
+	/* ******************** TAR ******************** */
+	ld	r4, THREAD_TM_TAR(r3)
+	mtspr	SPRN_TAR,	r4
 
-	mtctr	r3
-	mtlr	r4
-	mtcr	r5
-	mtxer	r6
+	/* Load up the PPR and DSCR in GPRs only at this stage */
+	ld	r5, THREAD_TM_DSCR(r3)
+	ld	r6, THREAD_TM_PPR(r3)
 
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
 	 */
 
 	REST_4GPRS(0, r7)			/* GPR0-3 */
-	REST_GPR(4, r7)				/* GPR4-6 */
-	REST_GPR(5, r7)
-	REST_GPR(6, r7)
+	REST_GPR(4, r7)				/* GPR4 */
 	REST_4GPRS(8, r7)			/* GPR8-11 */
 	REST_2GPRS(12, r7)			/* GPR12-13 */
 
 	REST_NVGPRS(r7)				/* GPR14-31 */
 
-	ld	r7, GPR7(r7)			/* GPR7 */
+	/* Load up PPR and DSCR here so we don't run with user values for long
+	 */
+	mtspr	SPRN_DSCR, r5
+	mtspr	SPRN_PPR, r6
+
+	REST_GPR(5, r7)				/* GPR5-7 */
+	REST_GPR(6, r7)
+	ld	r7, GPR7(r7)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
 
+	HMT_MEDIUM
+
 	/* Our transactional state has now changed.
 	 *
 	 * Now just get out of here.  Transactional (current) state will be
@@ -405,6 +431,12 @@ restore_gprs:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 	/* ****************************************************************** */
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 47afd08c90f7..fe7e97a1aad9 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -30,8 +30,8 @@
 V_FUNCTION_BEGIN(__kernel_getcpu)
   .cfi_startproc
 	mfspr	r5,SPRN_USPRG3
-	cmpdi	cr0,r3,0
-	cmpdi	cr1,r4,0
+	cmpwi	cr0,r3,0
+	cmpwi	cr1,r4,0
 	clrlwi  r6,r5,16
 	rlwinm  r7,r5,16,31-15,31-0
 	beq	cr0,1f
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 536016d792ba..56d2e72c85de 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1529,11 +1529,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 	const char *cp;
 
 	dn = dev->of_node;
-	if (!dn)
-		return -ENODEV;
+	if (!dn) {
+		strcpy(buf, "\n");
+		return strlen(buf);
+	}
 	cp = of_get_property(dn, "compatible", NULL);
-	if (!cp)
-		return -ENODEV;
+	if (!cp) {
+		strcpy(buf, "\n");
+		return strlen(buf);
+	}
 
 	return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
 }
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 5880dfb31074..b616e364dbe9 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -473,11 +473,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		slb_v = vcpu->kvm->arch.vrma_slb_v;
 	}
 
+	preempt_disable();
 	/* Find the HPTE in the hash table */
 	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
 					 HPTE_V_VALID | HPTE_V_ABSENT);
-	if (index < 0)
+	if (index < 0) {
+		preempt_enable();
 		return -ENOENT;
+	}
 	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
 	v = hptep[0] & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
@@ -485,6 +488,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Unlock the HPTE */
 	asm volatile("lwsync" : : : "memory");
 	hptep[0] = v;
+	preempt_enable();
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 717e5b525f3b..a54c59db7bd8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -82,10 +82,13 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
 
 	/* CPU points to the first thread of the core */
 	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
+#ifdef CONFIG_KVM_XICS
 		int real_cpu = cpu + vcpu->arch.ptid;
 		if (paca[real_cpu].kvm_hstate.xics_phys)
 			xics_wake_cpu(real_cpu);
-		else if (cpu_online(cpu))
+		else
+#endif
+		if (cpu_online(cpu))
 			smp_send_reschedule(cpu);
 	}
 	put_cpu();
@@ -1090,7 +1093,9 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (vcpu->arch.ptid) {
+#ifdef CONFIG_KVM_XICS
 		xics_wake_cpu(cpu);
+#endif
 		++vc->n_woken;
 	}
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6dcbb49105a4..049b899e40e4 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -724,6 +724,10 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
 long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			      unsigned long valid)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e4c70d..7bcd4d6e177b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1054,7 +1054,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
 	ld	r7, HSTATE_DSCR(r13)
-	std	r8, VCPU_DSCR(r7)
+	std	r8, VCPU_DSCR(r9)
 	mtspr	SPRN_DSCR, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 6d6f153b6c1d..c17600de7d59 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -127,7 +127,7 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 }
 
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
-		unsigned int eaddr, int as)
+		gva_t eaddr, int as)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	unsigned int victim, tsized;
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 167f72555d60..57a072065057 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -226,19 +226,35 @@ _GLOBAL(csum_partial)
 	blr
 
 
-	.macro source
+	.macro srcnr
 100:
 	.section __ex_table,"a"
 	.align 3
-	.llong 100b,.Lsrc_error
+	.llong 100b,.Lsrc_error_nr
 	.previous
 	.endm
 
-	.macro dest
+	.macro source
+150:
+	.section __ex_table,"a"
+	.align 3
+	.llong 150b,.Lsrc_error
+	.previous
+	.endm
+
+	.macro dstnr
 200:
 	.section __ex_table,"a"
 	.align 3
-	.llong 200b,.Ldest_error
+	.llong 200b,.Ldest_error_nr
+	.previous
+	.endm
+
+	.macro dest
+250:
+	.section __ex_table,"a"
+	.align 3
+	.llong 250b,.Ldest_error
 	.previous
 	.endm
 
@@ -269,16 +285,16 @@ _GLOBAL(csum_partial_copy_generic)
 	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
 	beq	.Lcopy_aligned
 
-	li	r7,4
-	sub	r6,r7,r6
+	li	r9,4
+	sub	r6,r9,r6
 	mtctr	r6
 
 1:
-source;	lhz	r6,0(r3)		/* align to doubleword */
+srcnr;	lhz	r6,0(r3)		/* align to doubleword */
 	subi	r5,r5,2
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	bdnz	1b
 
@@ -392,10 +408,10 @@ dest;	std	r16,56(r4)
 
 	mtctr	r6
 3:
-source;	ld	r6,0(r3)
+srcnr;	ld	r6,0(r3)
 	addi	r3,r3,8
 	adde	r0,r0,r6
-dest;	std	r6,0(r4)
+dstnr;	std	r6,0(r4)
 	addi	r4,r4,8
 	bdnz	3b
 
@@ -405,10 +421,10 @@ dest;	std	r6,0(r4)
 	srdi.	r6,r5,2
 	beq	.Lcopy_tail_halfword
 
-source;	lwz	r6,0(r3)
+srcnr;	lwz	r6,0(r3)
 	addi	r3,r3,4
 	adde	r0,r0,r6
-dest;	stw	r6,0(r4)
+dstnr;	stw	r6,0(r4)
 	addi	r4,r4,4
 	subi	r5,r5,4
 
@@ -416,10 +432,10 @@ dest;	stw	r6,0(r4)
 	srdi.	r6,r5,1
 	beq	.Lcopy_tail_byte
 
-source;	lhz	r6,0(r3)
+srcnr;	lhz	r6,0(r3)
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	subi	r5,r5,2
 
@@ -427,10 +443,10 @@ dest;	sth	r6,0(r4)
 	andi.	r6,r5,1
 	beq	.Lcopy_finish
 
-source;	lbz	r6,0(r3)
+srcnr;	lbz	r6,0(r3)
 	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
 	adde	r0,r0,r9
-dest;	stb	r6,0(r4)
+dstnr;	stb	r6,0(r4)
 
 .Lcopy_finish:
 	addze	r0,r0			/* add in final carry */
@@ -440,6 +456,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Lsrc_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Lsrc_error_nr:
 	cmpdi	0,r7,0
 	beqlr
 	li	r6,-EFAULT
@@ -447,6 +468,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Ldest_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldest_error_nr:
 	cmpdi	0,r8,0
 	beqlr
 	li	r6,-EFAULT
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index b2c68ce139ae..a5b30c71a8d3 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -231,6 +231,87 @@ _GLOBAL(_rest32gpr_31_x)
 	mr	1,11
 	blr
 
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area.  */
+
+_GLOBAL(_savevr_20)
+	li	r11,-192
+	stvx	vr20,r11,r0
+_GLOBAL(_savevr_21)
+	li	r11,-176
+	stvx	vr21,r11,r0
+_GLOBAL(_savevr_22)
+	li	r11,-160
+	stvx	vr22,r11,r0
+_GLOBAL(_savevr_23)
+	li	r11,-144
+	stvx	vr23,r11,r0
+_GLOBAL(_savevr_24)
+	li	r11,-128
+	stvx	vr24,r11,r0
+_GLOBAL(_savevr_25)
+	li	r11,-112
+	stvx	vr25,r11,r0
+_GLOBAL(_savevr_26)
+	li	r11,-96
+	stvx	vr26,r11,r0
+_GLOBAL(_savevr_27)
+	li	r11,-80
+	stvx	vr27,r11,r0
+_GLOBAL(_savevr_28)
+	li	r11,-64
+	stvx	vr28,r11,r0
+_GLOBAL(_savevr_29)
+	li	r11,-48
+	stvx	vr29,r11,r0
+_GLOBAL(_savevr_30)
+	li	r11,-32
+	stvx	vr30,r11,r0
+_GLOBAL(_savevr_31)
+	li	r11,-16
+	stvx	vr31,r11,r0
+	blr
+
+_GLOBAL(_restvr_20)
+	li	r11,-192
+	lvx	vr20,r11,r0
+_GLOBAL(_restvr_21)
+	li	r11,-176
+	lvx	vr21,r11,r0
+_GLOBAL(_restvr_22)
+	li	r11,-160
+	lvx	vr22,r11,r0
+_GLOBAL(_restvr_23)
+	li	r11,-144
+	lvx	vr23,r11,r0
+_GLOBAL(_restvr_24)
+	li	r11,-128
+	lvx	vr24,r11,r0
+_GLOBAL(_restvr_25)
+	li	r11,-112
+	lvx	vr25,r11,r0
+_GLOBAL(_restvr_26)
+	li	r11,-96
+	lvx	vr26,r11,r0
+_GLOBAL(_restvr_27)
+	li	r11,-80
+	lvx	vr27,r11,r0
+_GLOBAL(_restvr_28)
+	li	r11,-64
+	lvx	vr28,r11,r0
+_GLOBAL(_restvr_29)
+	li	r11,-48
+	lvx	vr29,r11,r0
+_GLOBAL(_restvr_30)
+	li	r11,-32
+	lvx	vr30,r11,r0
+_GLOBAL(_restvr_31)
+	li	r11,-16
+	lvx	vr31,r11,r0
+	blr
+
+#endif /* CONFIG_ALTIVEC */
+
 #else /* CONFIG_PPC64 */
 
 	.section ".text.save.restore","ax",@progbits
@@ -356,6 +437,111 @@ _restgpr0_31:
 	mtlr	r0
 	blr
 
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area.  */
+
+.globl	_savevr_20
+_savevr_20:
+	li	r12,-192
+	stvx	vr20,r12,r0
+.globl	_savevr_21
+_savevr_21:
+	li	r12,-176
+	stvx	vr21,r12,r0
+.globl	_savevr_22
+_savevr_22:
+	li	r12,-160
+	stvx	vr22,r12,r0
+.globl	_savevr_23
+_savevr_23:
+	li	r12,-144
+	stvx	vr23,r12,r0
+.globl	_savevr_24
+_savevr_24:
+	li	r12,-128
+	stvx	vr24,r12,r0
+.globl	_savevr_25
+_savevr_25:
+	li	r12,-112
+	stvx	vr25,r12,r0
+.globl	_savevr_26
+_savevr_26:
+	li	r12,-96
+	stvx	vr26,r12,r0
+.globl	_savevr_27
+_savevr_27:
+	li	r12,-80
+	stvx	vr27,r12,r0
+.globl	_savevr_28
+_savevr_28:
+	li	r12,-64
+	stvx	vr28,r12,r0
+.globl	_savevr_29
+_savevr_29:
+	li	r12,-48
+	stvx	vr29,r12,r0
+.globl	_savevr_30
+_savevr_30:
+	li	r12,-32
+	stvx	vr30,r12,r0
+.globl	_savevr_31
+_savevr_31:
+	li	r12,-16
+	stvx	vr31,r12,r0
+	blr
+
+.globl	_restvr_20
+_restvr_20:
+	li	r12,-192
+	lvx	vr20,r12,r0
+.globl	_restvr_21
+_restvr_21:
+	li	r12,-176
+	lvx	vr21,r12,r0
+.globl	_restvr_22
+_restvr_22:
+	li	r12,-160
+	lvx	vr22,r12,r0
+.globl	_restvr_23
+_restvr_23:
+	li	r12,-144
+	lvx	vr23,r12,r0
+.globl	_restvr_24
+_restvr_24:
+	li	r12,-128
+	lvx	vr24,r12,r0
+.globl	_restvr_25
+_restvr_25:
+	li	r12,-112
+	lvx	vr25,r12,r0
+.globl	_restvr_26
+_restvr_26:
+	li	r12,-96
+	lvx	vr26,r12,r0
+.globl	_restvr_27
+_restvr_27:
+	li	r12,-80
+	lvx	vr27,r12,r0
+.globl	_restvr_28
+_restvr_28:
+	li	r12,-64
+	lvx	vr28,r12,r0
+.globl	_restvr_29
+_restvr_29:
+	li	r12,-48
+	lvx	vr29,r12,r0
+.globl	_restvr_30
+_restvr_30:
+	li	r12,-32
+	lvx	vr30,r12,r0
+.globl	_restvr_31
+_restvr_31:
+	li	r12,-16
+	lvx	vr31,r12,r0
+	blr
+
+#endif /* CONFIG_ALTIVEC */
+
 #endif /* CONFIG_PPC64 */
 
 #endif
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e15c521846ca..08490ecc465e 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1395,7 +1395,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				regs->gpr[rd] = byterev_4(val);
 			goto ldst_done;
 
-#ifdef CONFIG_PPC_CPU
+#ifdef CONFIG_PPC_FPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779e1409..d9196c9f93d9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
-	if (is_write)
-		flags |= FAULT_FLAG_WRITE;
-
 #ifdef CONFIG_PPC_ICSWX
 	/*
 	 * we need to do this early because this "data storage
@@ -280,6 +277,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -408,6 +408,7 @@ good_area:
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index cafad4017765..08c6f3185d45 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -31,6 +31,8 @@
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/topology.h>
 #include <asm/firmware.h>
 #include <asm/paca.h>
 #include <asm/hvcall.h>
@@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn,
 	}
 }
 
-static void map_cpu_to_node(int cpu, int node)
+static void reset_numa_cpu_lookup_table(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		numa_cpu_lookup_table[cpu] = -1;
+}
+
+static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
+}
+
+static void map_cpu_to_node(int cpu, int node)
+{
+	update_numa_cpu_lookup_table(cpu, node);
 
 	dbg("adding cpu %d to node %d\n", cpu, node);
 
@@ -519,11 +534,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int __cpuinit numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = 0;
-	struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
+	int nid;
+	struct device_node *cpu;
+
+	/*
+	 * If a valid cpu-to-node mapping is already available, use it
+	 * directly instead of querying the firmware, since it represents
+	 * the most recent mapping notified to us by the platform (eg: VPHN).
+	 */
+	if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+		map_cpu_to_node(lcpu, nid);
+		return nid;
+	}
+
+	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
 		WARN_ON(1);
+		nid = 0;
 		goto out;
 	}
 
@@ -558,8 +586,8 @@ static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 		unmap_cpu_from_node(lcpu);
-		break;
 		ret = NOTIFY_OK;
+		break;
 #endif
 	}
 	return ret;
@@ -1066,6 +1094,7 @@ void __init do_init_bootmem(void)
 	 */
 	setup_node_to_cpumask_map();
 
+	reset_numa_cpu_lookup_table();
 	register_cpu_notifier(&ppc64_numa_nb);
 	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
 			  (void *)(unsigned long)boot_cpuid);
@@ -1443,6 +1472,33 @@ static int update_cpu_topology(void *data)
 	return 0;
 }
 
+static int update_lookup_table(void *data)
+{
+	struct topology_update_data *update;
+
+	if (!data)
+		return -EINVAL;
+
+	/*
+	 * Upon topology update, the numa-cpu lookup table needs to be updated
+	 * for all threads in the core, including offline CPUs, to ensure that
+	 * future hotplug operations respect the cpu-to-node associativity
+	 * properly.
+	 */
+	for (update = data; update; update = update->next) {
+		int nid, base, j;
+
+		nid = update->new_nid;
+		base = cpu_first_thread_sibling(update->cpu);
+
+		for (j = 0; j < threads_per_core; j++) {
+			update_numa_cpu_lookup_table(base + j, nid);
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
@@ -1511,6 +1567,14 @@ int arch_update_cpu_topology(void)
 
 	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
+	/*
+	 * Update the numa-cpu lookup table with the new mappings, even for
+	 * offline CPUs. It is best to perform this update from the stop-
+	 * machine context.
+	 */
+	stop_machine(update_lookup_table, &updates[0],
+					cpumask_of(raw_smp_processor_id()));
+
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		unregister_cpu_under_node(ud->cpu, ud->old_nid);
 		register_cpu_under_node(ud->cpu, ud->new_nid);
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 3e99c149271a..7ce9cf3b6988 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr,
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!(available.high_slices & (1u << slice));
+		return !!(available.high_slices & (1ul << slice));
 	}
 }
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index c427ae36374a..a012a9747cdd 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -209,10 +209,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+		case BPF_S_ALU_DIV_K: /* A /= K */
+			if (K == 1)
+				break;
 			PPC_LI32(r_scratch1, K);
-			/* Top 32 bits of 64bit result -> A */
-			PPC_MULHWU(r_A, r_A, r_scratch1);
+			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
 		case BPF_S_ALU_AND_X:
 			ctx->seen |= SEEN_XREG;
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e780748b..2396dda282cd 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 		return 0;		/* must be 16-byte aligned */
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return 0;
-	if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+	if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
 		return 1;
 	/*
 	 * sp could decrease when we jump off an interrupt stack
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index d3ee2e50a3a6..846861a20b07 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -749,7 +749,22 @@ static void power_pmu_read(struct perf_event *event)
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
 	local64_add(delta, &event->count);
-	local64_sub(delta, &event->hw.period_left);
+
+	/*
+	 * A number of places program the PMC with (0x80000000 - period_left).
+	 * We never want period_left to be less than 1 because we will program
+	 * the PMC with a value >= 0x800000000 and an edge detected PMC will
+	 * roll around to 0 before taking an exception. We have seen this
+	 * on POWER8.
+	 *
+	 * To fix this, clamp the minimum value of period_left to 1.
+	 */
+	do {
+		prev = local64_read(&event->hw.period_left);
+		val = prev - delta;
+		if (val < 1)
+			val = 1;
+	} while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev);
 }
 
 /*
@@ -1327,6 +1342,9 @@ static int can_go_on_limited_pmc(struct perf_event *event, u64 ev,
 	if (ppmu->limited_pmc_event(ev))
 		return 1;
 
+	if (ppmu->flags & PPMU_ARCH_207S)
+		mtspr(SPRN_MMCR2, 0);
+
 	/*
 	 * The requested event_id isn't on a limited PMC already;
 	 * see if any alternative code goes on a limited PMC.
@@ -1421,7 +1439,7 @@ static int power_pmu_event_init(struct perf_event *event)
 
 	if (has_branch_stack(event)) {
 	        /* PMU has BHRB enabled */
-		if (!(ppmu->flags & PPMU_BHRB))
+		if (!(ppmu->flags & PPMU_ARCH_207S))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index d59f5b2d4c2f..ee3b4048ab4d 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -194,6 +194,7 @@
 #define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
 #define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
 #define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
+#define MMCR1_FAB_SHIFT			36
 #define MMCR1_DC_QUAL_SHIFT		47
 #define MMCR1_IC_QUAL_SHIFT		46
 
@@ -367,8 +368,8 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
 		 * the threshold bits are used for the match value.
 		 */
 		if (event_is_fab_match(event[i])) {
-			mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) &
-				  EVENT_THR_CTL_MASK;
+			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
+				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
 		} else {
 			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
 			mmcra |= val << MMCRA_THR_CTL_SHIFT;
@@ -591,7 +592,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.attr_groups		= power8_pmu_attr_groups,
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index 90f4496017e4..af54174801f7 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX
 
 config PPC_MPC5200_LPBFIFO
 	tristate "MPC5200 LocalPlus bus FIFO driver"
-	depends on PPC_MPC52xx
+	depends on PPC_MPC52xx && PPC_BESTCOMM
 	select PPC_BESTCOMM_GEN_BD
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7816beff1db8..b2bbb79bd99d 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -151,13 +151,23 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		rid_end = pe->rid + 1;
 	}
 
-	/* Associate PE in PELT */
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_MAP_PE);
 	if (rc) {
 		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
 		return -ENXIO;
 	}
+
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
 	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
 				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
 
@@ -779,7 +789,6 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
-	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct irq_data *idata;
 	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
@@ -796,7 +805,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 		return -ENXIO;
 
 	/* Force 32-bit MSI on some broken devices */
-	if (pdn && pdn->force_32bit_msi)
+	if (dev->no_64bit_msi)
 		is_64 = 0;
 
 	/* Assign XIVE to PE */
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 277343cc6a3d..8ee842ce3aba 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1,3 +1,4 @@
+
 /*
  * Support PCI/PCIe on PowerNV platforms
  *
@@ -47,9 +48,8 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
+	if (pdev->no_64bit_msi && !phb->msi32_support)
 		return -ENODEV;
 
 	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b456b157d33d..68f97d5a4679 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -400,6 +400,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
 			} else {
 				result = EEH_STATE_NOT_SUPPORT;
 			}
+			break;
 		default:
 			result = EEH_STATE_NOT_SUPPORT;
 		}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 217ca5c75b20..2882d614221f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -34,12 +34,7 @@
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
-	.token = RTAS_UNKNOWN_SERVICE,
-	.nargs = 0,
-	.nret = 1,
-	.rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
 static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
 							CPU_STATE_OFFLINE;
@@ -92,15 +87,20 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args *args = &rtas_stop_self_args;
+	struct rtas_args args = {
+		.token = cpu_to_be32(rtas_stop_self_token),
+		.nargs = 0,
+		.nret = 1,
+		.rets = &args.args[0],
+	};
 
 	local_irq_disable();
 
-	BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
 
 	printk("cpu %u (hwid %u) Ready to die...\n",
 	       smp_processor_id(), hard_smp_processor_id());
-	enter_rtas(__pa(args));
+	enter_rtas(__pa(&args));
 
 	panic("Alas, I survived.\n");
 }
@@ -391,10 +391,10 @@ static int __init pseries_cpu_hotplug_init(void)
 		}
 	}
 
-	rtas_stop_self_args.token = rtas_token("stop-self");
+	rtas_stop_self_token = rtas_token("stop-self");
 	qcss_tok = rtas_token("query-cpu-stopped-state");
 
-	if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+	if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9a432de363b8..bebe64ed5dc3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -158,7 +158,7 @@ static int pseries_remove_memory(struct device_node *np)
 static inline int pseries_remove_memblock(unsigned long base,
 					  unsigned int memblock_size)
 {
-	return -EOPNOTSUPP;
+	return 0;
 }
 static inline int pseries_remove_memory(struct device_node *np)
 {
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 6d2f0abce6fa..3b350fb91285 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -426,7 +426,7 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 	 */
 again:
 	if (type == PCI_CAP_ID_MSI) {
-		if (pdn->force_32bit_msi) {
+		if (pdev->no_64bit_msi) {
 			rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec);
 			if (rc < 0) {
 				/*
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 96bf5bd30fbc..94599a65cc66 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -288,10 +288,10 @@ static inline void disable_surveillance(void)
 	args.token = rtas_token("set-indicator");
 	if (args.token == RTAS_UNKNOWN_SERVICE)
 		return;
-	args.nargs = 3;
-	args.nret = 1;
+	args.nargs = cpu_to_be32(3);
+	args.nret = cpu_to_be32(1);
 	args.rets = &args.args[3];
-	args.args[0] = SURVEILLANCE_TOKEN;
+	args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN);
 	args.args[1] = 0;
 	args.args[2] = 0;
 	enter_rtas(__pa(&args));
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 97dcbea97a1c..d8d6eeca56b0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -116,6 +116,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b4dbade8ca24..fd104db9cea1 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/spinlock.h>
 #include "crypt_s390.h"
 
 #define AES_KEYLEN_128		1
@@ -32,10 +33,10 @@
 #define AES_KEYLEN_256		4
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 static char keylen_flag;
 
 struct s390_aes_ctx {
-	u8 iv[AES_BLOCK_SIZE];
 	u8 key[AES_MAX_KEY_SIZE];
 	long enc;
 	long dec;
@@ -56,8 +57,7 @@ struct pcc_param {
 
 struct s390_xts_ctx {
 	u8 key[32];
-	u8 xts_param[16];
-	struct pcc_param pcc;
+	u8 pcc_key[32];
 	long enc;
 	long dec;
 	int key_len;
@@ -441,30 +441,36 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return aes_set_key(tfm, in_key, key_len);
 }
 
-static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, void *param,
+static int cbc_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct blkcipher_walk *walk)
 {
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[AES_BLOCK_SIZE];
+		u8 key[AES_MAX_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(param, walk->iv, AES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+	memcpy(param.key, sctx->key, sctx->key_len);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, param, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= AES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, param, AES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -481,7 +487,7 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc,
 		return fallback_blk_enc(desc, dst, src, nbytes);
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, sctx->enc, sctx->iv, &walk);
+	return cbc_aes_crypt(desc, sctx->enc, &walk);
 }
 
 static int cbc_aes_decrypt(struct blkcipher_desc *desc,
@@ -495,7 +501,7 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc,
 		return fallback_blk_dec(desc, dst, src, nbytes);
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, sctx->dec, sctx->iv, &walk);
+	return cbc_aes_crypt(desc, sctx->dec, &walk);
 }
 
 static struct crypto_alg cbc_aes_alg = {
@@ -586,7 +592,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		xts_ctx->enc = KM_XTS_128_ENCRYPT;
 		xts_ctx->dec = KM_XTS_128_DECRYPT;
 		memcpy(xts_ctx->key + 16, in_key, 16);
-		memcpy(xts_ctx->pcc.key + 16, in_key + 16, 16);
+		memcpy(xts_ctx->pcc_key + 16, in_key + 16, 16);
 		break;
 	case 48:
 		xts_ctx->enc = 0;
@@ -597,7 +603,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		xts_ctx->enc = KM_XTS_256_ENCRYPT;
 		xts_ctx->dec = KM_XTS_256_DECRYPT;
 		memcpy(xts_ctx->key, in_key, 32);
-		memcpy(xts_ctx->pcc.key, in_key + 32, 32);
+		memcpy(xts_ctx->pcc_key, in_key + 32, 32);
 		break;
 	default:
 		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
@@ -616,29 +622,33 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, long func,
 	unsigned int nbytes = walk->nbytes;
 	unsigned int n;
 	u8 *in, *out;
-	void *param;
+	struct pcc_param pcc_param;
+	struct {
+		u8 key[32];
+		u8 init[16];
+	} xts_param;
 
 	if (!nbytes)
 		goto out;
 
-	memset(xts_ctx->pcc.block, 0, sizeof(xts_ctx->pcc.block));
-	memset(xts_ctx->pcc.bit, 0, sizeof(xts_ctx->pcc.bit));
-	memset(xts_ctx->pcc.xts, 0, sizeof(xts_ctx->pcc.xts));
-	memcpy(xts_ctx->pcc.tweak, walk->iv, sizeof(xts_ctx->pcc.tweak));
-	param = xts_ctx->pcc.key + offset;
-	ret = crypt_s390_pcc(func, param);
+	memset(pcc_param.block, 0, sizeof(pcc_param.block));
+	memset(pcc_param.bit, 0, sizeof(pcc_param.bit));
+	memset(pcc_param.xts, 0, sizeof(pcc_param.xts));
+	memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+	memcpy(pcc_param.key, xts_ctx->pcc_key, 32);
+	ret = crypt_s390_pcc(func, &pcc_param.key[offset]);
 	if (ret < 0)
 		return -EIO;
 
-	memcpy(xts_ctx->xts_param, xts_ctx->pcc.xts, 16);
-	param = xts_ctx->key + offset;
+	memcpy(xts_param.key, xts_ctx->key, 32);
+	memcpy(xts_param.init, pcc_param.xts, 16);
 	do {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 
-		ret = crypt_s390_km(func, param, out, in, n);
+		ret = crypt_s390_km(func, &xts_param.key[offset], out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
@@ -748,43 +758,70 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return aes_set_key(tfm, in_key, key_len);
 }
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+		       AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[AES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
 
 	if (!walk->nbytes)
 		return ret;
 
-	memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= AES_BLOCK_SIZE) {
-			/* only use complete blocks, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-						 nbytes & ~(AES_BLOCK_SIZE - 1);
-			for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
-				       AES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = AES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, sctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > AES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
-			crypto_inc(ctrblk, AES_BLOCK_SIZE);
+			crypto_inc(ctrptr, AES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
@@ -792,14 +829,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, sctx->key, buf, in,
-				       AES_BLOCK_SIZE, ctrblk);
+				       AES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != AES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, AES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, AES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
 	return ret;
 }
 
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index bcca01c9989d..f2d6cccddcf8 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
 #define DES3_KEY_SIZE	(3 * DES_KEY_SIZE)
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 
 struct s390_des_ctx {
 	u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func,
 }
 
 static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
-			    u8 *iv, struct blkcipher_walk *walk)
+			    struct blkcipher_walk *walk)
 {
+	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[DES_BLOCK_SIZE];
+		u8 key[DES3_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.key, ctx->key, DES3_KEY_SIZE);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, iv, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -179,22 +186,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
 }
 
 static int cbc_des_decrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des_alg = {
@@ -327,22 +332,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
 }
 
 static int cbc_des3_decrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,83 @@ static struct crypto_alg cbc_des3_alg = {
 	}
 };
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* align to block size, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+	for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
-			    struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+			    struct s390_des_ctx *ctx,
+			    struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[DES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
+
+	if (!walk->nbytes)
+		return ret;
 
-	memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= DES_BLOCK_SIZE) {
-			/* align to block size, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-				nbytes & ~(DES_BLOCK_SIZE - 1);
-			for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
-				       DES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = DES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, ctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > DES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
 				       DES_BLOCK_SIZE);
-			crypto_inc(ctrblk, DES_BLOCK_SIZE);
+			crypto_inc(ctrptr, DES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
-
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, ctx->key, buf, in,
-				       DES_BLOCK_SIZE, ctrblk);
+				       DES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != DES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, DES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, DES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
 	return ret;
 }
 
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8be580..31b5ca8f8c3d 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define to_ccwdev(n) container_of(n, struct ccw_device, dev)
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_probe_console(struct ccw_driver *);
 extern void ccw_device_wait_idle(struct ccw_device *);
 extern int ccw_device_force_console(struct ccw_device *);
 
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190dc73e..346b1c85ffb4 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("0:	brcl 0,0\n"
+	asm_volatile_goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
 		ASM_ALIGN "\n"
 		ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141408cd..2bed4f02a558 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -142,9 +142,9 @@ struct _lowcore {
 	__u8	pad_0x02fc[0x0300-0x02fc];	/* 0x02fc */
 
 	/* Interrupt response block */
-	__u8	irb[64];			/* 0x0300 */
+	__u8	irb[96];			/* 0x0300 */
 
-	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
+	__u8	pad_0x0360[0x0e00-0x0360];	/* 0x0360 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -288,12 +288,13 @@ struct _lowcore {
 	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
 
 	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0400 */
+	__u8	irb[96];			/* 0x0400 */
+	__u8	pad_0x0460[0x0480-0x0460];	/* 0x0460 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0440 */
+	__u32	paste[16];			/* 0x0480 */
 
-	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
+	__u8	pad_0x04c0[0x0e00-0x04c0];	/* 0x04c0 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h
index a61d538756f2..471eb09184d4 100644
--- a/arch/s390/include/uapi/asm/statfs.h
+++ b/arch/s390/include/uapi/asm/statfs.h
@@ -35,11 +35,11 @@ struct statfs {
 struct statfs64 {
 	unsigned int	f_type;
 	unsigned int	f_bsize;
-	unsigned long	f_blocks;
-	unsigned long	f_bfree;
-	unsigned long	f_bavail;
-	unsigned long	f_files;
-	unsigned long	f_ffree;
+	unsigned long long f_blocks;
+	unsigned long long f_bfree;
+	unsigned long long f_bavail;
+	unsigned long long f_files;
+	unsigned long long f_ffree;
 	__kernel_fsid_t f_fsid;
 	unsigned int	f_namelen;
 	unsigned int	f_frsize;
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 8b6e4f5288a2..a98afed9348b 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -248,7 +248,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 4d5e6f8a7978..32bb7bf29397 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -265,6 +265,7 @@ sysc_sigpending:
 	tm	__TI_flags+3(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
 	xr	%r8,%r8			# svc 0 returns -ENOSYS
 	clc	__PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 4c17eece707e..2e3befddecee 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -293,6 +293,7 @@ sysc_sigpending:
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	lghi	%r8,0			# svc 0 returns -ENOSYS
 	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae2579c..d7c00507568a 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@ ENTRY(startup_continue)
 	.quad	0			# cr12: tracing off
 	.quad	0			# cr13: home space segment table
 	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	0			# cr15: linkage stack operations
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -67,12 +67,15 @@ ENTRY(startup_continue)
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,0,0,0,.Lduald,0,0,0
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
 	.long	0,0,0,0,0,0,0,0
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
 	.align	128
 .Lduald:.rept	8
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 
 ENTRY(_ehead)
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index a314c57f4e94..9677d935583c 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -314,7 +314,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * psw and gprs are stored on the stack
 		 */
 		if (addr == (addr_t) &dummy->regs.psw.mask &&
-		    ((data & ~PSW_MASK_USER) != psw_user_bits ||
+		    (((data^psw_user_bits) & ~PSW_MASK_USER) ||
+		     (((data^psw_user_bits) & PSW_MASK_ASC) &&
+		      ((data|psw_user_bits) & PSW_MASK_ASC) == PSW_MASK_ASC) ||
 		     ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
 			/* Invalid psw mask. */
 			return -EINVAL;
@@ -627,7 +629,10 @@ static int __poke_user_compat(struct task_struct *child,
 		 */
 		if (addr == (addr_t) &dummy32->regs.psw.mask) {
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits)
+			if (((tmp^psw32_user_bits) & ~PSW32_MASK_USER) ||
+			    (((tmp^psw32_user_bits) & PSW32_MASK_ASC) &&
+			     ((tmp|psw32_user_bits) & PSW32_MASK_ASC)
+			     == PSW32_MASK_ASC))
 				/* Invalid psw mask. */
 				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 4f977d0d25c2..14647fe09d0c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -933,7 +933,7 @@ static ssize_t show_idle_count(struct device *dev,
 		idle_count = ACCESS_ONCE(idle->idle_count);
 		if (ACCESS_ONCE(idle->clock_idle_enter))
 			idle_count++;
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	return sprintf(buf, "%llu\n", idle_count);
 }
 static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
@@ -951,7 +951,7 @@ static ssize_t show_idle_time(struct device *dev,
 		idle_time = ACCESS_ONCE(idle->idle_time);
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 3fb09359eda6..737d50caa4fe 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -190,7 +190,7 @@ cputime64_t s390_get_idle_time(int cpu)
 		sequence = ACCESS_ONCE(idle->sequence);
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
 }
 
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 1c01a9912989..6acb24d606fd 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -130,7 +130,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 {
-	int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+	int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
 
 	trace_kvm_s390_handle_diag(vcpu, code);
 	switch (code) {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5c948177529e..bc79ab00536f 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -71,6 +71,7 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 			return 0;
 		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
 			return 1;
+		return 0;
 	case KVM_S390_INT_EMERGENCY:
 		if (psw_extint_disabled(vcpu))
 			return 0;
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 50ea137a2d3c..1bf40ef57cf6 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -78,11 +78,14 @@ static size_t copy_in_kernel(size_t count, void __user *to,
  * contains the (negative) exception code.
  */
 #ifdef CONFIG_64BIT
+
 static unsigned long follow_table(struct mm_struct *mm,
 				  unsigned long address, int write)
 {
 	unsigned long *table = (unsigned long *)__pa(mm->pgd);
 
+	if (unlikely(address > mm->context.asce_limit - 1))
+		return -0x38UL;
 	switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
 	case _ASCE_TYPE_REGION1:
 		table = table + ((address >> 53) & 0x7ff);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 047c3e4c59a2..416facec4a33 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	address = trans_exc_code & __FAIL_ADDR_MASK;
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
 	down_read(&mm->mmap_sem);
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e9dfb0..27c50f4d90cb 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
 
 #define ESSA_SET_STABLE		1
 #define ESSA_SET_UNUSED		2
@@ -41,6 +43,14 @@ void __init cmma_init(void)
 
 	if (!cmma_flag)
 		return;
+	/*
+	 * Disable CMM for dump, otherwise  the tprot based memory
+	 * detection can fail because of unstable pages.
+	 */
+	if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+		cmma_flag = 0;
+		return;
+	}
 	asm volatile(
 		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
 		"0:     la      %0,0\n"
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 82f165f8078c..3bc6b7e43b24 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -243,7 +243,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 	case BPF_S_LD_W_IND:
 	case BPF_S_LD_H_IND:
 	case BPF_S_LD_B_IND:
-	case BPF_S_LDX_B_MSH:
 	case BPF_S_LD_IMM:
 	case BPF_S_LD_MEM:
 	case BPF_S_MISC_TXA:
@@ -335,14 +334,16 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
-		/* m %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
-		/* lr %r5,%r4 */
-		EMIT2(0x1854);
+	case BPF_S_ALU_DIV_K: /* A /= K */
+		if (K == 1)
+			break;
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
 	case BPF_S_ALU_MOD_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -352,16 +353,21 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
 	case BPF_S_ALU_MOD_K: /* A %= K */
+		if (K == 1) {
+			/* lhi %r5,0 */
+			EMIT4(0xa7580000);
+			break;
+		}
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* d %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c8def8bc9020..91182e95b887 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -109,3 +109,6 @@ source "security/Kconfig"
 source "crypto/Kconfig"
 
 source "lib/Kconfig"
+
+config NO_IOMEM
+       def_bool y
diff --git a/arch/score/Makefile b/arch/score/Makefile
index 974aefe86123..9e3e060290e0 100644
--- a/arch/score/Makefile
+++ b/arch/score/Makefile
@@ -20,8 +20,8 @@ cflags-y += -G0 -pipe -mel -mnhwloop -D__SCOREEL__ \
 #
 KBUILD_AFLAGS += $(cflags-y)
 KBUILD_CFLAGS += $(cflags-y)
-KBUILD_AFLAGS_MODULE += -mlong-calls
-KBUILD_CFLAGS_MODULE += -mlong-calls
+KBUILD_AFLAGS_MODULE +=
+KBUILD_CFLAGS_MODULE +=
 LDFLAGS += --oformat elf32-littlescore
 LDFLAGS_vmlinux	+= -G0 -static -nostdlib
 
diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h
index f909ac3144a4..961bd64015a8 100644
--- a/arch/score/include/asm/checksum.h
+++ b/arch/score/include/asm/checksum.h
@@ -184,48 +184,57 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				__wsum sum)
 {
 	__asm__ __volatile__(
-		".set\tnoreorder\t\t\t# csum_ipv6_magic\n\t"
-		".set\tnoat\n\t"
-		"addu\t%0, %5\t\t\t# proto (long in network byte order)\n\t"
-		"sltu\t$1, %0, %5\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %6\t\t\t# csum\n\t"
-		"sltu\t$1, %0, %6\n\t"
-		"lw\t%1, 0(%2)\t\t\t# four words source address\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 4(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 8(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 12(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 0(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 4(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 8(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 12(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"addu\t%0, $1\t\t\t# Add final carry\n\t"
-		".set\tnoat\n\t"
-		".set\tnoreorder"
+		".set\tvolatile\t\t\t# csum_ipv6_magic\n\t"
+		"add\t%0, %0, %5\t\t\t# proto (long in network byte order)\n\t"
+		"cmp.c\t%5, %0\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %6\t\t\t# csum\n\t"
+		"cmp.c\t%6, %0\n\t"
+		"lw\t%1, [%2, 0]\t\t\t# four words source address\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"1:lw\t%1, [%2, 4]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%2,8]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%2, 12]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0,%1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 0]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 4]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 8]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 12]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:\n\t"
+		".set\toptimize"
 		: "=r" (sum), "=r" (proto)
 		: "r" (saddr), "r" (daddr),
 		  "0" (htonl(len)), "1" (htonl(proto)), "r" (sum));
diff --git a/arch/score/include/asm/io.h b/arch/score/include/asm/io.h
index fbbfd7132e3b..574c8827abe2 100644
--- a/arch/score/include/asm/io.h
+++ b/arch/score/include/asm/io.h
@@ -5,5 +5,4 @@
 
 #define virt_to_bus	virt_to_phys
 #define bus_to_virt	phys_to_virt
-
 #endif /* _ASM_SCORE_IO_H */
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 059a61b7071b..716b3fd1d863 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -2,7 +2,7 @@
 #define _ASM_SCORE_PGALLOC_H
 
 #include <linux/mm.h>
-
+#include <linux/highmem.h>
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 	pte_t *pte)
 {
diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S
index 7234ed09b7b7..befb87d30a89 100644
--- a/arch/score/kernel/entry.S
+++ b/arch/score/kernel/entry.S
@@ -264,7 +264,7 @@ resume_kernel:
 	disable_irq
 	lw	r8, [r28, TI_PRE_COUNT]
 	cmpz.c	r8
-	bne	r8, restore_all
+	bne	restore_all
 need_resched:
 	lw	r8, [r28, TI_FLAGS]
 	andri.c	r9, r8, _TIF_NEED_RESCHED
@@ -415,7 +415,7 @@ ENTRY(handle_sys)
 	sw	r9, [r0, PT_EPC]
 
 	cmpi.c	r27, __NR_syscalls 	# check syscall number
-	bgeu	illegal_syscall
+	bcs	illegal_syscall
 
 	slli	r8, r27, 2		# get syscall routine
 	la	r11, sys_call_table
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index f4c6d02421d3..a1519ad3d49d 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -78,8 +78,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	p->thread.reg0 = (unsigned long) childregs;
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
-		p->thread->reg12 = usp;
-		p->thread->reg13 = arg;
+		p->thread.reg12 = usp;
+		p->thread.reg13 = arg;
 		p->thread.reg3 = (unsigned long) ret_from_kernel_thread;
 	} else {
 		*childregs = *current_pt_regs();
diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S
index eebcbaa4e978..7274b5c4287e 100644
--- a/arch/score/kernel/vmlinux.lds.S
+++ b/arch/score/kernel/vmlinux.lds.S
@@ -49,6 +49,7 @@ SECTIONS
 	}
 
 	. = ALIGN(16);
+	_sdata =  .;			/* Start of data section */
 	RODATA
 
 	EXCEPTION_TABLE(16)
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 47b600e4b2c5..52238983527d 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 	const int field = sizeof(unsigned long) * 2;
+	unsigned long flags = 0;
 	siginfo_t info;
 	int fault;
 
@@ -75,6 +76,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -95,18 +99,18 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
 			goto bad_area;
 	}
 
-survive:
 	/*
 	* If for any reason at all we couldn't handle the fault,
 	* make sure we exit gracefully rather than endlessly redo
 	* the fault.
 	*/
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -167,15 +171,10 @@ no_context:
 	*/
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
-	printk("VM: killing process %s\n", tsk->comm);
-	if (user_mode(regs))
-		do_group_exit(SIGKILL);
-	goto no_context;
+	if (!user_mode(regs))
+		goto no_context;
+	pagefault_out_of_memory();
+	return;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 13e9966464c2..e79fb6ebaa42 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -40,15 +40,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 /* arch/sh/kernel/return_address.c */
 extern void *return_address(unsigned int);
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index b959f5592604..8dfe645bcc4b 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -115,7 +115,7 @@ static int print_trace_stack(void *data, char *name)
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk(data);
+	printk("%s", (char *)data);
 	printk_address(addr, reliable);
 }
 
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 38b313909ac9..adad46e41a1d 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -13,6 +13,7 @@
 #include <linux/kdebug.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 
diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 2a0a596ebf67..d77f2f6c7ff0 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -20,6 +20,11 @@ EXPORT_SYMBOL(csum_partial_copy_generic);
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(empty_zero_page);
+#ifdef CONFIG_FLATMEM
+/* need in pfn_valid macro */
+EXPORT_SYMBOL(min_low_pfn);
+EXPORT_SYMBOL(max_low_pfn);
+#endif
 
 #define DECLARE_EXPORT(name)		\
 	extern void name(void);EXPORT_SYMBOL(name)
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29e3174..3baff31e58cf 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@ lib-y  = delay.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
 # Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
 	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
 	 udiv_qrnnd.o
 
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28affa9..541dc6101508 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -400,9 +400,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	int fault;
-	int write = error_code & FAULT_CODE_WRITE;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (write ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -476,6 +474,11 @@ good_area:
 
 	set_thread_fault_code(error_code);
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (error_code & FAULT_CODE_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 9ac9f1666339..03a1bc3c3dde 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,7 +25,7 @@ config SPARC
 	select RTC_DRV_M48T59
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -77,6 +77,7 @@ config SPARC64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select HAVE_C_RECORDMCOUNT
 	select NO_BOOTMEM
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 905832aa9e9e..a0ed182ae73c 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -21,7 +21,7 @@
 
 extern int __atomic_add_return(int, atomic_t *);
 extern int atomic_cmpxchg(atomic_t *, int, int);
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+extern int atomic_xchg(atomic_t *, int);
 extern int __atomic_add_unless(atomic_t *, int, int);
 extern void atomic_set(atomic_t *, int);
 
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a02e3c2..ae0f9a7a314d 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -11,22 +11,14 @@
 #ifndef __ARCH_SPARC_CMPXCHG__
 #define __ARCH_SPARC_CMPXCHG__
 
-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
-	__asm__ __volatile__("swap [%2], %0"
-			     : "=&r" (val)
-			     : "0" (val), "r" (m)
-			     : "memory");
-	return val;
-}
-
+extern unsigned long __xchg_u32(volatile u32 *m, u32 new);
 extern void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 4:
-		return xchg_u32(ptr, x);
+		return __xchg_u32(ptr, x);
 	}
 	__xchg_called_with_bad_pointer();
 	return x;
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16a832f..ec2e2e2aba7d 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-		asm goto("1:\n\t"
+		asm_volatile_goto("1:\n\t"
 			 "nop\n\t"
 			 "nop\n\t"
 			 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 7619f2f792af..6663604a902a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@
 
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
  * The PROM resides in an area spanning 0xf0000000 to 0x100000000.
  * The vmalloc area spans 0x100000000 to 0x200000000.
  * Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
  * 0x400000000.
  */
 #define	TLBTEMP_BASE		_AC(0x0000000006000000,UL)
-#define	TSBMAP_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_8K_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_4M_BASE		_AC(0x0000000008400000,UL)
 #define MODULES_VADDR		_AC(0x0000000010000000,UL)
 #define MODULES_LEN		_AC(0x00000000e0000000,UL)
 #define MODULES_END		_AC(0x00000000f0000000,UL)
@@ -616,7 +618,7 @@ static inline unsigned long pte_present(pte_t pte)
 }
 
 #define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
 	return pte_val(a) & _PAGE_VALID;
 }
@@ -806,7 +808,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
-	if (likely(mm != &init_mm) && pte_accessible(orig))
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
 		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index f0d6a9700f4c..1a4bb971e06d 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -35,6 +35,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 {
 }
 
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
 #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
 extern void flush_tlb_pending(void);
@@ -49,11 +51,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
 
-#define flush_tlb_kernel_range(start,end) \
-do {	flush_tsb_kernel_range(start,end); \
-	__flush_tlb_kernel_range(start,end); \
-} while (0)
-
 static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
@@ -64,11 +61,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
-#define flush_tlb_kernel_range(start, end) \
-do {	flush_tsb_kernel_range(start,end); \
-	smp_flush_tlb_kernel_range(start, end); \
-} while (0)
-
 #define global_flush_tlb_page(mm, vaddr) \
 	smp_flush_tlb_page(mm, vaddr)
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index e562d3caee57..ad7e178337f1 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -262,8 +262,8 @@ extern unsigned long __must_check __clear_user(void __user *, unsigned long);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
 struct pt_regs;
 extern unsigned long compute_effective_address(struct pt_regs *,
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa838861..55841c184e6d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -118,12 +118,18 @@ struct vio_disk_attr_info {
 	u8			vdisk_type;
 #define VD_DISK_TYPE_SLICE	0x01 /* Slice in block device	*/
 #define VD_DISK_TYPE_DISK	0x02 /* Entire block device	*/
-	u16			resv1;
+	u8			vdisk_mtype;		/* v1.1 */
+#define VD_MEDIA_TYPE_FIXED	0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD	0x02 /* CD Device    */
+#define VD_MEDIA_TYPE_DVD	0x03 /* DVD Device   */
+	u8			resv1;
 	u32			vdisk_block_size;
 	u64			operations;
-	u64			vdisk_size;
+	u64			vdisk_size;		/* v1.1 */
 	u64			max_xfer_size;
-	u64			resv2[2];
+	u32			phys_block_size;	/* v1.2 */
+	u32			resv2;
+	u64			resv3[1];
 };
 
 struct vio_disk_desc {
@@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr,
 				  unsigned int ring_size)
 {
 	return (dr->pending -
-		((dr->prod - dr->cons) & (ring_size - 1)));
+		((dr->prod - dr->cons) & (ring_size - 1)) - 1);
 }
 
 #define VIO_MAX_TYPE_LEN	32
diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h
index a34ad079487e..4c7c12d69bea 100644
--- a/arch/sparc/include/uapi/asm/swab.h
+++ b/arch/sparc/include/uapi/asm/swab.h
@@ -9,9 +9,9 @@ static inline __u16 __arch_swab16p(const __u16 *addr)
 {
 	__u16 ret;
 
-	__asm__ __volatile__ ("lduha [%1] %2, %0"
+	__asm__ __volatile__ ("lduha [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab16p __arch_swab16p
@@ -20,9 +20,9 @@ static inline __u32 __arch_swab32p(const __u32 *addr)
 {
 	__u32 ret;
 
-	__asm__ __volatile__ ("lduwa [%1] %2, %0"
+	__asm__ __volatile__ ("lduwa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab32p __arch_swab32p
@@ -31,9 +31,9 @@ static inline __u64 __arch_swab64p(const __u64 *addr)
 {
 	__u64 ret;
 
-	__asm__ __volatile__ ("ldxa [%1] %2, %0"
+	__asm__ __volatile__ ("ldxa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab64p __arch_swab64p
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 5ef48dab5636..252f8768aac6 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -842,9 +842,8 @@ void ldom_reboot(const char *boot_command)
 	if (boot_command && strlen(boot_command)) {
 		unsigned long len;
 
-		strcpy(full_boot_str, "boot ");
-		strlcpy(full_boot_str + strlen("boot "), boot_command,
-			sizeof(full_boot_str + strlen("boot ")));
+		snprintf(full_boot_str, sizeof(full_boot_str), "boot %s",
+			 boot_command);
 		len = strlen(full_boot_str);
 
 		if (reboot_data_supported) {
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index e2a030045089..33c02b15f478 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -839,7 +839,7 @@ sys_sigreturn:
 	 nop
 
 	call	syscall_trace
-	 nop
+	 mov	1, %o1
 
 1:
 	/* We don't want to muck with user registers like a
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 0746e5e32b37..fde5a419cf27 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -25,11 +25,10 @@ kvmap_itlb:
 	 */
 kvmap_itlb_4v:
 
-kvmap_itlb_nonlinear:
 	/* Catch kernel NULL pointer calls.  */
 	sethi		%hi(PAGE_SIZE), %g5
 	cmp		%g4, %g5
-	bleu,pn		%xcc, kvmap_dtlb_longpath
+	blu,pn		%xcc, kvmap_itlb_longpath
 	 nop
 
 	KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 54df554b82d9..fa4c900a0d1f 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1336,7 +1336,7 @@ int ldc_connect(struct ldc_channel *lp)
 	if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) ||
 	    !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) ||
 	    lp->hs_state != LDC_HS_OPEN)
-		err = -EINVAL;
+		err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL);
 	else
 		err = start_handshake(lp);
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index baf4366e2d6a..906cbf0f8608 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -399,8 +399,8 @@ static void apb_fake_ranges(struct pci_dev *dev,
 	apb_calc_first_last(map, &first, &last);
 	res = bus->resource[1];
 	res->flags = IORESOURCE_MEM;
-	region.start = (first << 21);
-	region.end = (last << 21) + ((1 << 21) - 1);
+	region.start = (first << 29);
+	region.end = (last << 29) + ((1 << 29) - 1);
 	pcibios_bus_to_resource(dev, res, &region);
 }
 
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 8f76f23dac38..f9c6813c132d 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 {
 	unsigned long csr_reg, csr, csr_error_bits;
 	irqreturn_t ret = IRQ_NONE;
-	u16 stat;
+	u32 stat;
 
 	csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
 	csr = upa_readq(csr_reg);
@@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 			       pbm->name);
 		ret = IRQ_HANDLED;
 	}
-	pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat);
+	pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
 	if (stat & (PCI_STATUS_PARITY |
 		    PCI_STATUS_SIG_TARGET_ABORT |
 		    PCI_STATUS_REC_TARGET_ABORT |
@@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 		    PCI_STATUS_SIG_SYSTEM_ERROR)) {
 		printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
 		       pbm->name, stat);
-		pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff);
+		pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
 		ret = IRQ_HANDLED;
 	}
 	return ret;
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index baebab215492..b9cc9763faf4 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -57,9 +57,12 @@ void arch_cpu_idle(void)
 {
 	if (tlb_type != hypervisor) {
 		touch_nmi_watchdog();
+		local_irq_enable();
 	} else {
 		unsigned long pstate;
 
+		local_irq_enable();
+
                 /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
                  * the cpu sleep hypervisor call.
                  */
@@ -81,7 +84,6 @@ void arch_cpu_idle(void)
 			: "=&r" (pstate)
 			: "i" (PSTATE_IE));
 	}
-	local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 77539eda928c..173964d5e948 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -150,7 +150,7 @@ void cpu_panic(void)
 #define NUM_ROUNDS	64	/* magic value */
 #define NUM_ITERS	5	/* likewise */
 
-static DEFINE_SPINLOCK(itc_sync_lock);
+static DEFINE_RAW_SPINLOCK(itc_sync_lock);
 static unsigned long go[SLAVE + 1];
 
 #define DEBUG_TICK_SYNC	0
@@ -258,7 +258,7 @@ static void smp_synchronize_one_tick(int cpu)
 	go[MASTER] = 0;
 	membar_safe("#StoreLoad");
 
-	spin_lock_irqsave(&itc_sync_lock, flags);
+	raw_spin_lock_irqsave(&itc_sync_lock, flags);
 	{
 		for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
 			while (!go[MASTER])
@@ -269,7 +269,7 @@ static void smp_synchronize_one_tick(int cpu)
 			membar_safe("#StoreLoad");
 		}
 	}
-	spin_unlock_irqrestore(&itc_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&itc_sync_lock, flags);
 }
 
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
@@ -821,13 +821,17 @@ void arch_send_call_function_single_ipi(int cpu)
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_interrupt();
+	irq_exit();
 }
 
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_single_interrupt();
+	irq_exit();
 }
 
 static void tsb_sync(void *info)
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index f7c72b6efc27..d066eb18650c 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1)
 SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
 SIGN1(sys32_mq_open, compat_sys_mq_open, %o1)
 SIGN1(sys32_select, compat_sys_select, %o0)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 22a1098961f5..c79c687fbe1e 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -152,7 +152,7 @@ linux_syscall_trace32:
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
-	ba,pt	%xcc, 2f
+	ba,pt	%xcc, 5f
 	 srl	%i3, 0, %o3
 
 linux_syscall_trace:
@@ -182,14 +182,15 @@ linux_sparc_syscall32:
 	srl	%i1, 0, %o1				! IEU0	Group
 	ldx	[%g6 + TI_FLAGS], %l0		! Load
 
-	srl	%i5, 0, %o5				! IEU1
+	srl	%i3, 0, %o3				! IEU0
 	srl	%i2, 0, %o2				! IEU0	Group
 	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	bne,pn	%icc, linux_syscall_trace32		! CTI
 	 mov	%i0, %l5				! IEU1
-	call	%l7					! CTI	Group brk forced
-	 srl	%i3, 0, %o3				! IEU0
-	ba,a,pt	%xcc, 3f
+5:	call	%l7					! CTI	Group brk forced
+	 srl	%i5, 0, %o5				! IEU1
+	ba,pt	%xcc, 3f
+	 sra	%o0, 0, %o0
 
 	/* Linux native system calls enter here... */
 	.align	32
@@ -217,7 +218,6 @@ linux_sparc_syscall:
 3:	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
 	ldx	[%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-	sra	%o0, 0, %o0
 	mov	%ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
 	sllx	%g2, 32, %g2
 
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index 2e973a26fbda..3a43edb46aa3 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -131,7 +131,6 @@ startup_continue:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 	mov		15, %l7
 	BRANCH_IF_ANY_CHEETAH(g1,g5,2f)
@@ -224,7 +223,6 @@ niagara_lock_tlb:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 1:
 	mov		HV_FAST_MMU_MAP_PERM_ADDR, %o5
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 8201c25e7669..4db8898199f7 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -163,17 +163,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs)
 unsigned long compute_effective_address(struct pt_regs *regs,
 					unsigned int insn, unsigned int rd)
 {
+	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	unsigned int rs1 = (insn >> 14) & 0x1f;
 	unsigned int rs2 = insn & 0x1f;
-	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	unsigned long addr;
 
 	if (insn & 0x2000) {
 		maybe_flush_windows(rs1, 0, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
+		addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
 	} else {
 		maybe_flush_windows(rs1, rs2, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
+		addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
 	}
+
+	if (!from_kernel && test_thread_flag(TIF_32BIT))
+		addr &= 0xffffffff;
+
+	return addr;
 }
 
 /* This is just to make gcc think die_if_kernel does return... */
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 2c20ad63ddbf..30eee6e8a81b 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 */
 	VISEntryHalf
 
+	membar		#Sync
 	alignaddr	%o1, %g0, %g0
 
 	add		%o1, (64 - 1), %o4
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 1d32b54089aa..8f2f94d53434 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v)
 }
 EXPORT_SYMBOL(__atomic_add_return);
 
+int atomic_xchg(atomic_t *v, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);
+	ret = v->counter;
+	v->counter = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
+	return ret;
+}
+EXPORT_SYMBOL(atomic_xchg);
+
 int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
 	return (unsigned long)prev;
 }
 EXPORT_SYMBOL(__cmpxchg_u32);
+
+unsigned long __xchg_u32(volatile u32 *ptr, u32 new)
+{
+	unsigned long flags;
+	u32 prev;
+
+	spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
+	prev = *ptr;
+	*ptr = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
+
+	return (unsigned long)prev;
+}
+EXPORT_SYMBOL(__xchg_u32);
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 0c4e35e522fa..323335b9cd2b 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -98,15 +98,6 @@ EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(___copy_in_user);
 EXPORT_SYMBOL(__clear_user);
 
-/* RW semaphores */
-EXPORT_SYMBOL(__down_read);
-EXPORT_SYMBOL(__down_read_trylock);
-EXPORT_SYMBOL(__down_write);
-EXPORT_SYMBOL(__down_write_trylock);
-EXPORT_SYMBOL(__up_read);
-EXPORT_SYMBOL(__up_write);
-EXPORT_SYMBOL(__downgrade_write);
-
 /* Atomic counter implementation. */
 EXPORT_SYMBOL(atomic_add);
 EXPORT_SYMBOL(atomic_add_ret);
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index aa4d55b0bdf0..5ce8f2f64604 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 		case 0: fsr = *pfsr;
 			if (IR == -1) IR = 2;
 			/* fcc is always fcc0 */
-			fsr &= ~0xc00; fsr |= (IR << 10); break;
+			fsr &= ~0xc00; fsr |= (IR << 10);
 			*pfsr = fsr;
 			break;
 		case 1: rd->s = IR; break;
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda205a2..59dbd4645725 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int fault, code;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (write ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (text_fault)
 		address = regs->pc;
@@ -235,6 +234,11 @@ good_area:
 			goto bad_area;
 	}
 
+	if (from_user)
+		flags |= FAULT_FLAG_USER;
+	if (write)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write)
 	struct vm_area_struct *vma;
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
+	unsigned int flags = FAULT_FLAG_USER;
 	int code;
 
 	code = SEGV_MAPERR;
@@ -402,11 +407,12 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+	switch (handle_mm_fault(mm, vma, address, flags)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 5062ff389e83..3841a081beb3 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -95,38 +95,51 @@ static unsigned int get_user_insn(unsigned long tpc)
 	pte_t *ptep, pte;
 	unsigned long pa;
 	u32 insn = 0;
-	unsigned long pstate;
 
-	if (pgd_none(*pgdp))
-		goto outret;
+	if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
+		goto out;
 	pudp = pud_offset(pgdp, tpc);
-	if (pud_none(*pudp))
-		goto outret;
-	pmdp = pmd_offset(pudp, tpc);
-	if (pmd_none(*pmdp))
-		goto outret;
-
-	/* This disables preemption for us as well. */
-	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
-	__asm__ __volatile__("wrpr %0, %1, %%pstate"
-				: : "r" (pstate), "i" (PSTATE_IE));
-	ptep = pte_offset_map(pmdp, tpc);
-	pte = *ptep;
-	if (!pte_present(pte))
+	if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
 		goto out;
 
-	pa  = (pte_pfn(pte) << PAGE_SHIFT);
-	pa += (tpc & ~PAGE_MASK);
-
-	/* Use phys bypass so we don't pollute dtlb/dcache. */
-	__asm__ __volatile__("lduwa [%1] %2, %0"
-			     : "=r" (insn)
-			     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+	/* This disables preemption for us as well. */
+	local_irq_disable();
 
+	pmdp = pmd_offset(pudp, tpc);
+	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+		goto out_irq_enable;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(*pmdp)) {
+		if (pmd_trans_splitting(*pmdp))
+			goto out_irq_enable;
+
+		pa  = pmd_pfn(*pmdp) << PAGE_SHIFT;
+		pa += tpc & ~HPAGE_MASK;
+
+		/* Use phys bypass so we don't pollute dtlb/dcache. */
+		__asm__ __volatile__("lduwa [%1] %2, %0"
+				     : "=r" (insn)
+				     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+	} else
+#endif
+	{
+		ptep = pte_offset_map(pmdp, tpc);
+		pte = *ptep;
+		if (pte_present(pte)) {
+			pa  = (pte_pfn(pte) << PAGE_SHIFT);
+			pa += (tpc & ~PAGE_MASK);
+
+			/* Use phys bypass so we don't pollute dtlb/dcache. */
+			__asm__ __volatile__("lduwa [%1] %2, %0"
+					     : "=r" (insn)
+					     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+		}
+		pte_unmap(ptep);
+	}
+out_irq_enable:
+	local_irq_enable();
 out:
-	pte_unmap(ptep);
-	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
-outret:
 	return insn;
 }
 
@@ -152,7 +165,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 }
 
 static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
-			     unsigned int insn, int fault_code)
+			     unsigned long fault_addr, unsigned int insn,
+			     int fault_code)
 {
 	unsigned long addr;
 	siginfo_t info;
@@ -160,10 +174,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	info.si_code = code;
 	info.si_signo = sig;
 	info.si_errno = 0;
-	if (fault_code & FAULT_CODE_ITLB)
+	if (fault_code & FAULT_CODE_ITLB) {
 		addr = regs->tpc;
-	else
-		addr = compute_effective_address(regs, insn, 0);
+	} else {
+		/* If we were able to probe the faulting instruction, use it
+		 * to compute a precise fault address.  Otherwise use the fault
+		 * time provided address which may only have page granularity.
+		 */
+		if (insn)
+			addr = compute_effective_address(regs, insn, 0);
+		else
+			addr = fault_addr;
+	}
 	info.si_addr = (void __user *) addr;
 	info.si_trapno = 0;
 
@@ -238,7 +260,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
 		/* The si_code was set to make clear whether
 		 * this was a SEGV_MAPERR or SEGV_ACCERR fault.
 		 */
-		do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+		do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code);
 		return;
 	}
 
@@ -258,18 +280,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
 	show_regs(regs);
 }
 
-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
-							 unsigned long addr)
-{
-	static int times;
-
-	if (times++ < 10)
-		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
-		       "reports 64-bit fault address [%lx]\n",
-		       current->comm, current->pid, addr);
-	show_regs(regs);
-}
-
 asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 {
 	struct mm_struct *mm = current->mm;
@@ -298,10 +308,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 				goto intr_or_no_mm;
 			}
 		}
-		if (unlikely((address >> 32) != 0)) {
-			bogus_32bit_fault_address(regs, address);
+		if (unlikely((address >> 32) != 0))
 			goto intr_or_no_mm;
-		}
 	}
 
 	if (regs->tstate & TSTATE_PRIV) {
@@ -315,7 +323,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			bad_kernel_pc(regs, address);
 			return;
 		}
-	}
+	} else
+		flags |= FAULT_FLAG_USER;
 
 	/*
 	 * If we're in an interrupt or have no user
@@ -418,13 +427,14 @@ good_area:
 		    vma->vm_file != NULL)
 			set_thread_fault_code(fault_code |
 					      FAULT_CODE_BLKCOMMIT);
+
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		/* Allow reads even for write-only mappings */
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
 
-	flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
 	fault = handle_mm_fault(mm, vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
@@ -519,7 +529,7 @@ do_sigbus:
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code);
 
 	/* Kernel mode? Handle exceptions or die */
 	if (regs->tstate & TSTATE_PRIV)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 04fd55a6e461..a751023dbdcd 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -350,6 +350,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 	mm = vma->vm_mm;
 
+	/* Don't insert a non-valid PTE into the TSB, we'll deadlock.  */
+	if (!pte_accessible(mm, pte))
+		return;
+
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -2764,3 +2768,26 @@ void hugetlb_setup(struct pt_regs *regs)
 	}
 }
 #endif
+
+#ifdef CONFIG_SMP
+#define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range
+#else
+#define do_flush_tlb_kernel_range	__flush_tlb_kernel_range
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) {
+		if (start < LOW_OBP_ADDRESS) {
+			flush_tsb_kernel_range(start, LOW_OBP_ADDRESS);
+			do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
+		}
+		if (end > HI_OBP_ADDRESS) {
+			flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
+			do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+		}
+	} else {
+		flush_tsb_kernel_range(start, end);
+		do_flush_tlb_kernel_range(start, end);
+	}
+}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 2cc3bce5ee91..71d99a6c75a7 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	mm->context.tsb_block[tsb_idx].tsb_nentries =
 		tsb_bytes / sizeof(struct tsb);
 
-	base = TSBMAP_BASE;
+	switch (tsb_idx) {
+	case MM_TSB_BASE:
+		base = TSBMAP_8K_BASE;
+		break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	case MM_TSB_HUGE:
+		base = TSBMAP_4M_BASE;
+		break;
+#endif
+	default:
+		BUG();
+	}
+
 	tte = pgprot_val(PAGE_KERNEL_LOCKED);
 	tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
 	BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index d36a85ebb5e0..224fc0c71b8a 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BNE		(F2(0, 2) | CONDNE)
 
 #ifdef CONFIG_SPARC64
-#define BNE_PTR		(F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BNE_PTR		BNE
+#define BE_PTR		BE
 #endif
 
 #define SETHI(K, REG)	\
@@ -497,9 +497,20 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_MUL_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K */
-				emit_alu_K(MUL, K);
-				emit_read_y(r_A);
+			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+				if (K == 1)
+					break;
+				emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+				/* The Sparc v8 architecture requires
+				 * three instructions between a %y
+				 * register write and the first use.
+				 */
+				emit_nop();
+				emit_nop();
+				emit_nop();
+#endif
+				emit_alu_K(DIV, K);
 				break;
 			case BPF_S_ALU_DIV_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
@@ -589,7 +600,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ANC_IFINDEX:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load32(r_A, struct net_device, ifindex, r_A);
 				break;
@@ -602,7 +613,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ANC_HATYPE:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 78f1f2ded86c..ffd4493efc78 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -281,7 +281,6 @@ long compat_sys_pread64(unsigned int fd, char __user *ubuf, size_t count,
 			u32 dummy, u32 low, u32 high);
 long compat_sys_pwrite64(unsigned int fd, char __user *ubuf, size_t count,
 			 u32 dummy, u32 low, u32 high);
-long compat_sys_lookup_dcookie(u32 low, u32 high, char __user *buf, size_t len);
 long compat_sys_sync_file_range2(int fd, unsigned int flags,
 				 u32 offset_lo, u32 offset_hi,
 				 u32 nbytes_lo, u32 nbytes_hi);
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5a8efb..4f7ae39fa202 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
 #ifndef _ASM_TILE_PERCPU_H
 #define _ASM_TILE_PERCPU_H
 
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+	unsigned long tp;
+	register unsigned long *sp asm("sp");
+	asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+	return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 3d2b81c163a6..3ff289f422e6 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -280,8 +280,7 @@ static int handle_page_fault(struct pt_regs *regs,
 	if (!is_page_fault)
 		write = 1;
 
-	flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-		 (write ? FAULT_FLAG_WRITE : 0));
+	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	is_kernel_mode = (EX1_PL(regs->ex1) != USER_PL);
 
@@ -365,6 +364,9 @@ static int handle_page_fault(struct pt_regs *regs,
 		goto bad_area_nosemaphore;
 	}
 
+	if (!is_kernel_mode)
+		flags |= FAULT_FLAG_USER;
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -425,12 +427,12 @@ good_area:
 #endif
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!is_page_fault || !(vma->vm_flags & VM_READ))
 			goto bad_area;
 	}
 
- survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -568,15 +570,10 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
-	pr_alert("VM: killing process %s\n", tsk->comm);
-	if (!is_kernel_mode)
-		do_group_exit(SIGKILL);
-	goto no_context;
+	if (is_kernel_mode)
+		goto no_context;
+	pagefault_out_of_memory();
+	return 0;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);
diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c
index 829df49dee99..41ebbfebb333 100644
--- a/arch/um/kernel/exitcode.c
+++ b/arch/um/kernel/exitcode.c
@@ -40,9 +40,11 @@ static ssize_t exitcode_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
 {
 	char *end, buf[sizeof("nnnnn\0")];
+	size_t size;
 	int tmp;
 
-	if (copy_from_user(buf, buffer, count))
+	size = min(count, sizeof(buf));
+	if (copy_from_user(buf, buffer, size))
 		return -EFAULT;
 
 	tmp = simple_strtol(buf, &end, 0);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 089f3987e273..5c3aef74237f 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	pmd_t *pmd;
 	pte_t *pte;
 	int err = -EFAULT;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 (is_write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	*code_out = SEGV_MAPERR;
 
@@ -42,6 +41,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	if (in_atomic())
 		goto out_nosemaphore;
 
+	if (is_user)
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -58,12 +59,15 @@ retry:
 
 good_area:
 	*code_out = SEGV_ACCERR;
-	if (is_write && !(vma->vm_flags & VM_WRITE))
-		goto out;
-
-	/* Don't require VM_READ|VM_EXEC for write faults! */
-	if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
-		goto out;
+	if (is_write) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto out;
+		flags |= FAULT_FLAG_WRITE;
+	} else {
+		/* Don't require VM_READ|VM_EXEC for write faults! */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto out;
+	}
 
 	do {
 		int fault;
@@ -124,6 +128,8 @@ out_of_memory:
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	up_read(&mm->mmap_sem);
+	if (!is_user)
+		goto out_nosemaphore;
 	pagefault_out_of_memory();
 	return 0;
 }
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index de7dc5fdd58b..24e836023e6c 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/unaligned.h>
 
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index f9b5c10bccee..0dc922dba915 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -222,6 +221,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (!(fsr ^ 0x12))
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -278,6 +282,13 @@ retry:
 	       (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we
+	 * have no context to handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -288,13 +299,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 787072769a80..3115eae96ad8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -121,6 +121,7 @@ config X86
 	select OLD_SIGACTION if X86_32
 	select COMPAT_OLD_SIGACTION if IA32_EMULATION
 	select RTC_LIB
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -957,10 +958,27 @@ config VM86
 	default y
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run 16-bit legacy
-	  code on X86 processors. It also may be needed by software like
-	  XFree86 to initialize some video cards via BIOS. Disabling this
-	  option saves about 6k.
+	  This option is required by programs like DOSEMU to run
+	  16-bit real mode legacy code on x86 processors. It also may
+	  be needed by software like XFree86 to initialize some video
+	  cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+	bool "Enable support for 16-bit segments" if EXPERT
+	default y
+	---help---
+	  This option is required by programs like Wine to run 16-bit
+	  protected mode legacy code on x86 processors.  Disabling
+	  this option saves about 300 bytes on i386, or around 6K text
+	  plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+	def_bool y
+	depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+	def_bool y
+	depends on X86_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"
@@ -1566,6 +1584,7 @@ config EFI
 config EFI_STUB
        bool "EFI stub support"
        depends on EFI
+       select RELOCATABLE
        ---help---
           This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5c477260294f..412189d2bff9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,6 +31,9 @@ ifeq ($(CONFIG_X86_32),y)
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
+        # Don't autogenerate MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse
+
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
         # with nonstandard options
         KBUILD_CFLAGS += -fno-pic
@@ -57,8 +60,11 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+        # Don't autogenerate MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse
+
 	# Use -mpreferred-stack-boundary=3 if supported.
-	KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
 
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 379814bc41e3..6cf0111783d3 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -53,18 +53,18 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 
 # How to compile the 16-bit code.  Note we always compile for -march=i386,
 # that way we can complain to the user if the CPU is insufficient.
-KBUILD_CFLAGS	:= $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+KBUILD_CFLAGS	:= $(USERINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ \
 		   -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/code16gcc.h \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+		   -mno-mmx -mno-sse \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
-			$(call cc-option, -fno-unit-at-a-time)) \
+		   $(call cc-option, -fno-unit-at-a-time)) \
 		   $(call cc-option, -fno-stack-protector) \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS	+= $(call cc-option, -m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 5ef205c5f37b..7194d9f094bc 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -12,6 +12,7 @@ KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
 KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mno-mmx -mno-sse
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d606463aa6d6..17177e80d466 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -865,6 +865,9 @@ fail:
  * Because the x86 boot code expects to be passed a boot_params we
  * need to create one ourselves (usually the bootloader would create
  * one for us).
+ *
+ * The caller is responsible for filling out ->code32_start in the
+ * returned boot_params.
  */
 struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 {
@@ -875,14 +878,15 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 	struct efi_info *efi;
 	efi_loaded_image_t *image;
 	void *options;
-	u32 load_options_size;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
-	unsigned long cmdline;
+	char *cmdline_ptr;
 	u16 *s2;
 	u8 *s1;
 	int i;
+	unsigned long ramdisk_addr;
+	unsigned long ramdisk_size;
 
 	sys_table = _table;
 
@@ -893,13 +897,14 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 	status = efi_call_phys3(sys_table->boottime->handle_protocol,
 				handle, &proto, (void *)&image);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+		efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
 		return NULL;
 	}
 
-	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+	status = efi_low_alloc(sys_table, 0x4000, 1,
+			       (unsigned long *)&boot_params);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc lowmem for boot params\n");
+		efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
 		return NULL;
 	}
 
@@ -921,45 +926,13 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 	hdr->vid_mode = 0xffff;
 	hdr->boot_flag = 0xAA55;
 
-	hdr->code32_start = (__u64)(unsigned long)image->image_base;
-
 	hdr->type_of_loader = 0x21;
 
 	/* Convert unicode cmdline to ascii */
-	options = image->load_options;
-	load_options_size = image->load_options_size / 2; /* ASCII */
-	cmdline = 0;
-	s2 = (u16 *)options;
-
-	if (s2) {
-		while (*s2 && *s2 != '\n' && options_size < load_options_size) {
-			s2++;
-			options_size++;
-		}
-
-		if (options_size) {
-			if (options_size > hdr->cmdline_size)
-				options_size = hdr->cmdline_size;
-
-			options_size++;	/* NUL termination */
-
-			status = low_alloc(options_size, 1, &cmdline);
-			if (status != EFI_SUCCESS) {
-				efi_printk("Failed to alloc mem for cmdline\n");
-				goto fail;
-			}
-
-			s1 = (u8 *)(unsigned long)cmdline;
-			s2 = (u16 *)options;
-
-			for (i = 0; i < options_size - 1; i++)
-				*s1++ = *s2++;
-
-			*s1 = '\0';
-		}
-	}
-
-	hdr->cmd_line_ptr = cmdline;
+	cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
+	if (!cmdline_ptr)
+		goto fail;
+	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
 
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
@@ -969,16 +942,20 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 
 	memset(sdt, 0, sizeof(*sdt));
 
-	status = handle_ramdisks(image, hdr);
+	status = handle_cmdline_files(sys_table, image,
+				      (char *)(unsigned long)hdr->cmd_line_ptr,
+				      "initrd=", hdr->initrd_addr_max,
+				      &ramdisk_addr, &ramdisk_size);
 	if (status != EFI_SUCCESS)
 		goto fail2;
+	hdr->ramdisk_image = ramdisk_addr;
+	hdr->ramdisk_size = ramdisk_size;
 
 	return boot_params;
 fail2:
-	if (options_size)
-		low_free(options_size, hdr->cmd_line_ptr);
+	efi_free(sys_table, options_size, hdr->cmd_line_ptr);
 fail:
-	low_free(0x4000, (unsigned long)boot_params);
+	efi_free(sys_table, 0x4000, (unsigned long)boot_params);
 	return NULL;
 }
 
@@ -1001,7 +978,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 again:
 	size += sizeof(*mem_map) * 2;
 	_size = size;
-	status = low_alloc(size, 1, (unsigned long *)&mem_map);
+	status = efi_low_alloc(sys_table, size, 1, (unsigned long *)&mem_map);
 	if (status != EFI_SUCCESS)
 		return status;
 
@@ -1009,7 +986,7 @@ get_map:
 	status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
 				mem_map, &key, &desc_size, &desc_version);
 	if (status == EFI_BUFFER_TOO_SMALL) {
-		low_free(_size, (unsigned long)mem_map);
+		efi_free(sys_table, _size, (unsigned long)mem_map);
 		goto again;
 	}
 
@@ -1111,44 +1088,10 @@ get_map:
 	return EFI_SUCCESS;
 
 free_mem_map:
-	low_free(_size, (unsigned long)mem_map);
+	efi_free(sys_table, _size, (unsigned long)mem_map);
 	return status;
 }
 
-static efi_status_t relocate_kernel(struct setup_header *hdr)
-{
-	unsigned long start, nr_pages;
-	efi_status_t status;
-
-	/*
-	 * The EFI firmware loader could have placed the kernel image
-	 * anywhere in memory, but the kernel has various restrictions
-	 * on the max physical address it can run at. Attempt to move
-	 * the kernel to boot_params.pref_address, or as low as
-	 * possible.
-	 */
-	start = hdr->pref_address;
-	nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-
-	status = efi_call_phys4(sys_table->boottime->allocate_pages,
-				EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
-				nr_pages, &start);
-	if (status != EFI_SUCCESS) {
-		status = low_alloc(hdr->init_size, hdr->kernel_alignment,
-				   &start);
-		if (status != EFI_SUCCESS)
-			efi_printk("Failed to alloc mem for kernel\n");
-	}
-
-	if (status == EFI_SUCCESS)
-		memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
-		       hdr->init_size);
-
-	hdr->pref_address = hdr->code32_start;
-	hdr->code32_start = (__u32)start;
-
-	return status;
-}
 
 /*
  * On success we return a pointer to a boot_params structure, and NULL
@@ -1177,14 +1120,15 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 				EFI_LOADER_DATA, sizeof(*gdt),
 				(void **)&gdt);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc mem for gdt structure\n");
+		efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
 		goto fail;
 	}
 
 	gdt->size = 0x800;
-	status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
+	status = efi_low_alloc(sys_table, gdt->size, 8,
+			   (unsigned long *)&gdt->address);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc mem for gdt\n");
+		efi_printk(sys_table, "Failed to alloc mem for gdt\n");
 		goto fail;
 	}
 
@@ -1192,7 +1136,7 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 				EFI_LOADER_DATA, sizeof(*idt),
 				(void **)&idt);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc mem for idt structure\n");
+		efi_printk(sys_table, "Failed to alloc mem for idt structure\n");
 		goto fail;
 	}
 
@@ -1204,10 +1148,16 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 	 * address, relocate it.
 	 */
 	if (hdr->pref_address != hdr->code32_start) {
-		status = relocate_kernel(hdr);
-
+		unsigned long bzimage_addr = hdr->code32_start;
+		status = efi_relocate_kernel(sys_table, &bzimage_addr,
+					     hdr->init_size, hdr->init_size,
+					     hdr->pref_address,
+					     hdr->kernel_alignment);
 		if (status != EFI_SUCCESS)
 			goto fail;
+
+		hdr->pref_address = hdr->code32_start;
+		hdr->code32_start = bzimage_addr;
 	}
 
 	status = exit_boot(boot_params, handle);
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f91c5f..cc78e2da7af9 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -10,8 +10,6 @@
 #define SEG_GRANULARITY_4KB	(1 << 0)
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
-
-#define EFI_PAGE_SIZE		(1UL << EFI_PAGE_SHIFT)
 #define EFI_READ_CHUNK_SIZE	(1024 * 1024)
 
 #define EFI_CONSOLE_OUT_DEVICE_GUID    \
@@ -40,6 +38,24 @@ struct efi_graphics_output_mode_info {
 	u32 pixels_per_scan_line;
 } __packed;
 
+struct efi_graphics_output_protocol_mode_32 {
+	u32 max_mode;
+	u32 mode;
+	u32 info;
+	u32 size_of_info;
+	u64 frame_buffer_base;
+	u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+	u32 max_mode;
+	u32 mode;
+	u64 info;
+	u64 size_of_info;
+	u64 frame_buffer_base;
+	u64 frame_buffer_size;
+} __packed;
+
 struct efi_graphics_output_protocol_mode {
 	u32 max_mode;
 	u32 mode;
@@ -49,6 +65,20 @@ struct efi_graphics_output_protocol_mode {
 	unsigned long frame_buffer_size;
 } __packed;
 
+struct efi_graphics_output_protocol_32 {
+	u32 query_mode;
+	u32 set_mode;
+	u32 blt;
+	u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+	u64 query_mode;
+	u64 set_mode;
+	u64 blt;
+	u64 mode;
+};
+
 struct efi_graphics_output_protocol {
 	void *query_mode;
 	unsigned long set_mode;
@@ -56,16 +86,22 @@ struct efi_graphics_output_protocol {
 	struct efi_graphics_output_protocol_mode *mode;
 };
 
+struct efi_uga_draw_protocol_32 {
+	u32 get_mode;
+	u32 set_mode;
+	u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+	u64 get_mode;
+	u64 set_mode;
+	u64 blt;
+};
+
 struct efi_uga_draw_protocol {
 	void *get_mode;
 	void *set_mode;
 	void *blt;
 };
 
-struct efi_simple_text_output_protocol {
-	void *reset;
-	void *output_string;
-	void *test_string;
-};
-
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1e3184f6072f..abb988a54c69 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -50,6 +50,13 @@ ENTRY(efi_pe_entry)
 	pushl	%eax
 	pushl	%esi
 	pushl	%ecx
+
+	call	reloc
+reloc:
+	popl	%ecx
+	subl	reloc, %ecx
+	movl	%ecx, BP_code32_start(%eax)
+
 	sub	$0x4, %esp
 
 ENTRY(efi_stub_entry)
@@ -63,12 +70,7 @@ ENTRY(efi_stub_entry)
 	hlt
 	jmp	1b
 2:
-	call	3f
-3:
-	popl	%eax
-	subl	$3b, %eax
-	subl	BP_pref_address(%esi), %eax
-	add	BP_code32_start(%esi), %eax
+	movl	BP_code32_start(%esi), %eax
 	leal	preferred_addr(%eax), %eax
 	jmp	*%eax
 
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 16f24e6dad79..92059b8f3f7b 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -217,6 +217,8 @@ ENTRY(efi_pe_entry)
 	cmpq	$0,%rax
 	je	1f
 	mov	%rax, %rdx
+	leaq	startup_32(%rip), %rax
+	movl	%eax, BP_code32_start(%rdx)
 	popq	%rsi
 	popq	%rdi
 
@@ -230,12 +232,7 @@ ENTRY(efi_stub_entry)
 	hlt
 	jmp	1b
 2:
-	call	3f
-3:
-	popq	%rax
-	subq	$3b, %rax
-	subq	BP_pref_address(%rsi), %rax
-	add	BP_code32_start(%esi), %eax
+	movl	BP_code32_start(%esi), %eax
 	leaq	preferred_addr(%rax), %rax
 	jmp	*%rax
 
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1f6d61..425712462178 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct floppy boot is not supported. "
-	.ascii	"Use a boot loader program instead.\r\n"
+	.ascii	"Use a boot loader.\r\n"
 	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot ...\r\n"
+	.ascii	"Remove disk and press any key to reboot...\r\n"
 	.byte	0
 
 #ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	3				# nr_sections
+	.word	4				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -250,6 +249,25 @@ section_table:
 	.word	0				# NumberOfLineNumbers
 	.long	0x60500020			# Characteristics (section flags)
 
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".bss"
+	.byte	0
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0xc8000080			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 94c544650020..971a0ce062aa 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -141,7 +141,7 @@ static void usage(void)
 
 #ifdef CONFIG_EFI_STUB
 
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
 {
 	unsigned int pe_header;
 	unsigned short num_sections;
@@ -162,10 +162,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 			put_unaligned_le32(size, section + 0x8);
 
 			/* section header vma field */
-			put_unaligned_le32(offset, section + 0xc);
+			put_unaligned_le32(vma, section + 0xc);
 
 			/* section header 'size of initialised data' field */
-			put_unaligned_le32(size, section + 0x10);
+			put_unaligned_le32(datasz, section + 0x10);
 
 			/* section header 'file offset' field */
 			put_unaligned_le32(offset, section + 0x14);
@@ -177,6 +177,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 	}
 }
 
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
 static void update_pecoff_setup_and_reloc(unsigned int size)
 {
 	u32 setup_offset = 0x200;
@@ -201,9 +206,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 
 	pe_header = get_unaligned_le32(&buf[0x3c]);
 
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
 	/*
 	 * Size of code: Subtract the size of the first sector (512 bytes)
 	 * which includes the header.
@@ -218,6 +220,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+	unsigned int pe_header;
+	unsigned int bss_sz = init_sz - file_sz;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of uninitialized data */
+	put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+	/* Size of image */
+	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+	update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
 #endif /* CONFIG_EFI_STUB */
 
 
@@ -268,6 +286,9 @@ int main(int argc, char ** argv)
 	int fd;
 	void *kernel;
 	u32 crc = 0xffffffffUL;
+#ifdef CONFIG_EFI_STUB
+	unsigned int init_sz;
+#endif
 
 	/* Defaults for old kernel */
 #ifdef CONFIG_X86_32
@@ -338,7 +359,9 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
 #ifdef CONFIG_EFI_STUB
-	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+	init_sz = get_unaligned_le32(&buf[0x260]);
+	update_pecoff_bss(i + (sys_size * 16), init_sz);
 
 #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
 	efi_stub_entry -= 0x200;
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 586f41aac361..185fad49d86f 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -24,10 +24,6 @@
 .align 16
 .Lbswap_mask:
 	.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
-	.octa 0xc2000000000000000000000000000001
-.Ltwo_one:
-	.octa 0x00000001000000000000000000000001
 
 #define DATA	%xmm0
 #define SHASH	%xmm1
@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
 .Lupdate_just_ret:
 	ret
 ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
-	movaps .Lbswap_mask, BSWAP
-	movups (%rsi), %xmm0
-	PSHUFB_XMM BSWAP %xmm0
-	movaps %xmm0, %xmm1
-	psllq $1, %xmm0
-	psrlq $63, %xmm1
-	movaps %xmm1, %xmm2
-	pslldq $8, %xmm1
-	psrldq $8, %xmm2
-	por %xmm1, %xmm0
-	# reduction
-	pshufd $0b00100100, %xmm2, %xmm1
-	pcmpeqd .Ltwo_one, %xmm1
-	pand .Lpoly, %xmm1
-	pxor %xmm1, %xmm0
-	movups %xmm0, (%rdi)
-	ret
-ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 6759dd1135be..d785cf2c529c 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash);
 void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
 			const be128 *shash);
 
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
 struct ghash_async_ctx {
 	struct cryptd_ahash *cryptd_tfm;
 };
@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
 	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *x = (be128 *)key;
+	u64 a, b;
 
 	if (keylen != GHASH_BLOCK_SIZE) {
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	clmul_ghash_setkey(&ctx->shash, key);
+	/* perform multiplication by 'x' in GF(2^128) */
+	a = be64_to_cpu(x->a);
+	b = be64_to_cpu(x->b);
+
+	ctx->shash.a = (__be64)((b << 1) | (a >> 63));
+	ctx->shash.b = (__be64)((a << 1) | (b >> 63));
+
+	if (a >> 63)
+		ctx->shash.b ^= cpu_to_be64(0xc2);
 
 	return 0;
 }
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 6cbd8df348d2..9f5e71f06671 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
 
 	/* save number of bits */
 	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61;
+	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
 
 	/* Pad out to 112 mod 128 and append length */
 	index = sctx->count[0] & 0x7f;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 474dc1b59f72..c9305ef1d411 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target)
 1:	movl	(%rbp),%ebp
 	_ASM_EXTABLE(1b,ia32_badarg)
 	ASM_CLAC
+
+	/*
+	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * ourselves.  To save a few cycles, we can check whether
+	 * NT was set instead of doing an unconditional popfq.
+	 */
+	testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp)
+	jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
 	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	CFI_REMEMBER_STATE
@@ -184,6 +194,8 @@ sysexit_from_sys_call:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS_SYSEXIT32
 
+	CFI_RESTORE_STATE
+
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
 	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
@@ -226,7 +238,6 @@ sysexit_from_sys_call:
 	.endm
 
 sysenter_auditsys:
-	CFI_RESTORE_STATE
 	auditsys_entry_common
 	movl %ebp,%r9d			/* reload 6th syscall arg */
 	jmp sysenter_dispatch
@@ -235,6 +246,11 @@ sysexit_audit:
 	auditsys_exit sysexit_from_sys_call
 #endif
 
+sysenter_fix_flags:
+	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	popfq_cfi
+	jmp sysenter_flags_fixed
+
 sysenter_tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e99ac27f95b2..4af181dacf9e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -365,7 +365,7 @@ extern const char * const x86_power_flags[32];
 static __always_inline __pure bool __static_cpu_has(u16 bit)
 {
 #if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index cccd07fa5e3a..779c2efe2e97 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -29,7 +29,7 @@ extern void e820_setup_gap(void);
 extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
 			unsigned long start_addr, unsigned long long end_addr);
 struct setup_data;
-extern void parse_e820_ext(struct setup_data *data);
+extern void parse_e820_ext(u64 phys_addr, u32 data_len);
 
 #if defined(CONFIG_X86_64) || \
 	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 60c89f30c727..7a76dc284166 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,7 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9c999c1674fa..01f15b227d7e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -155,8 +155,9 @@ do {						\
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)		\
-	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x)					\
+	(elf_check_arch_ia32(x) ||					\
+	 (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
 
 #if __USER32_DS != __USER_DS
 # error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 000000000000..99efebb2f69d
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0dc7d9e21c34..9d7d36c82fc2 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -123,14 +123,14 @@ enum fixed_addresses {
 	__end_of_permanent_fixed_addresses,
 
 	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * 512 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
 	 *
-	 * If necessary we round it up to the next 256 pages boundary so
+	 * If necessary we round it up to the next 512 pages boundary so
 	 * that we can have a single pgd entry and a single pte table:
 	 */
 #define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
+#define FIX_BTMAPS_SLOTS	8
 #define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
 	FIX_BTMAP_END =
 	 (__end_of_permanent_fixed_addresses ^
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index e25cc33ec54d..e72b2e41499e 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -295,12 +295,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"		/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.fpu.has_fpu));
+	if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (tsk->thread.fpu.has_fpu));
+	}
 
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a8091216963b..68c05398bba9 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	ptep_clear_flush(vma, addr, ptep);
 }
 
 static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e624..0a8b519226b8 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3a16c1483b45..029766958e69 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
+	asm_volatile_goto("1:"
 		STATIC_KEY_INITIAL_NOP
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5137dca9e9d6..b15a6b5fa341 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -448,7 +448,7 @@ struct kvm_vcpu_arch {
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
 
 	struct mtrr_state_type mtrr_state;
-	u32 pat;
+	u64 pat;
 
 	int switch_db_regs;
 	unsigned long db[KVM_NR_DB_REGS];
@@ -466,6 +466,7 @@ struct kvm_vcpu_arch {
 	u64 mmio_gva;
 	unsigned access;
 	gfn_t mmio_gfn;
+	u64 mmio_gen;
 
 	struct kvm_pmu pmu;
 
@@ -955,6 +956,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
+static inline u64 get_canonical(u64 la)
+{
+	return ((int64_t)la << 16) >> 16;
+}
+
+static inline bool is_noncanonical_address(u64 la)
+{
+#ifdef CONFIG_X86_64
+	return get_canonical(la) != la;
+#else
+	return false;
+#endif
+}
+
 #define TSS_IOPB_BASE_OFFSET 0x66
 #define TSS_BASE_SIZE 0x68
 #define TSS_IOPB_SIZE (65536 / 8)
@@ -1013,7 +1028,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
 
 void kvm_define_shared_msr(unsigned index, u32 msr);
-void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ef17af013475..4376b458aef7 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -18,7 +18,6 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define STACKFAULT_STACK 0
 #define DOUBLEFAULT_STACK 1
 #define NMI_STACK 0
 #define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6c896fbe21db..970f3097ee33 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
 #define IRQ_STACK_ORDER 2
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1e672234c4ff..5460bf923e16 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -415,9 +415,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d883440cb9a..b1609f2c524c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 942a08623a1a..68e9f007cd4a 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -232,6 +232,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 #define ARCH_HAS_USER_SINGLE_STEP_INFO
 
+/*
+ * When hitting ptrace_stop(), we cannot return using SYSRET because
+ * that does not restore the full CPU state, only a minimal set.  The
+ * ptracer can change arbitrary register values, which is usually okay
+ * because the usual ptrace stops run off the signal delivery path which
+ * forces IRET; however, ptrace_event() stops happen in arbitrary places
+ * in the kernel and don't force IRET path.
+ *
+ * So force IRET path after a ptrace stop.
+ */
+#define arch_ptrace_stop_needed(code, info)				\
+({									\
+	set_thread_flag(TIF_NOTIFY_RESUME);				\
+	false;								\
+})
+
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index b7bf3505e1ec..2e327f114a1b 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -62,6 +62,8 @@ static inline void x86_ce4100_early_setup(void) { }
 
 #ifndef _SETUP
 
+#include <asm/espfix.h>
+
 /*
  * This is set up by the setup-routine at boot-time
  */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692eaabab5..e3ddd7db723f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a1df6e84691f..d3e0ff5962fe 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -147,7 +147,7 @@ struct thread_info {
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
 	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
-	 _TIF_USER_RETURN_NOTIFY)
+	 _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 095b21507b6a..60bd2748a7c9 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { }
 
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720afc..2874be9aef0a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void)
 		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
-		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+		asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 
 	return p;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
 	unsigned long pfn;
-	int ret = 0;
+	int ret;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely(mfn >= machine_to_phys_nr)) {
-		pfn = ~0;
-		goto try_override;
-	}
-	pfn = 0;
+	if (unlikely(mfn >= machine_to_phys_nr))
+		return ~0;
+
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-	/* ret might be < 0 if there are no entries in the m2p for mfn */
 	if (ret < 0)
-		pfn = ~0;
-	else if (get_phys_to_machine(pfn) != mfn)
+		return ~0;
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
 		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
 		 */
 		pfn = m2p_find_override_pfn(mfn, ~0);
+	}
 
 	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index 46727eb37bfe..6e1aaf73852a 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@ struct user_desc {
 	unsigned int  seg_not_present:1;
 	unsigned int  useable:1;
 #ifdef __x86_64__
+	/*
+	 * Because this bit is not present in 32-bit user code, user
+	 * programs can pass uninitialized values here.  Therefore, in
+	 * any context in which a user_desc comes from a 32-bit program,
+	 * the kernel must act as though lm == 0, regardless of the
+	 * actual value.
+	 */
 	unsigned int  lm:1;
 #endif
 };
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 2af848dfa754..d3fd447ecbee 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -179,6 +179,7 @@
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 54991a746043..b16e6d28f149 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -6,7 +6,7 @@
  * EFLAGS bits
  */
 #define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
-#define X86_EFLAGS_BIT1	0x00000002 /* Bit 1 - always on */
+#define X86_EFLAGS_FIXED 0x00000002 /* Bit 1 - always on */
 #define X86_EFLAGS_PF	0x00000004 /* Parity Flag */
 #define X86_EFLAGS_AF	0x00000010 /* Auxiliary carry Flag */
 #define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d651082c7cf7..7a34e8fe54bd 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,7 @@
 #define EXIT_REASON_EOI_INDUCED         45
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT              50
 #define EXIT_REASON_PREEMPTION_TIMER    52
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7bd3bd310106..111eb356dbea 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 904611bf0e5a..033eb44dc661 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1263,7 +1263,7 @@ void __cpuinit setup_local_APIC(void)
 	unsigned int value, queued;
 	int i, j, acked = 0;
 	unsigned long long tsc = 0, ntsc;
-	long long max_loops = cpu_khz;
+	long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
 	if (cpu_has_tsc)
 		rdtscll(tsc);
@@ -1360,7 +1360,7 @@ void __cpuinit setup_local_APIC(void)
 			break;
 		}
 		if (queued) {
-			if (cpu_has_tsc) {
+			if (cpu_has_tsc && cpu_khz) {
 				rdtscll(ntsc);
 				max_loops = (cpu_khz << 10) - (ntsc - tsc);
 			} else
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 794f6eb54cd3..b32dbb411a9a 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -98,7 +98,7 @@ static int __init early_get_pnodeid(void)
 		break;
 	case UV3_HUB_PART_NUMBER:
 	case UV3_HUB_PART_NUMBER_X:
-		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
 	}
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5013a48d1aff..ae177a014180 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -508,6 +508,16 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
 	}
 #endif
+
+	/* F16h erratum 793, CVE-2013-6885 */
+	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
+		u64 val;
+
+		rdmsrl(MSR_AMD64_LS_CFG, val);
+		if (!(val & BIT(15)))
+			wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
+	}
+
 }
 
 static const int amd_erratum_383[];
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 22018f70a671..564140155c36 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int __init x86_xsave_setup(char *s)
 {
+	if (strlen(s))
+		return 0;
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
@@ -284,8 +286,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
-	if (cpu_has(c, X86_FEATURE_SMAP))
+	if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
 		set_in_cr4(X86_CR4_SMAP);
+#else
+		clear_in_cr4(X86_CR4_SMAP);
+#endif
+	}
 }
 
 /*
@@ -1129,7 +1136,7 @@ void syscall_init(void)
 	/* Flags to clear on syscall */
 	wrmsrl(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
-	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9b0c441c03f5..8533e69d2b89 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -154,6 +154,21 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
 	}
+
+	/*
+	 * Intel Quark Core DevMan_001.pdf section 6.4.11
+	 * "The operating system also is required to invalidate (i.e., flush)
+	 *  the TLB when any changes are made to any of the page table entries.
+	 *  The operating system must reload CR3 to cause the TLB to be flushed"
+	 *
+	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified
+	 */
+	if (c->x86 == 5 && c->x86_model == 9) {
+		pr_info("Disabling PGE capability bit\n");
+		setup_clear_cpu_cap(X86_FEATURE_PGE);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -387,7 +402,8 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+	if (c->x86 == 6 && cpu_has_clflush &&
+	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
@@ -627,7 +643,7 @@ static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
 		tlb_flushall_shift = 5;
 		break;
 	case 0x63a: /* Ivybridge */
-		tlb_flushall_shift = 1;
+		tlb_flushall_shift = 2;
 		break;
 	default:
 		tlb_flushall_shift = 6;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1025f3c99d20..123d9e2271dc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1165,6 +1165,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
 
+			if (i >= cpuc->n_events - cpuc->n_added)
+				--cpuc->n_added;
+
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, event);
 
@@ -1249,10 +1252,20 @@ void perf_events_lapic_init(void)
 static int __kprobes
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
+	int ret;
+	u64 start_clock;
+	u64 finish_clock;
+
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
-	return x86_pmu.handle_irq(regs);
+	start_clock = local_clock();
+	ret = x86_pmu.handle_irq(regs);
+	finish_clock = local_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+
+	return ret;
 }
 
 struct event_constraint emptyconstraint;
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 5f0581e713c2..b46601ada813 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/ptrace.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/apic.h>
 
@@ -816,6 +817,18 @@ out:
 	return ret;
 }
 
+static void ibs_eilvt_setup(void)
+{
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+}
+
 static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
@@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+	clear_APIC_ibs(NULL);
+	return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+	ibs_eilvt_setup();
+	setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+	.resume		= perf_ibs_resume,
+	.suspend	= perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+	register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
 static int __cpuinit
 perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -877,18 +920,12 @@ static __init int amd_ibs_init(void)
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	/*
-	 * Force LVT offset assignment for family 10h: The offsets are
-	 * not assigned by the BIOS for this family, so the OS is
-	 * responsible for doing it. If the OS assignment fails, fall
-	 * back to BIOS settings and try to setup this.
-	 */
-	if (boot_cpu_data.x86 == 0x10)
-		force_ibs_eilvt_setup();
+	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
 		goto out;
 
+	perf_ibs_pm_init();
 	get_online_cpus();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a9e22073bd56..6d6bb6f4fd43 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1199,6 +1199,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
@@ -2163,6 +2172,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 8aac56bda7dc..7185af255fb5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2657,6 +2657,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+	return event->pmu->event_init == uncore_pmu_event_init;
+}
+
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -2671,13 +2682,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
 		return -EINVAL;
 
 	n = box->n_events;
-	box->event_list[n] = leader;
-	n++;
+
+	if (is_uncore_event(leader)) {
+		box->event_list[n] = leader;
+		n++;
+	}
+
 	if (!dogrp)
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
+		if (!is_uncore_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
 		if (n >= max_count)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..66e274a3d968 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
 		[ DEBUG_STACK-1			]	= "#DB",
 		[ NMI_STACK-1			]	= "NMI",
 		[ DOUBLEFAULT_STACK-1		]	= "#DF",
-		[ STACKFAULT_STACK-1		]	= "#SS",
 		[ MCE_STACK-1			]	= "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
 		[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d32abeabbda5..174da5fc5a7b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -658,15 +658,18 @@ __init void e820_setup_gap(void)
  * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
  * linked list of struct setup_data, which is parsed here.
  */
-void __init parse_e820_ext(struct setup_data *sdata)
+void __init parse_e820_ext(u64 phys_addr, u32 data_len)
 {
 	int entries;
 	struct e820entry *extmap;
+	struct setup_data *sdata;
 
+	sdata = early_memremap(phys_addr, data_len);
 	entries = sdata->len / sizeof(struct e820entry);
 	extmap = (struct e820entry *)(sdata->data);
 	__append_e820_map(extmap, entries);
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	early_iounmap(sdata, data_len);
 	printk(KERN_INFO "e820: extended physical RAM map:\n");
 	e820_print_map("extended");
 }
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 63bdb29b2549..4f7c82cdd0f5 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -202,18 +202,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
- 	 * Revision 13 of all triggering devices id in this quirk have
-	 * a problem draining interrupts when irq remapping is enabled,
-	 * and should be flagged as broken.  Additionally revisions 0x12
-	 * and 0x22 of device id 0x3405 has this problem.
+	 * Revision <= 13 of all triggering devices id in this quirk
+	 * have a problem draining interrupts when irq remapping is
+	 * enabled, and should be flagged as broken. Additionally
+	 * revision 0x22 of device id 0x3405 has this problem.
 	 */
-	if (revision == 0x13)
+	if (revision <= 0x13)
 		set_irq_remapping_broken();
-	else if ((device == 0x3405) &&
-	    ((revision == 0x12) ||
-	     (revision == 0x22)))
+	else if (device == 0x3405 && revision == 0x22)
 		set_irq_remapping_broken();
-
 }
 
 #define QFLAG_APPLY_ONCE 	0x1
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8f3e2dec1df3..5c38e2b298cd 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -434,8 +434,9 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
+sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -516,6 +517,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -530,6 +532,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -540,6 +543,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 irq_return:
@@ -552,13 +556,9 @@ ENTRY(iret_exc)
 .previous
 	_ASM_EXTABLE(irq_return,iret_exc)
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
@@ -600,6 +600,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -690,8 +691,13 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,%eax
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
 /*
@@ -707,6 +713,7 @@ END(syscall_badsys)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -716,8 +723,10 @@ END(syscall_badsys)
 	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -728,6 +737,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1075,7 +1085,7 @@ ENTRY(ftrace_caller)
 	pushl $0	/* Pass NULL as regs pointer */
 	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
-	leal function_trace_op, %ecx
+	movl function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
 
 .globl ftrace_call
@@ -1133,7 +1143,7 @@ ENTRY(ftrace_regs_caller)
 	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
 	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
 	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
 	pushl %esp		/* Save pt_regs as 4th parameter */
 
 GLOBAL(ftrace_regs_call)
@@ -1335,11 +1345,13 @@ END(debug)
 ENTRY(nmi)
 	RING0_INT_FRAME
 	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1379,6 +1391,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1400,6 +1413,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 727208941030..948b2e14df8c 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -88,7 +89,7 @@ END(function_hook)
 	MCOUNT_SAVE_FRAME \skip
 
 	/* Load the ftrace_ops into the 3rd parameter */
-	leaq function_trace_op, %rdx
+	movq function_trace_op(%rip), %rdx
 
 	/* Load ip into the first parameter */
 	movq RIP(%rsp), %rdi
@@ -365,7 +366,7 @@ ENDPROC(native_usergs_sysret64)
 	/*CFI_REL_OFFSET	ss,0*/
 	pushq_cfi %rax /* rsp */
 	CFI_REL_OFFSET	rsp,0
-	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */
+	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */
 	/*CFI_REL_OFFSET	rflags,0*/
 	pushq_cfi $__KERNEL_CS /* cs */
 	/*CFI_REL_OFFSET	cs,0*/
@@ -1056,32 +1057,52 @@ restore_args:
 
 irq_return:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
 
-#ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
-	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
+	/*
+	 * Are we returning to a stack segment from the LDT?  Note: in
+	 * 64-bit mode SS:RSP on the exception stack is always valid.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	testb $4,(SS-RIP)(%rsp)
+	jnz native_irq_return_ldt
 #endif
 
-	.section .fixup,"ax"
-bad_iret:
+.global native_irq_return_iret
+native_irq_return_iret:
 	/*
-	 * The iret traps when the %cs or %ss being restored is bogus.
-	 * We've lost the original trap vector and error code.
-	 * #GPF is the most likely one to get for an invalid selector.
-	 * So pretend we completed the iret and took the #GPF in user mode.
-	 *
-	 * We are now running with the kernel GS after exception recovery.
-	 * But error_entry expects us to have user GS to match the user %cs,
-	 * so swap back.
+	 * This may fault.  Non-paranoid faults on return to userspace are
+	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
+	 * Double-faults due to espfix64 are handled in do_double_fault.
+	 * Other faults here are fatal.
 	 */
-	pushq $0
+	iretq
 
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
 	SWAPGS
-	jmp general_protection
-
-	.previous
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp native_irq_return_iret
+#endif
 
 	/* edi: workmask, edx: work */
 retint_careful:
@@ -1127,9 +1148,9 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
 /*
  * End of kprobes section
  */
@@ -1468,7 +1489,7 @@ apicinterrupt HYPERVISOR_CALLBACK_VECTOR \
 
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
 #ifdef CONFIG_XEN
 zeroentry xen_debug do_debug
 zeroentry xen_int3 do_int3
@@ -1578,16 +1599,15 @@ error_sti:
 
 /*
  * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here.  B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
-	je error_swapgs
+	je error_bad_iret
 	movl %ecx,%eax	/* zero extend */
 	cmpq %rax,RIP+8(%rsp)
 	je bstep_iret
@@ -1598,7 +1618,15 @@ error_kernelspace:
 bstep_iret:
 	/* Fix truncated RIP */
 	movq %rcx,RIP+8(%rsp)
-	jmp error_swapgs
+	/* fall through */
+
+error_bad_iret:
+	SWAPGS
+	mov %rsp,%rdi
+	call fixup_bad_iret
+	mov %rax,%rsp
+	decl %ebx	/* Return to usergs */
+	jmp error_sti
 	CFI_ENDPROC
 END(error_entry)
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 000000000000..94d857fb1033
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms and conditions of the GNU General Public License,
+ *   version 2, as published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but WITHOUT
+ *   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *   more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer.  This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart.  When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace.  The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables.  The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE	(8*8UL)
+#define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES  DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+	__aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+	unsigned long page, slot;
+	unsigned long addr;
+
+	page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+	slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+	addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+	addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+	addr += ESPFIX_BASE_ADDR;
+	return addr;
+}
+
+#define PTE_STRIDE        (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT	  ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+	unsigned long rand;
+
+	/*
+	 * This is run before the entropy pools are initialized,
+	 * but this is hopefully better than nothing.
+	 */
+	if (!arch_get_random_long(&rand)) {
+		/* The constant is an arbitrary large prime */
+		rdtscll(rand);
+		rand *= 0xc345c6b72fd16123UL;
+	}
+
+	slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+	page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+		& (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+	pgd_t *pgd_p;
+	pteval_t ptemask;
+
+	ptemask = __supported_pte_mask;
+
+	/* Install the espfix pud into the kernel page directory */
+	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+	/* Randomize the locations */
+	init_espfix_random();
+
+	/* The rest is the same as for any other processor */
+	init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+	unsigned int cpu, page;
+	unsigned long addr;
+	pud_t pud, *pud_p;
+	pmd_t pmd, *pmd_p;
+	pte_t pte, *pte_p;
+	int n;
+	void *stack_page;
+	pteval_t ptemask;
+
+	/* We only have to do this once... */
+	if (likely(this_cpu_read(espfix_stack)))
+		return;		/* Already initialized */
+
+	cpu = smp_processor_id();
+	addr = espfix_base_addr(cpu);
+	page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+	/* Did another CPU already set this up? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (likely(stack_page))
+		goto done;
+
+	mutex_lock(&espfix_init_mutex);
+
+	/* Did we race on the lock? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (stack_page)
+		goto unlock_done;
+
+	ptemask = __supported_pte_mask;
+
+	pud_p = &espfix_pud_page[pud_index(addr)];
+	pud = *pud_p;
+	if (!pud_present(pud)) {
+		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+			set_pud(&pud_p[n], pud);
+	}
+
+	pmd_p = pmd_offset(&pud, addr);
+	pmd = *pmd_p;
+	if (!pmd_present(pmd)) {
+		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+			set_pmd(&pmd_p[n], pmd);
+	}
+
+	pte_p = pte_offset_kernel(&pmd, addr);
+	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+		set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+	/* Job is done for this CPU and any CPU which shares this page */
+	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+	mutex_unlock(&espfix_init_mutex);
+done:
+	this_cpu_write(espfix_stack, addr);
+	this_cpu_write(espfix_waddr, (unsigned long)stack_page
+		       + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 42a392a9fd02..1ffc32dbe450 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+	return ip;
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
+	ip = text_ip_addr(ip);
+
 	/* replace the text with the new text */
-	if (do_ftrace_mod_code(ip, new_code))
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	sync_core();
@@ -221,33 +222,56 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 	return -EINVAL;
 }
 
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	unsigned char old[MCOUNT_INSN_SIZE];
 	int ret;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, (unsigned long)func);
+	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+	ftrace_update_func = ip;
+	/* Make sure the breakpoints see the ftrace_update_func update */
+	smp_wmb();
 
 	/* See comment above by declaration of modifying_ftrace_code */
 	atomic_inc(&modifying_ftrace_code);
 
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
+	return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char *new;
+	int ret;
+
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
 	/* Also update the regs callback function */
 	if (!ret) {
 		ip = (unsigned long)(&ftrace_regs_call);
-		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = update_ftrace_func(ip, new);
 	}
 
-	atomic_dec(&modifying_ftrace_code);
-
 	return ret;
 }
 
+static int is_ftrace_caller(unsigned long ip)
+{
+	if (ip == ftrace_update_func)
+		return 1;
+
+	return 0;
+}
+
 /*
  * A breakpoint was added to the code address we are about to
  * modify, and this is the handle that will just skip over it.
@@ -257,10 +281,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
  */
 int ftrace_int3_handler(struct pt_regs *regs)
 {
+	unsigned long ip;
+
 	if (WARN_ON_ONCE(!regs))
 		return 0;
 
-	if (!ftrace_location(regs->ip - 1))
+	ip = regs->ip - 1;
+	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
 		return 0;
 
 	regs->ip += MCOUNT_INSN_SIZE - 1;
@@ -632,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 		ret = -EPERM;
 		goto out;
 	}
-	run_sync();
  out:
+	run_sync();
 	return ret;
 
  fail_update:
@@ -665,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data)
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
-static int ftrace_mod_jmp(unsigned long ip,
-			  int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
-	unsigned char code[MCOUNT_INSN_SIZE];
+	static union ftrace_code_union calc;
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	/* Jmp not a call (ignore the .e8) */
+	calc.e8		= 0xe9;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
 
-	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
-		return -EINVAL;
+	/*
+	 * ftrace external locks synchronize the access to the static variable.
+	 */
+	return calc.code;
+}
 
-	*(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+	unsigned char *new;
 
-	if (do_ftrace_mod_code(ip, &code))
-		return -EPERM;
+	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
-	return 0;
+	return update_ftrace_func(ip, new);
 }
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
 
-	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
-
-	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
 
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
 
 #endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 73afd11799ca..df63cae573e0 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -566,6 +566,10 @@ ENDPROC(early_idt_handlers)
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $2,(%esp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -616,8 +620,9 @@ ex_entry:
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a8368608ab41..f2a9a2aa98f3 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $2,(%rsp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f7ea30dce238..b03ff1842547 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index cd6d9a5a42f6..c4ff2a916139 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -279,7 +279,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
-	pv_info.paravirt_enabled = 1;
+
+	/*
+	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
+	 * guest kernel works like a bare metal kernel with additional
+	 * features, and paravirt_enabled is about features that are
+	 * missing.
+	 */
+	pv_info.paravirt_enabled = 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 3dd37ebd591b..41514f56c241 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -265,7 +265,6 @@ void __init kvmclock_init(void)
 #endif
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
-	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc987398923..c37886d759cc 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index efdec7cd8e01..b516dfb411ec 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -430,7 +430,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
 	if (request_firmware(&fw, (const char *)fw_name, device)) {
-		pr_err("failed to load file %s\n", fw_name);
+		pr_debug("failed to load file %s\n", fw_name);
 		goto out;
 	}
 
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93eb..a1da6737ba5b 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 872079a67e4d..f7d0672481fd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 	flag |= __GFP_ZERO;
 again:
 	page = NULL;
-	if (!(flag & GFP_ATOMIC))
+	/* CMA can be used only in the context which permits sleeping */
+	if (flag & __GFP_WAIT)
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+	/* fallback */
 	if (!page)
 		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
 	if (!page)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 81a5f5e8f142..59b90379cb6a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -391,9 +391,9 @@ static void amd_e400_idle(void)
 		 * The switch back from broadcast mode needs to be
 		 * called with interrupts disabled.
 		 */
-		 local_irq_disable();
-		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		 local_irq_enable();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
 	} else
 		default_idle();
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7305f7dfc7ab..0339f5c14bf9 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -147,7 +147,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		childregs->bp = arg;
 		childregs->orig_ax = -1;
 		childregs->cs = __KERNEL_CS | get_kernel_rpl();
-		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 		p->fpu_counter = 0;
 		p->thread.io_bitmap_ptr = NULL;
 		memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 355ae06dbf94..7099ab1e075b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -176,7 +176,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		childregs->bp = arg;
 		childregs->orig_ax = -1;
 		childregs->cs = __KERNEL_CS | get_kernel_rpl();
-		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 		return 0;
 	}
 	*childregs = *current_pt_regs();
@@ -279,24 +279,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
-	/*
-	 * Reload esp0, LDT and the page table pointer:
-	 */
+	/* Reload esp0 and ss1. */
 	load_sp0(tss, next);
 
-	/*
-	 * Switch DS and ES.
-	 * This won't pick up thread selector changes, but I guess that is ok.
-	 */
-	savesegment(es, prev->es);
-	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es);
-
-	savesegment(ds, prev->ds);
-	if (unlikely(next->ds | prev->ds))
-		loadsegment(ds, next->ds);
-
-
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
 	 *
@@ -305,41 +290,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	savesegment(fs, fsindex);
 	savesegment(gs, gsindex);
 
+	/*
+	 * Load TLS before restoring any segments so that segment loads
+	 * reference the correct GDT entries.
+	 */
 	load_TLS(next, cpu);
 
 	/*
-	 * Leave lazy mode, flushing any hypercalls made here.
-	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
-	 * to date.
+	 * Leave lazy mode, flushing any hypercalls made here.  This
+	 * must be done after loading TLS entries in the GDT but before
+	 * loading segments that might reference them, and and it must
+	 * be done before math_state_restore, so the TS bit is up to
+	 * date.
 	 */
 	arch_end_context_switch(next_p);
 
+	/* Switch DS and ES.
+	 *
+	 * Reading them only returns the selectors, but writing them (if
+	 * nonzero) loads the full descriptor from the GDT or LDT.  The
+	 * LDT for next is loaded in switch_mm, and the GDT is loaded
+	 * above.
+	 *
+	 * We therefore need to write new values to the segment
+	 * registers on every context switch unless both the new and old
+	 * values are zero.
+	 *
+	 * Note that we don't need to do anything for CS and SS, as
+	 * those are saved and restored as part of pt_regs.
+	 */
+	savesegment(es, prev->es);
+	if (unlikely(next->es | prev->es))
+		loadsegment(es, next->es);
+
+	savesegment(ds, prev->ds);
+	if (unlikely(next->ds | prev->ds))
+		loadsegment(ds, next->ds);
+
 	/*
 	 * Switch FS and GS.
 	 *
-	 * Segment register != 0 always requires a reload.  Also
-	 * reload when it has changed.  When prev process used 64bit
-	 * base always reload to avoid an information leak.
+	 * These are even more complicated than FS and GS: they have
+	 * 64-bit bases are that controlled by arch_prctl.  Those bases
+	 * only differ from the values in the GDT or LDT if the selector
+	 * is 0.
+	 *
+	 * Loading the segment register resets the hidden base part of
+	 * the register to 0 or the value from the GDT / LDT.  If the
+	 * next base address zero, writing 0 to the segment register is
+	 * much faster than using wrmsr to explicitly zero the base.
+	 *
+	 * The thread_struct.fs and thread_struct.gs values are 0
+	 * if the fs and gs bases respectively are not overridden
+	 * from the values implied by fsindex and gsindex.  They
+	 * are nonzero, and store the nonzero base addresses, if
+	 * the bases are overridden.
+	 *
+	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+	 * be impossible.
+	 *
+	 * Therefore we need to reload the segment registers if either
+	 * the old or new selector is nonzero, and we need to override
+	 * the base address if next thread expects it to be overridden.
+	 *
+	 * This code is unnecessarily slow in the case where the old and
+	 * new indexes are zero and the new base is nonzero -- it will
+	 * unnecessarily write 0 to the selector before writing the new
+	 * base address.
+	 *
+	 * Note: This all depends on arch_prctl being the only way that
+	 * user code can override the segment base.  Once wrfsbase and
+	 * wrgsbase are enabled, most of this code will need to change.
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
+
 		/*
-		 * Check if the user used a selector != 0; if yes
-		 *  clear 64bit base, since overloaded base is always
-		 *  mapped to the Null selector
+		 * If user code wrote a nonzero value to FS, then it also
+		 * cleared the overridden base address.
+		 *
+		 * XXX: if user code wrote 0 to FS and cleared the base
+		 * address itself, we won't notice and we'll incorrectly
+		 * restore the prior base address next time we reschdule
+		 * the process.
 		 */
 		if (fsindex)
 			prev->fs = 0;
 	}
-	/* when next process has a 64bit base use it */
 	if (next->fs)
 		wrmsrl(MSR_FS_BASE, next->fs);
 	prev->fsindex = fsindex;
 
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
+
+		/* This works (and fails) the same way as fsindex above. */
 		if (gsindex)
 			prev->gs = 0;
 	}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 29a8120e6fe8..baa61e7370b7 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1475,15 +1475,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 	force_sig_info(SIGTRAP, &info, tsk);
 }
 
-
-#ifdef CONFIG_X86_32
-# define IS_IA32	1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32	is_compat_task()
-#else
-# define IS_IA32	0
-#endif
-
 /*
  * We must return the syscall number to actually look up in the table.
  * This can be -1L to skip running any syscall at all.
@@ -1521,7 +1512,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->orig_ax);
 
-	if (IS_IA32)
+	if (is_ia32_task())
 		audit_syscall_entry(AUDIT_ARCH_I386,
 				    regs->orig_ax,
 				    regs->bx, regs->cx,
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2e4c02..52dbf1e400dc 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
 		return;
 
 	pci_read_config_dword(nb_ht, 0x60, &val);
-	node = val & 7;
+	node = pcibus_to_node(dev->bus) | (val & 7);
 	/*
 	 * Some hardware may return an invalid node ID,
 	 * so check it first:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f7703401d6cb..3876c04feef9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -447,6 +447,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Dell PowerEdge C6100. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
+	{	/* Some C6100 machines were shipped with vendor being 'Dell'. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a8..80eab01c1a68 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 56f7fcfe7fa2..a3627ade4b15 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -426,25 +426,23 @@ static void __init reserve_initrd(void)
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
-	u64 pa_data;
+	u64 pa_data, pa_next;
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		u32 data_len, map_len;
+		u32 data_len, map_len, data_type;
 
 		map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
 			      (u64)sizeof(struct setup_data));
 		data = early_memremap(pa_data, map_len);
 		data_len = data->len + sizeof(struct setup_data);
-		if (data_len > map_len) {
-			early_iounmap(data, map_len);
-			data = early_memremap(pa_data, data_len);
-			map_len = data_len;
-		}
+		data_type = data->type;
+		pa_next = data->next;
+		early_iounmap(data, map_len);
 
-		switch (data->type) {
+		switch (data_type) {
 		case SETUP_E820_EXT:
-			parse_e820_ext(data);
+			parse_e820_ext(pa_data, data_len);
 			break;
 		case SETUP_DTB:
 			add_dtb(pa_data);
@@ -452,8 +450,7 @@ static void __init parse_setup_data(void)
 		default:
 			break;
 		}
-		pa_data = data->next;
-		early_iounmap(data, map_len);
+		pa_data = pa_next;
 	}
 }
 
@@ -911,11 +908,11 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
-		set_bit(EFI_64BIT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
 	}
 
 	if (efi_enabled(EFI_BOOT))
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 087ab2af381a..66deef41512f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -677,6 +677,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		 * handler too.
 		 */
 		regs->flags &= ~X86_EFLAGS_TF;
+		/*
+		 * Ensure the signal handler starts with the new fpu state.
+		 */
+		if (used_math())
+			drop_init_fpu(current);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bfd348e99369..87084ab90d19 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -265,6 +265,13 @@ notrace static void __cpuinit start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold vector_lock so there the set of online cpus
 	 * does not change while we are assigning vectors to cpus.  Holding
 	 * this lock ensures we don't half assign or remove an irq from a cpu.
@@ -1277,6 +1284,9 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_sibling_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(cpu_sibling_mask(cpu));
 	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09e3e3a..4e942f31b1a7 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,37 @@ static int get_free_idx(void)
 	return -ESRCH;
 }
 
+static bool tls_desc_okay(const struct user_desc *info)
+{
+	if (LDT_empty(info))
+		return true;
+
+	/*
+	 * espfix is required for 16-bit data segments, but espfix
+	 * only works for LDT segments.
+	 */
+	if (!info->seg_32bit)
+		return false;
+
+	/* Only allow data segments in the TLS array. */
+	if (info->contents > 1)
+		return false;
+
+	/*
+	 * Non-present segments with DPL 3 present an interesting attack
+	 * surface.  The kernel should handle such segments correctly,
+	 * but TLS is very difficult to protect in a sandbox, so prevent
+	 * such segments from being created.
+	 *
+	 * If userspace needs to remove a TLS entry, it can still delete
+	 * it outright.
+	 */
+	if (info->seg_not_present)
+		return false;
+
+	return true;
+}
+
 static void set_tls_desc(struct task_struct *p, int idx,
 			 const struct user_desc *info, int n)
 {
@@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
 
+	if (!tls_desc_okay(&info))
+		return -EINVAL;
+
 	if (idx == -1)
 		idx = info.entry_number;
 
@@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 {
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
+	int i;
 
 	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	else
 		info = infobuf;
 
+	for (i = 0; i < count / sizeof(struct user_desc); i++)
+		if (!tls_desc_okay(info + i))
+			return -EINVAL;
+
 	set_tls_desc(target,
 		     GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
 		     info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 772e2a846dec..332cafe909eb 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -220,33 +220,41 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
 		coprocessor_segment_overrun)
 DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
 DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-#ifdef CONFIG_X86_32
 DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-#endif
 DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
 		BUS_ADRALN, 0)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
-	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-		       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
-		preempt_conditional_sti(regs);
-		do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-		preempt_conditional_cli(regs);
-	}
-	exception_exit(prev_state);
-}
-
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
 
+#ifdef CONFIG_X86_ESPFIX64
+	extern unsigned char native_irq_return_iret[];
+
+	/*
+	 * If IRET takes a non-IST fault on the espfix64 stack, then we
+	 * end up promoting it to a doublefault.  In that case, modify
+	 * the stack to make it look like we just entered the #GP
+	 * handler from user space, similar to bad_iret.
+	 */
+	if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+		regs->cs == __KERNEL_CS &&
+		regs->ip == (unsigned long)native_irq_return_iret)
+	{
+		struct pt_regs *normal_regs = task_pt_regs(current);
+
+		/* Fake a #GP(0) from userspace. */
+		memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+		normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+		regs->ip = (unsigned long)general_protection;
+		regs->sp = (unsigned long)&normal_regs->orig_ax;
+		return;
+	}
+#endif
+
 	exception_enter();
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -373,6 +381,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 		*regs = *eregs;
 	return regs;
 }
+
+struct bad_iret_stack {
+	void *error_entry_ret;
+	struct pt_regs regs;
+};
+
+asmlinkage __visible
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+	/*
+	 * This is called from entry_64.S early in handling a fault
+	 * caused by a bad iret to user mode.  To handle the fault
+	 * correctly, we want move our stack frame to task_pt_regs
+	 * and we want to pretend that the exception came from the
+	 * iret target.
+	 */
+	struct bad_iret_stack *new_stack =
+		container_of(task_pt_regs(current),
+			     struct bad_iret_stack, regs);
+
+	/* Copy the IRET target to the new stack. */
+	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+	/* Copy the remainder of the stack from the current stack. */
+	memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+	BUG_ON(!user_mode_vm(&new_stack->regs));
+	return new_stack;
+}
 #endif
 
 /*
@@ -745,7 +782,7 @@ void __init trap_init(void)
 	set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
 	set_intr_gate(X86_TRAP_TS, &invalid_TSS);
 	set_intr_gate(X86_TRAP_NP, &segment_not_present);
-	set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+	set_intr_gate(X86_TRAP_SS, stack_segment);
 	set_intr_gate(X86_TRAP_GP, &general_protection);
 	set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
 	set_intr_gate(X86_TRAP_MF, &coprocessor_error);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 098b3cfda72e..4e27ba53c40c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -968,14 +968,17 @@ void __init tsc_init(void)
 
 	x86_init.timers.tsc_pre_init();
 
-	if (!cpu_has_tsc)
+	if (!cpu_has_tsc) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
 	tsc_khz = x86_platform.calibrate_tsc();
 	cpu_khz = tsc_khz;
 
 	if (!tsc_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
 	}
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 9a907a67be8f..c52c07efe970 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
-			      level, current->comm, task_pid_nr(current),
-			      message, regs->ip, regs->cs,
-			      regs->sp, regs->ax, regs->si, regs->di);
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index ada87a329edc..1ee723298e90 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
 		return -1;
 
-	drop_init_fpu(tsk);	/* trigger finit */
-
 	return 0;
 }
 
@@ -400,8 +398,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 			set_used_math();
 		}
 
-		if (use_eager_fpu())
+		if (use_eager_fpu()) {
+			preempt_disable();
 			math_state_restore();
+			preempt_enable();
+		}
 
 		return err;
 	} else {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5953dcea752d..4c01f022c6ac 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -663,11 +663,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
 	masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
 }
 
-static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
-{
-	register_address_increment(ctxt, &ctxt->_eip, rel);
-}
-
 static u32 desc_limit_scaled(struct desc_struct *desc)
 {
 	u32 limit = get_desc_limit(desc);
@@ -741,6 +736,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt)
 	return emulate_exception(ctxt, NM_VECTOR, 0, false);
 }
 
+static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+			       int cs_l)
+{
+	switch (ctxt->op_bytes) {
+	case 2:
+		ctxt->_eip = (u16)dst;
+		break;
+	case 4:
+		ctxt->_eip = (u32)dst;
+		break;
+	case 8:
+		if ((cs_l && is_noncanonical_address(dst)) ||
+		    (!cs_l && (dst & ~(u32)-1)))
+			return emulate_gp(ctxt, 0);
+		ctxt->_eip = dst;
+		break;
+	default:
+		WARN(1, "unsupported eip assignment size\n");
+	}
+	return X86EMUL_CONTINUE;
+}
+
+static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+{
+	return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64);
+}
+
+static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+{
+	return assign_eip_near(ctxt, ctxt->_eip + rel);
+}
+
 static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
 {
 	u16 selector;
@@ -2161,13 +2188,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt)
 	case 2: /* call near abs */ {
 		long int old_eip;
 		old_eip = ctxt->_eip;
-		ctxt->_eip = ctxt->src.val;
+		rc = assign_eip_near(ctxt, ctxt->src.val);
+		if (rc != X86EMUL_CONTINUE)
+			break;
 		ctxt->src.val = old_eip;
 		rc = em_push(ctxt);
 		break;
 	}
 	case 4: /* jmp abs */
-		ctxt->_eip = ctxt->src.val;
+		rc = assign_eip_near(ctxt, ctxt->src.val);
 		break;
 	case 5: /* jmp far */
 		rc = em_jmp_far(ctxt);
@@ -2199,16 +2228,21 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
 
 static int em_ret(struct x86_emulate_ctxt *ctxt)
 {
-	ctxt->dst.type = OP_REG;
-	ctxt->dst.addr.reg = &ctxt->_eip;
-	ctxt->dst.bytes = ctxt->op_bytes;
-	return em_pop(ctxt);
+	int rc;
+	unsigned long eip;
+
+	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	return assign_eip_near(ctxt, eip);
 }
 
 static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long cs;
+	int cpl = ctxt->ops->cpl(ctxt);
 
 	rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2218,6 +2252,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
+	/* Outer-privilege level return is not implemented */
+	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+		return X86EMUL_UNHANDLEABLE;
 	rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
@@ -2465,7 +2502,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 {
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	struct desc_struct cs, ss;
-	u64 msr_data;
+	u64 msr_data, rcx, rdx;
 	int usermode;
 	u16 cs_sel = 0, ss_sel = 0;
 
@@ -2481,6 +2518,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 	else
 		usermode = X86EMUL_MODE_PROT32;
 
+	rcx = reg_read(ctxt, VCPU_REGS_RCX);
+	rdx = reg_read(ctxt, VCPU_REGS_RDX);
+
 	cs.dpl = 3;
 	ss.dpl = 3;
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
@@ -2498,6 +2538,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 		ss_sel = cs_sel + 8;
 		cs.d = 0;
 		cs.l = 1;
+		if (is_noncanonical_address(rcx) ||
+		    is_noncanonical_address(rdx))
+			return emulate_gp(ctxt, 0);
 		break;
 	}
 	cs_sel |= SELECTOR_RPL_MASK;
@@ -2506,8 +2549,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
-	ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
-	*reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
+	ctxt->_eip = rdx;
+	*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3046,10 +3089,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
 
 static int em_call(struct x86_emulate_ctxt *ctxt)
 {
+	int rc;
 	long rel = ctxt->src.val;
 
 	ctxt->src.val = (unsigned long)ctxt->_eip;
-	jmp_rel(ctxt, rel);
+	rc = jmp_rel(ctxt, rel);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
 	return em_push(ctxt);
 }
 
@@ -3081,11 +3127,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
 static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
+	unsigned long eip;
 
-	ctxt->dst.type = OP_REG;
-	ctxt->dst.addr.reg = &ctxt->_eip;
-	ctxt->dst.bytes = ctxt->op_bytes;
-	rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
+	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	rc = assign_eip_near(ctxt, eip);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rsp_increment(ctxt, ctxt->src.val);
@@ -3375,20 +3422,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt)
 
 static int em_loop(struct x86_emulate_ctxt *ctxt)
 {
+	int rc = X86EMUL_CONTINUE;
+
 	register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
 	if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
 	    (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 
-	return X86EMUL_CONTINUE;
+	return rc;
 }
 
 static int em_jcxz(struct x86_emulate_ctxt *ctxt)
 {
+	int rc = X86EMUL_CONTINUE;
+
 	if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 
-	return X86EMUL_CONTINUE;
+	return rc;
 }
 
 static int em_in(struct x86_emulate_ctxt *ctxt)
@@ -4207,7 +4258,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpMem8:
 		ctxt->memop.bytes = 1;
 		if (ctxt->memop.type == OP_REG) {
-			ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1);
+			int highbyte_regs = ctxt->rex_prefix == 0;
+
+			ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+					       highbyte_regs);
 			fetch_register_operand(&ctxt->memop);
 		}
 		goto mem_common;
@@ -4714,7 +4768,7 @@ special_insn:
 		break;
 	case 0x70 ... 0x7f: /* jcc (short) */
 		if (test_cc(ctxt->b, ctxt->eflags))
-			jmp_rel(ctxt, ctxt->src.val);
+			rc = jmp_rel(ctxt, ctxt->src.val);
 		break;
 	case 0x8d: /* lea r16/r32, m */
 		ctxt->dst.val = ctxt->src.addr.mem.ea;
@@ -4743,7 +4797,7 @@ special_insn:
 		break;
 	case 0xe9: /* jmp rel */
 	case 0xeb: /* jmp rel short */
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 		ctxt->dst.type = OP_NONE; /* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
@@ -4855,7 +4909,7 @@ twobyte_insn:
 		break;
 	case 0x80 ... 0x8f: /* jnz rel, etc*/
 		if (test_cc(ctxt->b, ctxt->eflags))
-			jmp_rel(ctxt, ctxt->src.val);
+			rc = jmp_rel(ctxt, ctxt->src.val);
 		break;
 	case 0x90 ... 0x9f:     /* setcc r/m8 */
 		ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 412a5aa0ef94..298781d4cfb4 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -37,6 +37,7 @@
 
 #include "irq.h"
 #include "i8254.h"
+#include "x86.h"
 
 #ifndef CONFIG_X86_64
 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -261,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 		return;
 
 	timer = &pit->pit_state.timer;
+	mutex_lock(&pit->pit_state.lock);
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	mutex_unlock(&pit->pit_state.lock);
 }
 
 static void destroy_pit_timer(struct kvm_pit *pit)
@@ -349,6 +352,23 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 	atomic_set(&ps->pending, 0);
 	ps->irq_ack = 1;
 
+	/*
+	 * Do not allow the guest to program periodic timers with small
+	 * interval, since the hrtimers are not throttled by the host
+	 * scheduler.
+	 */
+	if (ps->is_periodic) {
+		s64 min_period = min_timer_period_us * 1000LL;
+
+		if (ps->period < min_period) {
+			pr_info_ratelimited(
+			    "kvm: requested %lld ns "
+			    "i8254 timer period limited to %lld ns\n",
+			    ps->period, min_period);
+			ps->period = min_period;
+		}
+	}
+
 	hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
 		      HRTIMER_MODE_ABS);
 }
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc874688b..3ec38cb56bd5 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 
 	vector = kvm_cpu_get_extint(v);
 
-	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+	if (vector != -1)
 		return vector;			/* PIC */
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0eee2c8b64d1..681e4e251f00 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -71,9 +71,6 @@
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)
 
-static unsigned int min_timer_period_us = 500;
-module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
-
 static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
 {
 	*((u32 *) (apic->regs + reg_off)) = val;
@@ -153,6 +150,8 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
+#define KVM_X2APIC_CID_BITS 0
+
 static void recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -190,7 +189,8 @@ static void recalculate_apic_map(struct kvm *kvm)
 		if (apic_x2apic_mode(apic)) {
 			new->ldr_bits = 32;
 			new->cid_shift = 16;
-			new->cid_mask = new->lid_mask = 0xffff;
+			new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+			new->lid_mask = 0xffff;
 		} else if (kvm_apic_sw_enabled(apic) &&
 				!new->cid_mask /* flat mode */ &&
 				kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
@@ -362,31 +362,90 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
-	apic->irr_pending = false;
+	struct kvm_vcpu *vcpu;
+
+	vcpu = apic->vcpu;
+
 	apic_clear_vector(vec, apic->regs + APIC_IRR);
-	if (apic_search_irr(apic) != -1)
-		apic->irr_pending = true;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		/* try to update RVI */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	else {
+		vec = apic_search_irr(apic);
+		apic->irr_pending = (vec != -1);
+	}
 }
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
-	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+
+	if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * With APIC virtualization enabled, all caching is disabled
+	 * because the processor can modify ISR under the hood.  Instead
+	 * just set SVI.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+	else {
 		++apic->isr_count;
-	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		/*
+		 * ISR (in service register) bit is set when injecting an interrupt.
+		 * The highest vector is injected. Thus the latest bit set matches
+		 * the highest bit in ISR.
+		 */
+		apic->highest_isr_cache = vec;
+	}
+}
+
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
 	/*
-	 * ISR (in service register) bit is set when injecting an interrupt.
-	 * The highest vector is injected. Thus the latest bit set matches
-	 * the highest bit in ISR.
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
 	 */
-	apic->highest_isr_cache = vec;
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
 }
 
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -466,22 +525,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
-}
-
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -855,7 +898,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
+	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+		apic->lapic_timer.period == 0)
 		return 0;
 
 	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -1360,8 +1404,12 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
+	if (!kvm_vcpu_is_bsp(apic->vcpu))
+		value &= ~MSR_IA32_APICBASE_BSP;
+	vcpu->arch.apic_base = value;
+
 	/* update jump label if enable bit changes */
-	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		else
@@ -1369,10 +1417,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		recalculate_apic_map(vcpu->kvm);
 	}
 
-	if (!kvm_vcpu_is_bsp(apic->vcpu))
-		value &= ~MSR_IA32_APICBASE_BSP;
-
-	vcpu->arch.apic_base = value;
 	if ((old_value ^ value) & X2APIC_ENABLE) {
 		if (value & X2APIC_ENABLE) {
 			u32 id = kvm_apic_id(apic);
@@ -1621,6 +1665,13 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	if (vector == -1)
 		return -1;
 
+	/*
+	 * We get here even with APIC virtualization enabled, if doing
+	 * nested virtualization and L1 runs with the "acknowledge interrupt
+	 * on exit" mode.  Then we cannot inject the interrupt via RVI,
+	 * because the process would deliver it through the IDT.
+	 */
+
 	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
@@ -1705,7 +1756,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data;
-	void *vapic;
 
 	if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
 		apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
@@ -1713,9 +1763,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
-	kunmap_atomic(vapic);
+	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
@@ -1751,7 +1800,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	u32 data, tpr;
 	int max_irr, max_isr;
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	void *vapic;
 
 	apic_sync_pv_eoi_to_guest(vcpu, apic);
 
@@ -1767,18 +1815,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 		max_isr = 0;
 	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
-	kunmap_atomic(vapic);
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 }
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
-	vcpu->arch.apic->vapic_addr = vapic_addr;
-	if (vapic_addr)
+	if (vapic_addr) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+					&vcpu->arch.apic->vapic_cache,
+					vapic_addr, sizeof(u32)))
+			return -EINVAL;
 		__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
-	else
+	} else {
 		__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	}
+
+	vcpu->arch.apic->vapic_addr = vapic_addr;
+	return 0;
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c730ac9fe801..c8b0d0d2da5c 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -34,7 +34,7 @@ struct kvm_lapic {
 	 */
 	void *regs;
 	gpa_t vapic_addr;
-	struct page *vapic_page;
+	struct gfn_to_hva_cache vapic_cache;
 	unsigned long pending_events;
 	unsigned int sipi_vector;
 };
@@ -76,7 +76,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
 void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f47d2e11108e..0cc34f594c2a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2585,6 +2585,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 	int emulate = 0;
 	gfn_t pseudo_gfn;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return 0;
+
 	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
 		if (iterator.level == level) {
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
@@ -2748,6 +2751,9 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	bool ret = false;
 	u64 spte = 0ull;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return false;
+
 	if (!page_fault_can_be_fast(vcpu, error_code))
 		return false;
 
@@ -3066,7 +3072,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	vcpu_clear_mmio_info(vcpu, ~0ul);
+	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 	if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3139,6 +3145,9 @@ static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
 	struct kvm_shadow_walk_iterator iterator;
 	u64 spte = 0ull;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return spte;
+
 	walk_shadow_page_lockless_begin(vcpu);
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
 		if (!is_shadow_present_pte(spte))
@@ -4329,6 +4338,9 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 	u64 spte;
 	int nr_sptes = 0;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return nr_sptes;
+
 	walk_shadow_page_lockless_begin(vcpu);
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
 		sptes[iterator.level-1] = spte;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index e1af2394a23f..a6a6370c2010 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -441,6 +441,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		goto out_gpte_changed;
+
 	for (shadow_walk_init(&it, vcpu, addr);
 	     shadow_walk_okay(&it) && it.level > gw->level;
 	     shadow_walk_next(&it)) {
@@ -689,6 +692,11 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 	 */
 	mmu_topup_memory_caches(vcpu);
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) {
+		WARN_ON(1);
+		return;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	for_each_shadow_entry(vcpu, gva, iterator) {
 		level = iterator.level;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 934befea3e36..03f7d03c92a2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2985,10 +2985,8 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(svm);
-	if (irqchip_in_kernel(svm->vcpu.kvm)) {
-		clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	if (irqchip_in_kernel(svm->vcpu.kvm))
 		return r;
-	}
 	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return r;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3198,7 +3196,7 @@ static int wrmsr_interception(struct vcpu_svm *svm)
 	msr.host_initiated = false;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	if (svm_set_msr(&svm->vcpu, &msr)) {
+	if (kvm_set_msr(&svm->vcpu, &msr)) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(&svm->vcpu, 0);
 	} else {
@@ -3480,9 +3478,9 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
-		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
-		kvm_run->hw.hardware_exit_reason = exit_code;
-		return 0;
+		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
 	}
 
 	return svm_exit_handlers[exit_code](svm);
@@ -3550,6 +3548,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
 		return;
 
+	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	if (irr == -1)
 		return;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index af423252c265..d969fb91f17b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2493,12 +2493,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			break;
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
+			u64 old_msr_data = msr->data;
 			msr->data = data;
 			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
 				preempt_disable();
-				kvm_set_shared_msr(msr->index, msr->data,
-						   msr->mask);
+				ret = kvm_set_shared_msr(msr->index, msr->data,
+							 msr->mask);
 				preempt_enable();
+				if (ret)
+					msr->data = old_msr_data;
 			}
 			break;
 		}
@@ -5062,7 +5065,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu)
 	msr.data = data;
 	msr.index = ecx;
 	msr.host_initiated = false;
-	if (vmx_set_msr(vcpu, &msr) != 0) {
+	if (kvm_set_msr(vcpu, &msr) != 0) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -6239,6 +6242,12 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -6283,6 +6292,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6509,6 +6519,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
 	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
 	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+	case EXIT_REASON_INVEPT:
 		/*
 		 * VMX instructions trap unconditionally. This allows L1 to
 		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6651,10 +6662,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
 	else {
-		vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
-		vcpu->run->hw.hardware_exit_reason = exit_reason;
+		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
 	}
-	return 0;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
@@ -7133,8 +7144,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	free_vpid(vmx);
-	free_nested(vmx);
 	free_loaded_vmcs(vmx->loaded_vmcs);
+	free_nested(vmx);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
@@ -7949,7 +7960,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
 	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
-	vmx_set_rflags(vcpu, X86_EFLAGS_BIT1);
+	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	/*
 	 * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
 	 * actually changed, because it depends on the current state of
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 37d9503b81ea..ce20cb65de58 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -94,6 +94,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 static bool ignore_msrs = 0;
 module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+unsigned int min_timer_period_us = 500;
+module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+
 bool kvm_has_tsc_control;
 EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
 u32  kvm_max_guest_tsc_khz;
@@ -222,20 +225,25 @@ static void kvm_shared_msr_cpu_online(void)
 		shared_msr_update(i, shared_msrs_global.msrs[i]);
 }
 
-void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	int err;
 
 	if (((value ^ smsr->values[slot].curr) & mask) == 0)
-		return;
+		return 0;
 	smsr->values[slot].curr = value;
-	wrmsrl(shared_msrs_global.msrs[slot], value);
+	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+	if (err)
+		return 1;
+
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
 		smsr->registered = true;
 	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
@@ -917,7 +925,6 @@ void kvm_enable_efer_bits(u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
-
 /*
  * Writes msr value into into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
@@ -925,8 +932,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
  */
 int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
+	switch (msr->index) {
+	case MSR_FS_BASE:
+	case MSR_GS_BASE:
+	case MSR_KERNEL_GS_BASE:
+	case MSR_CSTAR:
+	case MSR_LSTAR:
+		if (is_noncanonical_address(msr->data))
+			return 1;
+		break;
+	case MSR_IA32_SYSENTER_EIP:
+	case MSR_IA32_SYSENTER_ESP:
+		/*
+		 * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
+		 * non-canonical address is written on Intel but not on
+		 * AMD (which ignores the top 32-bits, because it does
+		 * not implement 64-bit SYSENTER).
+		 *
+		 * 64-bit code should hence be able to write a non-canonical
+		 * value on AMD.  Making the address canonical ensures that
+		 * vmentry does not fail on Intel after writing a non-canonical
+		 * value, and that something deterministic happens if the guest
+		 * invokes 64-bit SYSENTER.
+		 */
+		msr->data = get_canonical(msr->data);
+	}
 	return kvm_x86_ops->set_msr(vcpu, msr);
 }
+EXPORT_SYMBOL_GPL(kvm_set_msr);
 
 /*
  * Adapt set_msr() to msr_io()'s calling convention
@@ -1193,20 +1226,37 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
+		int faulted = 0;
+
 		/* n.b - signed multiplication and division required */
 		usdiff = data - kvm->arch.last_tsc_write;
 #ifdef CONFIG_X86_64
 		usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
 #else
 		/* do_div() only does unsigned */
-		asm("idivl %2; xor %%edx, %%edx"
-		: "=A"(usdiff)
-		: "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+		asm("1: idivl %[divisor]\n"
+		    "2: xor %%edx, %%edx\n"
+		    "   movl $0, %[faulted]\n"
+		    "3:\n"
+		    ".section .fixup,\"ax\"\n"
+		    "4: movl $1, %[faulted]\n"
+		    "   jmp  3b\n"
+		    ".previous\n"
+
+		_ASM_EXTABLE(1b, 4b)
+
+		: "=A"(usdiff), [faulted] "=r" (faulted)
+		: "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz));
+
 #endif
 		do_div(elapsed, 1000);
 		usdiff -= elapsed;
 		if (usdiff < 0)
 			usdiff = -usdiff;
+
+		/* idivl overflow => difference is larger than USEC_PER_SEC */
+		if (faulted)
+			usdiff = USEC_PER_SEC;
 	} else
 		usdiff = USEC_PER_SEC; /* disable TSC match window below */
 
@@ -3141,8 +3191,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
-		r = 0;
-		kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4788,7 +4837,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
-	if (!is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
@@ -5542,36 +5591,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static int vapic_enter(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	struct page *page;
-
-	if (!apic || !apic->vapic_addr)
-		return 0;
-
-	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	if (is_error_page(page))
-		return -EFAULT;
-
-	vcpu->arch.apic->vapic_page = page;
-	return 0;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int idx;
-
-	if (!apic || !apic->vapic_addr)
-		return;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	kvm_release_page_dirty(apic->vapic_page);
-	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 {
 	int max_irr, tpr;
@@ -5892,11 +5911,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	r = vapic_enter(vcpu);
-	if (r) {
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-		return r;
-	}
 
 	r = 1;
 	while (r > 0) {
@@ -5954,8 +5968,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 
-	vapic_exit(vcpu);
-
 	return r;
 }
 
@@ -6020,7 +6032,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 		if (vcpu->mmio_is_write)
 			return 1;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e224f7a671b6..7626d3efa064 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmio_gva = gva & PAGE_MASK;
 	vcpu->arch.access = access;
 	vcpu->arch.mmio_gfn = gfn;
+	vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
 }
 
 /*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
  */
+#define MMIO_GVA_ANY (~(gva_t)0)
+
 static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+	if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
 		return;
 
 	vcpu->arch.mmio_gva = 0;
@@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 
 static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 {
-	if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+	      vcpu->arch.mmio_gva == (gva & PAGE_MASK))
 		return true;
 
 	return false;
@@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 
 static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
-	if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+	      vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
 		return true;
 
 	return false;
@@ -124,5 +134,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 
 extern u64 host_xcr0;
 
+extern unsigned int min_timer_period_us;
+
 extern struct static_key kvm_no_apic_vcpu;
 #endif
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a33081..e04e67753238 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned long current_address;
 	const struct addr_marker *marker;
+	unsigned long lines;
 };
 
 struct addr_marker {
 	unsigned long start_address;
 	const char *name;
+	unsigned long max_lines;
 };
 
 /* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+	ESPFIX_START_NR,
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,		"Low Kernel Mapping" },
 	{ VMALLOC_START,        "vmalloc() Area" },
 	{ VMEMMAP_START,        "Vmemmap" },
+	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 	{ __START_KERNEL_map,   "High Kernel Mapping" },
 	{ MODULES_VADDR,        "Modules" },
 	{ MODULES_END,          "End Modules" },
@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		      pgprot_t new_prot, int level)
 {
 	pgprotval_t prot, cur;
-	static const char units[] = "KMGTPE";
+	static const char units[] = "BKMGTPE";
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		st->current_prot = new_prot;
 		st->level = level;
 		st->marker = address_markers;
+		st->lines = 0;
 		seq_printf(m, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != cur || level != st->level ||
 		   st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%0*lx-0x%0*lx   ",
-			   width, st->start_address,
-			   width, st->current_address);
-
-		delta = (st->current_address - st->start_address) >> 10;
-		while (!(delta & 1023) && unit[1]) {
-			delta >>= 10;
-			unit++;
+		if (!st->marker->max_lines ||
+		    st->lines < st->marker->max_lines) {
+			seq_printf(m, "0x%0*lx-0x%0*lx   ",
+				   width, st->start_address,
+				   width, st->current_address);
+
+			delta = (st->current_address - st->start_address);
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			seq_printf(m, "%9lu%c ", delta, *unit);
+			printk_prot(m, st->current_prot, st->level);
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
-		printk_prot(m, st->current_prot, st->level);
+		st->lines++;
 
 		/*
 		 * We print markers for special areas of address space,
@@ -206,7 +215,15 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		 * This helps in the interpretation.
 		 */
 		if (st->current_address >= st->marker[1].start_address) {
+			if (st->marker->max_lines &&
+			    st->lines > st->marker->max_lines) {
+				unsigned long nskip =
+					st->lines - st->marker->max_lines;
+				seq_printf(m, "... %lu entr%s skipped ... \n",
+					   nskip, nskip == 1 ? "y" : "ies");
+			}
 			st->marker++;
+			st->lines = 0;
 			seq_printf(m, "---[ %s ]---\n", st->marker->name);
 		}
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae3047..d8b1ff68dbb9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline int
+static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if (fatal_signal_pending(current)) {
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address, 0, 0);
-		return 1;
+	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+		up_read(&current->mm->mmap_sem);
+		no_context(regs, error_code, address, 0, 0);
+		return;
 	}
-	if (!(fault & VM_FAULT_ERROR))
-		return 0;
 
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address,
 				   SIGSEGV, SEGV_MAPERR);
-			return 1;
+			return;
 		}
 
 		up_read(&current->mm->mmap_sem);
@@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		else
 			BUG();
 	}
-	return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -989,6 +980,12 @@ static int fault_in_kernel_space(unsigned long address)
 
 static inline bool smap_violation(int error_code, struct pt_regs *regs)
 {
+	if (!IS_ENABLED(CONFIG_X86_SMAP))
+		return false;
+
+	if (!static_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
 	if (error_code & PF_USER)
 		return false;
 
@@ -1011,9 +1008,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
-	int write = error_code & PF_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1083,6 +1078,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (user_mode_vm(regs)) {
 		local_irq_enable();
 		error_code |= PF_USER;
+		flags |= FAULT_FLAG_USER;
 	} else {
 		if (regs->flags & X86_EFLAGS_IF)
 			local_irq_enable();
@@ -1091,11 +1087,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	if (unlikely(smap_violation(error_code, regs))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
@@ -1109,6 +1103,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		return;
 	}
 
+	if (error_code & PF_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in
@@ -1187,9 +1184,17 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 
-	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		if (mm_fault_error(regs, error_code, address, fault))
-			return;
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+		return;
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		mm_fault_error(regs, error_code, address, fault);
+		return;
 	}
 
 	/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bb00c4672ad6..2db3f30bed75 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1142,7 +1142,7 @@ void mark_rodata_ro(void)
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
 	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
 	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
-	unsigned long all_end = PFN_ALIGN(&_end);
+	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -1153,7 +1153,16 @@ void mark_rodata_ro(void)
 	/*
 	 * The rodata/data/bss/brk section (but not the kernel text!)
 	 * should also be not-executable.
+	 *
+	 * We align all_end to PMD_SIZE because the existing mapping
+	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+	 * split the PMD and the reminder between _brk_end and the end
+	 * of the PMD will remain mapped executable.
+	 *
+	 * Any PMD which was setup after the one which covers _brk_end
+	 * has been zapped already via cleanup_highmem().
 	 */
+	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9a1e6583910c..86c758de4b34 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	return err;
 }
 
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+			       void *arg)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; ++i)
+		if (pfn_valid(start_pfn + i) &&
+		    !PageReserved(pfn_to_page(start_pfn + i)))
+			return 1;
+
+	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
+
+	return 0;
+}
+
 /*
  * Remap an arbitrary physical address space into the kernel virtual
  * address space. Needed when the kernel wants to access high addresses
@@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
+	pfn      = phys_addr >> PAGE_SHIFT;
 	last_pfn = last_addr >> PAGE_SHIFT;
-	for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) {
-		int is_ram = page_is_ram(pfn);
-
-		if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))
-			return NULL;
-		WARN_ON_ONCE(is_ram);
-	}
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+				  __ioremap_check_ram) == 1)
+		return NULL;
 
 	/*
 	 * Mappings have to be page-aligned
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480c2d71..aabdf762f592 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -389,7 +389,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
 	psize = page_level_size(level);
 	pmask = page_level_mask(level);
 	offset = virt_addr & ~pmask;
-	phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+	phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 	return (phys_addr | offset);
 }
 EXPORT_SYMBOL_GPL(slow_virt_to_phys);
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1b2152..01495755701b 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@ bpf_slow_path_byte_msh:
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
-	mov	$SIZE,%ecx;	/* size */			\
+	mov	$SIZE,%edx;	/* size */			\
 	call	bpf_internal_load_pointer_neg_helper;		\
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index f66b54086ce5..0c966fecfb8c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -324,15 +324,21 @@ void bpf_jit_compile(struct sk_filter *fp)
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
 			case BPF_S_ALU_MOD_K: /* A %= K; */
+				if (K == 1) {
+					CLEAR_A();
+					break;
+				}
 				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
 				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
 				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
-			case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
-				EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
-				EMIT(K, 4);
-				EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+			case BPF_S_ALU_DIV_K: /* A /= K */
+				if (K == 1)
+					break;
+				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
+				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
+				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				break;
 			case BPF_S_ALU_AND_X:
 				seen |= SEEN_XREG;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 94919e307f8e..2883f0840201 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		/* The low 1MB range is reserved for ISA cards */
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d2fbcedcf6ea..816e940b3998 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -60,34 +60,19 @@
 
 static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
 
-struct efi __read_mostly efi = {
-	.mps        = EFI_INVALID_TABLE_ADDR,
-	.acpi       = EFI_INVALID_TABLE_ADDR,
-	.acpi20     = EFI_INVALID_TABLE_ADDR,
-	.smbios     = EFI_INVALID_TABLE_ADDR,
-	.sal_systab = EFI_INVALID_TABLE_ADDR,
-	.boot_info  = EFI_INVALID_TABLE_ADDR,
-	.hcdp       = EFI_INVALID_TABLE_ADDR,
-	.uga        = EFI_INVALID_TABLE_ADDR,
-	.uv_systab  = EFI_INVALID_TABLE_ADDR,
-};
-EXPORT_SYMBOL(efi);
-
 struct efi_memory_map memmap;
 
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
-unsigned long x86_efi_facility;
+static __initdata efi_config_table_type_t arch_tables[] = {
+#ifdef CONFIG_X86_UV
+	{UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+	{NULL_GUID, NULL, 0},
+};
 
-/*
- * Returns 1 if 'facility' is enabled, 0 otherwise.
- */
-int efi_enabled(int facility)
-{
-	return test_bit(facility, &x86_efi_facility) != 0;
-}
-EXPORT_SYMBOL(efi_enabled);
+u64 efi_setup;		/* efi setup_data physical address */
 
 static bool __initdata disable_runtime = false;
 static int __init setup_noefi(char *arg)
@@ -397,6 +382,8 @@ int __init efi_memblock_x86_reserve_range(void)
 
 	memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
 
+	efi.memmap = &memmap;
+
 	return 0;
 }
 
@@ -438,7 +425,7 @@ void __init efi_reserve_boot_services(void)
 		 * - Not within any part of the kernel
 		 * - Not the bios reserved area
 		*/
-		if ((start+size >= __pa_symbol(_text)
+		if ((start + size > __pa_symbol(_text)
 				&& start <= __pa_symbol(_end)) ||
 			!e820_all_mapped(start, start+size, E820_RAM) ||
 			memblock_is_region_reserved(start, size)) {
@@ -454,7 +441,7 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_unmap_memmap(void)
 {
-	clear_bit(EFI_MEMMAP, &x86_efi_facility);
+	clear_bit(EFI_MEMMAP, &efi.flags);
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
@@ -576,80 +563,6 @@ static int __init efi_systab_init(void *phys)
 	return 0;
 }
 
-static int __init efi_config_init(u64 tables, int nr_tables)
-{
-	void *config_tables, *tablep;
-	int i, sz;
-
-	if (efi_enabled(EFI_64BIT))
-		sz = sizeof(efi_config_table_64_t);
-	else
-		sz = sizeof(efi_config_table_32_t);
-
-	/*
-	 * Let's see what config tables the firmware passed to us.
-	 */
-	config_tables = early_ioremap(tables, nr_tables * sz);
-	if (config_tables == NULL) {
-		pr_err("Could not map Configuration table!\n");
-		return -ENOMEM;
-	}
-
-	tablep = config_tables;
-	pr_info("");
-	for (i = 0; i < efi.systab->nr_tables; i++) {
-		efi_guid_t guid;
-		unsigned long table;
-
-		if (efi_enabled(EFI_64BIT)) {
-			u64 table64;
-			guid = ((efi_config_table_64_t *)tablep)->guid;
-			table64 = ((efi_config_table_64_t *)tablep)->table;
-			table = table64;
-#ifdef CONFIG_X86_32
-			if (table64 >> 32) {
-				pr_cont("\n");
-				pr_err("Table located above 4GB, disabling EFI.\n");
-				early_iounmap(config_tables,
-					      efi.systab->nr_tables * sz);
-				return -EINVAL;
-			}
-#endif
-		} else {
-			guid = ((efi_config_table_32_t *)tablep)->guid;
-			table = ((efi_config_table_32_t *)tablep)->table;
-		}
-		if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
-			efi.mps = table;
-			pr_cont(" MPS=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
-			efi.acpi20 = table;
-			pr_cont(" ACPI 2.0=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
-			efi.acpi = table;
-			pr_cont(" ACPI=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
-			efi.smbios = table;
-			pr_cont(" SMBIOS=0x%lx ", table);
-#ifdef CONFIG_X86_UV
-		} else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
-			efi.uv_systab = table;
-			pr_cont(" UVsystab=0x%lx ", table);
-#endif
-		} else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
-			efi.hcdp = table;
-			pr_cont(" HCDP=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
-			efi.uga = table;
-			pr_cont(" UGA=0x%lx ", table);
-		}
-		tablep += sz;
-	}
-	pr_cont("\n");
-	early_iounmap(config_tables, efi.systab->nr_tables * sz);
-	return 0;
-}
-
 static int __init efi_runtime_init(void)
 {
 	efi_runtime_services_t *runtime;
@@ -725,7 +638,11 @@ void __init efi_init(void)
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
-	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+	efi.config_table = (unsigned long)efi.systab->tables;
+	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
+	efi.runtime	 = (unsigned long)efi.systab->runtime;
 
 	/*
 	 * Show what we know for posterity
@@ -743,10 +660,10 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
+	if (efi_config_init(arch_tables))
 		return;
 
-	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
+	set_bit(EFI_CONFIG_TABLES, &efi.flags);
 
 	/*
 	 * Note: We currently don't support runtime services on an EFI
@@ -758,20 +675,13 @@ void __init efi_init(void)
 	else {
 		if (disable_runtime || efi_runtime_init())
 			return;
-		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
+		set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 	}
 
 	if (efi_memmap_init())
 		return;
 
-	set_bit(EFI_MEMMAP, &x86_efi_facility);
-
-#ifdef CONFIG_X86_32
-	if (efi_is_native()) {
-		x86_platform.get_wallclock = efi_get_time;
-		x86_platform.set_wallclock = efi_set_rtc_mmss;
-	}
-#endif
+	set_bit(EFI_MEMMAP, &efi.flags);
 
 #if EFI_DEBUG
 	print_efi_memmap();
@@ -814,34 +724,6 @@ static void __init runtime_code_page_mkexec(void)
 	}
 }
 
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
-	void *p;
-	if (WARN_ON(!memmap.map))
-		return NULL;
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-		u64 end = md->phys_addr + size;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		if (!md->virt_addr)
-			continue;
-		if (phys_addr >= md->phys_addr && phys_addr < end) {
-			phys_addr += md->virt_addr - md->phys_addr;
-			return (__force void __iomem *)(unsigned long)phys_addr;
-		}
-	}
-	return NULL;
-}
-
 void efi_memory_uc(u64 addr, unsigned long size)
 {
 	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
@@ -910,10 +792,13 @@ void __init efi_enter_virtual_mode(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+			if (md->type != EFI_BOOT_SERVICES_CODE &&
+			    md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+				continue;
+		}
 
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 88692871823f..9cac82588cbc 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -73,9 +73,10 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/../../boot/code16gcc.h \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+		   -mno-mmx -mno-sse \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
-			$(call cc-option, -fno-unit-at-a-time)) \
+		   $(call cc-option, -fno-unit-at-a-time)) \
 		   $(call cc-option, -fno-stack-protector) \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65dfd14f..63a899304d27 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -212,10 +212,10 @@
 203	common	sched_setaffinity	sys_sched_setaffinity
 204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	common	io_setup		sys_io_setup
+206	64	io_setup		sys_io_setup
 207	common	io_destroy		sys_io_destroy
 208	common	io_getevents		sys_io_getevents
-209	common	io_submit		sys_io_submit
+209	64	io_submit		sys_io_submit
 210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
 212	common	lookup_dcookie		sys_lookup_dcookie
@@ -356,3 +356,5 @@
 540	x32	process_vm_writev	compat_sys_process_vm_writev
 541	x32	setsockopt		compat_sys_setsockopt
 542	x32	getsockopt		compat_sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e87544411..ab6ba35a9357 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -117,30 +117,45 @@ subsys_initcall(init_vdso);
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa5927e..156344448d19 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -878,7 +878,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -925,8 +924,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	 * frontend pages while they are being shared with the backend,
 	 * because mfn_to_pfn (that ends up being called by GUPF) will
 	 * return the backend pfn rather than the frontend pfn. */
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == mfn)
 		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
 
 	return 0;
@@ -941,7 +940,6 @@ int m2p_remove_override(struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	mfn = get_phys_to_machine(pfn);
@@ -1019,8 +1017,8 @@ int m2p_remove_override(struct page *page,
 	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
 	 * pfn again. */
 	mfn &= ~FOREIGN_FRAME_BIT;
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
 			m2p_find_override(mfn) == NULL)
 		set_phys_to_machine(pfn, mfn);
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index a1e58e19d0cc..570c9a5c4d3f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -245,6 +245,15 @@ static void __init xen_smp_prepare_boot_cpu(void)
 	   old memory can be recycled */
 	make_lowmem_page_readwrite(xen_initial_gdt);
 
+#ifdef CONFIG_X86_32
+	/*
+	 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+	 * expects __USER_DS
+	 */
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+#endif
+
 	xen_filter_cpu_maps();
 	xen_setup_vcpu_info_placement();
 }
diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h
deleted file mode 100644
index 36dc7a684397..000000000000
--- a/arch/xtensa/include/asm/ftrace.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * arch/xtensa/include/asm/ftrace.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2013 Tensilica Inc.
- */
-#ifndef _XTENSA_FTRACE_H
-#define _XTENSA_FTRACE_H
-
-#include <asm/processor.h>
-
-#define HAVE_ARCH_CALLER_ADDR
-#define CALLER_ADDR0 ({ unsigned long a0, a1; \
-		__asm__ __volatile__ ( \
-			"mov %0, a0\n" \
-			"mov %1, a1\n" \
-			: "=r"(a0), "=r"(a1) : : ); \
-		MAKE_PC_FROM_RA(a0, a1); })
-#ifdef CONFIG_FRAME_POINTER
-extern unsigned long return_address(unsigned level);
-#define CALLER_ADDR1 return_address(1)
-#define CALLER_ADDR2 return_address(2)
-#define CALLER_ADDR3 return_address(3)
-#else
-#define CALLER_ADDR1 (0)
-#define CALLER_ADDR2 (0)
-#define CALLER_ADDR3 (0)
-#endif
-
-#endif /* _XTENSA_FTRACE_H */
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index d7546c94da52..385efb23ddce 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -68,7 +68,12 @@
 #define VMALLOC_START		0xC0000000
 #define VMALLOC_END		0xC7FEFFFF
 #define TLBTEMP_BASE_1		0xC7FF0000
-#define TLBTEMP_BASE_2		0xC7FF8000
+#define TLBTEMP_BASE_2		(TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
+#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
+#define TLBTEMP_SIZE		(2 * DCACHE_WAY_SIZE)
+#else
+#define TLBTEMP_SIZE		ICACHE_WAY_SIZE
+#endif
 
 /*
  * Xtensa Linux config PTE layout (when present):
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 917488a0ab00..f2faa58f9a43 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -22,25 +22,37 @@ extern void do_unhandled(struct pt_regs *regs, unsigned long exccause);
 
 static inline void spill_registers(void)
 {
-
+#if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"movi	a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
-		"mov	a12, a0\n\t"
-		"rsr	a13, sar\n\t"
-		"xsr	a14, ps\n\t"
-		"movi	a0, _spill_registers\n\t"
-		"rsync\n\t"
-		"callx0 a0\n\t"
-		"mov	a0, a12\n\t"
-		"wsr	a13, sar\n\t"
-		"wsr	a14, ps\n\t"
-		: :
-#if defined(CONFIG_FRAME_POINTER)
-		: "a2", "a3", "a4",       "a11", "a12", "a13", "a14", "a15",
+		"	call12	1f\n"
+		"	_j	2f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	_entry	a1, 48\n"
+		"	addi	a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	_entry	a1, 48\n"
+		"	mov	a12, a0\n"
+		"	.endr\n"
+#endif
+		"	_entry	a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+		"	mov	a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+		"	mov	a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a4, a4\n"
+#endif
+		"	retw\n"
+		"2:\n"
+		: : : "a12", "a13", "memory");
 #else
-		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+	__asm__ __volatile__ (
+		"	mov	a12, a12\n"
+		: : : "memory");
 #endif
-		  "memory");
 }
 
 #endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index fd686dc45d1a..c7211e7e182d 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -52,7 +52,12 @@
  */
 	.macro	get_fs	ad, sp
 	GET_CURRENT(\ad,\sp)
+#if THREAD_CURRENT_DS > 1020
+	addi	\ad, \ad, TASK_THREAD
+	l32i	\ad, \ad, THREAD_CURRENT_DS - TASK_THREAD
+#else
 	l32i	\ad, \ad, THREAD_CURRENT_DS
+#endif
 	.endm
 
 /*
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index b4cb1100c0fb..a47909f0c34b 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -28,17 +28,17 @@
 #define TCSETSW		0x5403
 #define TCSETSF		0x5404
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x80127417	/* _IOR('t', 23, struct termio) */
+#define TCSETA		0x40127418	/* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x40127419	/* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x4012741C	/* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
-#define TIOCSWINSZ	_IOW('t', 103, struct winsize)
-#define TIOCGWINSZ	_IOR('t', 104, struct winsize)
+#define TIOCSWINSZ	0x40087467	/* _IOW('t', 103, struct winsize) */
+#define TIOCGWINSZ	0x80087468	/* _IOR('t', 104, struct winsize) */
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */
 #define	TIOCSTOP	_IO('t', 111)		/* stop output, like ^S */
 #define TIOCOUTQ        _IOR('t', 115, int)     /* output queue size */
@@ -88,7 +88,6 @@
 #define TIOCSETD	_IOW('T', 35, int)
 #define TIOCGETD	_IOR('T', 36, int)
 #define TCSBRKP		_IOW('T', 37, int)   /* Needed for POSIX tcsendbreak()*/
-#define TIOCTTYGSTRUCT	_IOR('T', 38, struct tty_struct) /* For debugging only*/
 #define TIOCSBRK	_IO('T', 39) 	     /* BSD compatibility */
 #define TIOCCBRK	_IO('T', 40)	     /* BSD compatibility */
 #define TIOCGSID	_IOR('T', 41, pid_t) /* Return the session ID of FD*/
@@ -114,8 +113,10 @@
 #define TIOCSERGETLSR   _IOR('T', 89, unsigned int) /* Get line status reg. */
   /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
 # define TIOCSER_TEMT    0x01		     /* Transmitter physically empty */
-#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config  */
-#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */
+#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config  */
+			/* _IOR('T', 90, struct serial_multiport_struct) */
+#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */
+			/* _IOW('T', 91, struct serial_multiport_struct) */
 
 #define TIOCMIWAIT	_IO('T', 92) /* wait for a change on serial input line(s) */
 #define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fec6990..513effd48060 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1)
 #define __NR_pivot_root 			175
 __SYSCALL(175, sys_pivot_root, 2)
 #define __NR_umount 				176
-__SYSCALL(176, sys_umount, 2)
+__SYSCALL(176, sys_oldumount, 1)
+#define __ARCH_WANT_SYS_OLDUMOUNT
 #define __NR_swapoff 				177
 __SYSCALL(177, sys_swapoff, 1)
 #define __NR_sync 				178
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 5082507d5631..6e53174f8556 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1121,9 +1121,8 @@ ENTRY(fast_syscall_xtensa)
 	movi	a7, 4			# sizeof(unsigned int)
 	access_ok a3, a7, a0, a2, .Leac	# a0: scratch reg, a2: sp
 
-	addi	a6, a6, -1		# assuming SYS_XTENSA_ATOMIC_SET = 1
-	_bgeui	a6, SYS_XTENSA_COUNT - 1, .Lill
-	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp
+	_bgeui	a6, SYS_XTENSA_COUNT, .Lill
+	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp
 
 	/* Fall through for ATOMIC_CMP_SWP. */
 
@@ -1135,27 +1134,26 @@ TRY	s32i	a5, a3, 0		# different, modify value
 	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 1			# and return 1
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 1:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 0			# return 0 (note that we cannot set
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 .Lnswp:	/* Atomic set, add, and exg_add. */
 
 TRY	l32i	a7, a3, 0		# orig
+	addi	a6, a6, -SYS_XTENSA_ATOMIC_SET
 	add	a0, a4, a7		# + arg
 	moveqz	a0, a4, a6		# set
+	addi	a6, a6, SYS_XTENSA_ATOMIC_SET
 TRY	s32i	a0, a3, 0		# write new value
 
 	mov	a0, a2
 	mov	a2, a7
 	l32i	a7, a0, PT_AREG7	# restore a7
 	l32i	a0, a0, PT_AREG0	# restore a0
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 CATCH
@@ -1164,7 +1162,7 @@ CATCH
 	movi	a2, -EFAULT
 	rfe
 
-.Lill:	l32i	a7, a2, PT_AREG0	# restore a7
+.Lill:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, -EINVAL
 	rfe
@@ -1703,7 +1701,7 @@ ENTRY(fast_second_level_miss)
 	rsr	a0, excvaddr
 	bltu	a0, a3, 2f
 
-	addi	a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT))
+	addi	a1, a0, -TLBTEMP_SIZE
 	bgeu	a1, a3, 2f
 
 	/* Check if we have to restore an ITLB mapping. */
@@ -1912,6 +1910,43 @@ ENTRY(system_call)
 
 ENDPROC(system_call)
 
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+	.macro	spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+	call12	1f
+	_j	2f
+	retw
+	.align	4
+1:
+	_entry	a1, 48
+	addi	a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+	.rept	(XCHAL_NUM_AREGS - 32) / 12
+	_entry	a1, 48
+	mov	a12, a0
+	.endr
+#endif
+	_entry	a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+	mov	a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+	mov	a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+	mov	a4, a4
+#endif
+	retw
+2:
+#else
+	mov	a12, a12
+#endif
+	.endm
 
 /*
  * Task switch.
@@ -1924,21 +1959,25 @@ ENTRY(_switch_to)
 
 	entry	a1, 16
 
-	mov	a12, a2			# preserve 'prev' (a2)
-	mov	a13, a3			# and 'next' (a3)
+	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
 	l32i	a5, a3, TASK_THREAD_INFO
 
-	save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a12, THREAD_RA	# save return address
-	s32i	a1, a12, THREAD_SP	# save stack pointer
+#if THREAD_RA > 1020 || THREAD_SP > 1020
+	addi	a10, a2, TASK_THREAD
+	s32i	a0, a10, THREAD_RA - TASK_THREAD	# save return address
+	s32i	a1, a10, THREAD_SP - TASK_THREAD	# save stack pointer
+#else
+	s32i	a0, a2, THREAD_RA	# save return address
+	s32i	a1, a2, THREAD_SP	# save stack pointer
+#endif
 
 	/* Disable ints while we manipulate the stack pointer. */
 
-	movi	a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
-	xsr	a14, ps
+	rsil	a14, LOCKLEVEL
 	rsr	a3, excsave1
 	rsync
 	s32i	a3, a3, EXC_TABLE_FIXUP	/* enter critical section */
@@ -1953,7 +1992,7 @@ ENTRY(_switch_to)
 
 	/* Flush register file. */
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	spill_registers_kernel
 
 	/* Set kernel stack (and leave critical section)
 	 * Note: It's save to set it here. The stack will not be overwritten
@@ -1969,13 +2008,12 @@ ENTRY(_switch_to)
 
 	/* restore context of the task 'next' */
 
-	l32i	a0, a13, THREAD_RA	# restore return address
-	l32i	a1, a13, THREAD_SP	# restore stack pointer
+	l32i	a0, a11, THREAD_RA	# restore return address
+	l32i	a1, a11, THREAD_SP	# restore stack pointer
 
-	load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a12			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 2d9cc6dbfd78..e8b76b8e4b29 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
 
 	/* We currently don't support coherent memory outside KSEG */
 
-	if (ret < XCHAL_KSEG_CACHED_VADDR
-	    || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
+	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 
 	if (ret != 0) {
@@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *hwdev, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
-	long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR;
+	unsigned long addr = (unsigned long)vaddr +
+		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
 
-	if (addr < 0 || addr >= XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
+	       addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 	free_pages(addr, get_order(size));
 }
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 718eca1850bd..98b67d5f1514 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -341,7 +341,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	sp = regs->areg[1];
 
-	if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && ! on_sig_stack(sp)) {
+	if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && sas_ss_flags(sp) == 0) {
 		sp = current->sas_ss_sp + current->sas_ss_size;
 	}
 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8db170f..70fa7bc42b4a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@ void do_page_fault(struct pt_regs *regs)
 	       address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
 #endif
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 96ef8eeb064e..8a95204cbdae 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -195,7 +195,7 @@ void platform_calibrate_ccount(void)
  *  Ethernet -- OpenCores Ethernet MAC (ethoc driver)
  */
 
-static struct resource ethoc_res[] __initdata = {
+static struct resource ethoc_res[] = {
 	[0] = { /* register space */
 		.start = OETH_REGS_PADDR,
 		.end   = OETH_REGS_PADDR + OETH_REGS_SIZE - 1,
@@ -213,7 +213,7 @@ static struct resource ethoc_res[] __initdata = {
 	},
 };
 
-static struct ethoc_platform_data ethoc_pdata __initdata = {
+static struct ethoc_platform_data ethoc_pdata = {
 	/*
 	 * The MAC address for these boards is 00:50:c2:13:6f:xx.
 	 * The last byte (here as zero) is read from the DIP switches on the
@@ -223,7 +223,7 @@ static struct ethoc_platform_data ethoc_pdata __initdata = {
 	.phy_id = -1,
 };
 
-static struct platform_device ethoc_device __initdata = {
+static struct platform_device ethoc_device = {
 	.name = "ethoc",
 	.id = -1,
 	.num_resources = ARRAY_SIZE(ethoc_res),
@@ -237,13 +237,13 @@ static struct platform_device ethoc_device __initdata = {
  *  UART
  */
 
-static struct resource serial_resource __initdata = {
+static struct resource serial_resource = {
 	.start	= DUART16552_PADDR,
 	.end	= DUART16552_PADDR + 0x1f,
 	.flags	= IORESOURCE_MEM,
 };
 
-static struct plat_serial8250_port serial_platform_data[] __initdata = {
+static struct plat_serial8250_port serial_platform_data[] = {
 	[0] = {
 		.mapbase	= DUART16552_PADDR,
 		.irq		= DUART16552_INTNUM,
@@ -256,7 +256,7 @@ static struct plat_serial8250_port serial_platform_data[] __initdata = {
 	{ },
 };
 
-static struct platform_device xtavnet_uart __initdata = {
+static struct platform_device xtavnet_uart = {
 	.name		= "serial8250",
 	.id		= PLAT8250_DEV_PLATFORM,
 	.dev		= {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e8918ffaf96d..1ff8e97f853a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -876,6 +876,20 @@ void blkcg_drain_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
 
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
 	blk_throtl_drain(q);
 }
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4e595ee8c915..749afadfbb33 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -399,9 +399,9 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
 	uint64_t v;
 
 	do {
-		start = u64_stats_fetch_begin(&stat->syncp);
+		start = u64_stats_fetch_begin_bh(&stat->syncp);
 		v = stat->cnt;
-	} while (u64_stats_fetch_retry(&stat->syncp, start));
+	} while (u64_stats_fetch_retry_bh(&stat->syncp, start));
 
 	return v;
 }
@@ -467,9 +467,9 @@ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
 	struct blkg_rwstat tmp;
 
 	do {
-		start = u64_stats_fetch_begin(&rwstat->syncp);
+		start = u64_stats_fetch_begin_bh(&rwstat->syncp);
 		tmp = *rwstat;
-	} while (u64_stats_fetch_retry(&rwstat->syncp, start));
+	} while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
 
 	return tmp;
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index d5745b5833c9..cba537b18d36 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -645,10 +645,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
 	if (blkcg_init_queue(q))
-		goto fail_id;
+		goto fail_bdi;
 
 	return q;
 
+fail_bdi:
+	bdi_destroy(&q->backing_dev_info);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
@@ -739,9 +741,17 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 
 	q->sg_reserved_size = INT_MAX;
 
+	/* Protect q->elevator from elevator_change */
+	mutex_lock(&q->sysfs_lock);
+
 	/* init elevator */
-	if (elevator_init(q, NULL))
+	if (elevator_init(q, NULL)) {
+		mutex_unlock(&q->sysfs_lock);
 		return NULL;
+	}
+
+	mutex_unlock(&q->sysfs_lock);
+
 	return q;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -2229,6 +2239,7 @@ void blk_start_request(struct request *req)
 	if (unlikely(blk_bidi_rq(req)))
 		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
 
+	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 	blk_add_timer(req);
 }
 EXPORT_SYMBOL(blk_start_request);
@@ -2288,7 +2299,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
@@ -3180,7 +3191,8 @@ int __init blk_dev_init(void)
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
-					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+					    WQ_MEM_RECLAIM | WQ_HIGHPRI |
+					    WQ_POWER_EFFICIENT, 0);
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 9c4bb8266bc8..4464c823cff2 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -144,7 +144,8 @@ void put_io_context(struct io_context *ioc)
 	if (atomic_long_dec_and_test(&ioc->refcount)) {
 		spin_lock_irqsave(&ioc->lock, flags);
 		if (!hlist_empty(&ioc->icq_list))
-			schedule_work(&ioc->release_work);
+			queue_work(system_power_efficient_wq,
+					&ioc->release_work);
 		else
 			free_ioc = true;
 		spin_unlock_irqrestore(&ioc->lock, flags);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index d6f50d572565..9a32f5868fb9 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -121,6 +121,14 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+
+		/*
+		 * We can loop for a long time in here, if someone does
+		 * full device discards (like mkfs). Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
 	}
 	blk_finish_plug(&plug);
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index c50ecf0ea3b1..ec00a0f75212 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -144,6 +144,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
+	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
 	lim->max_write_same_sectors = UINT_MAX;
 }
@@ -552,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		bottom = max(b->physical_block_size, b->io_min) + alignment;
 
 		/* Verify that top and bottom intervals line up */
-		if (max(top, bottom) & (min(top, bottom) - 1)) {
+		if (max(top, bottom) % min(top, bottom)) {
 			t->misaligned = 1;
 			ret = -1;
 		}
@@ -593,7 +594,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
-		& (max(t->physical_block_size, t->io_min) - 1);
+		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/block/blk-tag.c b/block/blk-tag.c
index cc345e1d8d4e..0c51b4b34f47 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device
  *
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 6e4744cbfb56..5a6296ef9a81 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -90,8 +90,8 @@ static void blk_rq_timed_out(struct request *req)
 		__blk_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:
-		blk_clear_rq_complete(req);
 		blk_add_timer(req);
+		blk_clear_rq_complete(req);
 		break;
 	case BLK_EH_NOT_HANDLED:
 		/*
@@ -173,7 +173,6 @@ void blk_add_timer(struct request *req)
 		return;
 
 	BUG_ON(!list_empty(&req->timeout_list));
-	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 
 	/*
 	 * Some LLDs, like scsi, peek at the timeout to prevent a
diff --git a/block/blk.h b/block/blk.h
index e837b8f619b7..b3bdeb36f361 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -96,7 +96,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			q->flush_queue_delayed = 1;
 			return NULL;
 		}
-		if (unlikely(blk_queue_dying(q)) ||
+		if (unlikely(blk_queue_bypass(q)) ||
 		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d5bbdcfd0dab..c981097dd634 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 static void
 cfq_update_group_weight(struct cfq_group *cfqg)
 {
-	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
 	if (cfqg->new_weight) {
 		cfqg->weight = cfqg->new_weight;
 		cfqg->new_weight = 0;
 	}
+}
+
+static void
+cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
 	if (cfqg->new_leaf_weight) {
 		cfqg->leaf_weight = cfqg->new_leaf_weight;
@@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	/* add to the service tree */
 	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
-	cfq_update_group_weight(cfqg);
+	cfq_update_group_leaf_weight(cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/*
@@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	 */
 	while ((parent = cfqg_parent(pos))) {
 		if (propagate) {
+			cfq_update_group_weight(pos);
 			propagate = !parent->nr_active++;
 			parent->children_weight += pos->weight;
 		}
@@ -1803,7 +1808,7 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
 
 	if (samples) {
 		v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum);
-		do_div(v, samples);
+		v = div64_u64(v, samples);
 	}
 	__blkg_prfill_u64(sf, pd, v);
 	return 0;
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 7c668c8a6f95..21ad6869a5ce 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -689,6 +689,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKROSET:
 	case BLKDISCARD:
 	case BLKSECDISCARD:
+	case BLKZEROOUT:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/elevator.c b/block/elevator.c
index 668394d18588..6d765f7e2b2b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -186,6 +186,12 @@ int elevator_init(struct request_queue *q, char *name)
 	struct elevator_type *e = NULL;
 	int err;
 
+	/*
+	 * q->sysfs_lock must be held to provide mutual exclusion between
+	 * elevator_switch() and here.
+	 */
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (unlikely(q->elevator))
 		return 0;
 
@@ -959,7 +965,7 @@ fail_init:
 /*
  * Switch this queue to the given IO scheduler.
  */
-int elevator_change(struct request_queue *q, const char *name)
+static int __elevator_change(struct request_queue *q, const char *name)
 {
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
@@ -981,6 +987,18 @@ int elevator_change(struct request_queue *q, const char *name)
 
 	return elevator_switch(q, e);
 }
+
+int elevator_change(struct request_queue *q, const char *name)
+{
+	int ret;
+
+	/* Protect q->elevator from elevator_init() */
+	mutex_lock(&q->sysfs_lock);
+	ret = __elevator_change(q, name);
+	mutex_unlock(&q->sysfs_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(elevator_change);
 
 ssize_t elv_iosched_store(struct request_queue *q, const char *name,
@@ -991,7 +1009,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 	if (!q->elevator)
 		return count;
 
-	ret = elevator_change(q, name);
+	ret = __elevator_change(q, name);
 	if (!ret)
 		return count;
 
diff --git a/block/genhd.c b/block/genhd.c
index cdeb5277dfd4..ea49f8631c22 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -28,10 +28,10 @@ struct kobject *block_depr;
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 
-/* For extended devt allocation.  ext_devt_mutex prevents look up
+/* For extended devt allocation.  ext_devt_lock prevents look up
  * results from going away underneath its user.
  */
-static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
@@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	}
 
 	/* allocate ext devt */
-	mutex_lock(&ext_devt_mutex);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
-	mutex_unlock(&ext_devt_mutex);
+	idr_preload(GFP_KERNEL);
+
+	spin_lock(&ext_devt_lock);
+	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
+	spin_unlock(&ext_devt_lock);
+
+	idr_preload_end();
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	might_sleep();
-
 	if (devt == MKDEV(0, 0))
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 }
 
@@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
-	blk_free_devt(disk_to_dev(disk)->devt);
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 
 	return disk;
@@ -1069,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
 	struct disk_part_tbl *new_ptbl;
 	int len = old_ptbl ? old_ptbl->len : 0;
-	int target = partno + 1;
+	int i, target;
 	size_t size;
-	int i;
+
+	/*
+	 * check for int overflow, since we can get here from blkpg_ioctl()
+	 * with a user passed 'partno'.
+	 */
+	target = partno + 1;
+	if (target < 0)
+		return -EINVAL;
 
 	/* disk_max_parts() is zero during initialization, ignore if so */
 	if (disk_max_parts(disk) && target > disk_max_parts(disk))
@@ -1098,6 +1106,7 @@ static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
@@ -1489,9 +1498,11 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now)
 	intv = disk_events_poll_jiffies(disk);
 	set_timer_slack(&ev->dwork.timer, intv / 4);
 	if (check_now)
-		queue_delayed_work(system_freezable_wq, &ev->dwork, 0);
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, 0);
 	else if (intv)
-		queue_delayed_work(system_freezable_wq, &ev->dwork, intv);
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, intv);
 out_unlock:
 	spin_unlock_irqrestore(&ev->lock, flags);
 }
@@ -1534,7 +1545,8 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
 	spin_lock_irq(&ev->lock);
 	ev->clearing |= mask;
 	if (!ev->block)
-		mod_delayed_work(system_freezable_wq, &ev->dwork, 0);
+		mod_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, 0);
 	spin_unlock_irq(&ev->lock);
 }
 
@@ -1627,7 +1639,8 @@ static void disk_check_events(struct disk_events *ev,
 
 	intv = disk_events_poll_jiffies(disk);
 	if (!ev->block && intv)
-		queue_delayed_work(system_freezable_wq, &ev->dwork, intv);
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, intv);
 
 	spin_unlock_irq(&ev->lock);
 
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 789cdea05893..0d9e5f97f0a8 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	blk_free_devt(dev->devt);
 	free_part_stats(p);
 	free_part_info(p);
 	kfree(p);
@@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno)
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
-	blk_free_devt(part_devt(part));
 
 	hd_struct_put(part);
 }
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index a5ffcc988f0b..1b4988b4bc11 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -506,7 +506,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
 		err = DRIVER_ERROR << 24;
-		goto out;
+		goto error;
 	}
 
 	memset(sense, 0, sizeof(sense));
@@ -516,7 +516,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	blk_execute_rq(q, disk, rq, 0);
 
-out:
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
 		if (rq->sense_len && rq->sense) {
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bf8148e74e73..a1eba1845367 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -179,6 +179,10 @@ config CRYPTO_ABLK_HELPER_X86
 	depends on X86
 	select CRYPTO_CRYPTD
 
+config CRYPTO_ABLK_HELPER
+	tristate
+	select CRYPTO_CRYPTD
+
 config CRYPTO_GLUE_HELPER_X86
 	tristate
 	depends on X86
diff --git a/crypto/Makefile b/crypto/Makefile
index a8e9b0fefbe9..5d0b869b173f 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -101,3 +101,4 @@ obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 obj-$(CONFIG_XOR_BLOCKS) += xor.o
 obj-$(CONFIG_ASYNC_CORE) += async_tx/
 obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_ABLK_HELPER) += ablk_helper.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
new file mode 100644
index 000000000000..62568b1fc885
--- /dev/null
+++ b/crypto/ablk_helper.c
@@ -0,0 +1,150 @@
+/*
+ * Shared async block cipher helpers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on aesni-intel_glue.c by:
+ *  Copyright (C) 2008, Intel Corp.
+ *    Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <crypto/ablk_helper.h>
+#include <asm/simd.h>
+
+int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+		 unsigned int key_len)
+{
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+	int err;
+
+	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+				    & CRYPTO_TFM_REQ_MASK);
+	err = crypto_ablkcipher_setkey(child, key, key_len);
+	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+				    & CRYPTO_TFM_RES_MASK);
+	return err;
+}
+EXPORT_SYMBOL_GPL(ablk_set_key);
+
+int __ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct blkcipher_desc desc;
+
+	desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+	desc.info = req->info;
+	desc.flags = 0;
+
+	return crypto_blkcipher_crt(desc.tfm)->encrypt(
+		&desc, req->dst, req->src, req->nbytes);
+}
+EXPORT_SYMBOL_GPL(__ablk_encrypt);
+
+int ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!may_use_simd()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_encrypt(cryptd_req);
+	} else {
+		return __ablk_encrypt(req);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_encrypt);
+
+int ablk_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!may_use_simd()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_decrypt(cryptd_req);
+	} else {
+		struct blkcipher_desc desc;
+
+		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+		desc.info = req->info;
+		desc.flags = 0;
+
+		return crypto_blkcipher_crt(desc.tfm)->decrypt(
+			&desc, req->dst, req->src, req->nbytes);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_decrypt);
+
+void ablk_exit(struct crypto_tfm *tfm)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+EXPORT_SYMBOL_GPL(ablk_exit);
+
+int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_ablkcipher *cryptd_tfm;
+
+	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	ctx->cryptd_tfm = cryptd_tfm;
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ablk_init_common);
+
+int ablk_init(struct crypto_tfm *tfm)
+{
+	char drv_name[CRYPTO_MAX_ALG_NAME];
+
+	snprintf(drv_name, sizeof(drv_name), "__driver-%s",
+					crypto_tfm_alg_driver_name(tfm));
+
+	return ablk_init_common(tfm, drv_name);
+}
+EXPORT_SYMBOL_GPL(ablk_init);
+
+MODULE_LICENSE("GPL");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ac33d5f30778..6ef6e2ad344e 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 
 struct alg_type_list {
 	const struct af_alg_type *type;
@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 
 	sock_init_data(newsock, sk2);
 	sock_graft(sk2, newsock);
+	security_sk_clone(sk, sk2);
 
 	err = type->accept(ask->private, sk2);
 	if (err) {
@@ -447,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err)
 {
 	struct af_alg_completion *completion = req->data;
 
+	if (err == -EINPROGRESS)
+		return;
+
 	completion->err = err;
 	complete(&completion->completion);
 }
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 0262210cad38..850246206b12 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -114,6 +114,9 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page,
 	struct hash_ctx *ctx = ask->private;
 	int err;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	lock_sock(sk);
 	sg_init_table(ctx->sgl.sg, 1);
 	sg_set_page(ctx->sgl.sg, page, size, offset);
@@ -161,8 +164,6 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
 	else if (len < ds)
 		msg->msg_flags |= MSG_TRUNC;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	if (ctx->more) {
 		ctx->more = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a1c4f0a55583..83187f497c7c 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -49,7 +49,7 @@ struct skcipher_ctx {
 	struct ablkcipher_request req;
 };
 
-#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \
+#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
 static inline int skcipher_sndbuf(struct sock *sk)
@@ -378,6 +378,9 @@ static ssize_t skcipher_sendpage(struct socket *sock, struct page *page,
 	struct skcipher_sg_list *sgl;
 	int err = -EINVAL;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	lock_sock(sk);
 	if (!ctx->more && ctx->used)
 		goto unlock;
@@ -432,7 +435,6 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 	long copied = 0;
 
 	lock_sock(sk);
-	msg->msg_namelen = 0;
 	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index c0bb3778f1ae..666f1962a160 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -230,11 +230,11 @@ remainder:
 	 */
 	if (byte_count < DEFAULT_BLK_SZ) {
 empty_rbuf:
-		for (; ctx->rand_data_valid < DEFAULT_BLK_SZ;
-			ctx->rand_data_valid++) {
+		while (ctx->rand_data_valid < DEFAULT_BLK_SZ) {
 			*ptr = ctx->rand_data[ctx->rand_data_valid];
 			ptr++;
 			byte_count--;
+			ctx->rand_data_valid++;
 			if (byte_count == 0)
 				goto done;
 		}
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 06007f0e880c..52222a2f34ba 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -106,7 +106,6 @@ error_no_sig:
 static int x509_key_preparse(struct key_preparsed_payload *prep)
 {
 	struct x509_certificate *cert;
-	struct tm now;
 	size_t srlen, sulen;
 	char *desc = NULL;
 	int ret;
@@ -137,43 +136,6 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		goto error_free_cert;
 	}
 
-	time_to_tm(CURRENT_TIME.tv_sec, 0, &now);
-	pr_devel("Now: %04ld-%02d-%02d %02d:%02d:%02d\n",
-		 now.tm_year + 1900, now.tm_mon + 1, now.tm_mday,
-		 now.tm_hour, now.tm_min,  now.tm_sec);
-	if (now.tm_year < cert->valid_from.tm_year ||
-	    (now.tm_year == cert->valid_from.tm_year &&
-	     (now.tm_mon < cert->valid_from.tm_mon ||
-	      (now.tm_mon == cert->valid_from.tm_mon &&
-	       (now.tm_mday < cert->valid_from.tm_mday ||
-		(now.tm_mday == cert->valid_from.tm_mday &&
-		 (now.tm_hour < cert->valid_from.tm_hour ||
-		  (now.tm_hour == cert->valid_from.tm_hour &&
-		   (now.tm_min < cert->valid_from.tm_min ||
-		    (now.tm_min == cert->valid_from.tm_min &&
-		     (now.tm_sec < cert->valid_from.tm_sec
-		      ))))))))))) {
-		pr_warn("Cert %s is not yet valid\n", cert->fingerprint);
-		ret = -EKEYREJECTED;
-		goto error_free_cert;
-	}
-	if (now.tm_year > cert->valid_to.tm_year ||
-	    (now.tm_year == cert->valid_to.tm_year &&
-	     (now.tm_mon > cert->valid_to.tm_mon ||
-	      (now.tm_mon == cert->valid_to.tm_mon &&
-	       (now.tm_mday > cert->valid_to.tm_mday ||
-		(now.tm_mday == cert->valid_to.tm_mday &&
-		 (now.tm_hour > cert->valid_to.tm_hour ||
-		  (now.tm_hour == cert->valid_to.tm_hour &&
-		   (now.tm_min > cert->valid_to.tm_min ||
-		    (now.tm_min == cert->valid_to.tm_min &&
-		     (now.tm_sec > cert->valid_to.tm_sec
-		      ))))))))))) {
-		pr_warn("Cert %s has expired\n", cert->fingerprint);
-		ret = -EKEYEXPIRED;
-		goto error_free_cert;
-	}
-
 	cert->pub->algo = x509_public_key_algorithms[cert->pkey_algo];
 	cert->pub->id_type = PKEY_ID_X509;
 
diff --git a/crypto/authenc.c b/crypto/authenc.c
index ffce19de05cf..528b00bc4769 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -368,9 +368,10 @@ static void crypto_authenc_encrypt_done(struct crypto_async_request *req,
 	if (!err) {
 		struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
 		struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-		struct ablkcipher_request *abreq = aead_request_ctx(areq);
-		u8 *iv = (u8 *)(abreq + 1) +
-			 crypto_ablkcipher_reqsize(ctx->enc);
+		struct authenc_request_ctx *areq_ctx = aead_request_ctx(areq);
+		struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
+							    + ctx->reqoff);
+		u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(ctx->enc);
 
 		err = crypto_authenc_genicv(areq, iv, 0);
 	}
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9ab86e..0122bec38564 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
-					       struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
 					       unsigned int bsize)
 {
 	u8 *addr;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
 	return bsize;
@@ -105,7 +103,6 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
 	unsigned int nbytes = 0;
 
 	if (likely(err >= 0)) {
@@ -117,7 +114,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 			err = -EINVAL;
 			goto err;
 		} else
-			n = blkcipher_done_slow(tfm, walk, n);
+			n = blkcipher_done_slow(walk, n);
 
 		nbytes = walk->total - n;
 		err = 0;
@@ -136,7 +133,7 @@ err:
 	}
 
 	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
@@ -226,22 +223,20 @@ static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
 static int blkcipher_walk_next(struct blkcipher_desc *desc,
 			       struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 	unsigned int bsize;
 	unsigned int n;
 	int err;
 
 	n = walk->total;
-	if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+	if (unlikely(n < walk->cipher_blocksize)) {
 		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
+	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
 		walk->flags |= BLKCIPHER_WALK_COPY;
 		if (!walk->page) {
 			walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->blocksize, n);
+	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
 	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
 		goto set_phys_lowmem;
 	}
 
@@ -277,28 +272,26 @@ set_phys_lowmem:
 	return err;
 }
 
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
-				    struct crypto_blkcipher *tfm,
-				    unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
 {
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
+	unsigned bs = walk->walk_blocksize;
+	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+	unsigned int size = aligned_bs * 2 +
+			    walk->ivsize + max(aligned_bs, walk->ivsize) -
+			    (walk->alignmask + 1);
 	u8 *iv;
 
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
 	walk->buffer = kmalloc(size, GFP_ATOMIC);
 	if (!walk->buffer)
 		return -ENOMEM;
 
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, ivsize);
+	iv = blkcipher_get_spot(iv, walk->ivsize);
 
-	walk->iv = memcpy(iv, walk->iv, ivsize);
+	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
 	return 0;
 }
 
@@ -306,7 +299,10 @@ int blkcipher_walk_virt(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@ EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
 static int blkcipher_walk_first(struct blkcipher_desc *desc,
 				struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
@@ -335,8 +331,8 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc,
 
 	walk->buffer = NULL;
 	walk->iv = desc->info;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = blkcipher_copy_iv(walk, tfm, alignmask);
+	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+		int err = blkcipher_copy_iv(walk);
 		if (err)
 			return err;
 	}
@@ -353,11 +349,28 @@ int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      unsigned int blocksize)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = blocksize;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
 
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize)
+{
+	walk->flags &= ~BLKCIPHER_WALK_PHYS;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+	walk->ivsize = crypto_aead_ivsize(tfm);
+	walk->alignmask = crypto_aead_alignmask(tfm);
+	return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
 static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 499c91717d93..ed009b77e67d 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -271,7 +271,8 @@ static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain,
 	}
 
 	/* compute plaintext into mac */
-	get_data_to_compute(cipher, pctx, plain, cryptlen);
+	if (cryptlen)
+		get_data_to_compute(cipher, pctx, plain, cryptlen);
 
 out:
 	return err;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 1512e41cd93d..43665d0d0905 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -466,7 +466,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	type -= CRYPTO_MSG_BASE;
 	link = &crypto_dispatch[type];
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) &&
diff --git a/crypto/crypto_wq.c b/crypto/crypto_wq.c
index adad92a44ba2..2f1b8d12952a 100644
--- a/crypto/crypto_wq.c
+++ b/crypto/crypto_wq.c
@@ -33,7 +33,7 @@ static void __exit crypto_wq_exit(void)
 	destroy_workqueue(kcrypto_wq);
 }
 
-module_init(crypto_wq_init);
+subsys_initcall(crypto_wq_init);
 module_exit(crypto_wq_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 9953a42809ec..d27feb5460f3 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -166,4 +166,6 @@ source "drivers/ipack/Kconfig"
 
 source "drivers/reset/Kconfig"
 
+source "drivers/gator/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 130abc1dfd65..292d528e22f1 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -152,3 +152,6 @@ obj-$(CONFIG_IIO)		+= iio/
 obj-$(CONFIG_VME_BUS)		+= vme/
 obj-$(CONFIG_IPACK_BUS)		+= ipack/
 obj-$(CONFIG_NTB)		+= ntb/
+
+obj-$(CONFIG_GATOR)		+= gator/
+obj-$(CONFIG_CORESIGHT)		+= coresight/
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index f40acef80269..a6977e12d574 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -39,6 +39,7 @@
 #include <linux/ipmi.h>
 #include <linux/device.h>
 #include <linux/pnp.h>
+#include <linux/spinlock.h>
 
 MODULE_AUTHOR("Zhao Yakui");
 MODULE_DESCRIPTION("ACPI IPMI Opregion driver");
@@ -57,7 +58,7 @@ struct acpi_ipmi_device {
 	struct list_head head;
 	/* the IPMI request message list */
 	struct list_head tx_msg_list;
-	struct mutex	tx_msg_lock;
+	spinlock_t	tx_msg_lock;
 	acpi_handle handle;
 	struct pnp_dev *pnp_dev;
 	ipmi_user_t	user_interface;
@@ -147,6 +148,7 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 	struct kernel_ipmi_msg *msg;
 	struct acpi_ipmi_buffer *buffer;
 	struct acpi_ipmi_device *device;
+	unsigned long flags;
 
 	msg = &tx_msg->tx_message;
 	/*
@@ -177,10 +179,10 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 
 	/* Get the msgid */
 	device = tx_msg->device;
-	mutex_lock(&device->tx_msg_lock);
+	spin_lock_irqsave(&device->tx_msg_lock, flags);
 	device->curr_msgid++;
 	tx_msg->tx_msgid = device->curr_msgid;
-	mutex_unlock(&device->tx_msg_lock);
+	spin_unlock_irqrestore(&device->tx_msg_lock, flags);
 }
 
 static void acpi_format_ipmi_response(struct acpi_ipmi_msg *msg,
@@ -242,6 +244,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 	int msg_found = 0;
 	struct acpi_ipmi_msg *tx_msg;
 	struct pnp_dev *pnp_dev = ipmi_device->pnp_dev;
+	unsigned long flags;
 
 	if (msg->user != ipmi_device->user_interface) {
 		dev_warn(&pnp_dev->dev, "Unexpected response is returned. "
@@ -250,7 +253,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		ipmi_free_recv_msg(msg);
 		return;
 	}
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_for_each_entry(tx_msg, &ipmi_device->tx_msg_list, head) {
 		if (msg->msgid == tx_msg->tx_msgid) {
 			msg_found = 1;
@@ -258,7 +261,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		}
 	}
 
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	if (!msg_found) {
 		dev_warn(&pnp_dev->dev, "Unexpected response (msg id %ld) is "
 			"returned.\n", msg->msgid);
@@ -378,6 +381,7 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	struct acpi_ipmi_device *ipmi_device = handler_context;
 	int err, rem_time;
 	acpi_status status;
+	unsigned long flags;
 	/*
 	 * IPMI opregion message.
 	 * IPMI message is firstly written to the BMC and system software
@@ -395,9 +399,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 		return AE_NO_MEMORY;
 
 	acpi_format_ipmi_msg(tx_msg, address, value);
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_add_tail(&tx_msg->head, &ipmi_device->tx_msg_list);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	err = ipmi_request_settime(ipmi_device->user_interface,
 					&tx_msg->addr,
 					tx_msg->tx_msgid,
@@ -413,9 +417,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	status = AE_OK;
 
 end_label:
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_del(&tx_msg->head);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	kfree(tx_msg);
 	return status;
 }
@@ -457,7 +461,7 @@ static void acpi_add_ipmi_device(struct acpi_ipmi_device *ipmi_device)
 
 	INIT_LIST_HEAD(&ipmi_device->head);
 
-	mutex_init(&ipmi_device->tx_msg_lock);
+	spin_lock_init(&ipmi_device->tx_msg_lock);
 	INIT_LIST_HEAD(&ipmi_device->tx_msg_list);
 	ipmi_install_space_handler(ipmi_device);
 
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index d5bfbd331bfd..95896886fc5a 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -254,6 +254,7 @@ struct acpi_create_field_info {
 	u32 field_bit_position;
 	u32 field_bit_length;
 	u16 resource_length;
+	u16 pin_number_index;
 	u8 field_flags;
 	u8 attribute;
 	u8 field_type;
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index cc7ab6dd724e..a47cc78ffd4f 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -263,6 +263,7 @@ struct acpi_object_region_field {
 	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length;
 	union acpi_operand_object *region_obj;	/* Containing op_region object */
 	u8 *resource_buffer;	/* resource_template for serial regions/fields */
+	u16 pin_number_index;	/* Index relative to previous Connection/Template */
 };
 
 struct acpi_object_bank_field {
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index feadeed1012d..e651d4ec7c4c 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -360,6 +360,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 			 */
 			info->resource_buffer = NULL;
 			info->connection_node = NULL;
+			info->pin_number_index = 0;
 
 			/*
 			 * A Connection() is either an actual resource descriptor (buffer)
@@ -437,6 +438,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 			}
 
 			info->field_bit_position += info->field_bit_length;
+			info->pin_number_index++;	/* Index relative to previous Connection() */
 			break;
 
 		default:
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 6555e350fc1f..8fab9262d98a 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -141,6 +141,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	union acpi_operand_object *region_obj2;
 	void *region_context = NULL;
 	struct acpi_connection_info *context;
+	acpi_physical_address address;
 
 	ACPI_FUNCTION_TRACE(ev_address_space_dispatch);
 
@@ -235,25 +236,23 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	/* We have everything we need, we can invoke the address space handler */
 
 	handler = handler_desc->address_space.handler;
-
-	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
-			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
-			  &region_obj->region.handler->address_space, handler,
-			  ACPI_FORMAT_NATIVE_UINT(region_obj->region.address +
-						  region_offset),
-			  acpi_ut_get_region_name(region_obj->region.
-						  space_id)));
+	address = (region_obj->region.address + region_offset);
 
 	/*
 	 * Special handling for generic_serial_bus and general_purpose_io:
 	 * There are three extra parameters that must be passed to the
 	 * handler via the context:
-	 *   1) Connection buffer, a resource template from Connection() op.
-	 *   2) Length of the above buffer.
-	 *   3) Actual access length from the access_as() op.
+	 *   1) Connection buffer, a resource template from Connection() op
+	 *   2) Length of the above buffer
+	 *   3) Actual access length from the access_as() op
+	 *
+	 * In addition, for general_purpose_io, the Address and bit_width fields
+	 * are defined as follows:
+	 *   1) Address is the pin number index of the field (bit offset from
+	 *      the previous Connection)
+	 *   2) bit_width is the actual bit length of the field (number of pins)
 	 */
-	if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) ||
-	     (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) &&
+	if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) &&
 	    context && field_obj) {
 
 		/* Get the Connection (resource_template) buffer */
@@ -262,6 +261,24 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 		context->length = field_obj->field.resource_length;
 		context->access_length = field_obj->field.access_length;
 	}
+	if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) &&
+	    context && field_obj) {
+
+		/* Get the Connection (resource_template) buffer */
+
+		context->connection = field_obj->field.resource_buffer;
+		context->length = field_obj->field.resource_length;
+		context->access_length = field_obj->field.access_length;
+		address = field_obj->field.pin_number_index;
+		bit_width = field_obj->field.bit_length;
+	}
+
+	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
+			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
+			  &region_obj->region.handler->address_space, handler,
+			  ACPI_FORMAT_NATIVE_UINT(address),
+			  acpi_ut_get_region_name(region_obj->region.
+						  space_id)));
 
 	if (!(handler_desc->address_space.handler_flags &
 	      ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) {
@@ -275,9 +292,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 
 	/* Call the handler */
 
-	status = handler(function,
-			 (region_obj->region.address + region_offset),
-			 bit_width, value, context,
+	status = handler(function, address, bit_width, value, context,
 			 region_obj2->extra.region_context);
 
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index 7d4bae71e8c6..0108d59665ab 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -178,6 +178,37 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state,
 		buffer = &buffer_desc->integer.value;
 	}
 
+	if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+	    (obj_desc->field.region_obj->region.space_id ==
+	     ACPI_ADR_SPACE_GPIO)) {
+		/*
+		 * For GPIO (general_purpose_io), the Address will be the bit offset
+		 * from the previous Connection() operator, making it effectively a
+		 * pin number index. The bit_length is the length of the field, which
+		 * is thus the number of pins.
+		 */
+		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+				  "GPIO FieldRead [FROM]:  Pin %u Bits %u\n",
+				  obj_desc->field.pin_number_index,
+				  obj_desc->field.bit_length));
+
+		/* Lock entire transaction if requested */
+
+		acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+		/* Perform the write */
+
+		status = acpi_ex_access_region(obj_desc, 0,
+					       (u64 *)buffer, ACPI_READ);
+		acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+		if (ACPI_FAILURE(status)) {
+			acpi_ut_remove_reference(buffer_desc);
+		} else {
+			*ret_buffer_desc = buffer_desc;
+		}
+		return_ACPI_STATUS(status);
+	}
+
 	ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
 			  "FieldRead [TO]:   Obj %p, Type %X, Buf %p, ByteLen %X\n",
 			  obj_desc, obj_desc->common.type, buffer,
@@ -325,6 +356,42 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc,
 
 		*result_desc = buffer_desc;
 		return_ACPI_STATUS(status);
+	} else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+		   (obj_desc->field.region_obj->region.space_id ==
+		    ACPI_ADR_SPACE_GPIO)) {
+		/*
+		 * For GPIO (general_purpose_io), we will bypass the entire field
+		 * mechanism and handoff the bit address and bit width directly to
+		 * the handler. The Address will be the bit offset
+		 * from the previous Connection() operator, making it effectively a
+		 * pin number index. The bit_length is the length of the field, which
+		 * is thus the number of pins.
+		 */
+		if (source_desc->common.type != ACPI_TYPE_INTEGER) {
+			return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
+		}
+
+		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+				  "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X  [TO]:  Pin %u Bits %u\n",
+				  acpi_ut_get_type_name(source_desc->common.
+							type),
+				  source_desc->common.type,
+				  (u32)source_desc->integer.value,
+				  obj_desc->field.pin_number_index,
+				  obj_desc->field.bit_length));
+
+		buffer = &source_desc->integer.value;
+
+		/* Lock entire transaction if requested */
+
+		acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+		/* Perform the write */
+
+		status = acpi_ex_access_region(obj_desc, 0,
+					       (u64 *)buffer, ACPI_WRITE);
+		acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+		return_ACPI_STATUS(status);
 	}
 
 	/* Get a pointer to the data to be written */
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index b60c877f5906..c3241b188434 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -963,10 +963,17 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 					 */
 					return_desc =
 					    *(operand[0]->reference.where);
-					if (return_desc) {
-						acpi_ut_add_reference
-						    (return_desc);
+					if (!return_desc) {
+						/*
+						 * Element is NULL, do not allow the dereference.
+						 * This provides compatibility with other ACPI
+						 * implementations.
+						 */
+						return_ACPI_STATUS
+						    (AE_AML_UNINITIALIZED_ELEMENT);
 					}
+
+					acpi_ut_add_reference(return_desc);
 					break;
 
 				default:
@@ -991,11 +998,40 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 									 acpi_namespace_node
 									 *)
 									return_desc);
-				}
+					if (!return_desc) {
+						break;
+					}
 
-				/* Add another reference to the object! */
+					/*
+					 * June 2013:
+					 * buffer_fields/field_units require additional resolution
+					 */
+					switch (return_desc->common.type) {
+					case ACPI_TYPE_BUFFER_FIELD:
+					case ACPI_TYPE_LOCAL_REGION_FIELD:
+					case ACPI_TYPE_LOCAL_BANK_FIELD:
+					case ACPI_TYPE_LOCAL_INDEX_FIELD:
 
-				acpi_ut_add_reference(return_desc);
+						status =
+						    acpi_ex_read_data_from_field
+						    (walk_state, return_desc,
+						     &temp_desc);
+						if (ACPI_FAILURE(status)) {
+							goto cleanup;
+						}
+
+						return_desc = temp_desc;
+						break;
+
+					default:
+
+						/* Add another reference to the object */
+
+						acpi_ut_add_reference
+						    (return_desc);
+						break;
+					}
+				}
 				break;
 
 			default:
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 6b728aef2dca..df212fe4cf6c 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -479,6 +479,8 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 			obj_desc->field.resource_length = info->resource_length;
 		}
 
+		obj_desc->field.pin_number_index = info->pin_number_index;
+
 		/* Allow full data read from EC address space */
 
 		if ((obj_desc->field.region_obj->region.space_id ==
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 93c6049c2d75..b1ad39443cb6 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -57,6 +57,11 @@ acpi_ex_store_object_to_index(union acpi_operand_object *val_desc,
 			      union acpi_operand_object *dest_desc,
 			      struct acpi_walk_state *walk_state);
 
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+			     struct acpi_namespace_node *node,
+			     struct acpi_walk_state *walk_state);
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ex_store
@@ -376,7 +381,11 @@ acpi_ex_store_object_to_index(union acpi_operand_object *source_desc,
  *              When storing into an object the data is converted to the
  *              target object type then stored in the object. This means
  *              that the target object type (for an initialized target) will
- *              not be changed by a store operation.
+ *              not be changed by a store operation. A copy_object can change
+ *              the target type, however.
+ *
+ *              The implicit_conversion flag is set to NO/FALSE only when
+ *              storing to an arg_x -- as per the rules of the ACPI spec.
  *
  *              Assumes parameters are already validated.
  *
@@ -400,7 +409,7 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 	target_type = acpi_ns_get_type(node);
 	target_desc = acpi_ns_get_attached_object(node);
 
-	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p(%s) into node %p(%s)\n",
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p (%s) to node %p (%s)\n",
 			  source_desc,
 			  acpi_ut_get_object_type_name(source_desc), node,
 			  acpi_ut_get_type_name(target_type)));
@@ -414,46 +423,31 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 		return_ACPI_STATUS(status);
 	}
 
-	/* If no implicit conversion, drop into the default case below */
-
-	if ((!implicit_conversion) ||
-	    ((walk_state->opcode == AML_COPY_OP) &&
-	     (target_type != ACPI_TYPE_LOCAL_REGION_FIELD) &&
-	     (target_type != ACPI_TYPE_LOCAL_BANK_FIELD) &&
-	     (target_type != ACPI_TYPE_LOCAL_INDEX_FIELD))) {
-		/*
-		 * Force execution of default (no implicit conversion). Note:
-		 * copy_object does not perform an implicit conversion, as per the ACPI
-		 * spec -- except in case of region/bank/index fields -- because these
-		 * objects must retain their original type permanently.
-		 */
-		target_type = ACPI_TYPE_ANY;
-	}
-
 	/* Do the actual store operation */
 
 	switch (target_type) {
-	case ACPI_TYPE_BUFFER_FIELD:
-	case ACPI_TYPE_LOCAL_REGION_FIELD:
-	case ACPI_TYPE_LOCAL_BANK_FIELD:
-	case ACPI_TYPE_LOCAL_INDEX_FIELD:
-
-		/* For fields, copy the source data to the target field. */
-
-		status = acpi_ex_write_data_to_field(source_desc, target_desc,
-						     &walk_state->result_obj);
-		break;
-
 	case ACPI_TYPE_INTEGER:
 	case ACPI_TYPE_STRING:
 	case ACPI_TYPE_BUFFER:
 
 		/*
-		 * These target types are all of type Integer/String/Buffer, and
-		 * therefore support implicit conversion before the store.
-		 *
-		 * Copy and/or convert the source object to a new target object
+		 * The simple data types all support implicit source operand
+		 * conversion before the store.
 		 */
+
+		if ((walk_state->opcode == AML_COPY_OP) || !implicit_conversion) {
+			/*
+			 * However, copy_object and Stores to arg_x do not perform
+			 * an implicit conversion, as per the ACPI specification.
+			 * A direct store is performed instead.
+			 */
+			status = acpi_ex_store_direct_to_node(source_desc, node,
+							      walk_state);
+			break;
+		}
+
+		/* Store with implicit source operand conversion support */
+
 		status =
 		    acpi_ex_store_object_to_object(source_desc, target_desc,
 						   &new_desc, walk_state);
@@ -467,13 +461,12 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 			 * the Name's type to that of the value being stored in it.
 			 * source_desc reference count is incremented by attach_object.
 			 *
-			 * Note: This may change the type of the node if an explicit store
-			 * has been performed such that the node/object type has been
-			 * changed.
+			 * Note: This may change the type of the node if an explicit
+			 * store has been performed such that the node/object type
+			 * has been changed.
 			 */
-			status =
-			    acpi_ns_attach_object(node, new_desc,
-						  new_desc->common.type);
+			status = acpi_ns_attach_object(node, new_desc,
+						       new_desc->common.type);
 
 			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 					  "Store %s into %s via Convert/Attach\n",
@@ -484,38 +477,83 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 		}
 		break;
 
-	default:
-
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "Storing [%s] (%p) directly into node [%s] (%p)"
-				  " with no implicit conversion\n",
-				  acpi_ut_get_object_type_name(source_desc),
-				  source_desc,
-				  acpi_ut_get_object_type_name(target_desc),
-				  node));
+	case ACPI_TYPE_BUFFER_FIELD:
+	case ACPI_TYPE_LOCAL_REGION_FIELD:
+	case ACPI_TYPE_LOCAL_BANK_FIELD:
+	case ACPI_TYPE_LOCAL_INDEX_FIELD:
+		/*
+		 * For all fields, always write the source data to the target
+		 * field. Any required implicit source operand conversion is
+		 * performed in the function below as necessary. Note, field
+		 * objects must retain their original type permanently.
+		 */
+		status = acpi_ex_write_data_to_field(source_desc, target_desc,
+						     &walk_state->result_obj);
+		break;
 
+	default:
 		/*
 		 * No conversions for all other types. Directly store a copy of
-		 * the source object. NOTE: This is a departure from the ACPI
-		 * spec, which states "If conversion is impossible, abort the
-		 * running control method".
+		 * the source object. This is the ACPI spec-defined behavior for
+		 * the copy_object operator.
 		 *
-		 * This code implements "If conversion is impossible, treat the
-		 * Store operation as a CopyObject".
+		 * NOTE: For the Store operator, this is a departure from the
+		 * ACPI spec, which states "If conversion is impossible, abort
+		 * the running control method". Instead, this code implements
+		 * "If conversion is impossible, treat the Store operation as
+		 * a CopyObject".
 		 */
-		status =
-		    acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc,
-						    walk_state);
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
-		}
-
-		status =
-		    acpi_ns_attach_object(node, new_desc,
-					  new_desc->common.type);
-		acpi_ut_remove_reference(new_desc);
+		status = acpi_ex_store_direct_to_node(source_desc, node,
+						      walk_state);
 		break;
 	}
 
 	return_ACPI_STATUS(status);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_store_direct_to_node
+ *
+ * PARAMETERS:  source_desc             - Value to be stored
+ *              node                    - Named object to receive the value
+ *              walk_state              - Current walk state
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: "Store" an object directly to a node. This involves a copy
+ *              and an attach.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+			     struct acpi_namespace_node *node,
+			     struct acpi_walk_state *walk_state)
+{
+	acpi_status status;
+	union acpi_operand_object *new_desc;
+
+	ACPI_FUNCTION_TRACE(ex_store_direct_to_node);
+
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+			  "Storing [%s] (%p) directly into node [%s] (%p)"
+			  " with no implicit conversion\n",
+			  acpi_ut_get_object_type_name(source_desc),
+			  source_desc, acpi_ut_get_type_name(node->type),
+			  node));
+
+	/* Copy the source object to a new object */
+
+	status =
+	    acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc, walk_state);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Attach the new object to the node */
+
+	status = acpi_ns_attach_object(node, new_desc, new_desc->common.type);
+	acpi_ut_remove_reference(new_desc);
+	return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index e4c9291fc0a3..a63a4cdd2ce8 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -998,5 +998,11 @@ acpi_ut_copy_iobject_to_iobject(union acpi_operand_object *source_desc,
 		status = acpi_ut_copy_simple_object(source_desc, *dest_desc);
 	}
 
+	/* Delete the allocated object if copy failed */
+
+	if (ACPI_FAILURE(status)) {
+		acpi_ut_remove_reference(*dest_desc);
+	}
+
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index b3e36a81aa4d..ca6d2acafa66 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -349,7 +349,7 @@ void acpi_ut_print_string(char *string, u8 max_length)
 	}
 
 	acpi_os_printf("\"");
-	for (i = 0; string[i] && (i < max_length); i++) {
+	for (i = 0; (i < max_length) && string[i]; i++) {
 
 		/* Escape sequences */
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 95332717e4f5..7ae5ebd1e70e 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -34,6 +34,7 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/delay.h>
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -68,6 +69,7 @@ MODULE_AUTHOR("Alexey Starikovskiy <astarikovskiy@suse.de>");
 MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
+static int battery_bix_broken_package;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -443,7 +445,12 @@ static int acpi_battery_get_info(struct acpi_battery *battery)
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", name));
 		return -ENODEV;
 	}
-	if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
+
+	if (battery_bix_broken_package)
+		result = extract_package(battery, buffer.pointer,
+				extended_info_offsets + 1,
+				ARRAY_SIZE(extended_info_offsets) - 1);
+	else if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
 		result = extract_package(battery, buffer.pointer,
 				extended_info_offsets,
 				ARRAY_SIZE(extended_info_offsets));
@@ -1064,6 +1071,39 @@ static int battery_notify(struct notifier_block *nb,
 	return 0;
 }
 
+static struct dmi_system_id bat_dmi_table[] = {
+	{
+		.ident = "NEC LZ750/LS",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
+		},
+	},
+	{},
+};
+
+/*
+ * Some machines'(E,G Lenovo Z480) ECs are not stable
+ * during boot up and this causes battery driver fails to be
+ * probed due to failure of getting battery information
+ * from EC sometimes. After several retries, the operation
+ * may work. So add retry code here and 20ms sleep between
+ * every retries.
+ */
+static int acpi_battery_update_retry(struct acpi_battery *battery)
+{
+	int retry, ret;
+
+	for (retry = 5; retry; retry--) {
+		ret = acpi_battery_update(battery);
+		if (!ret)
+			break;
+
+		msleep(20);
+	}
+	return ret;
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -1083,9 +1123,11 @@ static int acpi_battery_add(struct acpi_device *device)
 	if (ACPI_SUCCESS(acpi_get_handle(battery->device->handle,
 			"_BIX", &handle)))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
-	result = acpi_battery_update(battery);
+
+	result = acpi_battery_update_retry(battery);
 	if (result)
 		goto fail;
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	result = acpi_battery_add_fs(device);
 #endif
@@ -1174,6 +1216,8 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 	if (!acpi_battery_dir)
 		return;
 #endif
+	if (dmi_check_system(bat_dmi_table))
+		battery_bix_broken_package = 1;
 	if (acpi_bus_register_driver(&acpi_battery_driver) < 0) {
 #ifdef CONFIG_ACPI_PROCFS_POWER
 		acpi_unlock_battery_dir(acpi_battery_dir);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index cb9629638def..76da257cfc28 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -327,6 +327,19 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"),
 		},
 	},
+	/*
+	 * Without this this EEEpc exports a non working WMI interface, with
+	 * this it exports a working "good old" eeepc_laptop interface, fixing
+	 * both brightness control, and rfkill not working.
+	 */
+	{
+	.callback = dmi_enable_osi_linux,
+	.ident = "Asus EEE PC 1015PX",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 292de3cab9cc..b62207a87430 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -33,6 +33,7 @@
 #include <linux/proc_fs.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
+#include <linux/regulator/machine.h>
 #ifdef CONFIG_X86
 #include <asm/mpspec.h>
 #endif
@@ -56,6 +57,12 @@ EXPORT_SYMBOL(acpi_root_dir);
 
 
 #ifdef CONFIG_X86
+#ifdef CONFIG_ACPI_CUSTOM_DSDT
+static inline int set_copy_dsdt(const struct dmi_system_id *id)
+{
+	return 0;
+}
+#else
 static int set_copy_dsdt(const struct dmi_system_id *id)
 {
 	printk(KERN_NOTICE "%s detected - "
@@ -63,6 +70,7 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	acpi_gbl_copy_dsdt_locally = 1;
 	return 0;
 }
+#endif
 
 static struct dmi_system_id dsdt_dmi_table[] __initdata = {
 	/*
@@ -705,6 +713,14 @@ void __init acpi_early_init(void)
 		goto error0;
 	}
 
+	/*
+	 * If the system is using ACPI then we can be reasonably
+	 * confident that any regulators are managed by the firmware
+	 * so tell the regulator core it has everything it needs to
+	 * know.
+	 */
+	regulator_has_full_constraints();
+
 	return;
 
       error0:
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 553527c2532b..3e865d2c59e0 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -965,6 +965,8 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 		acpi_dev_pm_full_power(adev);
 		__acpi_device_run_wake(adev, false);
 	}
+
+	dev->pm_domain->detach = acpi_dev_pm_detach;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 45af90a1ec1b..1ad5a4f9e0c3 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -175,9 +175,10 @@ static void start_transaction(struct acpi_ec *ec)
 static void advance_transaction(struct acpi_ec *ec, u8 status)
 {
 	unsigned long flags;
-	struct transaction *t = ec->curr;
+	struct transaction *t;
 
 	spin_lock_irqsave(&ec->lock, flags);
+	t = ec->curr;
 	if (!t)
 		goto unlock;
 	if (t->wlen > t->wi) {
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 41c5e1b799ef..f658e0948703 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -432,6 +432,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 				 pin_name(pin));
 		}
 
+		kfree(entry);
 		return 0;
 	}
 
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index e427dc516c76..a02a91cd1de4 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -63,6 +63,9 @@ static struct acpi_scan_handler pci_root_handler = {
 	.ids = root_device_ids,
 	.attach = acpi_pci_root_add,
 	.detach = acpi_pci_root_remove,
+	.hotplug = {
+		.ignore = true,
+	},
 };
 
 /* Lock to protect both acpi_pci_roots lists */
@@ -614,9 +617,12 @@ static void handle_root_bridge_removal(struct acpi_device *device)
 	ej_event->device = device;
 	ej_event->event = ACPI_NOTIFY_EJECT_REQUEST;
 
+	get_device(&device->dev);
 	status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, ej_event);
-	if (ACPI_FAILURE(status))
+	if (ACPI_FAILURE(status)) {
+		put_device(&device->dev);
 		kfree(ej_event);
+	}
 }
 
 static void _handle_hotplug_event_root(struct work_struct *work)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index eb133c77aadb..a88894190e41 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -121,17 +121,10 @@ static struct dmi_system_id __cpuinitdata processor_power_dmi_table[] = {
  */
 static void acpi_safe_halt(void)
 {
-	current_thread_info()->status &= ~TS_POLLING;
-	/*
-	 * TS_POLLING-cleared state must be visible before we
-	 * test NEED_RESCHED:
-	 */
-	smp_mb();
-	if (!need_resched()) {
+	if (!tif_need_resched()) {
 		safe_halt();
 		local_irq_disable();
 	}
-	current_thread_info()->status |= TS_POLLING;
 }
 
 #ifdef ARCH_APICTIMER_STOPS_ON_C3
@@ -739,6 +732,11 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
+			return -EINVAL;
+	}
+
 	lapic_timer_state_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 
@@ -792,18 +790,9 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	/*
@@ -821,9 +810,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
@@ -860,18 +846,9 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		}
 	}
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	acpi_unlazy_tlb(smp_processor_id());
@@ -917,9 +894,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
@@ -1127,9 +1101,9 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 
 	if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) {
 
-		cpuidle_pause_and_lock();
 		/* Protect against cpu-hotplug */
 		get_online_cpus();
+		cpuidle_pause_and_lock();
 
 		/* Disable all cpuidle devices */
 		for_each_online_cpu(cpu) {
@@ -1156,8 +1130,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 				cpuidle_enable_device(dev);
 			}
 		}
-		put_online_cpus();
 		cpuidle_resume_and_unlock();
+		put_online_cpus();
 	}
 
 	return 0;
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index e7dd2c1fee79..5e47d7bf4745 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -59,6 +59,12 @@ struct throttling_tstate {
 	int target_state;		/* target T-state */
 };
 
+struct acpi_processor_throttling_arg {
+	struct acpi_processor *pr;
+	int target_state;
+	bool force;
+};
+
 #define THROTTLING_PRECHANGE       (1)
 #define THROTTLING_POSTCHANGE      (2)
 
@@ -1063,16 +1069,24 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr,
 	return 0;
 }
 
+static long acpi_processor_throttling_fn(void *data)
+{
+	struct acpi_processor_throttling_arg *arg = data;
+	struct acpi_processor *pr = arg->pr;
+
+	return pr->throttling.acpi_processor_set_throttling(pr,
+			arg->target_state, arg->force);
+}
+
 int acpi_processor_set_throttling(struct acpi_processor *pr,
 						int state, bool force)
 {
-	cpumask_var_t saved_mask;
 	int ret = 0;
 	unsigned int i;
 	struct acpi_processor *match_pr;
 	struct acpi_processor_throttling *p_throttling;
+	struct acpi_processor_throttling_arg arg;
 	struct throttling_tstate t_state;
-	cpumask_var_t online_throttling_cpus;
 
 	if (!pr)
 		return -EINVAL;
@@ -1083,14 +1097,6 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 	if ((state < 0) || (state > (pr->throttling.state_count - 1)))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
-		free_cpumask_var(saved_mask);
-		return -ENOMEM;
-	}
-
 	if (cpu_is_offline(pr->id)) {
 		/*
 		 * the cpu pointed by pr->id is offline. Unnecessary to change
@@ -1099,17 +1105,15 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 		return -ENODEV;
 	}
 
-	cpumask_copy(saved_mask, &current->cpus_allowed);
 	t_state.target_state = state;
 	p_throttling = &(pr->throttling);
-	cpumask_and(online_throttling_cpus, cpu_online_mask,
-		    p_throttling->shared_cpu_map);
+
 	/*
 	 * The throttling notifier will be called for every
 	 * affected cpu in order to get one proper T-state.
 	 * The notifier event is THROTTLING_PRECHANGE.
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
 							&t_state);
@@ -1121,21 +1125,18 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 	 * it can be called only for the cpu pointed by pr.
 	 */
 	if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
-		/* FIXME: use work_on_cpu() */
-		if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
-			/* Can't migrate to the pr->id CPU. Exit */
-			ret = -ENODEV;
-			goto exit;
-		}
-		ret = p_throttling->acpi_processor_set_throttling(pr,
-						t_state.target_state, force);
+		arg.pr = pr;
+		arg.target_state = state;
+		arg.force = force;
+		ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
 		 * it is necessary to set T-state for every affected
 		 * cpus.
 		 */
-		for_each_cpu(i, online_throttling_cpus) {
+		for_each_cpu_and(i, cpu_online_mask,
+		    p_throttling->shared_cpu_map) {
 			match_pr = per_cpu(processors, i);
 			/*
 			 * If the pointer is invalid, we will report the
@@ -1156,13 +1157,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 					"on CPU %d\n", i));
 				continue;
 			}
-			t_state.cpu = i;
-			/* FIXME: use work_on_cpu() */
-			if (set_cpus_allowed_ptr(current, cpumask_of(i)))
-				continue;
-			ret = match_pr->throttling.
-				acpi_processor_set_throttling(
-				match_pr, t_state.target_state, force);
+
+			arg.pr = match_pr;
+			arg.target_state = state;
+			arg.force = force;
+			ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
+				&arg);
 		}
 	}
 	/*
@@ -1171,17 +1171,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 	 * affected cpu to update the T-states.
 	 * The notifier event is THROTTLING_POSTCHANGE
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
 							&t_state);
 	}
-	/* restore the previous state */
-	/* FIXME: use work_on_cpu() */
-	set_cpus_allowed_ptr(current, saved_mask);
-exit:
-	free_cpumask_var(online_throttling_cpus);
-	free_cpumask_var(saved_mask);
+
 	return ret;
 }
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3322b47ab7ca..b9cfaf1d94d8 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,18 +77,24 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &ares->data.memory24;
+		if (!memory24->minimum && !memory24->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory24->minimum,
 					 memory24->address_length,
 					 memory24->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &ares->data.memory32;
+		if (!memory32->minimum && !memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory32->minimum,
 					 memory32->address_length,
 					 memory32->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &ares->data.fixed_memory32;
+		if (!fixed_memory32->address && !fixed_memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, fixed_memory32->address,
 					 fixed_memory32->address_length,
 					 fixed_memory32->write_protect);
@@ -144,12 +150,16 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_IO:
 		io = &ares->data.io;
+		if (!io->minimum && !io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, io->minimum,
 					io->address_length,
 					io->io_decode);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
 		fixed_io = &ares->data.fixed_io;
+		if (!fixed_io->address && !fixed_io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, fixed_io->address,
 					fixed_io->address_length,
 					ACPI_DECODE_10);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index af658b2ff279..091682fb1617 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -244,8 +244,6 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source)
 			goto out;
 		}
 	}
-	acpi_evaluate_hotplug_ost(handle, ost_source,
-				  ACPI_OST_SC_INSERT_IN_PROGRESS, NULL);
 	error = acpi_bus_scan(handle);
 	if (error) {
 		acpi_handle_warn(handle, "Namespace scan failure\n");
@@ -771,12 +769,17 @@ static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
 	device->driver->ops.notify(device, event);
 }
 
-static acpi_status acpi_device_notify_fixed(void *data)
+static void acpi_device_notify_fixed(void *data)
 {
 	struct acpi_device *device = data;
 
 	/* Fixed hardware devices have no handles */
 	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
+}
+
+static acpi_status acpi_device_fixed_event(void *data)
+{
+	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
 	return AE_OK;
 }
 
@@ -787,12 +790,12 @@ static int acpi_device_install_notify_handler(struct acpi_device *device)
 	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
 		status =
 		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						     acpi_device_notify_fixed,
+						     acpi_device_fixed_event,
 						     device);
 	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
 		status =
 		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						     acpi_device_notify_fixed,
+						     acpi_device_fixed_event,
 						     device);
 	else
 		status = acpi_install_notify_handler(device->handle,
@@ -809,10 +812,10 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device)
 {
 	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
 		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						acpi_device_notify_fixed);
+						acpi_device_fixed_event);
 	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
 		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						acpi_device_notify_fixed);
+						acpi_device_fixed_event);
 	else
 		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
 					   acpi_device_notify);
@@ -1792,7 +1795,7 @@ static void acpi_scan_init_hotplug(acpi_handle handle, int type)
 	 */
 	list_for_each_entry(hwid, &pnp.ids, list) {
 		handler = acpi_scan_match_handler(hwid->id, NULL);
-		if (handler) {
+		if (handler && !handler->hotplug.ignore) {
 			acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
 					acpi_hotplug_notify_cb, handler);
 			break;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9c1a435d10e6..035920f2ab4d 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -78,6 +78,17 @@ static int acpi_sleep_prepare(u32 acpi_state)
 	return 0;
 }
 
+static bool acpi_sleep_state_supported(u8 sleep_state)
+{
+	acpi_status status;
+	u8 type_a, type_b;
+
+	status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b);
+	return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware
+		|| (acpi_gbl_FADT.sleep_control.address
+			&& acpi_gbl_FADT.sleep_status.address));
+}
+
 #ifdef CONFIG_ACPI_SLEEP
 static u32 acpi_target_sleep_state = ACPI_STATE_S0;
 
@@ -600,15 +611,9 @@ static void acpi_sleep_suspend_setup(void)
 {
 	int i;
 
-	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) {
-		acpi_status status;
-		u8 type_a, type_b;
-
-		status = acpi_get_sleep_type_data(i, &type_a, &type_b);
-		if (ACPI_SUCCESS(status)) {
+	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++)
+		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
-		}
-	}
 
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
@@ -739,11 +744,7 @@ static const struct platform_hibernation_ops acpi_hibernation_ops_old = {
 
 static void acpi_sleep_hibernate_setup(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
-
-	status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b);
-	if (ACPI_FAILURE(status))
+	if (!acpi_sleep_state_supported(ACPI_STATE_S4))
 		return;
 
 	hibernation_set_ops(old_suspend_ordering ?
@@ -792,8 +793,6 @@ static void acpi_power_off(void)
 
 int __init acpi_sleep_init(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
 	char supported[ACPI_S_STATE_COUNT * 3 + 1];
 	char *pos = supported;
 	int i;
@@ -808,8 +807,7 @@ int __init acpi_sleep_init(void)
 	acpi_sleep_suspend_setup();
 	acpi_sleep_hibernate_setup();
 
-	status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
 		sleep_states[ACPI_STATE_S5] = 1;
 		pm_power_off_prepare = acpi_power_off_prepare;
 		pm_power_off = acpi_power_off;
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 0e4b96b62c75..82a01cc45f9c 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -733,6 +733,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 	union acpi_object *o;
 	struct acpi_video_device_brightness *br = NULL;
 	int result = -EINVAL;
+	u32 value;
 
 	if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device, &obj))) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available "
@@ -763,7 +764,12 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 			printk(KERN_ERR PREFIX "Invalid data\n");
 			continue;
 		}
-		br->levels[count] = (u32) o->integer.value;
+		value = (u32) o->integer.value;
+		/* Skip duplicate entries */
+		if (count > 2 && br->levels[count - 1] == value)
+			continue;
+
+		br->levels[count] = value;
 
 		if (br->levels[count] > max_level)
 			max_level = br->levels[count];
@@ -846,7 +852,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 		for (i = 2; i < br->count; i++)
 			if (level_old == br->levels[i])
 				break;
-		if (i == br->count)
+		if (i == br->count || !level)
 			level = max_level;
 	}
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index cdbad3a454a0..4144a3a999bd 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -506,7 +506,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 
 		amba_put_disable_pclk(dev);
 
-		if (cid == AMBA_CID)
+		if (cid == AMBA_CID || cid == CORESIGHT_CID)
 			dev->periphid = pid;
 
 		if (!dev->periphid)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index b112625482ca..9064a2f2760c 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,6 +61,8 @@ enum board_ids {
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
 	board_ahci_ign_iferr,
+	board_ahci_nomsi,
+	board_ahci_noncq,
 	board_ahci_nosntf,
 	board_ahci_yes_fbs,
 
@@ -119,6 +121,20 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_nomsi] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_MSI),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
+	[board_ahci_noncq] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_nosntf] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_SNTF),
 		.flags		= AHCI_FLAG_COMMON,
@@ -292,6 +308,26 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x8d66), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x8d6e), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x23a3), board_ahci }, /* Coleto Creek AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c83), board_ahci }, /* Wildcat Point-LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -423,17 +459,29 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9128 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9125),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9125 */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_MARVELL_EXT, 0x9178,
+			 PCI_VENDOR_ID_MARVELL_EXT, 0x9170),
+	  .driver_data = board_ahci_yes_fbs },			/* 88se9170 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172),
+	  .driver_data = board_ahci_yes_fbs },			/* 88se9182 */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 on some Gigabyte */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0),
+	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
+	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642),
+	  .driver_data = board_ahci_yes_fbs },
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
+	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* Asmedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
@@ -441,6 +489,13 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci },	/* ASM1061 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
 
+	/*
+	 * Samsung SSDs found on some macbooks.  NCQ times out if MSI is
+	 * enabled.  https://bugzilla.kernel.org/show_bug.cgi?id=60731
+	 */
+	{ PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi },
+	{ PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi },
+
 	/* Enmotus */
 	{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
 
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index b92913a528b6..82aa7b550ea5 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -340,6 +340,14 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	{ 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt },
 	/* SATA Controller IDE (Coleto Creek) */
 	{ 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 
 	{ }	/* terminate list */
 };
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 7b9bdd822c62..8905e03a53a2 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1266,9 +1266,11 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
 {
 	struct ata_port *ap = link->ap;
 	struct ahci_host_priv *hpriv = ap->host->private_data;
+	struct ahci_port_priv *pp = ap->private_data;
 	const char *reason = NULL;
 	unsigned long now, msecs;
 	struct ata_taskfile tf;
+	bool fbs_disabled = false;
 	int rc;
 
 	DPRINTK("ENTER\n");
@@ -1278,6 +1280,16 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
 	if (rc && rc != -EOPNOTSUPP)
 		ata_link_warn(link, "failed to reset engine (errno=%d)\n", rc);
 
+	/*
+	 * According to AHCI-1.2 9.3.9: if FBS is enable, software shall
+	 * clear PxFBS.EN to '0' prior to issuing software reset to devices
+	 * that is attached to port multiplier.
+	 */
+	if (!ata_is_host_link(link) && pp->fbs_enabled) {
+		ahci_disable_fbs(ap);
+		fbs_disabled = true;
+	}
+
 	ata_tf_init(link->device, &tf);
 
 	/* issue the first D2H Register FIS */
@@ -1318,6 +1330,10 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
 	} else
 		*class = ahci_dev_classify(ap);
 
+	/* re-enable FBS if disabled before */
+	if (fbs_disabled)
+		ahci_enable_fbs(ap);
+
 	DPRINTK("EXIT, class=%u\n", *class);
 	return 0;
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index adf002a3c584..ca7c23d58a03 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2199,6 +2199,16 @@ int ata_dev_configure(struct ata_device *dev)
 	if (rc)
 		return rc;
 
+	/* some WD SATA-1 drives have issues with LPM, turn on NOLPM for them */
+	if ((dev->horkage & ATA_HORKAGE_WD_BROKEN_LPM) &&
+	    (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
+		dev->horkage |= ATA_HORKAGE_NOLPM;
+
+	if (dev->horkage & ATA_HORKAGE_NOLPM) {
+		ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
+		dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
+	}
+
 	/* let ACPI work its magic */
 	rc = ata_acpi_on_devcfg(dev);
 	if (rc)
@@ -2401,7 +2411,7 @@ int ata_dev_configure(struct ata_device *dev)
 			cdb_intr_string = ", CDB intr";
 		}
 
-		if (atapi_dmadir || atapi_id_dmadir(dev->id)) {
+		if (atapi_dmadir || (dev->horkage & ATA_HORKAGE_ATAPI_DMADIR) || atapi_id_dmadir(dev->id)) {
 			dev->flags |= ATA_DFLAG_DMADIR;
 			dma_dir_string = ", DMADIR";
 		}
@@ -4110,6 +4120,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "TORiSAN DVD-ROM DRD-N216", NULL,	ATA_HORKAGE_MAX_SEC_128 },
 	{ "QUANTUM DAT    DAT72-000", NULL,	ATA_HORKAGE_ATAPI_MOD16_DMA },
 	{ "Slimtype DVD A  DS8A8SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
+	{ "Slimtype DVD A  DS8A9SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 
 	/* Devices we expect to fail diagnostics */
 
@@ -4139,6 +4150,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "ST3320[68]13AS",	"SD1[5-9]",	ATA_HORKAGE_NONCQ |
 						ATA_HORKAGE_FIRMWARE_WARN },
 
+	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
 	{ "HTS541060G9SA00",    "MB3OC60D",     ATA_HORKAGE_NONCQ, },
@@ -4185,6 +4200,23 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "PIONEER DVD-RW  DVR-212D",	NULL,	ATA_HORKAGE_NOSETXFER },
 	{ "PIONEER DVD-RW  DVR-216D",	NULL,	ATA_HORKAGE_NOSETXFER },
 
+	/*
+	 * Some WD SATA-I drives spin up and down erratically when the link
+	 * is put into the slumber mode.  We don't have full list of the
+	 * affected devices.  Disable LPM if the device matches one of the
+	 * known prefixes and is SATA-1.  As a side effect LPM partial is
+	 * lost too.
+	 *
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=57211
+	 */
+	{ "WDC WD800JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD1200JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD1600JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD2000JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD2500JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD3000JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+	{ "WDC WD3200JD-*",		NULL,	ATA_HORKAGE_WD_BROKEN_LPM },
+
 	/* End Marker */
 	{ }
 };
@@ -4726,6 +4758,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
  *	ata_qc_new - Request an available ATA command, for queueing
  *	@ap: target port
  *
+ *	Some ATA host controllers may implement a queue depth which is less
+ *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ *	the hardware limitation.
+ *
  *	LOCKING:
  *	None.
  */
@@ -4733,21 +4769,27 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc = NULL;
-	unsigned int i;
+	unsigned int max_queue = ap->host->n_tags;
+	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	/* the last tag is reserved for internal command. */
-	for (i = 0; i < ATA_MAX_QUEUE - 1; i++)
-		if (!test_and_set_bit(i, &ap->qc_allocated)) {
-			qc = __ata_qc_from_tag(ap, i);
+	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+		tag = tag < max_queue ? tag : 0;
+
+		/* the last tag is reserved for internal command. */
+		if (tag == ATA_TAG_INTERNAL)
+			continue;
+
+		if (!test_and_set_bit(tag, &ap->qc_allocated)) {
+			qc = __ata_qc_from_tag(ap, tag);
+			qc->tag = tag;
+			ap->last_tag = tag;
 			break;
 		}
-
-	if (qc)
-		qc->tag = i;
+	}
 
 	return qc;
 }
@@ -6036,6 +6078,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
+	host->n_tags = ATA_MAX_QUEUE - 1;
 	host->dev = dev;
 	host->ops = ops;
 }
@@ -6117,6 +6160,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
 		dev_err(host->dev, "BUG: trying to register unstarted host\n");
@@ -6263,6 +6308,8 @@ int ata_host_activate(struct ata_host *host, int irq,
 static void ata_port_detach(struct ata_port *ap)
 {
 	unsigned long flags;
+	struct ata_link *link;
+	struct ata_device *dev;
 
 	if (!ap->ops->error_handler)
 		goto skip_eh;
@@ -6282,6 +6329,13 @@ static void ata_port_detach(struct ata_port *ap)
 	cancel_delayed_work_sync(&ap->hotplug_task);
 
  skip_eh:
+	/* clean up zpodd on port removal */
+	ata_for_each_link(link, ap, HOST_FIRST) {
+		ata_for_each_dev(dev, link, ALL) {
+			if (zpodd_dev_enabled(dev))
+				zpodd_exit(dev);
+		}
+	}
 	if (ap->pmp_link) {
 		int i;
 		for (i = 0; i < SATA_PMP_MAX_PORTS; i++)
@@ -6502,6 +6556,8 @@ static int __init ata_parse_force_one(char **cur,
 		{ "nosrst",	.lflags		= ATA_LFLAG_NO_SRST },
 		{ "norst",	.lflags		= ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST },
 		{ "rstonce",	.lflags		= ATA_LFLAG_RST_ONCE },
+		{ "atapi_dmadir", .horkage_on	= ATA_HORKAGE_ATAPI_DMADIR },
+		{ "disable",	.horkage_on	= ATA_HORKAGE_DISABLE },
 	};
 	char *start = *cur, *p = *cur;
 	char *id, *val, *endp;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c69fcce505c0..370462fa8e01 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1322,14 +1322,14 @@ void ata_eh_qc_complete(struct ata_queued_cmd *qc)
  *	should be retried.  To be used from EH.
  *
  *	SCSI midlayer limits the number of retries to scmd->allowed.
- *	scmd->retries is decremented for commands which get retried
+ *	scmd->allowed is incremented for commands which get retried
  *	due to unrelated failures (qc->err_mask is zero).
  */
 void ata_eh_qc_retry(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
-	if (!qc->err_mask && scmd->retries)
-		scmd->retries--;
+	if (!qc->err_mask)
+		scmd->allowed++;
 	__ata_eh_qc_complete(qc);
 }
 
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 20fd337a5731..7ccc084bf1df 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -447,8 +447,11 @@ static void sata_pmp_quirks(struct ata_port *ap)
 		 * otherwise.  Don't try hard to recover it.
 		 */
 		ap->pmp_link[ap->nr_pmp_links - 1].flags |= ATA_LFLAG_NO_RETRY;
-	} else if (vendor == 0x197b && devid == 0x2352) {
-		/* chip found in Thermaltake BlackX Duet, jmicron JMB350? */
+	} else if (vendor == 0x197b && (devid == 0x2352 || devid == 0x0325)) {
+		/*
+		 * 0x2352: found in Thermaltake BlackX Duet, jmicron JMB350?
+		 * 0x0325: jmicron JMB394.
+		 */
 		ata_for_each_link(link, ap, EDGE) {
 			/* SRST breaks detection and disks get misclassified
 			 * LPM disabled to avoid potential problems
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0101af541436..9933b4db7caf 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -112,12 +112,14 @@ static const char *ata_lpm_policy_names[] = {
 	[ATA_LPM_MIN_POWER]	= "min_power",
 };
 
-static ssize_t ata_scsi_lpm_store(struct device *dev,
+static ssize_t ata_scsi_lpm_store(struct device *device,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
+	struct Scsi_Host *shost = class_to_shost(device);
 	struct ata_port *ap = ata_shost_to_port(shost);
+	struct ata_link *link;
+	struct ata_device *dev;
 	enum ata_lpm_policy policy;
 	unsigned long flags;
 
@@ -133,10 +135,20 @@ static ssize_t ata_scsi_lpm_store(struct device *dev,
 		return -EINVAL;
 
 	spin_lock_irqsave(ap->lock, flags);
+
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, &ap->link, ENABLED) {
+			if (dev->horkage & ATA_HORKAGE_NOLPM) {
+				count = -EOPNOTSUPP;
+				goto out_unlock;
+			}
+		}
+	}
+
 	ap->target_lpm_policy = policy;
 	ata_port_schedule_eh(ap);
+out_unlock:
 	spin_unlock_irqrestore(ap->lock, flags);
-
 	return count;
 }
 
@@ -3614,6 +3626,7 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
 		shost->max_lun = 1;
 		shost->max_channel = 1;
 		shost->max_cmd_len = 16;
+		shost->no_write_same = 1;
 
 		/* Schedule policy is determined by ->qc_defer()
 		 * callback and it needs to see every deferred qc.
@@ -3863,6 +3876,27 @@ void ata_scsi_hotplug(struct work_struct *work)
 		return;
 	}
 
+	/*
+	 * XXX - UGLY HACK
+	 *
+	 * The block layer suspend/resume path is fundamentally broken due
+	 * to freezable kthreads and workqueue and may deadlock if a block
+	 * device gets removed while resume is in progress.  I don't know
+	 * what the solution is short of removing freezable kthreads and
+	 * workqueues altogether.
+	 *
+	 * The following is an ugly hack to avoid kicking off device
+	 * removal while freezer is active.  This is a joke but does avoid
+	 * this particular deadlock scenario.
+	 *
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=62801
+	 * http://marc.info/?l=linux-kernel&m=138695698516487
+	 */
+#ifdef CONFIG_FREEZER
+	while (pm_freezing)
+		msleep(10);
+#endif
+
 	DPRINTK("ENTER\n");
 	mutex_lock(&ap->scsi_scan_mutex);
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index b603720b877d..37acda6fa7e4 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2008,13 +2008,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask,
 
 	DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
 
-	/* software reset.  causes dev0 to be selected */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	ap->last_ctl = ap->ctl;
+	if (ap->ioaddr.ctl_addr) {
+		/* software reset.  causes dev0 to be selected */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		ap->last_ctl = ap->ctl;
+	}
 
 	/* wait the port to become ready */
 	return ata_sff_wait_after_reset(&ap->link, devmask, deadline);
@@ -2215,10 +2217,6 @@ void ata_sff_error_handler(struct ata_port *ap)
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	/* ignore ata_sff_softreset if ctl isn't accessible */
-	if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr)
-		softreset = NULL;
-
 	/* ignore built-in hardresets if SCR access is not available */
 	if ((hardreset == sata_std_hardreset ||
 	     hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link))
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index c04d393d20c1..08e67285645b 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -319,25 +319,25 @@ int ata_tport_add(struct device *parent,
 /*
  * ATA link attributes
  */
+static int noop(int x) { return x; }
 
-
-#define ata_link_show_linkspeed(field)					\
+#define ata_link_show_linkspeed(field, format)			        \
 static ssize_t								\
 show_ata_link_##field(struct device *dev,				\
 		      struct device_attribute *attr, char *buf)		\
 {									\
 	struct ata_link *link = transport_class_to_link(dev);		\
 									\
-	return sprintf(buf,"%s\n", sata_spd_string(fls(link->field)));	\
+	return sprintf(buf, "%s\n", sata_spd_string(format(link->field))); \
 }
 
-#define ata_link_linkspeed_attr(field)					\
-	ata_link_show_linkspeed(field)					\
+#define ata_link_linkspeed_attr(field, format)				\
+	ata_link_show_linkspeed(field, format)				\
 static DEVICE_ATTR(field, S_IRUGO, show_ata_link_##field, NULL)
 
-ata_link_linkspeed_attr(hw_sata_spd_limit);
-ata_link_linkspeed_attr(sata_spd_limit);
-ata_link_linkspeed_attr(sata_spd);
+ata_link_linkspeed_attr(hw_sata_spd_limit, fls);
+ata_link_linkspeed_attr(sata_spd_limit, fls);
+ata_link_linkspeed_attr(sata_spd, noop);
 
 
 static DECLARE_TRANSPORT_CLASS(ata_link_class,
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index 033f3f4c20ad..fa288597f01b 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -408,12 +408,13 @@ static int pata_at91_probe(struct platform_device *pdev)
 
 	host->private_data = info;
 
-	return ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
-			gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
-			irq_flags, &pata_at91_sht);
+	ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
+				gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
+				irq_flags, &pata_at91_sht);
+	if (ret)
+		goto err_put;
 
-	if (!ret)
-		return 0;
+	return 0;
 
 err_put:
 	clk_put(info->mck);
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index f35f15f4d83e..f7badaa39eb6 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -586,7 +586,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask,
  *	Note: Original code is ata_bus_softreset().
  */
 
-static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
+static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
                                       unsigned long deadline)
 {
 	struct ata_ioports *ioaddr = &ap->ioaddr;
@@ -600,9 +600,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
 	udelay(20);
 	out_be32(ioaddr->ctl_addr, ap->ctl);
 
-	scc_wait_after_reset(&ap->link, devmask, deadline);
-
-	return 0;
+	return scc_wait_after_reset(&ap->link, devmask, deadline);
 }
 
 /**
@@ -619,7 +617,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes,
 {
 	struct ata_port *ap = link->ap;
 	unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS;
-	unsigned int devmask = 0, err_mask;
+	unsigned int devmask = 0;
+	int rc;
 	u8 err;
 
 	DPRINTK("ENTER\n");
@@ -635,9 +634,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes,
 
 	/* issue bus reset */
 	DPRINTK("about to softreset, devmask=%x\n", devmask);
-	err_mask = scc_bus_softreset(ap, devmask, deadline);
-	if (err_mask) {
-		ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask);
+	rc = scc_bus_softreset(ap, devmask, deadline);
+	if (rc) {
+		ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc);
 		return -EIO;
 	}
 
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index f3febbce6c46..34c91ac3a814 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -252,12 +252,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev
 	pci_write_config_byte(pdev, 0x54, ultra_cfg);
 }
 
-static struct scsi_host_template serverworks_sht = {
+static struct scsi_host_template serverworks_osb4_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+	.sg_tablesize	= LIBATA_DUMB_MAX_PRD,
+};
+
+static struct scsi_host_template serverworks_csb_sht = {
 	ATA_BMDMA_SHT(DRV_NAME),
 };
 
 static struct ata_port_operations serverworks_osb4_port_ops = {
 	.inherits	= &ata_bmdma_port_ops,
+	.qc_prep	= ata_bmdma_dumb_qc_prep,
 	.cable_detect	= serverworks_cable_detect,
 	.mode_filter	= serverworks_osb4_filter,
 	.set_piomode	= serverworks_set_piomode,
@@ -266,6 +272,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = {
 
 static struct ata_port_operations serverworks_csb_port_ops = {
 	.inherits	= &serverworks_osb4_port_ops,
+	.qc_prep	= ata_bmdma_qc_prep,
 	.mode_filter	= serverworks_csb_filter,
 };
 
@@ -405,6 +412,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		}
 	};
 	const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL };
+	struct scsi_host_template *sht = &serverworks_csb_sht;
 	int rc;
 
 	rc = pcim_enable_device(pdev);
@@ -418,6 +426,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		/* Select non UDMA capable OSB4 if we can't do fixups */
 		if (rc < 0)
 			ppi[0] = &info[1];
+		sht = &serverworks_osb4_sht;
 	}
 	/* setup CSB5/CSB6 : South Bridge and IDE option RAID */
 	else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) ||
@@ -434,7 +443,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 			ppi[1] = &ata_dummy_port_info;
 	}
 
-	return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0);
+	return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 8401061b4040..38a2389f5b1b 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1501,7 +1501,7 @@ static int sata_fsl_probe(struct platform_device *ofdev)
 	host_priv->csr_base = csr_base;
 
 	irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	if (irq < 0) {
+	if (!irq) {
 		dev_err(&ofdev->dev, "invalid irq from platform\n");
 		goto error_exit_with_cleanup;
 	}
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 35c6b6d09c27..b256ff5b6579 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -304,6 +304,7 @@ enum {
 	MV5_LTMODE		= 0x30,
 	MV5_PHY_CTL		= 0x0C,
 	SATA_IFCFG		= 0x050,
+	LP_PHY_CTL		= 0x058,
 
 	MV_M2_PREAMP_MASK	= 0x7e0,
 
@@ -431,6 +432,7 @@ enum {
 	MV_HP_CUT_THROUGH	= (1 << 10),	/* can use EDMA cut-through */
 	MV_HP_FLAG_SOC		= (1 << 11),	/* SystemOnChip, no PCI */
 	MV_HP_QUIRK_LED_BLINK_EN = (1 << 12),	/* is led blinking enabled? */
+	MV_HP_FIX_LP_PHY_CTL	= (1 << 13),	/* fix speed in LP_PHY_CTL ? */
 
 	/* Port private flags (pp_flags) */
 	MV_PP_FLAG_EDMA_EN	= (1 << 0),	/* is EDMA engine enabled? */
@@ -1353,6 +1355,7 @@ static int mv_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val)
 
 	if (ofs != 0xffffffffU) {
 		void __iomem *addr = mv_ap_base(link->ap) + ofs;
+		struct mv_host_priv *hpriv = link->ap->host->private_data;
 		if (sc_reg_in == SCR_CONTROL) {
 			/*
 			 * Workaround for 88SX60x1 FEr SATA#26:
@@ -1369,6 +1372,18 @@ static int mv_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val)
 			 */
 			if ((val & 0xf) == 1 || (readl(addr) & 0xf) == 1)
 				val |= 0xf000;
+
+			if (hpriv->hp_flags & MV_HP_FIX_LP_PHY_CTL) {
+				void __iomem *lp_phy_addr =
+					mv_ap_base(link->ap) + LP_PHY_CTL;
+				/*
+				 * Set PHY speed according to SControl speed.
+				 */
+				if ((val & 0xf0) == 0x10)
+					writelfl(0x7, lp_phy_addr);
+				else
+					writelfl(0x227, lp_phy_addr);
+			}
 		}
 		writelfl(val, addr);
 		return 0;
@@ -4111,6 +4126,15 @@ static int mv_platform_probe(struct platform_device *pdev)
 	if (rc)
 		goto err;
 
+	/*
+	 * To allow disk hotplug on Armada 370/XP SoCs, the PHY speed must be
+	 * updated in the LP_PHY_CTL register.
+	 */
+	if (pdev->dev.of_node &&
+		of_device_is_compatible(pdev->dev.of_node,
+					"marvell,armada-370-sata"))
+		hpriv->hp_flags |= MV_HP_FIX_LP_PHY_CTL;
+
 	/* initialize adapter */
 	rc = mv_init_host(host);
 	if (rc)
@@ -4216,6 +4240,7 @@ static int mv_platform_resume(struct platform_device *pdev)
 
 #ifdef CONFIG_OF
 static struct of_device_id mv_sata_dt_ids[] = {
+	{ .compatible = "marvell,armada-370-sata", },
 	{ .compatible = "marvell,orion-sata", },
 	{},
 };
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 0ae3ca4bf5c0..dd1faa564eb2 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -157,6 +157,7 @@ static const struct sil_drivelist {
 	{ "ST380011ASL",	SIL_QUIRK_MOD15WRITE },
 	{ "ST3120022ASL",	SIL_QUIRK_MOD15WRITE },
 	{ "ST3160021ASL",	SIL_QUIRK_MOD15WRITE },
+	{ "TOSHIBA MK2561GSYN",	SIL_QUIRK_MOD15WRITE },
 	{ "Maxtor 4D060H3",	SIL_QUIRK_UDMA5MAX },
 	{ }
 };
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 272f00927761..1bdf104e90bb 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -3511,7 +3511,7 @@ static int init_card(struct atm_dev *dev)
 	tmp = dev_get_by_name(&init_net, tname);	/* jhs: was "tmp = dev_get(tname);" */
 	if (tmp) {
 		memcpy(card->atmdev->esi, tmp->dev_addr, 6);
-
+		dev_put(tmp);
 		printk("%s: ESI %pM\n", card->name, card->atmdev->esi);
 	}
 	/*
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 10cd80af2aec..4fe77b887457 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -187,6 +187,14 @@ config GENERIC_CPU_DEVICES
 	bool
 	default n
 
+config HAVE_CPU_AUTOPROBE
+	def_bool ARCH_HAS_CPU_AUTOPROBE
+
+config GENERIC_CPU_AUTOPROBE
+	bool
+	depends on !ARCH_HAS_CPU_AUTOPROBE
+	select HAVE_CPU_AUTOPROBE
+
 config SOC_BUS
 	bool
 
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index d414331b480e..558d562f4901 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -242,13 +242,15 @@ static ssize_t store_drivers_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device *dev;
+	int err = -EINVAL;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (!dev)
 		return -ENODEV;
-	if (bus_rescan_devices_helper(dev, NULL) != 0)
-		return -EINVAL;
-	return count;
+	if (bus_rescan_devices_helper(dev, NULL) == 0)
+		err = count;
+	put_device(dev);
+	return err;
 }
 
 static struct device *next_device(struct klist_iter *i)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2499cefdcdf2..2a19097a7cb1 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -765,12 +765,12 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj)
 	return &dir->kobj;
 }
 
+static DEFINE_MUTEX(gdp_mutex);
 
 static struct kobject *get_device_parent(struct device *dev,
 					 struct device *parent)
 {
 	if (dev->class) {
-		static DEFINE_MUTEX(gdp_mutex);
 		struct kobject *kobj = NULL;
 		struct kobject *parent_kobj;
 		struct kobject *k;
@@ -834,7 +834,9 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 	    glue_dir->kset != &dev->class->p->glue_dirs)
 		return;
 
+	mutex_lock(&gdp_mutex);
 	kobject_put(glue_dir);
+	mutex_unlock(&gdp_mutex);
 }
 
 static void cleanup_device_parent(struct device *dev)
@@ -1839,7 +1841,7 @@ EXPORT_SYMBOL_GPL(device_move);
  */
 void device_shutdown(void)
 {
-	struct device *dev;
+	struct device *dev, *parent;
 
 	spin_lock(&devices_kset->list_lock);
 	/*
@@ -1856,7 +1858,7 @@ void device_shutdown(void)
 		 * prevent it from being freed because parent's
 		 * lock is to be held
 		 */
-		get_device(dev->parent);
+		parent = get_device(dev->parent);
 		get_device(dev);
 		/*
 		 * Make sure the device is off the kset list, in the
@@ -1866,8 +1868,8 @@ void device_shutdown(void)
 		spin_unlock(&devices_kset->list_lock);
 
 		/* hold lock to avoid race with probe/release */
-		if (dev->parent)
-			device_lock(dev->parent);
+		if (parent)
+			device_lock(parent);
 		device_lock(dev);
 
 		/* Don't allow any more runtime suspends */
@@ -1885,11 +1887,11 @@ void device_shutdown(void)
 		}
 
 		device_unlock(dev);
-		if (dev->parent)
-			device_unlock(dev->parent);
+		if (parent)
+			device_unlock(parent);
 
 		put_device(dev);
-		put_device(dev->parent);
+		put_device(parent);
 
 		spin_lock(&devices_kset->list_lock);
 	}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 3d48fc887ef4..607efe6b7dc8 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -13,6 +13,9 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/percpu.h>
+#include <linux/acpi.h>
+#include <linux/of.h>
+#include <linux/cpufeature.h>
 
 #include "base.h"
 
@@ -260,6 +263,45 @@ static void cpu_device_release(struct device *dev)
 	 */
 }
 
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+static ssize_t print_cpu_modalias(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	ssize_t n;
+	u32 i;
+
+	n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
+		    CPU_FEATURE_TYPEVAL);
+
+	for (i = 0; i < MAX_CPU_FEATURES; i++)
+		if (cpu_have_feature(i)) {
+			if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
+				WARN(1, "CPU features overflow page\n");
+				break;
+			}
+			n += sprintf(&buf[n], ",%04X", i);
+		}
+	buf[n++] = '\n';
+	return n;
+}
+#else
+#define print_cpu_modalias	arch_print_cpu_modalias
+#endif
+
+static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf) {
+		print_cpu_modalias(NULL, NULL, buf);
+		add_uevent_var(env, "MODALIAS=%s", buf);
+		kfree(buf);
+	}
+	return 0;
+}
+#endif
+
 /*
  * register_cpu - Setup a sysfs device for a CPU.
  * @cpu - cpu->hotpluggable field set to 1 will generate a control file in
@@ -277,8 +319,8 @@ int __cpuinit register_cpu(struct cpu *cpu, int num)
 	cpu->dev.id = num;
 	cpu->dev.bus = &cpu_subsys;
 	cpu->dev.release = cpu_device_release;
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-	cpu->dev.bus->uevent = arch_cpu_uevent;
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+	cpu->dev.bus->uevent = cpu_uevent;
 #endif
 	error = device_register(&cpu->dev);
 	if (!error && cpu->hotpluggable)
@@ -307,8 +349,8 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
 
 static struct attribute *cpu_root_attrs[] = {
@@ -321,7 +363,7 @@ static struct attribute *cpu_root_attrs[] = {
 	&cpu_attrs[2].attr.attr,
 	&dev_attr_kernel_max.attr,
 	&dev_attr_offline.attr,
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
 	NULL
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 35fa36898916..8a8d611f2021 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex);
 static LIST_HEAD(deferred_probe_pending_list);
 static LIST_HEAD(deferred_probe_active_list);
 static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
 
 /**
  * deferred_probe_work_func() - Retry probing devices in the active list.
@@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false;
  * This functions moves all devices from the pending list to the active
  * list and schedules the deferred probe workqueue to process them.  It
  * should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
  */
 static void driver_deferred_probe_trigger(void)
 {
@@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void)
 	 * into the active list so they can be retried by the workqueue
 	 */
 	mutex_lock(&deferred_probe_mutex);
+	atomic_inc(&deferred_trigger_count);
 	list_splice_tail_init(&deferred_probe_pending_list,
 			      &deferred_probe_active_list);
 	mutex_unlock(&deferred_probe_mutex);
@@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
 static int really_probe(struct device *dev, struct device_driver *drv)
 {
 	int ret = 0;
+	int local_trigger_count = atomic_read(&deferred_trigger_count);
 
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
@@ -310,6 +324,9 @@ probe_failed:
 		/* Driver requested deferred probing */
 		dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
 		driver_deferred_probe_add(dev);
+		/* Did a trigger occur while probing? Need to re-trigger if yes */
+		if (local_trigger_count != atomic_read(&deferred_trigger_count))
+			driver_deferred_probe_trigger();
 	} else if (ret != -ENODEV && ret != -ENXIO) {
 		/* driver matched but the probe failed */
 		printk(KERN_WARNING
@@ -499,7 +516,7 @@ static void __device_release_driver(struct device *dev)
 						     BUS_NOTIFY_UNBIND_DRIVER,
 						     dev);
 
-		pm_runtime_put(dev);
+		pm_runtime_put_sync(dev);
 
 		if (dev->bus && dev->bus->remove)
 			dev->bus->remove(dev);
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 507379e7b763..545c4de412c3 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -91,7 +91,8 @@ static __always_inline struct devres * alloc_dr(dr_release_t release,
 	if (unlikely(!dr))
 		return NULL;
 
-	memset(dr, 0, tot_size);
+	memset(dr, 0, offsetof(struct devres, data));
+
 	INIT_LIST_HEAD(&dr->node.entry);
 	dr->node.release = release;
 	return dr;
@@ -110,7 +111,7 @@ void * __devres_alloc(dr_release_t release, size_t size, gfp_t gfp,
 {
 	struct devres *dr;
 
-	dr = alloc_dr(release, size, gfp);
+	dr = alloc_dr(release, size, gfp | __GFP_ZERO);
 	if (unlikely(!dr))
 		return NULL;
 	set_node_dbginfo(&dr->node, name, size);
@@ -135,7 +136,7 @@ void * devres_alloc(dr_release_t release, size_t size, gfp_t gfp)
 {
 	struct devres *dr;
 
-	dr = alloc_dr(release, size, gfp);
+	dr = alloc_dr(release, size, gfp | __GFP_ZERO);
 	if (unlikely(!dr))
 		return NULL;
 	return dr->data;
@@ -745,58 +746,62 @@ void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
 EXPORT_SYMBOL_GPL(devm_remove_action);
 
 /*
- * Managed kzalloc/kfree
+ * Managed kmalloc/kfree
  */
-static void devm_kzalloc_release(struct device *dev, void *res)
+static void devm_kmalloc_release(struct device *dev, void *res)
 {
 	/* noop */
 }
 
-static int devm_kzalloc_match(struct device *dev, void *res, void *data)
+static int devm_kmalloc_match(struct device *dev, void *res, void *data)
 {
 	return res == data;
 }
 
 /**
- * devm_kzalloc - Resource-managed kzalloc
+ * devm_kmalloc - Resource-managed kmalloc
  * @dev: Device to allocate memory for
  * @size: Allocation size
  * @gfp: Allocation gfp flags
  *
- * Managed kzalloc.  Memory allocated with this function is
+ * Managed kmalloc.  Memory allocated with this function is
  * automatically freed on driver detach.  Like all other devres
  * resources, guaranteed alignment is unsigned long long.
  *
  * RETURNS:
  * Pointer to allocated memory on success, NULL on failure.
  */
-void * devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 {
 	struct devres *dr;
 
 	/* use raw alloc_dr for kmalloc caller tracing */
-	dr = alloc_dr(devm_kzalloc_release, size, gfp);
+	dr = alloc_dr(devm_kmalloc_release, size, gfp);
 	if (unlikely(!dr))
 		return NULL;
 
+	/*
+	 * This is named devm_kzalloc_release for historical reasons
+	 * The initial implementation did not support kmalloc, only kzalloc
+	 */
 	set_node_dbginfo(&dr->node, "devm_kzalloc_release", size);
 	devres_add(dev, dr->data);
 	return dr->data;
 }
-EXPORT_SYMBOL_GPL(devm_kzalloc);
+EXPORT_SYMBOL_GPL(devm_kmalloc);
 
 /**
  * devm_kfree - Resource-managed kfree
  * @dev: Device this memory belongs to
  * @p: Memory to free
  *
- * Free memory allocated with devm_kzalloc().
+ * Free memory allocated with devm_kmalloc().
  */
 void devm_kfree(struct device *dev, void *p)
 {
 	int rc;
 
-	rc = devres_destroy(dev, devm_kzalloc_release, devm_kzalloc_match, p);
+	rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, p);
 	WARN_ON(rc);
 }
 EXPORT_SYMBOL_GPL(devm_kfree);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 01e21037d8fe..00a565676583 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1021,6 +1021,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	if (!firmware_p)
 		return -EINVAL;
 
+	if (!name || name[0] == '\0')
+		return -EINVAL;
+
 	ret = _request_firmware_prepare(&fw, name, device);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 7072404c8b6d..723b4254b13b 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -9,6 +9,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -2178,3 +2179,291 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ *  - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ *  - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ *    index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ *         into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+	struct list_head link;
+	struct device_node *node;
+	genpd_xlate_t xlate;
+	void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	if (genpdspec->args_count != 0)
+		return ERR_PTR(-EINVAL);
+	return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	struct genpd_onecell_data *genpd_data = data;
+	unsigned int idx = genpdspec->args[0];
+
+	if (genpdspec->args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	if (idx >= genpd_data->num_domains) {
+		pr_err("%s: invalid domain index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!genpd_data->domains[idx])
+		return ERR_PTR(-ENOENT);
+
+	return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data)
+{
+	struct of_genpd_provider *cp;
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->node = of_node_get(np);
+	cp->data = data;
+	cp->xlate = xlate;
+
+	mutex_lock(&of_genpd_mutex);
+	list_add(&cp->link, &of_genpd_providers);
+	mutex_unlock(&of_genpd_mutex);
+	pr_debug("Added domain provider from %s\n", np->full_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+	struct of_genpd_provider *cp;
+
+	mutex_lock(&of_genpd_mutex);
+	list_for_each_entry(cp, &of_genpd_providers, link) {
+		if (cp->node == np) {
+			list_del(&cp->link);
+			of_node_put(cp->node);
+			kfree(cp);
+			break;
+		}
+	}
+	mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+static struct generic_pm_domain *of_genpd_get_from_provider(
+					struct of_phandle_args *genpdspec)
+{
+	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+	struct of_genpd_provider *provider;
+
+	mutex_lock(&of_genpd_mutex);
+
+	/* Check if we have such a provider in our array */
+	list_for_each_entry(provider, &of_genpd_providers, link) {
+		if (provider->node == genpdspec->np)
+			genpd = provider->xlate(genpdspec, provider->data);
+		if (!IS_ERR(genpd))
+			break;
+	}
+
+	mutex_unlock(&of_genpd_mutex);
+
+	return genpd;
+}
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct generic_pm_domain *pd = NULL, *gpd;
+	int ret = 0;
+
+	if (!dev->pm_domain)
+		return;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (&gpd->domain == dev->pm_domain) {
+			pd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	if (!pd)
+		return;
+
+	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_remove_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to remove from PM domain %s: %d",
+			pd->name, ret);
+		return;
+	}
+
+	/* Check if PM domain can be powered off after removing this device. */
+	genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+	struct of_phandle_args pd_args;
+	struct generic_pm_domain *pd;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+					"#power-domain-cells", 0, &pd_args);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			return ret;
+
+		/*
+		 * Try legacy Samsung-specific bindings
+		 * (for backwards compatibility of DT ABI)
+		 */
+		pd_args.args_count = 0;
+		pd_args.np = of_parse_phandle(dev->of_node,
+						"samsung,power-domain", 0);
+		if (!pd_args.np)
+			return -ENOENT;
+	}
+
+	pd = of_genpd_get_from_provider(&pd_args);
+	if (IS_ERR(pd)) {
+		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+			__func__, PTR_ERR(pd));
+		of_node_put(dev->of_node);
+		return PTR_ERR(pd);
+	}
+
+	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_add_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to add to PM domain %s: %d",
+			pd->name, ret);
+		of_node_put(dev->of_node);
+		return ret;
+	}
+
+	dev->pm_domain->detach = genpd_dev_pm_detach;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 5a9b6569dd74..220ec3a3ca75 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -28,6 +28,8 @@
 #include <linux/sched.h>
 #include <linux/async.h>
 #include <linux/suspend.h>
+#include <trace/events/power.h>
+#include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
 #include "../base.h"
 #include "power.h"
@@ -713,6 +715,8 @@ void dpm_resume(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, NULL);
+
+	cpufreq_resume();
 }
 
 /**
@@ -1177,6 +1181,8 @@ int dpm_suspend(pm_message_t state)
 
 	might_sleep();
 
+	cpufreq_suspend();
+
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 975719bc3450..b41994fd8460 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -460,16 +460,20 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 {
 	struct rb_node *next;
 	struct regmap_range_node *range_node;
+	const char *devname = "dummy";
 
 	INIT_LIST_HEAD(&map->debugfs_off_cache);
 	mutex_init(&map->cache_lock);
 
+	if (map->dev)
+		devname = dev_name(map->dev);
+
 	if (name) {
 		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
-					      dev_name(map->dev), name);
+					      devname, name);
 		name = map->debugfs_name;
 	} else {
-		name = dev_name(map->dev);
+		name = devname;
 	}
 
 	map->debugfs = debugfs_create_dir(name, regmap_debugfs_root);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index d0c81d1f409c..6a66f0b7d3d4 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -114,7 +114,7 @@ bool regmap_readable(struct regmap *map, unsigned int reg)
 
 bool regmap_volatile(struct regmap *map, unsigned int reg)
 {
-	if (!regmap_readable(map, reg))
+	if (!map->format.format_write && !regmap_readable(map, reg))
 		return false;
 
 	if (map->volatile_reg)
@@ -1177,7 +1177,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 	}
 
 #ifdef LOG_DEVICE
-	if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+	if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
@@ -1437,7 +1437,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
 	ret = map->reg_read(context, reg, val);
 	if (ret == 0) {
 #ifdef LOG_DEVICE
-		if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+		if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index ae989c57cd5e..bcd19886fa1a 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -40,8 +40,7 @@
 static ssize_t show_##name(struct device *dev,			\
 		struct device_attribute *attr, char *buf)	\
 {								\
-	unsigned int cpu = dev->id;				\
-	return sprintf(buf, "%d\n", topology_##name(cpu));	\
+	return sprintf(buf, "%d\n", topology_##name(dev->id));	\
 }
 
 #if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index fc803ecbbce4..31262732db23 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -899,7 +899,7 @@ bio_pageinc(struct bio *bio)
 		 * but this has never been seen here.
 		 */
 		if (unlikely(PageCompound(page)))
-			if (compound_trans_head(page) != page) {
+			if (compound_head(page) != page) {
 				pr_crit("page tail used for block I/O\n");
 				BUG();
 			}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 9bf4371755f2..d91f1a56e861 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -545,7 +545,7 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 
 	mutex_lock(&brd_devices_mutex);
 	brd = brd_init_one(MINOR(dev) >> part_shift);
-	kobj = brd ? get_disk(brd->brd_disk) : ERR_PTR(-ENOMEM);
+	kobj = brd ? get_disk(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
 	*part = 0;
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 62b6c2cc80b5..90a4e6b940ac 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
 	int err;
 	u32 cp;
 
+	memset(&arg64, 0, sizeof(arg64));
 	err = 0;
 	err |=
 	    copy_from_user(&arg64.LUN_info, &arg32->LUN_info,
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 639d26b90b91..2b9440384536 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -1193,6 +1193,7 @@ out_passthru:
 		ida_pci_info_struct pciinfo;
 
 		if (!arg) return -EINVAL;
+		memset(&pciinfo, 0, sizeof(pciinfo));
 		pciinfo.bus = host->pci_dev->bus->number;
 		pciinfo.dev_fn = host->pci_dev->devfn;
 		pciinfo.board_id = host->board_id;
diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c
index 89c497c630b4..04a14e0f8878 100644
--- a/drivers/block/drbd/drbd_interval.c
+++ b/drivers/block/drbd/drbd_interval.c
@@ -79,6 +79,7 @@ bool
 drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 {
 	struct rb_node **new = &root->rb_node, *parent = NULL;
+	sector_t this_end = this->sector + (this->size >> 9);
 
 	BUG_ON(!IS_ALIGNED(this->size, 512));
 
@@ -87,6 +88,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			rb_entry(*new, struct drbd_interval, rb);
 
 		parent = *new;
+		if (here->end < this_end)
+			here->end = this_end;
 		if (this->sector < here->sector)
 			new = &(*new)->rb_left;
 		else if (this->sector > here->sector)
@@ -99,6 +102,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			return false;
 	}
 
+	this->end = this_end;
 	rb_link_node(&this->rb, parent, new);
 	rb_insert_augmented(&this->rb, root, &augment_callbacks);
 	return true;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 9e3f441e7e84..9c37f3d896a2 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -514,6 +514,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn)
 	struct task_struct *opa;
 
 	kref_get(&tconn->kref);
+	/* We may just have force_sig()'ed this thread
+	 * to get it out of some blocking network function.
+	 * Clear signals; otherwise kthread_run(), which internally uses
+	 * wait_on_completion_killable(), will mistake our pending signal
+	 * for a new fatal signal and fail. */
+	flush_signals(current);
 	opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n");
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 04ceb7e2fadd..eb3575b3fbf0 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3053,7 +3053,10 @@ static int raw_cmd_copyout(int cmd, void __user *param,
 	int ret;
 
 	while (ptr) {
-		ret = copy_to_user(param, ptr, sizeof(*ptr));
+		struct floppy_raw_cmd cmd = *ptr;
+		cmd.next = NULL;
+		cmd.kernel_data = NULL;
+		ret = copy_to_user(param, &cmd, sizeof(cmd));
 		if (ret)
 			return -EFAULT;
 		param += sizeof(struct floppy_raw_cmd);
@@ -3107,10 +3110,11 @@ loop:
 		return -ENOMEM;
 	*rcmd = ptr;
 	ret = copy_from_user(ptr, param, sizeof(*ptr));
-	if (ret)
-		return -EFAULT;
 	ptr->next = NULL;
 	ptr->buffer_length = 0;
+	ptr->kernel_data = NULL;
+	if (ret)
+		return -EFAULT;
 	param += sizeof(struct floppy_raw_cmd);
 	if (ptr->cmd_count > 33)
 			/* the command may now also take up the space
@@ -3126,7 +3130,6 @@ loop:
 	for (i = 0; i < 16; i++)
 		ptr->reply[i] = 0;
 	ptr->resultcode = 0;
-	ptr->kernel_data = NULL;
 
 	if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) {
 		if (ptr->length <= 0)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d92d50fd84b7..4a8116547873 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -894,13 +894,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	bio_list_init(&lo->lo_bio_list);
 
-	/*
-	 * set queue make_request_fn, and add limits based on lower level
-	 * device
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
-	lo->lo_queue->queuedata = lo;
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -1618,6 +1611,8 @@ static int loop_add(struct loop_device **l, int i)
 	if (!lo)
 		goto out;
 
+	lo->lo_state = Lo_unbound;
+
 	/* allocate id, if @id >= 0, we're requesting that specific id */
 	if (i >= 0) {
 		err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
@@ -1633,7 +1628,13 @@ static int loop_add(struct loop_device **l, int i)
 	err = -ENOMEM;
 	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!lo->lo_queue)
-		goto out_free_dev;
+		goto out_free_idr;
+
+	/*
+	 * set queue make_request_fn
+	 */
+	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue->queuedata = lo;
 
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
@@ -1678,6 +1679,8 @@ static int loop_add(struct loop_device **l, int i)
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
+out_free_idr:
+	idr_remove(&loop_index_idr, i);
 out_free_dev:
 	kfree(lo);
 out:
@@ -1741,7 +1744,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 	if (err < 0)
 		err = loop_add(&lo, MINOR(dev) >> part_shift);
 	if (err < 0)
-		kobj = ERR_PTR(err);
+		kobj = NULL;
 	else
 		kobj = get_disk(lo->lo_disk);
 	mutex_unlock(&loop_index_mutex);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 20dd52a2f92f..0d94e09221d9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -1493,6 +1493,37 @@ static inline void ata_swap_string(u16 *buf, unsigned int len)
 		be16_to_cpus(&buf[i]);
 }
 
+static void mtip_set_timeout(struct driver_data *dd,
+					struct host_to_dev_fis *fis,
+					unsigned int *timeout, u8 erasemode)
+{
+	switch (fis->command) {
+	case ATA_CMD_DOWNLOAD_MICRO:
+		*timeout = 120000; /* 2 minutes */
+		break;
+	case ATA_CMD_SEC_ERASE_UNIT:
+	case 0xFC:
+		if (erasemode)
+			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+		else
+			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
+		break;
+	case ATA_CMD_STANDBYNOW1:
+		*timeout = 120000;  /* 2 minutes */
+		break;
+	case 0xF7:
+	case 0xFA:
+		*timeout = 60000;  /* 60 seconds */
+		break;
+	case ATA_CMD_SMART:
+		*timeout = 15000;  /* 15 seconds */
+		break;
+	default:
+		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
+		break;
+	}
+}
+
 /*
  * Request the device identity information.
  *
@@ -1602,6 +1633,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	int rv;
 	struct host_to_dev_fis	fis;
 	unsigned long start;
+	unsigned int timeout;
 
 	/* Build the FIS. */
 	memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -1609,6 +1641,8 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	fis.opts	= 1 << 7;
 	fis.command	= ATA_CMD_STANDBYNOW1;
 
+	mtip_set_timeout(port->dd, &fis, &timeout, 0);
+
 	start = jiffies;
 	rv = mtip_exec_internal_command(port,
 					&fis,
@@ -1617,7 +1651,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 					0,
 					0,
 					GFP_ATOMIC,
-					15000);
+					timeout);
 	dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
 			jiffies_to_msecs(jiffies - start));
 	if (rv)
@@ -2156,36 +2190,6 @@ static unsigned int implicit_sector(unsigned char command,
 	}
 	return rv;
 }
-static void mtip_set_timeout(struct driver_data *dd,
-					struct host_to_dev_fis *fis,
-					unsigned int *timeout, u8 erasemode)
-{
-	switch (fis->command) {
-	case ATA_CMD_DOWNLOAD_MICRO:
-		*timeout = 120000; /* 2 minutes */
-		break;
-	case ATA_CMD_SEC_ERASE_UNIT:
-	case 0xFC:
-		if (erasemode)
-			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
-		else
-			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
-		break;
-	case ATA_CMD_STANDBYNOW1:
-		*timeout = 120000;  /* 2 minutes */
-		break;
-	case 0xF7:
-	case 0xFA:
-		*timeout = 60000;  /* 60 seconds */
-		break;
-	case ATA_CMD_SMART:
-		*timeout = 15000;  /* 15 seconds */
-		break;
-	default:
-		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
-		break;
-	}
-}
 
 /*
  * Executes a taskfile
@@ -4040,6 +4044,7 @@ skip_create_disk:
 	blk_queue_max_hw_sectors(dd->queue, 0xffff);
 	blk_queue_max_segment_size(dd->queue, 0x400000);
 	blk_queue_io_min(dd->queue, 4096);
+	blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
 
 	/*
 	 * write back cache is not supported in the device. FUA depends on
@@ -4283,6 +4288,57 @@ static DEFINE_HANDLER(5);
 static DEFINE_HANDLER(6);
 static DEFINE_HANDLER(7);
 
+static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev)
+{
+	int pos;
+	unsigned short pcie_dev_ctrl;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	if (pos) {
+		pci_read_config_word(pdev,
+			pos + PCI_EXP_DEVCTL,
+			&pcie_dev_ctrl);
+		if (pcie_dev_ctrl & (1 << 11) ||
+		    pcie_dev_ctrl & (1 << 4)) {
+			dev_info(&dd->pdev->dev,
+				"Disabling ERO/No-Snoop on bridge device %04x:%04x\n",
+					pdev->vendor, pdev->device);
+			pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN |
+						PCI_EXP_DEVCTL_RELAX_EN);
+			pci_write_config_word(pdev,
+				pos + PCI_EXP_DEVCTL,
+				pcie_dev_ctrl);
+		}
+	}
+}
+
+static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev)
+{
+	/*
+	 * This workaround is specific to AMD/ATI chipset with a PCI upstream
+	 * device with device id 0x5aXX
+	 */
+	if (pdev->bus && pdev->bus->self) {
+		if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI &&
+		    ((pdev->bus->self->device & 0xff00) == 0x5a00)) {
+			mtip_disable_link_opts(dd, pdev->bus->self);
+		} else {
+			/* Check further up the topology */
+			struct pci_dev *parent_dev = pdev->bus->self;
+			if (parent_dev->bus &&
+				parent_dev->bus->parent &&
+				parent_dev->bus->parent->self &&
+				parent_dev->bus->parent->self->vendor ==
+					 PCI_VENDOR_ID_ATI &&
+				(parent_dev->bus->parent->self->device &
+					0xff00) == 0x5a00) {
+				mtip_disable_link_opts(dd,
+					parent_dev->bus->parent->self);
+			}
+		}
+	}
+}
+
 /*
  * Called for each supported PCI device detected.
  *
@@ -4434,6 +4490,8 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 		goto block_initialize_err;
 	}
 
+	mtip_fix_ero_nosnoop(dd, pdev);
+
 	/* Initialize the block layer. */
 	rv = mtip_block_initialize(dd);
 	if (rv < 0) {
@@ -4726,13 +4784,13 @@ static int __init mtip_init(void)
  */
 static void __exit mtip_exit(void)
 {
-	debugfs_remove_recursive(dfs_parent);
-
 	/* Release the allocated major block device number. */
 	unregister_blkdev(mtip_major, MTIP_DRV_NAME);
 
 	/* Unregister the PCI driver. */
 	pci_unregister_driver(&mtip_pci_driver);
+
+	debugfs_remove_recursive(dfs_parent);
 }
 
 MODULE_AUTHOR("Micron Technology, Inc");
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 8c7421af8f15..9951e66b8502 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -937,12 +937,14 @@ static const char *rbd_dev_v1_snap_name(struct rbd_device *rbd_dev,
 					u64 snap_id)
 {
 	u32 which;
+	const char *snap_name;
 
 	which = rbd_dev_snap_index(rbd_dev, snap_id);
 	if (which == BAD_SNAP_INDEX)
-		return NULL;
+		return ERR_PTR(-ENOENT);
 
-	return _rbd_dev_v1_snap_name(rbd_dev, which);
+	snap_name = _rbd_dev_v1_snap_name(rbd_dev, which);
+	return snap_name ? snap_name : ERR_PTR(-ENOMEM);
 }
 
 static const char *rbd_snap_name(struct rbd_device *rbd_dev, u64 snap_id)
@@ -1126,6 +1128,7 @@ static void zero_bio_chain(struct bio *chain, int start_ofs)
 				buf = bvec_kmap_irq(bv, &flags);
 				memset(buf + remainder, 0,
 				       bv->bv_len - remainder);
+				flush_dcache_page(bv->bv_page);
 				bvec_kunmap_irq(buf, &flags);
 			}
 			pos += bv->bv_len;
@@ -1158,6 +1161,7 @@ static void zero_pages(struct page **pages, u64 offset, u64 end)
 		local_irq_save(flags);
 		kaddr = kmap_atomic(*page);
 		memset(kaddr + page_offset, 0, length);
+		flush_dcache_page(*page);
 		kunmap_atomic(kaddr);
 		local_irq_restore(flags);
 
@@ -1381,6 +1385,14 @@ static bool obj_request_exists_test(struct rbd_obj_request *obj_request)
 	return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
 }
 
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+	return obj_request->img_offset <
+	    round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
@@ -1397,6 +1409,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+	dout("%s: img %p (was %d)\n", __func__, img_request,
+	     atomic_read(&img_request->kref.refcount));
+	kref_get(&img_request->kref);
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request);
 static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
@@ -2150,6 +2169,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request)
 	img_request->next_completion = which;
 out:
 	spin_unlock_irq(&img_request->completion_lock);
+	rbd_img_request_put(img_request);
 
 	if (!more)
 		rbd_img_request_complete(img_request);
@@ -2171,9 +2191,9 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 	struct rbd_obj_request *obj_request = NULL;
 	struct rbd_obj_request *next_obj_request;
 	bool write_request = img_request_write_test(img_request);
-	struct bio *bio_list;
+	struct bio *bio_list = 0;
 	unsigned int bio_offset = 0;
-	struct page **pages;
+	struct page **pages = 0;
 	u64 img_offset;
 	u64 resid;
 	u16 opcode;
@@ -2211,6 +2231,11 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		rbd_segment_name_free(object_name);
 		if (!obj_request)
 			goto out_unwind;
+		/*
+		 * set obj_request->img_request before creating the
+		 * osd_request so that it gets the right snapc
+		 */
+		rbd_img_obj_request_add(img_request, obj_request);
 
 		if (type == OBJ_REQUEST_BIO) {
 			unsigned int clone_size;
@@ -2241,6 +2266,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 			goto out_partial;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
+		rbd_img_request_get(img_request);
 
 		osd_req_op_extent_init(osd_req, 0, opcode, offset, length,
 						0, 0);
@@ -2252,11 +2278,6 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 					obj_request->pages, length,
 					offset & ~PAGE_MASK, false, false);
 
-		/*
-		 * set obj_request->img_request before formatting
-		 * the osd_request so that it gets the right snapc
-		 */
-		rbd_img_obj_request_add(img_request, obj_request);
 		if (write_request)
 			rbd_osd_req_format_write(obj_request);
 		else
@@ -2274,7 +2295,7 @@ out_partial:
 	rbd_obj_request_put(obj_request);
 out_unwind:
 	for_each_obj_request_safe(img_request, obj_request, next_obj_request)
-		rbd_obj_request_put(obj_request);
+		rbd_img_obj_request_del(img_request, obj_request);
 
 	return -ENOMEM;
 }
@@ -2669,7 +2690,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	 */
 	if (!img_request_write_test(img_request) ||
 		!img_request_layered_test(img_request) ||
-		rbd_dev->parent_overlap <= obj_request->img_offset ||
+		!obj_request_overlaps_parent(obj_request) ||
 		((known = obj_request_known_test(obj_request)) &&
 			obj_request_exists_test(obj_request))) {
 
@@ -2817,7 +2838,7 @@ out_err:
 	obj_request_done_set(obj_request);
 }
 
-static int rbd_obj_notify_ack(struct rbd_device *rbd_dev, u64 notify_id)
+static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
 {
 	struct rbd_obj_request *obj_request;
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
@@ -2832,16 +2853,17 @@ static int rbd_obj_notify_ack(struct rbd_device *rbd_dev, u64 notify_id)
 	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
 	if (!obj_request->osd_req)
 		goto out;
-	obj_request->callback = rbd_obj_request_put;
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_NOTIFY_ACK,
 					notify_id, 0, 0);
 	rbd_osd_req_format_read(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
-out:
 	if (ret)
-		rbd_obj_request_put(obj_request);
+		goto out;
+	ret = rbd_obj_request_wait(obj_request);
+out:
+	rbd_obj_request_put(obj_request);
 
 	return ret;
 }
@@ -2861,7 +2883,7 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 	if (ret)
 		rbd_warn(rbd_dev, ": header refresh error (%d)\n", ret);
 
-	rbd_obj_notify_ack(rbd_dev, notify_id);
+	rbd_obj_notify_ack_sync(rbd_dev, notify_id);
 }
 
 /*
@@ -3205,7 +3227,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	page_count = (u32) calc_pages_for(offset, length);
 	pages = ceph_alloc_page_vector(page_count, GFP_KERNEL);
 	if (IS_ERR(pages))
-		ret = PTR_ERR(pages);
+		return PTR_ERR(pages);
 
 	ret = -ENOMEM;
 	obj_request = rbd_obj_request_create(object_name, offset, length,
@@ -3333,6 +3355,31 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev)
 		clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
 }
 
+static void rbd_dev_update_size(struct rbd_device *rbd_dev)
+{
+	sector_t size;
+	bool removing;
+
+	/*
+	 * Don't hold the lock while doing disk operations,
+	 * or lock ordering will conflict with the bdev mutex via:
+	 * rbd_add() -> blkdev_get() -> rbd_open()
+	 */
+	spin_lock_irq(&rbd_dev->lock);
+	removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
+	spin_unlock_irq(&rbd_dev->lock);
+	/*
+	 * If the device is being removed, rbd_dev->disk has
+	 * been destroyed, so don't try to update its size
+	 */
+	if (!removing) {
+		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
+		dout("setting size to %llu sectors", (unsigned long long)size);
+		set_capacity(rbd_dev->disk, size);
+		revalidate_disk(rbd_dev->disk);
+	}
+}
+
 static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 {
 	u64 mapping_size;
@@ -3351,12 +3398,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 	rbd_exists_validate(rbd_dev);
 	mutex_unlock(&ctl_mutex);
 	if (mapping_size != rbd_dev->mapping.size) {
-		sector_t size;
-
-		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
-		dout("setting size to %llu sectors", (unsigned long long)size);
-		set_capacity(rbd_dev->disk, size);
-		revalidate_disk(rbd_dev->disk);
+		rbd_dev_update_size(rbd_dev);
 	}
 
 	return ret;
@@ -3710,12 +3752,14 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
 	if (ret < sizeof (size_buf))
 		return -ERANGE;
 
-	if (order)
+	if (order) {
 		*order = size_buf.order;
+		dout("  order %u", (unsigned int)*order);
+	}
 	*snap_size = le64_to_cpu(size_buf.size);
 
-	dout("  snap_id 0x%016llx order = %u, snap_size = %llu\n",
-		(unsigned long long)snap_id, (unsigned int)*order,
+	dout("  snap_id 0x%016llx snap_size = %llu\n",
+		(unsigned long long)snap_id,
 		(unsigned long long)*snap_size);
 
 	return 0;
@@ -4030,8 +4074,13 @@ static u64 rbd_v2_snap_id_by_name(struct rbd_device *rbd_dev, const char *name)
 
 		snap_id = snapc->snaps[which];
 		snap_name = rbd_dev_v2_snap_name(rbd_dev, snap_id);
-		if (IS_ERR(snap_name))
-			break;
+		if (IS_ERR(snap_name)) {
+			/* ignore no-longer existing snapshots */
+			if (PTR_ERR(snap_name) == -ENOENT)
+				continue;
+			else
+				break;
+		}
 		found = !strcmp(name, snap_name);
 		kfree(snap_name);
 	}
@@ -4110,8 +4159,8 @@ static int rbd_dev_spec_update(struct rbd_device *rbd_dev)
 	/* Look up the snapshot name, and make a copy */
 
 	snap_name = rbd_snap_name(rbd_dev, spec->snap_id);
-	if (!snap_name) {
-		ret = -ENOMEM;
+	if (IS_ERR(snap_name)) {
+		ret = PTR_ERR(snap_name);
 		goto out_err;
 	}
 
@@ -5059,23 +5108,6 @@ err_out_module:
 	return (ssize_t)rc;
 }
 
-static struct rbd_device *__rbd_get_dev(unsigned long dev_id)
-{
-	struct list_head *tmp;
-	struct rbd_device *rbd_dev;
-
-	spin_lock(&rbd_dev_list_lock);
-	list_for_each(tmp, &rbd_dev_list) {
-		rbd_dev = list_entry(tmp, struct rbd_device, node);
-		if (rbd_dev->dev_id == dev_id) {
-			spin_unlock(&rbd_dev_list_lock);
-			return rbd_dev;
-		}
-	}
-	spin_unlock(&rbd_dev_list_lock);
-	return NULL;
-}
-
 static void rbd_dev_device_release(struct device *dev)
 {
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
@@ -5120,8 +5152,10 @@ static ssize_t rbd_remove(struct bus_type *bus,
 			  size_t count)
 {
 	struct rbd_device *rbd_dev = NULL;
-	int target_id;
+	struct list_head *tmp;
+	int dev_id;
 	unsigned long ul;
+	bool already = false;
 	int ret;
 
 	ret = strict_strtoul(buf, 10, &ul);
@@ -5129,30 +5163,51 @@ static ssize_t rbd_remove(struct bus_type *bus,
 		return ret;
 
 	/* convert to int; abort if we lost anything in the conversion */
-	target_id = (int) ul;
-	if (target_id != ul)
+	dev_id = (int)ul;
+	if (dev_id != ul)
 		return -EINVAL;
 
 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
 
-	rbd_dev = __rbd_get_dev(target_id);
-	if (!rbd_dev) {
-		ret = -ENOENT;
-		goto done;
+	ret = -ENOENT;
+	spin_lock(&rbd_dev_list_lock);
+	list_for_each(tmp, &rbd_dev_list) {
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_dev->dev_id == dev_id) {
+			ret = 0;
+			break;
+		}
 	}
-
-	spin_lock_irq(&rbd_dev->lock);
-	if (rbd_dev->open_count)
-		ret = -EBUSY;
-	else
-		set_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
-	spin_unlock_irq(&rbd_dev->lock);
-	if (ret < 0)
+	if (!ret) {
+		spin_lock_irq(&rbd_dev->lock);
+		if (rbd_dev->open_count)
+			ret = -EBUSY;
+		else
+			already = test_and_set_bit(RBD_DEV_FLAG_REMOVING,
+							&rbd_dev->flags);
+		spin_unlock_irq(&rbd_dev->lock);
+	}
+	spin_unlock(&rbd_dev_list_lock);
+	if (ret < 0 || already)
 		goto done;
-	rbd_bus_del_dev(rbd_dev);
+
 	ret = rbd_dev_header_watch_sync(rbd_dev, false);
 	if (ret)
 		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
+
+	/*
+	 * flush remaining watch callbacks - these must be complete
+	 * before the osd_client is shutdown
+	 */
+	dout("%s: flushing notifies", __func__);
+	ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
+	/*
+	 * Don't free anything from rbd_dev->disk until after all
+	 * notifies are completely processed. Otherwise
+	 * rbd_bus_del_dev() will race with rbd_watch_cb(), resulting
+	 * in a potential use after free of rbd_dev->disk or rbd_dev.
+	 */
+	rbd_bus_del_dev(rbd_dev);
 	rbd_dev_image_release(rbd_dev);
 	module_put(THIS_MODULE);
 	ret = count;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb6963d..0ebadf93b6c5 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/genhd.h>
+#include <linux/cdrom.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -22,8 +23,8 @@
 
 #define DRV_MODULE_NAME		"sunvdc"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"1.0"
-#define DRV_MODULE_RELDATE	"June 25, 2007"
+#define DRV_MODULE_VERSION	"1.1"
+#define DRV_MODULE_RELDATE	"February 13, 2013"
 
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
-#define VDC_TX_RING_SIZE	256
+#define VDC_TX_RING_SIZE	512
 
 #define WAITING_FOR_LINK_UP	0x01
 #define WAITING_FOR_TX_SPACE	0x02
@@ -65,11 +66,9 @@ struct vdc_port {
 	u64			operations;
 	u32			vdisk_size;
 	u8			vdisk_type;
+	u8			vdisk_mtype;
 
 	char			disk_name[32];
-
-	struct vio_disk_geom	geom;
-	struct vio_disk_vtoc	label;
 };
 
 static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
@@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
 
 /* Ordered from largest major to lowest */
 static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 1 },
 	{ .major = 1, .minor = 0 },
 };
 
+static inline int vdc_version_supported(struct vdc_port *port,
+					u16 major, u16 minor)
+{
+	return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
 #define VDCBLK_NAME	"vdisk"
 static int vdc_major;
 #define PARTITION_SHIFT	3
@@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
 static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct vdc_port *port = disk->private_data;
+	sector_t nsect = get_capacity(disk);
+	sector_t cylinders = nsect;
 
-	geo->heads = (u8) port->geom.num_hd;
-	geo->sectors = (u8) port->geom.num_sec;
-	geo->cylinders = port->geom.num_cyl;
+	geo->heads = 0xff;
+	geo->sectors = 0x3f;
+	sector_div(cylinders, geo->heads * geo->sectors);
+	geo->cylinders = cylinders;
+	if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+		geo->cylinders = 0xffff;
 
 	return 0;
 }
 
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+		     unsigned command, unsigned long argument)
+{
+	int i;
+	struct gendisk *disk;
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		pr_debug(PFX "Multisession CDs not supported\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY:
+		disk = bdev->bd_disk;
+
+		if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+			return 0;
+		return -EINVAL;
+
+	default:
+		pr_debug(PFX "ioctl %08x not supported\n", command);
+		return -EINVAL;
+	}
+}
+
 static const struct block_device_operations vdc_fops = {
 	.owner		= THIS_MODULE,
 	.getgeo		= vdc_getgeo,
+	.ioctl		= vdc_ioctl,
 };
 
 static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 	struct vio_disk_attr_info *pkt = arg;
 
 	viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
-	       "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+	       "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
 	       pkt->tag.stype, pkt->operations,
-	       pkt->vdisk_size, pkt->vdisk_type,
+	       pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
 	       pkt->xfer_mode, pkt->vdisk_block_size,
 	       pkt->max_xfer_size);
 
@@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 		}
 
 		port->operations = pkt->operations;
-		port->vdisk_size = pkt->vdisk_size;
 		port->vdisk_type = pkt->vdisk_type;
+		if (vdc_version_supported(port, 1, 1)) {
+			port->vdisk_size = pkt->vdisk_size;
+			port->vdisk_mtype = pkt->vdisk_mtype;
+		}
 		if (pkt->max_xfer_size < port->max_xfer_size)
 			port->max_xfer_size = pkt->max_xfer_size;
 		port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
-	if (blk_queue_stopped(port->disk->queue))
+	/* restart blk queue when ring is half emptied */
+	if (blk_queue_stopped(port->disk->queue) &&
+	    vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
 		blk_start_queue(port->disk->queue);
 }
 
@@ -388,12 +435,6 @@ static int __send_request(struct request *req)
 	for (i = 0; i < nsg; i++)
 		len += sg[i].length;
 
-	if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
-		blk_stop_queue(port->disk->queue);
-		err = -ENOMEM;
-		goto out;
-	}
-
 	desc = vio_dring_cur(dr);
 
 	err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +474,32 @@ static int __send_request(struct request *req)
 		port->req_id++;
 		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
 	}
-out:
 
 	return err;
 }
 
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
 {
-	while (1) {
-		struct request *req = blk_fetch_request(q);
+	struct request *req;
 
-		if (!req)
-			break;
+	while ((req = blk_peek_request(rq)) != NULL) {
+		struct vdc_port *port;
+		struct vio_dring_state *dr;
 
-		if (__send_request(req) < 0)
-			__blk_end_request_all(req, -EIO);
+		port = req->rq_disk->private_data;
+		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+		if (unlikely(vdc_tx_dring_avail(dr) < 1))
+			goto wait;
+
+		blk_start_request(req);
+
+		if (__send_request(req) < 0) {
+			blk_requeue_request(rq, req);
+wait:
+			/* Avoid pointless unplugs. */
+			blk_stop_queue(rq);
+			break;
+		}
 	}
 }
 
@@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port)
 	if (comp.err)
 		return comp.err;
 
-	err = generic_request(port, VD_OP_GET_VTOC,
-			      &port->label, sizeof(port->label));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err);
-		return err;
-	}
-
-	err = generic_request(port, VD_OP_GET_DISKGEOM,
-			      &port->geom, sizeof(port->geom));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
-		       "error %d\n", err);
-		return err;
+	if (vdc_version_supported(port, 1, 1)) {
+		/* vdisk_size should be set during the handshake, if it wasn't
+		 * then the underlying disk is reserved by another system
+		 */
+		if (port->vdisk_size == -1)
+			return -ENODEV;
+	} else {
+		struct vio_disk_geom geom;
+
+		err = generic_request(port, VD_OP_GET_DISKGEOM,
+				      &geom, sizeof(geom));
+		if (err < 0) {
+			printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+			       "error %d\n", err);
+			return err;
+		}
+		port->vdisk_size = ((u64)geom.num_cyl *
+				    (u64)geom.num_hd *
+				    (u64)geom.num_sec);
 	}
 
-	port->vdisk_size = ((u64)port->geom.num_cyl *
-			    (u64)port->geom.num_hd *
-			    (u64)port->geom.num_sec);
-
 	q = blk_init_queue(do_vdc_request, &port->vio.lock);
 	if (!q) {
 		printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port)
 
 	port->disk = g;
 
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(q, PAGE_SIZE);
+
 	blk_queue_max_segments(q, port->ring_cookies);
 	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
@@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port)
 
 	set_capacity(g, port->vdisk_size);
 
-	printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+	if (vdc_version_supported(port, 1, 1)) {
+		switch (port->vdisk_mtype) {
+		case VD_MEDIA_TYPE_CD:
+			pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_DVD:
+			pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_FIXED:
+			pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+			break;
+		}
+	}
+
+	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
-	       port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+	       port->vio.ver.major, port->vio.ver.minor);
 
 	add_disk(g);
 
@@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	else
 		snprintf(port->disk_name, sizeof(port->disk_name),
 			 VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+	port->vdisk_size = -1;
 
 	err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
 			      vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index d81dfca755d1..03dd4aa612db 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -649,6 +649,8 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	unsigned long secure;
 	struct phys_req preq;
 
+	xen_blkif_get(blkif);
+
 	preq.sector_number = req->u.discard.sector_number;
 	preq.nr_sects      = req->u.discard.nr_sectors;
 
@@ -661,7 +663,6 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	}
 	blkif->st_ds_req++;
 
-	xen_blkif_get(blkif);
 	secure = (blkif->vbd.discard_secure &&
 		 (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ?
 		 BLKDEV_DISCARD_SECURE : 0;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 69b45fc97276..ddd9a098bc67 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -104,7 +104,7 @@ struct blkfront_info
 	struct work_struct work;
 	struct gnttab_free_callback callback;
 	struct blk_shadow shadow[BLK_RING_SIZE];
-	struct list_head persistent_gnts;
+	struct list_head grants;
 	unsigned int persistent_gnts_c;
 	unsigned long shadow_free;
 	unsigned int feature_flush;
@@ -175,15 +175,17 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)
 		if (!gnt_list_entry)
 			goto out_of_memory;
 
-		granted_page = alloc_page(GFP_NOIO);
-		if (!granted_page) {
-			kfree(gnt_list_entry);
-			goto out_of_memory;
+		if (info->feature_persistent) {
+			granted_page = alloc_page(GFP_NOIO);
+			if (!granted_page) {
+				kfree(gnt_list_entry);
+				goto out_of_memory;
+			}
+			gnt_list_entry->pfn = page_to_pfn(granted_page);
 		}
 
-		gnt_list_entry->pfn = page_to_pfn(granted_page);
 		gnt_list_entry->gref = GRANT_INVALID_REF;
-		list_add(&gnt_list_entry->node, &info->persistent_gnts);
+		list_add(&gnt_list_entry->node, &info->grants);
 		i++;
 	}
 
@@ -191,9 +193,10 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)
 
 out_of_memory:
 	list_for_each_entry_safe(gnt_list_entry, n,
-	                         &info->persistent_gnts, node) {
+	                         &info->grants, node) {
 		list_del(&gnt_list_entry->node);
-		__free_page(pfn_to_page(gnt_list_entry->pfn));
+		if (info->feature_persistent)
+			__free_page(pfn_to_page(gnt_list_entry->pfn));
 		kfree(gnt_list_entry);
 		i--;
 	}
@@ -202,14 +205,14 @@ out_of_memory:
 }
 
 static struct grant *get_grant(grant_ref_t *gref_head,
+                               unsigned long pfn,
                                struct blkfront_info *info)
 {
 	struct grant *gnt_list_entry;
 	unsigned long buffer_mfn;
 
-	BUG_ON(list_empty(&info->persistent_gnts));
-	gnt_list_entry = list_first_entry(&info->persistent_gnts, struct grant,
-	                                  node);
+	BUG_ON(list_empty(&info->grants));
+	gnt_list_entry = list_first_entry(&info->grants, struct grant, node);
 	list_del(&gnt_list_entry->node);
 
 	if (gnt_list_entry->gref != GRANT_INVALID_REF) {
@@ -220,6 +223,10 @@ static struct grant *get_grant(grant_ref_t *gref_head,
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
+	if (!info->feature_persistent) {
+		BUG_ON(!pfn);
+		gnt_list_entry->pfn = pfn;
+	}
 	buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
 	gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
 	                                info->xbdev->otherend_id,
@@ -430,12 +437,12 @@ static int blkif_queue_request(struct request *req)
 			fsect = sg->offset >> 9;
 			lsect = fsect + (sg->length >> 9) - 1;
 
-			gnt_list_entry = get_grant(&gref_head, info);
+			gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
 			ref = gnt_list_entry->gref;
 
 			info->shadow[id].grants_used[i] = gnt_list_entry;
 
-			if (rq_data_dir(req)) {
+			if (rq_data_dir(req) && info->feature_persistent) {
 				char *bvec_data;
 				void *shared_data;
 
@@ -828,16 +835,17 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 		blk_stop_queue(info->rq);
 
 	/* Remove all persistent grants */
-	if (!list_empty(&info->persistent_gnts)) {
+	if (!list_empty(&info->grants)) {
 		list_for_each_entry_safe(persistent_gnt, n,
-		                         &info->persistent_gnts, node) {
+		                         &info->grants, node) {
 			list_del(&persistent_gnt->node);
 			if (persistent_gnt->gref != GRANT_INVALID_REF) {
 				gnttab_end_foreign_access(persistent_gnt->gref,
 				                          0, 0UL);
 				info->persistent_gnts_c--;
 			}
-			__free_page(pfn_to_page(persistent_gnt->pfn));
+			if (info->feature_persistent)
+				__free_page(pfn_to_page(persistent_gnt->pfn));
 			kfree(persistent_gnt);
 		}
 	}
@@ -874,7 +882,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 
 	nseg = s->req.u.rw.nr_segments;
 
-	if (bret->operation == BLKIF_OP_READ) {
+	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
 		/*
 		 * Copy the data received from the backend into the bvec.
 		 * Since bv_offset can be different than 0, and bv_len different
@@ -894,9 +902,30 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 		}
 	}
 	/* Add the persistent grant into the list of free grants */
-	for (i = 0; i < s->req.u.rw.nr_segments; i++) {
-		list_add(&s->grants_used[i]->node, &info->persistent_gnts);
-		info->persistent_gnts_c++;
+	for (i = 0; i < nseg; i++) {
+		if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+			/*
+			 * If the grant is still mapped by the backend (the
+			 * backend has chosen to make this grant persistent)
+			 * we add it at the head of the list, so it will be
+			 * reused first.
+			 */
+			if (!info->feature_persistent)
+				pr_alert_ratelimited("backed has not unmapped grant: %u\n",
+						     s->grants_used[i]->gref);
+			list_add(&s->grants_used[i]->node, &info->grants);
+			info->persistent_gnts_c++;
+		} else {
+			/*
+			 * If the grant is not mapped by the backend we end the
+			 * foreign access and add it to the tail of the list,
+			 * so it will not be picked again unless we run out of
+			 * persistent grants.
+			 */
+			gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
+			s->grants_used[i]->gref = GRANT_INVALID_REF;
+			list_add_tail(&s->grants_used[i]->node, &info->grants);
+		}
 	}
 }
 
@@ -1034,12 +1063,6 @@ static int setup_blkring(struct xenbus_device *dev,
 	for (i = 0; i < BLK_RING_SIZE; i++)
 		sg_init_table(info->shadow[i].sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
 
-	/* Allocate memory for grants */
-	err = fill_grant_buffer(info, BLK_RING_SIZE *
-	                              BLKIF_MAX_SEGMENTS_PER_REQUEST);
-	if (err)
-		goto fail;
-
 	err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
 	if (err < 0) {
 		free_page((unsigned long)sring);
@@ -1198,7 +1221,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 	spin_lock_init(&info->io_lock);
 	info->xbdev = dev;
 	info->vdevice = vdevice;
-	INIT_LIST_HEAD(&info->persistent_gnts);
+	INIT_LIST_HEAD(&info->grants);
 	info->persistent_gnts_c = 0;
 	info->connected = BLKIF_STATE_DISCONNECTED;
 	INIT_WORK(&info->work, blkif_restart_queue);
@@ -1227,7 +1250,8 @@ static int blkif_recover(struct blkfront_info *info)
 	int i;
 	struct blkif_request *req;
 	struct blk_shadow *copy;
-	int j;
+	unsigned int persistent;
+	int j, rc;
 
 	/* Stage 1: Make a safe copy of the shadow state. */
 	copy = kmemdup(info->shadow, sizeof(info->shadow),
@@ -1242,6 +1266,24 @@ static int blkif_recover(struct blkfront_info *info)
 	info->shadow_free = info->ring.req_prod_pvt;
 	info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
 
+	/* Check if the backend supports persistent grants */
+	rc = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			   "feature-persistent", "%u", &persistent,
+			   NULL);
+	if (rc)
+		info->feature_persistent = 0;
+	else
+		info->feature_persistent = persistent;
+
+	/* Allocate memory for grants */
+	rc = fill_grant_buffer(info, BLK_RING_SIZE *
+	                             BLKIF_MAX_SEGMENTS_PER_REQUEST);
+	if (rc) {
+		xenbus_dev_fatal(info->xbdev, rc, "setting grant buffer failed");
+		kfree(copy);
+		return rc;
+	}
+
 	/* Stage 3: Find pending requests and requeue them. */
 	for (i = 0; i < BLK_RING_SIZE; i++) {
 		/* Not in use? */
@@ -1306,8 +1348,12 @@ static int blkfront_resume(struct xenbus_device *dev)
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
 	err = talk_to_blkback(dev, info);
-	if (info->connected == BLKIF_STATE_SUSPENDED && !err)
-		err = blkif_recover(info);
+
+	/*
+	 * We have to wait for the backend to switch to
+	 * connected state, since we want to read which
+	 * features it supports.
+	 */
 
 	return err;
 }
@@ -1411,9 +1457,16 @@ static void blkfront_connect(struct blkfront_info *info)
 		       sectors);
 		set_capacity(info->gd, sectors);
 		revalidate_disk(info->gd);
+		return;
 
-		/* fall through */
 	case BLKIF_STATE_SUSPENDED:
+		/*
+		 * If we are recovering from suspension, we need to wait
+		 * for the backend to announce it's features before
+		 * reconnecting, we need to know if the backend supports
+		 * persistent grants.
+		 */
+		blkif_recover(info);
 		return;
 
 	default:
@@ -1481,6 +1534,14 @@ static void blkfront_connect(struct blkfront_info *info)
 	else
 		info->feature_persistent = persistent;
 
+	/* Allocate memory for grants */
+	err = fill_grant_buffer(info, BLK_RING_SIZE *
+	                              BLKIF_MAX_SEGMENTS_PER_REQUEST);
+	if (err) {
+		xenbus_dev_fatal(info->xbdev, err, "setting grant buffer failed");
+		return;
+	}
+
 	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
@@ -1518,13 +1579,16 @@ static void blkback_changed(struct xenbus_device *dev,
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
-	case XenbusStateClosed:
 		break;
 
 	case XenbusStateConnected:
 		blkfront_connect(info);
 		break;
 
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's Closing state -- fallthrough */
 	case XenbusStateClosing:
 		blkfront_closing(info);
 		break;
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index a12b923bbaca..2acabdaecec8 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -82,9 +82,11 @@ static struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x3004) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
 	{ USB_DEVICE(0x04CA, 0x3006) },
+	{ USB_DEVICE(0x04CA, 0x3007) },
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
+	{ USB_DEVICE(0x0CF3, 0xE005) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
@@ -123,9 +125,11 @@ static struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d0b3d900d452..61a8ec4e5f4d 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -102,6 +102,7 @@ static struct usb_device_id btusb_table[] = {
 
 	/* Broadcom BCM20702A0 */
 	{ USB_DEVICE(0x0b05, 0x17b5) },
+	{ USB_DEVICE(0x0b05, 0x17cb) },
 	{ USB_DEVICE(0x04ca, 0x2003) },
 	{ USB_DEVICE(0x0489, 0xe042) },
 	{ USB_DEVICE(0x413c, 0x8197) },
@@ -145,9 +146,11 @@ static struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
@@ -299,6 +302,9 @@ static void btusb_intr_complete(struct urb *urb)
 			BT_ERR("%s corrupted event packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_INTR_RUNNING, &data->flags))
@@ -387,6 +393,9 @@ static void btusb_bulk_complete(struct urb *urb)
 			BT_ERR("%s corrupted ACL packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_BULK_RUNNING, &data->flags))
@@ -481,6 +490,9 @@ static void btusb_isoc_complete(struct urb *urb)
 				hdev->stat.err_rx++;
 			}
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags))
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index b6154d5a07a5..db35c542eb20 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5)
 			break;
 
 		to_remove--;
-		seq = (seq - 1) % 8;
+		seq = (seq - 1) & 0x07;
 	}
 
 	if (seq != h5->rx_ack)
@@ -406,6 +406,7 @@ static int h5_rx_3wire_hdr(struct hci_uart *hu, unsigned char c)
 	    H5_HDR_PKT_TYPE(hdr) != HCI_3WIRE_LINK_PKT) {
 		BT_ERR("Non-link packet received in non-active state");
 		h5_reset_rx(h5);
+		return 0;
 	}
 
 	h5->rx_func = h5_rx_payload;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index bc68a440d432..c4d2f0e48685 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -118,10 +118,6 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 
 int hci_uart_tx_wakeup(struct hci_uart *hu)
 {
-	struct tty_struct *tty = hu->tty;
-	struct hci_dev *hdev = hu->hdev;
-	struct sk_buff *skb;
-
 	if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) {
 		set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 		return 0;
@@ -129,6 +125,22 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 
 	BT_DBG("");
 
+	schedule_work(&hu->write_work);
+
+	return 0;
+}
+
+static void hci_uart_write_work(struct work_struct *work)
+{
+	struct hci_uart *hu = container_of(work, struct hci_uart, write_work);
+	struct tty_struct *tty = hu->tty;
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+
+	/* REVISIT: should we cope with bad skbs or ->write() returning
+	 * and error value ?
+	 */
+
 restart:
 	clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 
@@ -153,7 +165,6 @@ restart:
 		goto restart;
 
 	clear_bit(HCI_UART_SENDING, &hu->tx_state);
-	return 0;
 }
 
 static void hci_uart_init_work(struct work_struct *work)
@@ -289,6 +300,7 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	tty->receive_room = 65536;
 
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
+	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
 	spin_lock_init(&hu->rx_lock);
 
@@ -326,6 +338,8 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 	if (hdev)
 		hci_uart_close(hdev);
 
+	cancel_work_sync(&hu->write_work);
+
 	if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) {
 		if (hdev) {
 			if (test_bit(HCI_UART_REGISTERED, &hu->flags))
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fffa61ff5cb1..12df101ca942 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -68,6 +68,7 @@ struct hci_uart {
 	unsigned long		hdev_flags;
 
 	struct work_struct	init_ready;
+	struct work_struct	write_work;
 
 	struct hci_uart_proto	*proto;
 	void			*priv;
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index b05ecab915c4..5286e2d333b0 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -26,4 +26,11 @@ config OMAP_INTERCONNECT
 
 	help
 	  Driver to enable OMAP interconnect error handling driver.
+
+config ARM_CCI
+	bool "ARM CCI driver support"
+	depends on ARM
+	help
+	  Driver supporting the CCI cache coherent interconnect for ARM
+	  platforms.
 endmenu
diff --git a/drivers/bus/Makefile b/drivers/bus/Makefile
index 3c7b53c12091..670cea443802 100644
--- a/drivers/bus/Makefile
+++ b/drivers/bus/Makefile
@@ -7,3 +7,5 @@ obj-$(CONFIG_OMAP_OCP2SCP)	+= omap-ocp2scp.o
 
 # Interconnect bus driver for OMAP SoCs.
 obj-$(CONFIG_OMAP_INTERCONNECT)	+= omap_l3_smx.o omap_l3_noc.o
+# CCI cache coherent interconnect for ARM platforms
+obj-$(CONFIG_ARM_CCI)		+= arm-cci.o
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
new file mode 100644
index 000000000000..d9d954eb0fa0
--- /dev/null
+++ b/drivers/bus/arm-cci.c
@@ -0,0 +1,947 @@
+/*
+ * CCI cache coherent interconnect driver
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/arm-cci.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+#include <asm/cacheflush.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+#include <asm/smp_plat.h>
+
+#define DRIVER_NAME		"CCI"
+
+#define CCI_PORT_CTRL		0x0
+#define CCI_CTRL_STATUS		0xc
+
+#define CCI_ENABLE_SNOOP_REQ	0x1
+#define CCI_ENABLE_DVM_REQ	0x2
+#define CCI_ENABLE_REQ		(CCI_ENABLE_SNOOP_REQ | CCI_ENABLE_DVM_REQ)
+
+struct cci_nb_ports {
+	unsigned int nb_ace;
+	unsigned int nb_ace_lite;
+};
+
+enum cci_ace_port_type {
+	ACE_INVALID_PORT = 0x0,
+	ACE_PORT,
+	ACE_LITE_PORT,
+};
+
+struct cci_ace_port {
+	void __iomem *base;
+	unsigned long phys;
+	enum cci_ace_port_type type;
+	struct device_node *dn;
+};
+
+static struct cci_ace_port *ports;
+static unsigned int nb_cci_ports;
+
+static void __iomem *cci_ctrl_base;
+static unsigned long cci_ctrl_phys;
+
+#ifdef CONFIG_HW_PERF_EVENTS
+
+static void __iomem *cci_pmu_base;
+
+#define CCI400_PMCR		0x0100
+
+#define CCI400_PMU_CYCLE_CNTR_BASE    0x0000
+#define CCI400_PMU_CNTR_BASE(idx)     (CCI400_PMU_CYCLE_CNTR_BASE + (idx) * 0x1000)
+
+#define CCI400_PMCR_CEN          0x00000001
+#define CCI400_PMCR_RST          0x00000002
+#define CCI400_PMCR_CCR          0x00000004
+#define CCI400_PMCR_CCD          0x00000008
+#define CCI400_PMCR_EX           0x00000010
+#define CCI400_PMCR_DP           0x00000020
+#define CCI400_PMCR_NCNT_MASK    0x0000F800
+#define CCI400_PMCR_NCNT_SHIFT   11
+
+#define CCI400_PMU_EVT_SEL       0x000
+#define CCI400_PMU_CNTR          0x004
+#define CCI400_PMU_CNTR_CTRL     0x008
+#define CCI400_PMU_OVERFLOW      0x00C
+
+#define CCI400_PMU_OVERFLOW_FLAG 1
+
+enum cci400_perf_events {
+	CCI400_PMU_CYCLES = 0xFF
+};
+
+#define CCI400_PMU_EVENT_MASK   0xff
+#define CCI400_PMU_EVENT_SOURCE(event) ((event >> 5) & 0x7)
+#define CCI400_PMU_EVENT_CODE(event) (event & 0x1f)
+
+#define CCI400_PMU_EVENT_SOURCE_S0 0
+#define CCI400_PMU_EVENT_SOURCE_S4 4
+#define CCI400_PMU_EVENT_SOURCE_M0 5
+#define CCI400_PMU_EVENT_SOURCE_M2 7
+
+#define CCI400_PMU_EVENT_SLAVE_MIN 0x0
+#define CCI400_PMU_EVENT_SLAVE_MAX 0x13
+
+#define CCI400_PMU_EVENT_MASTER_MIN 0x14
+#define CCI400_PMU_EVENT_MASTER_MAX 0x1A
+
+#define CCI400_PMU_MAX_HW_EVENTS 5   /* CCI PMU has 4 counters + 1 cycle counter */
+
+#define CCI400_PMU_CYCLE_COUNTER_IDX 0
+#define CCI400_PMU_COUNTER0_IDX      1
+#define CCI400_PMU_COUNTER_LAST(cci_pmu) (CCI400_PMU_CYCLE_COUNTER_IDX + cci_pmu->num_events - 1)
+
+
+static struct perf_event *events[CCI400_PMU_MAX_HW_EVENTS];
+static unsigned long used_mask[BITS_TO_LONGS(CCI400_PMU_MAX_HW_EVENTS)];
+static struct pmu_hw_events cci_hw_events = {
+	.events    = events,
+	.used_mask = used_mask,
+};
+
+static int cci_pmu_validate_hw_event(u8 hw_event)
+{
+	u8 ev_source = CCI400_PMU_EVENT_SOURCE(hw_event);
+	u8 ev_code = CCI400_PMU_EVENT_CODE(hw_event);
+
+	if (ev_source <= CCI400_PMU_EVENT_SOURCE_S4 &&
+	    ev_code <= CCI400_PMU_EVENT_SLAVE_MAX)
+			return hw_event;
+	else if (CCI400_PMU_EVENT_SOURCE_M0 <= ev_source &&
+		   ev_source <= CCI400_PMU_EVENT_SOURCE_M2 &&
+		   CCI400_PMU_EVENT_MASTER_MIN <= ev_code &&
+		    ev_code <= CCI400_PMU_EVENT_MASTER_MAX)
+			return hw_event;
+
+	return -EINVAL;
+}
+
+static inline int cci_pmu_counter_is_valid(struct arm_pmu *cci_pmu, int idx)
+{
+	return CCI400_PMU_CYCLE_COUNTER_IDX <= idx &&
+		idx <= CCI400_PMU_COUNTER_LAST(cci_pmu);
+}
+
+static inline u32 cci_pmu_read_register(int idx, unsigned int offset)
+{
+	return readl_relaxed(cci_pmu_base + CCI400_PMU_CNTR_BASE(idx) + offset);
+}
+
+static inline void cci_pmu_write_register(u32 value, int idx, unsigned int offset)
+{
+	return writel_relaxed(value, cci_pmu_base + CCI400_PMU_CNTR_BASE(idx) + offset);
+}
+
+static inline void cci_pmu_disable_counter(int idx)
+{
+	cci_pmu_write_register(0, idx, CCI400_PMU_CNTR_CTRL);
+}
+
+static inline void cci_pmu_enable_counter(int idx)
+{
+	cci_pmu_write_register(1, idx, CCI400_PMU_CNTR_CTRL);
+}
+
+static inline void cci_pmu_select_event(int idx, unsigned long event)
+{
+	event &= CCI400_PMU_EVENT_MASK;
+	cci_pmu_write_register(event, idx, CCI400_PMU_EVT_SEL);
+}
+
+static u32 cci_pmu_get_max_counters(void)
+{
+	u32 n_cnts = (readl_relaxed(cci_ctrl_base + CCI400_PMCR) &
+		      CCI400_PMCR_NCNT_MASK) >> CCI400_PMCR_NCNT_SHIFT;
+
+	/* add 1 for cycle counter */
+	return n_cnts + 1;
+}
+
+static struct pmu_hw_events *cci_pmu_get_hw_events(void)
+{
+	return &cci_hw_events;
+}
+
+static int cci_pmu_get_event_idx(struct pmu_hw_events *hw, struct perf_event *event)
+{
+	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hw_event = &event->hw;
+	unsigned long cci_event = hw_event->config_base & CCI400_PMU_EVENT_MASK;
+	int idx;
+
+	if (cci_event == CCI400_PMU_CYCLES) {
+		if (test_and_set_bit(CCI400_PMU_CYCLE_COUNTER_IDX, hw->used_mask))
+			return -EAGAIN;
+
+                return CCI400_PMU_CYCLE_COUNTER_IDX;
+        }
+
+	for (idx = CCI400_PMU_COUNTER0_IDX; idx <= CCI400_PMU_COUNTER_LAST(cci_pmu); ++idx) {
+		if (!test_and_set_bit(idx, hw->used_mask))
+			return idx;
+	}
+
+	/* No counters available */
+	return -EAGAIN;
+}
+
+static int cci_pmu_map_event(struct perf_event *event)
+{
+	int mapping;
+	u8 config = event->attr.config & CCI400_PMU_EVENT_MASK;
+
+	if (event->attr.type < PERF_TYPE_MAX)
+		return -ENOENT;
+
+	/* 0xff is used to represent CCI Cycles */
+	if (config == 0xff)
+		mapping = config;
+	else
+		mapping = cci_pmu_validate_hw_event(config);
+
+	return mapping;
+}
+
+static int cci_pmu_request_irq(struct arm_pmu *cci_pmu, irq_handler_t handler)
+{
+	int irq, err, i = 0;
+	struct platform_device *pmu_device = cci_pmu->plat_device;
+
+	if (unlikely(!pmu_device))
+		return -ENODEV;
+
+	/* CCI exports 6 interrupts - 1 nERRORIRQ + 5 nEVNTCNTOVERFLOW (PMU)
+	   nERRORIRQ will be handled by secure firmware on TC2. So we
+	   assume that all CCI interrupts listed in the linux device
+	   tree are PMU interrupts.
+
+	   The following code should then be able to handle different routing
+	   of the CCI PMU interrupts.
+	*/
+	while ((irq = platform_get_irq(pmu_device, i)) > 0) {
+		err = request_irq(irq, handler, 0, "arm-cci-pmu", cci_pmu);
+		if (err) {
+			dev_err(&pmu_device->dev, "unable to request IRQ%d for ARM CCI PMU counters\n",
+				irq);
+			return err;
+		}
+		i++;
+	}
+
+	return 0;
+}
+
+static irqreturn_t cci_pmu_handle_irq(int irq_num, void *dev)
+{
+	struct arm_pmu *cci_pmu = (struct arm_pmu *)dev;
+	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct perf_sample_data data;
+	struct pt_regs *regs;
+	int idx;
+
+	regs = get_irq_regs();
+
+	/* Iterate over counters and update the corresponding perf events.
+	   This should work regardless of whether we have per-counter overflow
+	   interrupt or a combined overflow interrupt. */
+	for (idx = CCI400_PMU_CYCLE_COUNTER_IDX; idx <= CCI400_PMU_COUNTER_LAST(cci_pmu); idx++) {
+		struct perf_event *event = events->events[idx];
+		struct hw_perf_event *hw_counter;
+
+		if (!event)
+			continue;
+
+		hw_counter = &event->hw;
+
+		/* Did this counter overflow? */
+		if (!(cci_pmu_read_register(idx, CCI400_PMU_OVERFLOW) & CCI400_PMU_OVERFLOW_FLAG))
+			continue;
+		cci_pmu_write_register(CCI400_PMU_OVERFLOW_FLAG, idx, CCI400_PMU_OVERFLOW);
+
+		armpmu_event_update(event);
+		perf_sample_data_init(&data, 0, hw_counter->last_period);
+		if (!armpmu_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			cci_pmu->disable(event);
+	}
+
+	irq_work_run();
+	return IRQ_HANDLED;
+}
+
+static void cci_pmu_free_irq(struct arm_pmu *cci_pmu)
+{
+	int irq, i = 0;
+	struct platform_device *pmu_device = cci_pmu->plat_device;
+
+	while ((irq = platform_get_irq(pmu_device, i)) > 0) {
+		free_irq(irq, cci_pmu);
+		i++;
+	}
+}
+
+static void cci_pmu_enable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct hw_perf_event *hw_counter = &event->hw;
+	int idx = hw_counter->idx;
+
+	if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+		dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Configure the event to count, unless you are counting cycles */
+	if (idx != CCI400_PMU_CYCLE_COUNTER_IDX)
+		cci_pmu_select_event(idx, hw_counter->config_base);
+
+	cci_pmu_enable_counter(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_disable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct hw_perf_event *hw_counter = &event->hw;
+	int idx = hw_counter->idx;
+
+	if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+		dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	cci_pmu_disable_counter(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_start(struct arm_pmu *cci_pmu)
+{
+	u32 val;
+	unsigned long flags;
+	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Enable all the PMU counters. */
+	val = readl(cci_ctrl_base + CCI400_PMCR) | CCI400_PMCR_CEN;
+	writel(val, cci_ctrl_base + CCI400_PMCR);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_stop(struct arm_pmu *cci_pmu)
+{
+	u32 val;
+	unsigned long flags;
+	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable all the PMU counters. */
+	val = readl(cci_ctrl_base + CCI400_PMCR) & ~CCI400_PMCR_CEN;
+	writel(val, cci_ctrl_base + CCI400_PMCR);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static u32 cci_pmu_read_counter(struct perf_event *event)
+{
+	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hw_counter = &event->hw;
+	int idx = hw_counter->idx;
+	u32 value;
+
+	if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+		dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+		return 0;
+	}
+	value = cci_pmu_read_register(idx, CCI400_PMU_CNTR);
+
+	return value;
+}
+
+static void cci_pmu_write_counter(struct perf_event *event, u32 value)
+{
+	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hw_counter = &event->hw;
+	int idx = hw_counter->idx;
+
+	if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx)))
+		dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+	else
+		cci_pmu_write_register(value, idx, CCI400_PMU_CNTR);
+}
+
+static struct arm_pmu cci_pmu = {
+	.name             = DRIVER_NAME,
+	.max_period       = (1LLU << 32) - 1,
+	.get_hw_events    = cci_pmu_get_hw_events,
+	.get_event_idx    = cci_pmu_get_event_idx,
+	.map_event        = cci_pmu_map_event,
+	.request_irq      = cci_pmu_request_irq,
+	.handle_irq       = cci_pmu_handle_irq,
+	.free_irq         = cci_pmu_free_irq,
+	.enable           = cci_pmu_enable_event,
+	.disable          = cci_pmu_disable_event,
+	.start            = cci_pmu_start,
+	.stop             = cci_pmu_stop,
+	.read_counter     = cci_pmu_read_counter,
+	.write_counter    = cci_pmu_write_counter,
+};
+
+static int cci_pmu_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cci_pmu_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(cci_pmu_base))
+		return PTR_ERR(cci_pmu_base);
+
+	cci_pmu.plat_device = pdev;
+	cci_pmu.num_events = cci_pmu_get_max_counters();
+	raw_spin_lock_init(&cci_hw_events.pmu_lock);
+	cpumask_setall(&cci_pmu.valid_cpus);
+
+	return armpmu_register(&cci_pmu, -1);
+}
+
+static const struct of_device_id arm_cci_pmu_matches[] = {
+	{.compatible = "arm,cci-400-pmu"},
+	{},
+};
+
+static struct platform_driver cci_pmu_platform_driver = {
+	.driver = {
+		   .name = DRIVER_NAME,
+		   .of_match_table = arm_cci_pmu_matches,
+		  },
+	.probe = cci_pmu_probe,
+};
+
+static int __init cci_pmu_init(void)
+{
+	if (platform_driver_register(&cci_pmu_platform_driver))
+		WARN(1, "unable to register CCI platform driver\n");
+	return 0;
+}
+
+#else
+
+static int __init cci_pmu_init(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
+struct cpu_port {
+	u64 mpidr;
+	u32 port;
+};
+
+/*
+ * Use the port MSB as valid flag, shift can be made dynamic
+ * by computing number of bits required for port indexes.
+ * Code disabling CCI cpu ports runs with D-cache invalidated
+ * and SCTLR bit clear so data accesses must be kept to a minimum
+ * to improve performance; for now shift is left static to
+ * avoid one more data access while disabling the CCI port.
+ */
+#define PORT_VALID_SHIFT	31
+#define PORT_VALID		(0x1 << PORT_VALID_SHIFT)
+
+static inline void init_cpu_port(struct cpu_port *port, u32 index, u64 mpidr)
+{
+	port->port = PORT_VALID | index;
+	port->mpidr = mpidr;
+}
+
+static inline bool cpu_port_is_valid(struct cpu_port *port)
+{
+	return !!(port->port & PORT_VALID);
+}
+
+static inline bool cpu_port_match(struct cpu_port *port, u64 mpidr)
+{
+	return port->mpidr == (mpidr & MPIDR_HWID_BITMASK);
+}
+
+static struct cpu_port cpu_port[NR_CPUS];
+
+/**
+ * __cci_ace_get_port - Function to retrieve the port index connected to
+ *			a cpu or device.
+ *
+ * @dn: device node of the device to look-up
+ * @type: port type
+ *
+ * Return value:
+ *	- CCI port index if success
+ *	- -ENODEV if failure
+ */
+static int __cci_ace_get_port(struct device_node *dn, int type)
+{
+	int i;
+	bool ace_match;
+	struct device_node *cci_portn;
+
+	cci_portn = of_parse_phandle(dn, "cci-control-port", 0);
+	for (i = 0; i < nb_cci_ports; i++) {
+		ace_match = ports[i].type == type;
+		if (ace_match && cci_portn == ports[i].dn)
+			return i;
+	}
+	return -ENODEV;
+}
+
+int cci_ace_get_port(struct device_node *dn)
+{
+	return __cci_ace_get_port(dn, ACE_LITE_PORT);
+}
+EXPORT_SYMBOL_GPL(cci_ace_get_port);
+
+static void __init cci_ace_init_ports(void)
+{
+	int port, ac, cpu;
+	u64 hwid;
+	const u32 *cell;
+	struct device_node *cpun, *cpus;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (WARN(!cpus, "Missing cpus node, bailing out\n"))
+		return;
+
+	if (WARN_ON(of_property_read_u32(cpus, "#address-cells", &ac)))
+		ac = of_n_addr_cells(cpus);
+
+	/*
+	 * Port index look-up speeds up the function disabling ports by CPU,
+	 * since the logical to port index mapping is done once and does
+	 * not change after system boot.
+	 * The stashed index array is initialized for all possible CPUs
+	 * at probe time.
+	 */
+	for_each_child_of_node(cpus, cpun) {
+		if (of_node_cmp(cpun->type, "cpu"))
+			continue;
+		cell = of_get_property(cpun, "reg", NULL);
+		if (WARN(!cell, "%s: missing reg property\n", cpun->full_name))
+			continue;
+
+		hwid = of_read_number(cell, ac);
+		cpu = get_logical_index(hwid & MPIDR_HWID_BITMASK);
+
+		if (cpu < 0 || !cpu_possible(cpu))
+			continue;
+		port = __cci_ace_get_port(cpun, ACE_PORT);
+		if (port < 0)
+			continue;
+
+		init_cpu_port(&cpu_port[cpu], port, cpu_logical_map(cpu));
+	}
+
+	for_each_possible_cpu(cpu) {
+		WARN(!cpu_port_is_valid(&cpu_port[cpu]),
+			"CPU %u does not have an associated CCI port\n",
+			cpu);
+	}
+}
+/*
+ * Functions to enable/disable a CCI interconnect slave port
+ *
+ * They are called by low-level power management code to disable slave
+ * interfaces snoops and DVM broadcast.
+ * Since they may execute with cache data allocation disabled and
+ * after the caches have been cleaned and invalidated the functions provide
+ * no explicit locking since they may run with D-cache disabled, so normal
+ * cacheable kernel locks based on ldrex/strex may not work.
+ * Locking has to be provided by BSP implementations to ensure proper
+ * operations.
+ */
+
+/**
+ * cci_port_control() - function to control a CCI port
+ *
+ * @port: index of the port to setup
+ * @enable: if true enables the port, if false disables it
+ */
+static void notrace cci_port_control(unsigned int port, bool enable)
+{
+	void __iomem *base = ports[port].base;
+
+	writel_relaxed(enable ? CCI_ENABLE_REQ : 0, base + CCI_PORT_CTRL);
+	/*
+	 * This function is called from power down procedures
+	 * and must not execute any instruction that might
+	 * cause the processor to be put in a quiescent state
+	 * (eg wfi). Hence, cpu_relax() can not be added to this
+	 * read loop to optimize power, since it might hide possibly
+	 * disruptive operations.
+	 */
+	while (readl_relaxed(cci_ctrl_base + CCI_CTRL_STATUS) & 0x1)
+			;
+}
+
+/**
+ * cci_disable_port_by_cpu() - function to disable a CCI port by CPU
+ *			       reference
+ *
+ * @mpidr: mpidr of the CPU whose CCI port should be disabled
+ *
+ * Disabling a CCI port for a CPU implies disabling the CCI port
+ * controlling that CPU cluster. Code disabling CPU CCI ports
+ * must make sure that the CPU running the code is the last active CPU
+ * in the cluster ie all other CPUs are quiescent in a low power state.
+ *
+ * Return:
+ *	0 on success
+ *	-ENODEV on port look-up failure
+ */
+int notrace cci_disable_port_by_cpu(u64 mpidr)
+{
+	int cpu;
+	bool is_valid;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
+		is_valid = cpu_port_is_valid(&cpu_port[cpu]);
+		if (is_valid && cpu_port_match(&cpu_port[cpu], mpidr)) {
+			cci_port_control(cpu_port[cpu].port, false);
+			return 0;
+		}
+	}
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(cci_disable_port_by_cpu);
+
+/**
+ * cci_enable_port_for_self() - enable a CCI port for calling CPU
+ *
+ * Enabling a CCI port for the calling CPU implies enabling the CCI
+ * port controlling that CPU's cluster. Caller must make sure that the
+ * CPU running the code is the first active CPU in the cluster and all
+ * other CPUs are quiescent in a low power state  or waiting for this CPU
+ * to complete the CCI initialization.
+ *
+ * Because this is called when the MMU is still off and with no stack,
+ * the code must be position independent and ideally rely on callee
+ * clobbered registers only.  To achieve this we must code this function
+ * entirely in assembler.
+ *
+ * On success this returns with the proper CCI port enabled.  In case of
+ * any failure this never returns as the inability to enable the CCI is
+ * fatal and there is no possible recovery at this stage.
+ */
+asmlinkage void __naked cci_enable_port_for_self(void)
+{
+	asm volatile ("\n"
+
+"	mrc	p15, 0, r0, c0, c0, 5	@ get MPIDR value \n"
+"	and	r0, r0, #"__stringify(MPIDR_HWID_BITMASK)" \n"
+"	adr	r1, 5f \n"
+"	ldr	r2, [r1] \n"
+"	add	r1, r1, r2		@ &cpu_port \n"
+"	add	ip, r1, %[sizeof_cpu_port] \n"
+
+	/* Loop over the cpu_port array looking for a matching MPIDR */
+"1:	ldr	r2, [r1, %[offsetof_cpu_port_mpidr_lsb]] \n"
+"	cmp	r2, r0 			@ compare MPIDR \n"
+"	bne	2f \n"
+
+	/* Found a match, now test port validity */
+"	ldr	r3, [r1, %[offsetof_cpu_port_port]] \n"
+"	tst	r3, #"__stringify(PORT_VALID)" \n"
+"	bne	3f \n"
+
+	/* no match, loop with the next cpu_port entry */
+"2:	add	r1, r1, %[sizeof_struct_cpu_port] \n"
+"	cmp	r1, ip			@ done? \n"
+"	blo	1b \n"
+
+	/* CCI port not found -- cheaply try to stall this CPU */
+"cci_port_not_found: \n"
+"	wfi \n"
+"	wfe \n"
+"	b	cci_port_not_found \n"
+
+	/* Use matched port index to look up the corresponding ports entry */
+"3:	bic	r3, r3, #"__stringify(PORT_VALID)" \n"
+"	adr	r0, 6f \n"
+"	ldmia	r0, {r1, r2} \n"
+"	sub	r1, r1, r0 		@ virt - phys \n"
+"	ldr	r0, [r0, r2] 		@ *(&ports) \n"
+"	mov	r2, %[sizeof_struct_ace_port] \n"
+"	mla	r0, r2, r3, r0		@ &ports[index] \n"
+"	sub	r0, r0, r1		@ virt_to_phys() \n"
+
+	/* Enable the CCI port */
+"	ldr	r0, [r0, %[offsetof_port_phys]] \n"
+"	mov	r3, %[cci_enable_req]\n"		   
+"	str	r3, [r0, #"__stringify(CCI_PORT_CTRL)"] \n"
+
+	/* poll the status reg for completion */
+"	adr	r1, 7f \n"
+"	ldr	r0, [r1] \n"
+"	ldr	r0, [r0, r1]		@ cci_ctrl_base \n"
+"4:	ldr	r1, [r0, #"__stringify(CCI_CTRL_STATUS)"] \n"
+"	tst	r1, %[cci_control_status_bits] \n"			
+"	bne	4b \n"
+
+"	mov	r0, #0 \n"
+"	bx	lr \n"
+
+"	.align	2 \n"
+"5:	.word	cpu_port - . \n"
+"6:	.word	. \n"
+"	.word	ports - 6b \n"
+"7:	.word	cci_ctrl_phys - . \n"
+	: :
+	[sizeof_cpu_port] "i" (sizeof(cpu_port)),
+	[cci_enable_req] "i" cpu_to_le32(CCI_ENABLE_REQ),
+	[cci_control_status_bits] "i" cpu_to_le32(1),
+#ifndef __ARMEB__
+	[offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)),
+#else
+	[offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)+4),
+#endif
+	[offsetof_cpu_port_port] "i" (offsetof(struct cpu_port, port)),
+	[sizeof_struct_cpu_port] "i" (sizeof(struct cpu_port)),
+	[sizeof_struct_ace_port] "i" (sizeof(struct cci_ace_port)),
+	[offsetof_port_phys] "i" (offsetof(struct cci_ace_port, phys)) );
+
+	unreachable();
+}
+
+/**
+ * __cci_control_port_by_device() - function to control a CCI port by device
+ *				    reference
+ *
+ * @dn: device node pointer of the device whose CCI port should be
+ *      controlled
+ * @enable: if true enables the port, if false disables it
+ *
+ * Return:
+ *	0 on success
+ *	-ENODEV on port look-up failure
+ */
+int notrace __cci_control_port_by_device(struct device_node *dn, bool enable)
+{
+	int port;
+
+	if (!dn)
+		return -ENODEV;
+
+	port = __cci_ace_get_port(dn, ACE_LITE_PORT);
+	if (WARN_ONCE(port < 0, "node %s ACE lite port look-up failure\n",
+				dn->full_name))
+		return -ENODEV;
+	cci_port_control(port, enable);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__cci_control_port_by_device);
+
+/**
+ * __cci_control_port_by_index() - function to control a CCI port by port index
+ *
+ * @port: port index previously retrieved with cci_ace_get_port()
+ * @enable: if true enables the port, if false disables it
+ *
+ * Return:
+ *	0 on success
+ *	-ENODEV on port index out of range
+ *	-EPERM if operation carried out on an ACE PORT
+ */
+int notrace __cci_control_port_by_index(u32 port, bool enable)
+{
+	if (port >= nb_cci_ports || ports[port].type == ACE_INVALID_PORT)
+		return -ENODEV;
+	/*
+	 * CCI control for ports connected to CPUS is extremely fragile
+	 * and must be made to go through a specific and controlled
+	 * interface (ie cci_disable_port_by_cpu(); control by general purpose
+	 * indexing is therefore disabled for ACE ports.
+	 */
+	if (ports[port].type == ACE_PORT)
+		return -EPERM;
+
+	cci_port_control(port, enable);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__cci_control_port_by_index);
+
+static const struct cci_nb_ports cci400_ports = {
+	.nb_ace = 2,
+	.nb_ace_lite = 3
+};
+
+static const struct of_device_id arm_cci_matches[] = {
+	{.compatible = "arm,cci-400", .data = &cci400_ports },
+	{},
+};
+
+static const struct of_device_id arm_cci_ctrl_if_matches[] = {
+	{.compatible = "arm,cci-400-ctrl-if", },
+	{},
+};
+
+static int __init cci_probe(void)
+{
+	struct cci_nb_ports const *cci_config;
+	int ret, i, nb_ace = 0, nb_ace_lite = 0;
+	struct device_node *np, *cp;
+	struct resource res;
+	const char *match_str;
+	bool is_ace;
+
+	np = of_find_matching_node(NULL, arm_cci_matches);
+	if (!np)
+		return -ENODEV;
+
+	cci_config = of_match_node(arm_cci_matches, np)->data;
+	if (!cci_config)
+		return -ENODEV;
+
+	nb_cci_ports = cci_config->nb_ace + cci_config->nb_ace_lite;
+
+	ports = kcalloc(sizeof(*ports), nb_cci_ports, GFP_KERNEL);
+	if (!ports)
+		return -ENOMEM;
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (!ret) {
+		cci_ctrl_base = ioremap(res.start, resource_size(&res));
+		cci_ctrl_phys =	res.start;
+	}
+	if (ret || !cci_ctrl_base) {
+		WARN(1, "unable to ioremap CCI ctrl\n");
+		ret = -ENXIO;
+		goto memalloc_err;
+	}
+
+	for_each_child_of_node(np, cp) {
+		if (!of_match_node(arm_cci_ctrl_if_matches, cp))
+			continue;
+
+		i = nb_ace + nb_ace_lite;
+
+		if (i >= nb_cci_ports)
+			break;
+
+		if (of_property_read_string(cp, "interface-type",
+					&match_str)) {
+			WARN(1, "node %s missing interface-type property\n",
+				  cp->full_name);
+			continue;
+		}
+		is_ace = strcmp(match_str, "ace") == 0;
+		if (!is_ace && strcmp(match_str, "ace-lite")) {
+			WARN(1, "node %s containing invalid interface-type property, skipping it\n",
+					cp->full_name);
+			continue;
+		}
+
+		ret = of_address_to_resource(cp, 0, &res);
+		if (!ret) {
+			ports[i].base = ioremap(res.start, resource_size(&res));
+			ports[i].phys = res.start;
+		}
+		if (ret || !ports[i].base) {
+			WARN(1, "unable to ioremap CCI port %d\n", i);
+			continue;
+		}
+
+		if (is_ace) {
+			if (WARN_ON(nb_ace >= cci_config->nb_ace))
+				continue;
+			ports[i].type = ACE_PORT;
+			++nb_ace;
+		} else {
+			if (WARN_ON(nb_ace_lite >= cci_config->nb_ace_lite))
+				continue;
+			ports[i].type = ACE_LITE_PORT;
+			++nb_ace_lite;
+		}
+		ports[i].dn = cp;
+	}
+
+	 /* initialize a stashed array of ACE ports to speed-up look-up */
+	cci_ace_init_ports();
+
+	/*
+	 * Multi-cluster systems may need this data when non-coherent, during
+	 * cluster power-up/power-down. Make sure it reaches main memory.
+	 */
+	sync_cache_w(&cci_ctrl_base);
+	sync_cache_w(&cci_ctrl_phys);
+	sync_cache_w(&ports);
+	sync_cache_w(&cpu_port);
+	__sync_cache_range_w(ports, sizeof(*ports) * nb_cci_ports);
+	pr_info("ARM CCI driver probed\n");
+	return 0;
+
+memalloc_err:
+
+	kfree(ports);
+	return ret;
+}
+
+static int cci_init_status = -EAGAIN;
+static DEFINE_MUTEX(cci_probing);
+
+static int __init cci_init(void)
+{
+	if (cci_init_status != -EAGAIN)
+		return cci_init_status;
+
+	mutex_lock(&cci_probing);
+	if (cci_init_status == -EAGAIN)
+		cci_init_status = cci_probe();
+	mutex_unlock(&cci_probing);
+	return cci_init_status;
+}
+
+/*
+ * To sort out early init calls ordering a helper function is provided to
+ * check if the CCI driver has beed initialized. Function check if the driver
+ * has been initialized, if not it calls the init function that probes
+ * the driver and updates the return value.
+ */
+bool __init cci_probed(void)
+{
+	return cci_init() == 0;
+}
+EXPORT_SYMBOL_GPL(cci_probed);
+
+early_initcall(cci_init);
+core_initcall(cci_pmu_init);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ARM CCI support");
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 8740f46b4d0d..5dcc8305abd1 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -250,12 +250,6 @@ static int mvebu_mbus_window_conflicts(struct mvebu_mbus_state *mbus,
 		 */
 		if ((u64)base < wend && end > wbase)
 			return 0;
-
-		/*
-		 * Check if target/attribute conflicts
-		 */
-		if (target == wtarget && attr == wattr)
-			return 0;
 	}
 
 	return 1;
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index 974321a2508d..14790304b84b 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -345,7 +345,6 @@ out:
 			free_irq(apbs[i].irq, &dummy);
 		iounmap(apbs[i].RamIO);
 	}
-	pci_disable_device(dev);
 	return ret;
 }
 
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index 40cc0cf2ded6..e6939e13e338 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -664,6 +664,13 @@ static struct dmi_system_id __initdata i8k_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro"),
 		},
 	},
+	{
+		.ident = "Dell XPS421",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"),
+		},
+	},
         { }
 };
 
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index a22a7a502740..8156cafad11a 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt)
 
 static inline int read_all_bytes(struct si_sm_data *bt)
 {
-	unsigned char i;
+	unsigned int i;
 
 	/*
 	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c
index e53fc24c6af3..e1ddcf938519 100644
--- a/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -251,8 +251,9 @@ static inline int check_obf(struct si_sm_data *kcs, unsigned char status,
 	if (!GET_STATUS_OBF(status)) {
 		kcs->obf_timeout -= time;
 		if (kcs->obf_timeout < 0) {
-		    start_error_recovery(kcs, "OBF not ready in time");
-		    return 1;
+			kcs->obf_timeout = OBF_RETRY_TIMEOUT;
+			start_error_recovery(kcs, "OBF not ready in time");
+			return 1;
 		}
 		return 0;
 	}
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index af4b23ffc5a6..40b3f756f904 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -244,6 +244,9 @@ struct smi_info {
 	/* The timer for this si. */
 	struct timer_list   si_timer;
 
+	/* This flag is set, if the timer is running (timer_pending() isn't enough) */
+	bool		    timer_running;
+
 	/* The time (in jiffies) the last timeout occurred at. */
 	unsigned long       last_timeout_jiffies;
 
@@ -427,6 +430,13 @@ static void start_clear_flags(struct smi_info *smi_info)
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+	smi_info->last_timeout_jiffies = jiffies;
+	mod_timer(&smi_info->si_timer, new_val);
+	smi_info->timer_running = true;
+}
+
 /*
  * When we have a situtaion where we run out of memory and cannot
  * allocate messages, we just leave them in the BMC and run the system
@@ -439,8 +449,7 @@ static inline void disable_si_irq(struct smi_info *smi_info)
 		start_disable_irq(smi_info);
 		smi_info->interrupt_disabled = 1;
 		if (!atomic_read(&smi_info->stop_operation))
-			mod_timer(&smi_info->si_timer,
-				  jiffies + SI_TIMEOUT_JIFFIES);
+			smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
 	}
 }
 
@@ -900,15 +909,7 @@ static void sender(void                *send_info,
 		list_add_tail(&msg->link, &smi_info->xmit_msgs);
 
 	if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) {
-		/*
-		 * last_timeout_jiffies is updated here to avoid
-		 * smi_timeout() handler passing very large time_diff
-		 * value to smi_event_handler() that causes
-		 * the send command to abort.
-		 */
-		smi_info->last_timeout_jiffies = jiffies;
-
-		mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+		smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
 
 		if (smi_info->thread)
 			wake_up_process(smi_info->thread);
@@ -997,6 +998,17 @@ static int ipmi_thread(void *data)
 
 		spin_lock_irqsave(&(smi_info->si_lock), flags);
 		smi_result = smi_event_handler(smi_info, 0);
+
+		/*
+		 * If the driver is doing something, there is a possible
+		 * race with the timer.  If the timer handler see idle,
+		 * and the thread here sees something else, the timer
+		 * handler won't restart the timer even though it is
+		 * required.  So start it here if necessary.
+		 */
+		if (smi_result != SI_SM_IDLE && !smi_info->timer_running)
+			smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
 		spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 		busy_wait = ipmi_thread_busy_wait(smi_result, smi_info,
 						  &busy_until);
@@ -1066,10 +1078,6 @@ static void smi_timeout(unsigned long data)
 		     * SI_USEC_PER_JIFFY);
 	smi_result = smi_event_handler(smi_info, time_diff);
 
-	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
-
-	smi_info->last_timeout_jiffies = jiffies_now;
-
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		/* Running with interrupts, only do long timeouts. */
 		timeout = jiffies + SI_TIMEOUT_JIFFIES;
@@ -1091,7 +1099,10 @@ static void smi_timeout(unsigned long data)
 
  do_mod_timer:
 	if (smi_result != SI_SM_IDLE)
-		mod_timer(&(smi_info->si_timer), timeout);
+		smi_mod_timer(smi_info, timeout);
+	else
+		smi_info->timer_running = false;
+	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 }
 
 static irqreturn_t si_irq_handler(int irq, void *data)
@@ -1139,8 +1150,7 @@ static int smi_start_processing(void       *send_info,
 
 	/* Set up the timer that drives the interface. */
 	setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi);
-	new_smi->last_timeout_jiffies = jiffies;
-	mod_timer(&new_smi->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+	smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
 
 	/*
 	 * Check if the user forcefully enabled the daemon.
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 35487e8ded59..aee3464a5bdc 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -933,8 +933,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * pool while mixing, and hash one final time.
 	 */
 	sha_transform(hash.w, extract, workspace);
-	memset(extract, 0, sizeof(extract));
-	memset(workspace, 0, sizeof(workspace));
+	memzero_explicit(extract, sizeof(extract));
+	memzero_explicit(workspace, sizeof(workspace));
 
 	/*
 	 * In case the hash function has some recognizable output
@@ -957,7 +957,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	}
 
 	memcpy(out, &hash, EXTRACT_SIZE);
-	memset(&hash, 0, sizeof(hash));
+	memzero_explicit(&hash, sizeof(hash));
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,
@@ -1005,7 +1005,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 	}
 
 	/* Wipe data just returned from memory */
-	memset(tmp, 0, sizeof(tmp));
+	memzero_explicit(tmp, sizeof(tmp));
 
 	return ret;
 }
@@ -1043,7 +1043,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 	}
 
 	/* Wipe data just returned from memory */
-	memset(tmp, 0, sizeof(tmp));
+	memzero_explicit(tmp, sizeof(tmp));
 
 	return ret;
 }
@@ -1462,12 +1462,11 @@ ctl_table random_table[] = {
 
 static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-static int __init random_int_secret_init(void)
+int random_int_secret_init(void)
 {
 	get_random_bytes(random_int_secret, sizeof(random_int_secret));
 	return 0;
 }
-late_initcall(random_int_secret_init);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index f3223aac4df1..6e8d65e9b1d3 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -190,7 +190,7 @@ static int bind_get(int number, dev_t *dev)
 	struct raw_device_data *rawdev;
 	struct block_device *bdev;
 
-	if (number <= 0 || number >= MAX_RAW_MINORS)
+	if (number <= 0 || number >= max_raw_minors)
 		return -EINVAL;
 
 	rawdev = &raw_devices[number];
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index 7c3b3dcbfbc8..f659a571ad23 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -533,11 +533,10 @@ static int tpm_startup(struct tpm_chip *chip, __be16 startup_type)
 int tpm_get_timeouts(struct tpm_chip *chip)
 {
 	struct tpm_cmd_t tpm_cmd;
-	struct timeout_t *timeout_cap;
+	unsigned long new_timeout[4];
+	unsigned long old_timeout[4];
 	struct duration_t *duration_cap;
 	ssize_t rc;
-	u32 timeout;
-	unsigned int scale = 1;
 
 	tpm_cmd.header.in = tpm_getcap_header;
 	tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
@@ -571,25 +570,46 @@ int tpm_get_timeouts(struct tpm_chip *chip)
 	    != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32))
 		return -EINVAL;
 
-	timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout;
-	/* Don't overwrite default if value is 0 */
-	timeout = be32_to_cpu(timeout_cap->a);
-	if (timeout && timeout < 1000) {
-		/* timeouts in msec rather usec */
-		scale = 1000;
-		chip->vendor.timeout_adjusted = true;
+	old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a);
+	old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b);
+	old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c);
+	old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d);
+	memcpy(new_timeout, old_timeout, sizeof(new_timeout));
+
+	/*
+	 * Provide ability for vendor overrides of timeout values in case
+	 * of misreporting.
+	 */
+	if (chip->vendor.update_timeouts != NULL)
+		chip->vendor.timeout_adjusted =
+			chip->vendor.update_timeouts(chip, new_timeout);
+
+	if (!chip->vendor.timeout_adjusted) {
+		/* Don't overwrite default if value is 0 */
+		if (new_timeout[0] != 0 && new_timeout[0] < 1000) {
+			int i;
+
+			/* timeouts in msec rather usec */
+			for (i = 0; i != ARRAY_SIZE(new_timeout); i++)
+				new_timeout[i] *= 1000;
+			chip->vendor.timeout_adjusted = true;
+		}
 	}
-	if (timeout)
-		chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->b);
-	if (timeout)
-		chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->c);
-	if (timeout)
-		chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->d);
-	if (timeout)
-		chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale);
+
+	/* Report adjusted timeouts */
+	if (chip->vendor.timeout_adjusted) {
+		dev_info(chip->dev,
+			 HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n",
+			 old_timeout[0], new_timeout[0],
+			 old_timeout[1], new_timeout[1],
+			 old_timeout[2], new_timeout[2],
+			 old_timeout[3], new_timeout[3]);
+	}
+
+	chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]);
+	chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]);
+	chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]);
+	chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]);
 
 duration:
 	tpm_cmd.header.in = tpm_getcap_header;
@@ -1423,13 +1443,13 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 	int err, total = 0, retries = 5;
 	u8 *dest = out;
 
+	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
+		return -EINVAL;
+
 	chip = tpm_chip_find_get(chip_num);
 	if (chip == NULL)
 		return -ENODEV;
 
-	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
-		return -EINVAL;
-
 	do {
 		tpm_cmd.header.in = tpm_getrandom_header;
 		tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
@@ -1448,6 +1468,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 		num_bytes -= recd;
 	} while (retries-- && total < max);
 
+	tpm_chip_put(chip);
 	return total ? total : -EIO;
 }
 EXPORT_SYMBOL_GPL(tpm_get_random);
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 0770d1d79366..deffda7678a0 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -95,6 +95,9 @@ struct tpm_vendor_specific {
 	int (*send) (struct tpm_chip *, u8 *, size_t);
 	void (*cancel) (struct tpm_chip *);
 	u8 (*status) (struct tpm_chip *);
+	bool (*update_timeouts)(struct tpm_chip *chip,
+				unsigned long *timeout_cap);
+
 	void (*release) (struct device *);
 	struct miscdevice miscdev;
 	struct attribute_group *attr_group;
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 5bb8e2ddd3b3..156bd3c72770 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -410,6 +410,8 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 			     &chip->vendor.read_queue)
 	       == 0) {
 		burstcnt = get_burstcount(chip);
+		if (burstcnt < 0)
+			return burstcnt;
 		len = min_t(int, burstcnt, count - size);
 		I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
 		size += len;
@@ -451,7 +453,8 @@ static irqreturn_t tpm_ioserirq_handler(int irq, void *dev_id)
 static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 			    size_t len)
 {
-	u32 status, burstcnt = 0, i, size;
+	u32 status, i, size;
+	int burstcnt = 0;
 	int ret;
 	u8 data;
 	struct i2c_client *client;
@@ -482,6 +485,8 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 
 	for (i = 0; i < len - 1;) {
 		burstcnt = get_burstcount(chip);
+		if (burstcnt < 0)
+			return burstcnt;
 		size = min_t(int, len - i - 1, burstcnt);
 		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size);
 		if (ret < 0)
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index 2168d15bc728..811ad1e4d802 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -27,15 +27,18 @@ static char *tpm_device_name = "TPM";
 static acpi_status ppi_callback(acpi_handle handle, u32 level, void *context,
 				void **return_value)
 {
-	acpi_status status;
+	acpi_status status = AE_OK;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
-	if (strstr(buffer.pointer, context) != NULL) {
-		*return_value = handle;
+
+	if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) {
+		if (strstr(buffer.pointer, context) != NULL) {
+			*return_value = handle;
+			status = AE_CTRL_TERMINATE;
+		}
 		kfree(buffer.pointer);
-		return AE_CTRL_TERMINATE;
 	}
-	return AE_OK;
+
+	return status;
 }
 
 static inline void ppi_assign_params(union acpi_object params[4],
@@ -169,7 +172,7 @@ static ssize_t tpm_store_ppi_request(struct device *dev,
 	 * is updated with function index from SUBREQ to SUBREQ2 since PPI
 	 * version 1.1
 	 */
-	if (strcmp(version, "1.1") == -1)
+	if (strcmp(version, "1.1") < 0)
 		params[2].integer.value = TPM_PPI_FN_SUBREQ;
 	else
 		params[2].integer.value = TPM_PPI_FN_SUBREQ2;
@@ -179,7 +182,7 @@ static ssize_t tpm_store_ppi_request(struct device *dev,
 	 * string/package type. For PPI version 1.0 and 1.1, use buffer type
 	 * for compatibility, and use package type since 1.2 according to spec.
 	 */
-	if (strcmp(version, "1.2") == -1) {
+	if (strcmp(version, "1.2") < 0) {
 		params[3].type = ACPI_TYPE_BUFFER;
 		params[3].buffer.length = sizeof(req);
 		sscanf(buf, "%d", &req);
@@ -245,7 +248,7 @@ static ssize_t tpm_show_ppi_transition_action(struct device *dev,
 	 * (e.g. Capella with PPI 1.0) need integer/string/buffer type, so for
 	 * compatibility, define params[3].type as buffer, if PPI version < 1.2
 	 */
-	if (strcmp(version, "1.2") == -1) {
+	if (strcmp(version, "1.2") < 0) {
 		params[3].type = ACPI_TYPE_BUFFER;
 		params[3].buffer.length =  0;
 		params[3].buffer.pointer = NULL;
@@ -387,7 +390,7 @@ static ssize_t show_ppi_operations(char *buf, u32 start, u32 end)
 	kfree(output.pointer);
 	output.length = ACPI_ALLOCATE_BUFFER;
 	output.pointer = NULL;
-	if (strcmp(version, "1.2") == -1)
+	if (strcmp(version, "1.2") < 0)
 		return -EPERM;
 
 	params[2].integer.value = TPM_PPI_FN_GETOPR;
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 8a41b6be23a0..72f21377fa02 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -373,6 +373,36 @@ out_err:
 	return rc;
 }
 
+struct tis_vendor_timeout_override {
+	u32 did_vid;
+	unsigned long timeout_us[4];
+};
+
+static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = {
+	/* Atmel 3204 */
+	{ 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000),
+			(TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } },
+};
+
+static bool tpm_tis_update_timeouts(struct tpm_chip *chip,
+				    unsigned long *timeout_cap)
+{
+	int i;
+	u32 did_vid;
+
+	did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0));
+
+	for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) {
+		if (vendor_timeout_overrides[i].did_vid != did_vid)
+			continue;
+		memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us,
+		       sizeof(vendor_timeout_overrides[i].timeout_us));
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Early probing for iTPM with STS_DATA_EXPECT flaw.
  * Try sending command without itpm flag set and if that
@@ -475,6 +505,7 @@ static struct tpm_vendor_specific tpm_tis = {
 	.recv = tpm_tis_recv,
 	.send = tpm_tis_send,
 	.cancel = tpm_tis_ready,
+	.update_timeouts = tpm_tis_update_timeouts,
 	.req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_canceled = tpm_tis_req_canceled,
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 0357ac44638b..d0d9b2124752 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -42,7 +42,7 @@ config COMMON_CLK_WM831X
 
 config COMMON_CLK_VERSATILE
 	bool "Clock driver for ARM Reference designs"
-	depends on ARCH_INTEGRATOR || ARCH_REALVIEW || ARCH_VEXPRESS
+	depends on ARCH_INTEGRATOR || ARCH_REALVIEW || ARCH_VEXPRESS || ARM64
 	---help---
           Supports clocking on ARM Reference designs:
 	  - Integrator/AP and Integrator/CP
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 6d9674160430..a885284ead4d 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -24,7 +24,7 @@
  * Traits of this clock:
  * prepare - clk_prepare only ensures that parents are prepared
  * enable - clk_enable only ensures that parents are enabled
- * rate - rate is adjustable.  clk->rate = parent->rate / divisor
+ * rate - rate is adjustable.  clk->rate = DIV_ROUND_UP(parent->rate / divisor)
  * parent - fixed parent.  No clk_set_parent support
  */
 
@@ -43,6 +43,17 @@ static unsigned int _get_table_maxdiv(const struct clk_div_table *table)
 	return maxdiv;
 }
 
+static unsigned int _get_table_mindiv(const struct clk_div_table *table)
+{
+	unsigned int mindiv = UINT_MAX;
+	const struct clk_div_table *clkt;
+
+	for (clkt = table; clkt->div; clkt++)
+		if (clkt->div < mindiv)
+			mindiv = clkt->div;
+	return mindiv;
+}
+
 static unsigned int _get_maxdiv(struct clk_divider *divider)
 {
 	if (divider->flags & CLK_DIVIDER_ONE_BASED)
@@ -87,7 +98,7 @@ static unsigned int _get_table_val(const struct clk_div_table *table,
 	return 0;
 }
 
-static unsigned int _get_val(struct clk_divider *divider, u8 div)
+static unsigned int _get_val(struct clk_divider *divider, unsigned int div)
 {
 	if (divider->flags & CLK_DIVIDER_ONE_BASED)
 		return div;
@@ -115,7 +126,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 		return parent_rate;
 	}
 
-	return parent_rate / div;
+	return DIV_ROUND_UP(parent_rate, div);
 }
 
 /*
@@ -144,6 +155,91 @@ static bool _is_valid_div(struct clk_divider *divider, unsigned int div)
 	return true;
 }
 
+static int _round_up_table(const struct clk_div_table *table, int div)
+{
+	const struct clk_div_table *clkt;
+	int up = INT_MAX;
+
+	for (clkt = table; clkt->div; clkt++) {
+		if (clkt->div == div)
+			return clkt->div;
+		else if (clkt->div < div)
+			continue;
+
+		if ((clkt->div - div) < (up - div))
+			up = clkt->div;
+	}
+
+	return up;
+}
+
+static int _round_down_table(const struct clk_div_table *table, int div)
+{
+	const struct clk_div_table *clkt;
+	int down = _get_table_mindiv(table);
+
+	for (clkt = table; clkt->div; clkt++) {
+		if (clkt->div == div)
+			return clkt->div;
+		else if (clkt->div > div)
+			continue;
+
+		if ((div - clkt->div) < (div - down))
+			down = clkt->div;
+	}
+
+	return down;
+}
+
+static int _div_round_up(struct clk_divider *divider,
+		unsigned long parent_rate, unsigned long rate)
+{
+	int div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+		div = __roundup_pow_of_two(div);
+	if (divider->table)
+		div = _round_up_table(divider->table, div);
+
+	return div;
+}
+
+static int _div_round_closest(struct clk_divider *divider,
+		unsigned long parent_rate, unsigned long rate)
+{
+	int up, down, div;
+
+	up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
+
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) {
+		up = __roundup_pow_of_two(div);
+		down = __rounddown_pow_of_two(div);
+	} else if (divider->table) {
+		up = _round_up_table(divider->table, div);
+		down = _round_down_table(divider->table, div);
+	}
+
+	return (up - div) <= (div - down) ? up : down;
+}
+
+static int _div_round(struct clk_divider *divider, unsigned long parent_rate,
+		unsigned long rate)
+{
+	if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return _div_round_closest(divider, parent_rate, rate);
+
+	return _div_round_up(divider, parent_rate, rate);
+}
+
+static bool _is_best_div(struct clk_divider *divider,
+		unsigned long rate, unsigned long now, unsigned long best)
+{
+	if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return abs(rate - now) < abs(rate - best);
+
+	return now <= rate && now > best;
+}
+
 static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 		unsigned long *best_parent_rate)
 {
@@ -158,7 +254,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
 		parent_rate = *best_parent_rate;
-		bestdiv = DIV_ROUND_UP(parent_rate, rate);
+		bestdiv = _div_round(divider, parent_rate, rate);
 		bestdiv = bestdiv == 0 ? 1 : bestdiv;
 		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
 		return bestdiv;
@@ -175,8 +271,8 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 			continue;
 		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
 				MULT_ROUND_UP(rate, i));
-		now = parent_rate / i;
-		if (now <= rate && now > best) {
+		now = DIV_ROUND_UP(parent_rate, i);
+		if (_is_best_div(divider, rate, now, best)) {
 			bestdiv = i;
 			best = now;
 			*best_parent_rate = parent_rate;
@@ -197,7 +293,7 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
 	int div;
 	div = clk_divider_bestdiv(hw, rate, prate);
 
-	return *prate / div;
+	return DIV_ROUND_UP(*prate, div);
 }
 
 static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -208,7 +304,11 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long flags = 0;
 	u32 val;
 
-	div = parent_rate / rate;
+	div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (!_is_valid_div(divider, div))
+		return -EINVAL;
+
 	value = _get_val(divider, div);
 
 	if (value > div_mask(divider))
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 1144e8c7579d..fccac4a41386 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2084,6 +2084,12 @@ struct clk *of_clk_get_from_provider(struct of_phandle_args *clkspec)
 	return clk;
 }
 
+int of_clk_get_parent_count(struct device_node *np)
+{
+	return of_count_phandle_with_args(np, "clocks", "#clock-cells");
+}
+EXPORT_SYMBOL_GPL(of_clk_get_parent_count);
+
 const char *of_clk_get_parent_name(struct device_node *np, int index)
 {
 	struct of_phandle_args clkspec;
diff --git a/drivers/clk/mvebu/clk-core.c b/drivers/clk/mvebu/clk-core.c
index 0a53edbae8b8..e5c477b49934 100644
--- a/drivers/clk/mvebu/clk-core.c
+++ b/drivers/clk/mvebu/clk-core.c
@@ -126,8 +126,8 @@ static void __init mvebu_clk_core_setup(struct device_node *np,
 #define	    SARH_AXP_FAB_FREQ_OPT_SHIFT	    4
 
 static const u32 __initconst armada_370_tclk_frequencies[] = {
-	16600000,
-	20000000,
+	166000000,
+	200000000,
 };
 
 static u32 __init armada_370_get_tclk_freq(void __iomem *sar)
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 3c1f88868f29..b4b283b47308 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -40,7 +40,7 @@
 #define SRC_TOP1		0xc214
 #define SRC_CAM			0xc220
 #define SRC_TV			0xc224
-#define SRC_MFC			0xcc28
+#define SRC_MFC			0xc228
 #define SRC_G3D			0xc22c
 #define E4210_SRC_IMAGE		0xc230
 #define SRC_LCD0		0xc234
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 22d7699e7ced..92afc060673e 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -325,8 +325,8 @@ struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(smmu_gscl2, "smmu_gscl2", "aclk266", GATE_IP_GSCL, 9, 0, 0),
 	GATE(smmu_gscl3, "smmu_gscl3", "aclk266", GATE_IP_GSCL, 10, 0, 0),
 	GATE(mfc, "mfc", "aclk333", GATE_IP_MFC, 0, 0, 0),
-	GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 1, 0, 0),
-	GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 2, 0, 0),
+	GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 2, 0, 0),
+	GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 1, 0, 0),
 	GATE(rotator, "rotator", "aclk266", GATE_IP_GEN, 1, 0, 0),
 	GATE(jpeg, "jpeg", "aclk166", GATE_IP_GEN, 2, 0, 0),
 	GATE(mdma1, "mdma1", "aclk266", GATE_IP_GEN, 4, 0, 0),
@@ -377,7 +377,8 @@ struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(hsi2c2, "hsi2c2", "aclk66", GATE_IP_PERIC, 30, 0, 0),
 	GATE(hsi2c3, "hsi2c3", "aclk66", GATE_IP_PERIC, 31, 0, 0),
 	GATE(chipid, "chipid", "aclk66", GATE_IP_PERIS, 0, 0, 0),
-	GATE(sysreg, "sysreg", "aclk66", GATE_IP_PERIS, 1, 0, 0),
+	GATE(sysreg, "sysreg", "aclk66",
+			GATE_IP_PERIS, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(pmu, "pmu", "aclk66", GATE_IP_PERIS, 2, CLK_IGNORE_UNUSED, 0),
 	GATE(tzpc0, "tzpc0", "aclk66", GATE_IP_PERIS, 6, 0, 0),
 	GATE(tzpc1, "tzpc1", "aclk66", GATE_IP_PERIS, 7, 0, 0),
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index 080c3c5e33f6..1fe259021747 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -211,7 +211,7 @@ static inline void spear310_clk_init(void) { }
 /* array of all spear 320 clock lookups */
 #ifdef CONFIG_MACH_SPEAR320
 
-#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0000)
+#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0010)
 #define SPEAR320_EXT_CTRL_REG		(soc_config_base + 0x0018)
 
 	#define SPEAR320_UARTX_PCLK_MASK		0x1
diff --git a/drivers/clk/versatile/Makefile b/drivers/clk/versatile/Makefile
index c16ca787170a..6e76bf87ca87 100644
--- a/drivers/clk/versatile/Makefile
+++ b/drivers/clk/versatile/Makefile
@@ -4,4 +4,4 @@ obj-$(CONFIG_ARCH_INTEGRATOR)	+= clk-integrator.o
 obj-$(CONFIG_INTEGRATOR_IMPD1)	+= clk-impd1.o
 obj-$(CONFIG_ARCH_REALVIEW)	+= clk-realview.o
 obj-$(CONFIG_ARCH_VEXPRESS)	+= clk-vexpress.o clk-sp810.o
-obj-$(CONFIG_VEXPRESS_CONFIG)	+= clk-vexpress-osc.o
+obj-$(CONFIG_VEXPRESS_CONFIG)	+= clk-vexpress-osc.o clk-vexpress-spc.o
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index 67ccf4aa7277..f5e4c21b301f 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -107,7 +107,7 @@ static int icst_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	vco = icst_hz_to_vco(icst->params, rate);
 	icst->rate = icst_hz(icst->params, vco);
-	vco_set(icst->vcoreg, icst->lockreg, vco);
+	vco_set(icst->lockreg, icst->vcoreg, vco);
 	return 0;
 }
 
diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c
index 256c8be74df8..a535c7bf8574 100644
--- a/drivers/clk/versatile/clk-vexpress-osc.c
+++ b/drivers/clk/versatile/clk-vexpress-osc.c
@@ -102,12 +102,12 @@ void __init vexpress_osc_of_setup(struct device_node *node)
 
 	osc = kzalloc(sizeof(*osc), GFP_KERNEL);
 	if (!osc)
-		goto error;
+		return;
 
 	osc->func = vexpress_config_func_get_by_node(node);
 	if (!osc->func) {
 		pr_err("Failed to obtain config func for node '%s'!\n",
-				node->name);
+				node->full_name);
 		goto error;
 	}
 
@@ -119,7 +119,7 @@ void __init vexpress_osc_of_setup(struct device_node *node)
 
 	of_property_read_string(node, "clock-output-names", &init.name);
 	if (!init.name)
-		init.name = node->name;
+		init.name = node->full_name;
 
 	init.ops = &vexpress_osc_ops;
 	init.flags = CLK_IS_ROOT;
diff --git a/drivers/clk/versatile/clk-vexpress-spc.c b/drivers/clk/versatile/clk-vexpress-spc.c
new file mode 100644
index 000000000000..bb566e244b0c
--- /dev/null
+++ b/drivers/clk/versatile/clk-vexpress-spc.c
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2012 Linaro
+ *
+ * Author: Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/* SPC clock programming interface for Vexpress cpus */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vexpress.h>
+
+struct clk_spc {
+	struct clk_hw hw;
+	spinlock_t *lock;
+	int cluster;
+};
+
+#define to_clk_spc(spc) container_of(spc, struct clk_spc, hw)
+
+static unsigned long spc_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct clk_spc *spc = to_clk_spc(hw);
+	u32 freq;
+
+	if (vexpress_spc_get_performance(spc->cluster, &freq)) {
+		return -EIO;
+		pr_err("%s: Failed", __func__);
+	}
+
+	return freq * 1000;
+}
+
+static long spc_round_rate(struct clk_hw *hw, unsigned long drate,
+		unsigned long *parent_rate)
+{
+	return drate;
+}
+
+static int spc_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct clk_spc *spc = to_clk_spc(hw);
+
+	return vexpress_spc_set_performance(spc->cluster, rate / 1000);
+}
+
+static struct clk_ops clk_spc_ops = {
+	.recalc_rate = spc_recalc_rate,
+	.round_rate = spc_round_rate,
+	.set_rate = spc_set_rate,
+};
+
+struct clk *vexpress_clk_register_spc(const char *name, int cluster_id)
+{
+	struct clk_init_data init;
+	struct clk_spc *spc;
+	struct clk *clk;
+
+	if (!name) {
+		pr_err("Invalid name passed");
+		return ERR_PTR(-EINVAL);
+	}
+
+	spc = kzalloc(sizeof(*spc), GFP_KERNEL);
+	if (!spc) {
+		pr_err("could not allocate spc clk\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spc->hw.init = &init;
+	spc->cluster = cluster_id;
+
+	init.name = name;
+	init.ops = &clk_spc_ops;
+	init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+	init.num_parents = 0;
+
+	clk = clk_register(NULL, &spc->hw);
+	if (!IS_ERR_OR_NULL(clk))
+		return clk;
+
+	pr_err("clk register failed\n");
+	kfree(spc);
+
+	return NULL;
+}
+
+#if defined(CONFIG_OF)
+void __init vexpress_clk_of_register_spc(void)
+{
+	char name[14] = "cpu-cluster.X";
+	struct device_node *node = NULL;
+	struct clk *clk;
+	const u32 *val;
+	int cluster_id = 0, len;
+
+	if (!of_find_compatible_node(NULL, NULL, "arm,vexpress-spc")) {
+		pr_debug("%s: No SPC found, Exiting!!\n", __func__);
+		return;
+	}
+
+	while ((node = of_find_node_by_name(node, "cluster"))) {
+		val = of_get_property(node, "reg", &len);
+		if (val && len == 4)
+			cluster_id = be32_to_cpup(val);
+
+		name[12] = cluster_id + '0';
+		clk = vexpress_clk_register_spc(name, cluster_id);
+		if (IS_ERR(clk))
+			return;
+
+		pr_debug("Registered clock '%s'\n", name);
+		clk_register_clkdev(clk, NULL, name);
+	}
+}
+CLK_OF_DECLARE(spc, "arm,vexpress-spc", vexpress_clk_of_register_spc);
+#endif
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index f151c6cf27c3..593485b02ee5 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -67,6 +67,21 @@ config ARM_ARCH_TIMER
 	bool
 	select CLKSRC_OF if OF
 
+config ARM_ARCH_TIMER_EVTSTREAM
+	bool "Support for ARM architected timer event stream generation"
+	default y if ARM_ARCH_TIMER
+	help
+	  This option enables support for event stream generation based on
+	  the ARM architected timer. It is used for waking up CPUs executing
+	  the wfe instruction at a frequency represented as a power-of-2
+	  divisor of the clock rate.
+	  The main use of the event stream is wfe-based timeouts of userspace
+	  locking implementations. It might also be useful for imposing timeout
+	  on wfe to safeguard against any programming errors in case an expected
+	  event is not generated.
+	  This must be disabled for hardware validation purposes to detect any
+	  hardware anomalies of missing events.
+
 config CLKSRC_METAG_GENERIC
 	def_bool y if METAG
 	help
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 053d846ab5b1..67bbbd8ae507 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -13,16 +13,43 @@
 #include <linux/device.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
+#include <linux/of_address.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 #include <asm/arch_timer.h>
 #include <asm/virt.h>
 
 #include <clocksource/arm_arch_timer.h>
 
+#define CNTTIDR		0x08
+#define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
+
+#define CNTVCT_LO	0x08
+#define CNTVCT_HI	0x0c
+#define CNTFRQ		0x10
+#define CNTP_TVAL	0x28
+#define CNTP_CTL	0x2c
+#define CNTV_TVAL	0x38
+#define CNTV_CTL	0x3c
+
+#define ARCH_CP15_TIMER	BIT(0)
+#define ARCH_MEM_TIMER	BIT(1)
+static unsigned arch_timers_present __initdata;
+
+static void __iomem *arch_counter_base;
+
+struct arch_timer {
+	void __iomem *base;
+	struct clock_event_device evt;
+};
+
+#define to_arch_timer(e) container_of(e, struct arch_timer, evt)
+
 static u32 arch_timer_rate;
 
 enum ppi_nr {
@@ -38,19 +65,82 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 static struct clock_event_device __percpu *arch_timer_evt;
 
 static bool arch_timer_use_virtual = true;
+static bool arch_timer_mem_use_virtual;
 
 /*
  * Architected system timer support.
  */
 
-static inline irqreturn_t timer_handler(const int access,
+static __always_inline
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+		struct clock_event_device *clk)
+{
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		arch_timer_reg_write_cp15(access, reg, val);
+	}
+}
+
+static __always_inline
+u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
+		struct clock_event_device *clk)
+{
+	u32 val;
+
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		val = arch_timer_reg_read_cp15(access, reg);
+	}
+
+	return val;
+}
+
+static __always_inline irqreturn_t timer_handler(const int access,
 					struct clock_event_device *evt)
 {
 	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, evt);
 	if (ctrl & ARCH_TIMER_CTRL_IT_STAT) {
 		ctrl |= ARCH_TIMER_CTRL_IT_MASK;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, evt);
 		evt->event_handler(evt);
 		return IRQ_HANDLED;
 	}
@@ -72,15 +162,30 @@ static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id)
 	return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt);
 }
 
-static inline void timer_set_mode(const int access, int mode)
+static irqreturn_t arch_timer_handler_phys_mem(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	return timer_handler(ARCH_TIMER_MEM_PHYS_ACCESS, evt);
+}
+
+static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt);
+}
+
+static __always_inline void timer_set_mode(const int access, int mode,
+				  struct clock_event_device *clk)
 {
 	unsigned long ctrl;
 	switch (mode) {
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
 		ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 		break;
 	default:
 		break;
@@ -90,60 +195,121 @@ static inline void timer_set_mode(const int access, int mode)
 static void arch_timer_set_mode_virt(enum clock_event_mode mode,
 				     struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode);
+	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode, clk);
 }
 
 static void arch_timer_set_mode_phys(enum clock_event_mode mode,
 				     struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode);
+	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode, clk);
+}
+
+static void arch_timer_set_mode_virt_mem(enum clock_event_mode mode,
+					 struct clock_event_device *clk)
+{
+	timer_set_mode(ARCH_TIMER_MEM_VIRT_ACCESS, mode, clk);
+}
+
+static void arch_timer_set_mode_phys_mem(enum clock_event_mode mode,
+					 struct clock_event_device *clk)
+{
+	timer_set_mode(ARCH_TIMER_MEM_PHYS_ACCESS, mode, clk);
 }
 
-static inline void set_next_event(const int access, unsigned long evt)
+static __always_inline void set_next_event(const int access, unsigned long evt,
+				  struct clock_event_device *clk)
 {
 	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
 	ctrl |= ARCH_TIMER_CTRL_ENABLE;
 	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt);
-	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt, clk);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
 static int arch_timer_set_next_event_virt(unsigned long evt,
-					  struct clock_event_device *unused)
+					  struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt);
+	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
 
 static int arch_timer_set_next_event_phys(unsigned long evt,
-					  struct clock_event_device *unused)
+					  struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt);
+	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
 
-static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
+static void arch_timer_configure_evtstream(void)
 {
-	clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
-	clk->name = "arch_sys_timer";
-	clk->rating = 450;
-	if (arch_timer_use_virtual) {
-		clk->irq = arch_timer_ppi[VIRT_PPI];
-		clk->set_mode = arch_timer_set_mode_virt;
-		clk->set_next_event = arch_timer_set_next_event_virt;
+	int evt_stream_div, pos;
+
+	/* Find the closest power of two to the divisor */
+	evt_stream_div = arch_timer_rate / ARCH_TIMER_EVT_STREAM_FREQ;
+	pos = fls(evt_stream_div);
+	if (pos > 1 && !(evt_stream_div & (1 << (pos - 2))))
+		pos--;
+	/* enable event stream */
+	arch_timer_evtstrm_enable(min(pos, 15));
+}
+
+static int arch_timer_set_next_event_virt_mem(unsigned long evt,
+					      struct clock_event_device *clk)
+{
+	set_next_event(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk);
+	return 0;
+}
+
+static int arch_timer_set_next_event_phys_mem(unsigned long evt,
+					      struct clock_event_device *clk)
+{
+	set_next_event(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk);
+	return 0;
+}
+
+static void __cpuinit __arch_timer_setup(unsigned type,
+				       struct clock_event_device *clk)
+{
+	clk->features = CLOCK_EVT_FEAT_ONESHOT;
+
+	if (type == ARCH_CP15_TIMER) {
+		clk->features |= CLOCK_EVT_FEAT_C3STOP;
+		clk->name = "arch_sys_timer";
+		clk->rating = 450;
+		clk->cpumask = cpumask_of(smp_processor_id());
+		if (arch_timer_use_virtual) {
+			clk->irq = arch_timer_ppi[VIRT_PPI];
+			clk->set_mode = arch_timer_set_mode_virt;
+			clk->set_next_event = arch_timer_set_next_event_virt;
+		} else {
+			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+			clk->set_mode = arch_timer_set_mode_phys;
+			clk->set_next_event = arch_timer_set_next_event_phys;
+		}
 	} else {
-		clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
-		clk->set_mode = arch_timer_set_mode_phys;
-		clk->set_next_event = arch_timer_set_next_event_phys;
+		clk->name = "arch_mem_timer";
+		clk->rating = 400;
+		clk->cpumask = cpu_all_mask;
+		if (arch_timer_mem_use_virtual) {
+			clk->set_mode = arch_timer_set_mode_virt_mem;
+			clk->set_next_event =
+				arch_timer_set_next_event_virt_mem;
+		} else {
+			clk->set_mode = arch_timer_set_mode_phys_mem;
+			clk->set_next_event =
+				arch_timer_set_next_event_phys_mem;
+		}
 	}
 
-	clk->cpumask = cpumask_of(smp_processor_id());
+	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, clk);
 
-	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, NULL);
+	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
+}
 
-	clockevents_config_and_register(clk, arch_timer_rate,
-					0xf, 0x7fffffff);
+static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
+{
+	__arch_timer_setup(ARCH_CP15_TIMER, clk);
 
 	if (arch_timer_use_virtual)
 		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
@@ -154,31 +320,47 @@ static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
 	}
 
 	arch_counter_set_user_access();
+	if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
+		arch_timer_configure_evtstream();
 
 	return 0;
 }
 
-static int arch_timer_available(void)
+static void
+arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np)
 {
-	u32 freq;
-
-	if (arch_timer_rate == 0) {
-		freq = arch_timer_get_cntfrq();
-
-		/* Check the timer frequency. */
-		if (freq == 0) {
-			pr_warn("Architected timer frequency not available\n");
-			return -EINVAL;
-		}
+	/* Who has more than one independent system counter? */
+	if (arch_timer_rate)
+		return;
 
-		arch_timer_rate = freq;
+	/* Try to determine the frequency from the device tree or CNTFRQ */
+	if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) {
+		if (cntbase)
+			arch_timer_rate = readl_relaxed(cntbase + CNTFRQ);
+		else
+			arch_timer_rate = arch_timer_get_cntfrq();
 	}
 
-	pr_info_once("Architected local timer running at %lu.%02luMHz (%s).\n",
+	/* Check the timer frequency. */
+	if (arch_timer_rate == 0)
+		pr_warn("Architected timer frequency not available\n");
+}
+
+static void arch_timer_banner(unsigned type)
+{
+	pr_info("Architected %s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
+		     type & ARCH_CP15_TIMER ? "cp15" : "",
+		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  " and " : "",
+		     type & ARCH_MEM_TIMER ? "mmio" : "",
 		     (unsigned long)arch_timer_rate / 1000000,
 		     (unsigned long)(arch_timer_rate / 10000) % 100,
-		     arch_timer_use_virtual ? "virt" : "phys");
-	return 0;
+		     type & ARCH_CP15_TIMER ?
+			arch_timer_use_virtual ? "virt" : "phys" :
+			"",
+		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
+		     type & ARCH_MEM_TIMER ?
+			arch_timer_mem_use_virtual ? "virt" : "phys" :
+			"");
 }
 
 u32 arch_timer_get_rate(void)
@@ -186,11 +368,27 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }
 
-u64 arch_timer_read_counter(void)
+static u64 arch_counter_get_cntvct_mem(void)
 {
-	return arch_counter_get_cntvct();
+	u32 vct_lo, vct_hi, tmp_hi;
+
+	do {
+		vct_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+		vct_lo = readl_relaxed(arch_counter_base + CNTVCT_LO);
+		tmp_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+	} while (vct_hi != tmp_hi);
+
+	return ((u64) vct_hi << 32) | vct_lo;
 }
 
+/*
+ * Default to cp15 based access because arm64 uses this function for
+ * sched_clock() before DT is probed and the cp15 method is guaranteed
+ * to exist on arm64. arm doesn't use this before DT is probed so even
+ * if we don't have the cp15 accessors we won't have a problem.
+ */
+u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+
 static cycle_t arch_counter_read(struct clocksource *cs)
 {
 	return arch_counter_get_cntvct();
@@ -221,6 +419,23 @@ struct timecounter *arch_timer_get_timecounter(void)
 	return &timecounter;
 }
 
+static void __init arch_counter_register(unsigned type)
+{
+	u64 start_count;
+
+	/* Register the CP15 based counter if we have one */
+	if (type & ARCH_CP15_TIMER)
+		arch_timer_read_counter = arch_counter_get_cntvct;
+	else
+		arch_timer_read_counter = arch_counter_get_cntvct_mem;
+
+	start_count = arch_timer_read_counter();
+	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+	cyclecounter.mult = clocksource_counter.mult;
+	cyclecounter.shift = clocksource_counter.shift;
+	timecounter_init(&timecounter, &cyclecounter, start_count);
+}
+
 static void __cpuinit arch_timer_stop(struct clock_event_device *clk)
 {
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
@@ -260,27 +475,44 @@ static struct notifier_block arch_timer_cpu_nb __cpuinitdata = {
 	.notifier_call = arch_timer_cpu_notify,
 };
 
+#ifdef CONFIG_CPU_PM
+static unsigned int saved_cntkctl;
+static int arch_timer_cpu_pm_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	if (action == CPU_PM_ENTER)
+		saved_cntkctl = arch_timer_get_cntkctl();
+	else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
+		arch_timer_set_cntkctl(saved_cntkctl);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block arch_timer_cpu_pm_notifier = {
+	.notifier_call = arch_timer_cpu_pm_notify,
+};
+
+static int __init arch_timer_cpu_pm_init(void)
+{
+	return cpu_pm_register_notifier(&arch_timer_cpu_pm_notifier);
+}
+#else
+static int __init arch_timer_cpu_pm_init(void)
+{
+	return 0;
+}
+#endif
+
 static int __init arch_timer_register(void)
 {
 	int err;
 	int ppi;
 
-	err = arch_timer_available();
-	if (err)
-		goto out;
-
 	arch_timer_evt = alloc_percpu(struct clock_event_device);
 	if (!arch_timer_evt) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
-	cyclecounter.mult = clocksource_counter.mult;
-	cyclecounter.shift = clocksource_counter.shift;
-	timecounter_init(&timecounter, &cyclecounter,
-			 arch_counter_get_cntvct());
-
 	if (arch_timer_use_virtual) {
 		ppi = arch_timer_ppi[VIRT_PPI];
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
@@ -309,11 +541,17 @@ static int __init arch_timer_register(void)
 	if (err)
 		goto out_free_irq;
 
+	err = arch_timer_cpu_pm_init();
+	if (err)
+		goto out_unreg_notify;
+
 	/* Immediately configure the timer on the boot CPU */
 	arch_timer_setup(this_cpu_ptr(arch_timer_evt));
 
 	return 0;
 
+out_unreg_notify:
+	unregister_cpu_notifier(&arch_timer_cpu_nb);
 out_free_irq:
 	if (arch_timer_use_virtual)
 		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
@@ -331,24 +569,77 @@ out:
 	return err;
 }
 
+static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
+{
+	int ret;
+	irq_handler_t func;
+	struct arch_timer *t;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (!t)
+		return -ENOMEM;
+
+	t->base = base;
+	t->evt.irq = irq;
+	__arch_timer_setup(ARCH_MEM_TIMER, &t->evt);
+
+	if (arch_timer_mem_use_virtual)
+		func = arch_timer_handler_virt_mem;
+	else
+		func = arch_timer_handler_phys_mem;
+
+	ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
+	if (ret) {
+		pr_err("arch_timer: Failed to request mem timer irq\n");
+		kfree(t);
+	}
+
+	return ret;
+}
+
+static const struct of_device_id arch_timer_of_match[] __initconst = {
+	{ .compatible   = "arm,armv7-timer",    },
+	{ .compatible   = "arm,armv8-timer",    },
+	{},
+};
+
+static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
+	{ .compatible   = "arm,armv7-timer-mem", },
+	{},
+};
+
+static void __init arch_timer_common_init(void)
+{
+	unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
+
+	/* Wait until both nodes are probed if we have two timers */
+	if ((arch_timers_present & mask) != mask) {
+		if (of_find_matching_node(NULL, arch_timer_mem_of_match) &&
+				!(arch_timers_present & ARCH_MEM_TIMER))
+			return;
+		if (of_find_matching_node(NULL, arch_timer_of_match) &&
+				!(arch_timers_present & ARCH_CP15_TIMER))
+			return;
+	}
+
+	arch_timer_banner(arch_timers_present);
+	arch_counter_register(arch_timers_present);
+	arch_timer_arch_init();
+}
+
 static void __init arch_timer_init(struct device_node *np)
 {
-	u32 freq;
 	int i;
 
-	if (arch_timer_get_rate()) {
+	if (arch_timers_present & ARCH_CP15_TIMER) {
 		pr_warn("arch_timer: multiple nodes in dt, skipping\n");
 		return;
 	}
 
-	/* Try to determine the frequency from the device tree or CNTFRQ */
-	if (!of_property_read_u32(np, "clock-frequency", &freq))
-		arch_timer_rate = freq;
-
+	arch_timers_present |= ARCH_CP15_TIMER;
 	for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
 		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
-
-	of_node_put(np);
+	arch_timer_detect_rate(NULL, np);
 
 	/*
 	 * If HYP mode is available, we know that the physical timer
@@ -369,7 +660,73 @@ static void __init arch_timer_init(struct device_node *np)
 	}
 
 	arch_timer_register();
-	arch_timer_arch_init();
+	arch_timer_common_init();
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_init);
 CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_init);
+
+static void __init arch_timer_mem_init(struct device_node *np)
+{
+	struct device_node *frame, *best_frame = NULL;
+	void __iomem *cntctlbase, *base;
+	unsigned int irq;
+	u32 cnttidr;
+
+	arch_timers_present |= ARCH_MEM_TIMER;
+	cntctlbase = of_iomap(np, 0);
+	if (!cntctlbase) {
+		pr_err("arch_timer: Can't find CNTCTLBase\n");
+		return;
+	}
+
+	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
+	iounmap(cntctlbase);
+
+	/*
+	 * Try to find a virtual capable frame. Otherwise fall back to a
+	 * physical capable frame.
+	 */
+	for_each_available_child_of_node(np, frame) {
+		int n;
+
+		if (of_property_read_u32(frame, "frame-number", &n)) {
+			pr_err("arch_timer: Missing frame-number\n");
+			of_node_put(best_frame);
+			of_node_put(frame);
+			return;
+		}
+
+		if (cnttidr & CNTTIDR_VIRT(n)) {
+			of_node_put(best_frame);
+			best_frame = frame;
+			arch_timer_mem_use_virtual = true;
+			break;
+		}
+		of_node_put(best_frame);
+		best_frame = of_node_get(frame);
+	}
+
+	base = arch_counter_base = of_iomap(best_frame, 0);
+	if (!base) {
+		pr_err("arch_timer: Can't map frame's registers\n");
+		of_node_put(best_frame);
+		return;
+	}
+
+	if (arch_timer_mem_use_virtual)
+		irq = irq_of_parse_and_map(best_frame, 1);
+	else
+		irq = irq_of_parse_and_map(best_frame, 0);
+	of_node_put(best_frame);
+	if (!irq) {
+		pr_err("arch_timer: Frame missing %s irq",
+				arch_timer_mem_use_virtual ? "virt" : "phys");
+		return;
+	}
+
+	arch_timer_detect_rate(base, np);
+	arch_timer_mem_register(base, irq);
+	arch_timer_common_init();
+}
+CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
+		       arch_timer_mem_init);
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 6b02eddc5f50..f22417cb0969 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -77,7 +77,7 @@ static void __iomem *sched_io_base;
 
 static u32 read_sched_clock(void)
 {
-	return __raw_readl(sched_io_base);
+	return ~__raw_readl(sched_io_base);
 }
 
 static const struct of_device_id sptimer_ids[] __initconst = {
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 4329a29a5310..314184932293 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -301,7 +301,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 	ced->name = dev_name(&p->pdev->dev);
 	ced->features = CLOCK_EVT_FEAT_ONESHOT;
 	ced->rating = 200;
-	ced->cpumask = cpumask_of(0);
+	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = em_sti_clock_event_next;
 	ced->set_mode = em_sti_clock_event_mode;
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 662fcc065821..b7960185919d 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -429,8 +429,6 @@ static int __cpuinit exynos4_local_timer_setup(struct clock_event_device *evt)
 	evt->set_mode = exynos4_tick_set_mode;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;
-	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
-					0xf, 0x7fffffff);
 
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 
@@ -448,6 +446,8 @@ static int __cpuinit exynos4_local_timer_setup(struct clock_event_device *evt)
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
+	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
+					0xf, 0x7fffffff);
 
 	return 0;
 }
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 08ae128cce9b..3165811e2407 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -32,11 +32,23 @@
 #include <linux/atomic.h>
 #include <linux/pid_namespace.h>
 
-#include <asm/unaligned.h>
-
 #include <linux/cn_proc.h>
 
-#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
+/*
+ * Size of a cn_msg followed by a proc_event structure.  Since the
+ * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we
+ * add one 4-byte word to the size here, and then start the actual
+ * cn_msg structure 4 bytes into the stack buffer.  The result is that
+ * the immediately following proc_event structure is aligned to 8 bytes.
+ */
+#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4)
+
+/* See comment above; we test our assumption about sizeof struct cn_msg here. */
+static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
+{
+	BUILD_BUG_ON(sizeof(struct cn_msg) != 20);
+	return (struct cn_msg *)(buffer + 4);
+}
 
 static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
@@ -56,18 +68,19 @@ void proc_fork_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	struct task_struct *parent;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_FORK;
 	rcu_read_lock();
 	parent = rcu_dereference(task->real_parent);
@@ -80,6 +93,7 @@ void proc_fork_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	/*  If cn_netlink_send() failed, the data is not sent */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
@@ -89,16 +103,17 @@ void proc_exec_connector(struct task_struct *task)
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
 	ev->event_data.exec.process_tgid = task->tgid;
@@ -106,6 +121,7 @@ void proc_exec_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -113,15 +129,16 @@ void proc_id_connector(struct task_struct *task, int which_id)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	const struct cred *cred;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	ev->what = which_id;
 	ev->event_data.id.process_pid = task->pid;
 	ev->event_data.id.process_tgid = task->tgid;
@@ -140,11 +157,12 @@ void proc_id_connector(struct task_struct *task, int which_id)
 	rcu_read_unlock();
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -153,16 +171,17 @@ void proc_sid_connector(struct task_struct *task)
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_SID;
 	ev->event_data.sid.process_pid = task->pid;
 	ev->event_data.sid.process_tgid = task->tgid;
@@ -170,6 +189,7 @@ void proc_sid_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -178,16 +198,17 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_PTRACE;
 	ev->event_data.ptrace.process_pid  = task->pid;
 	ev->event_data.ptrace.process_tgid = task->tgid;
@@ -203,6 +224,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -211,16 +233,17 @@ void proc_comm_connector(struct task_struct *task)
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_COMM;
 	ev->event_data.comm.process_pid  = task->pid;
 	ev->event_data.comm.process_tgid = task->tgid;
@@ -229,6 +252,7 @@ void proc_comm_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -236,17 +260,18 @@ void proc_coredump_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
 	ev->event_data.coredump.process_tgid = task->tgid;
@@ -254,6 +279,7 @@ void proc_coredump_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -261,17 +287,18 @@ void proc_exit_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
 	ev->event_data.exit.process_tgid = task->tgid;
@@ -281,6 +308,7 @@ void proc_exit_connector(struct task_struct *task)
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -296,23 +324,25 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
+	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	msg->seq = rcvd_seq;
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->cpu = -1;
 	ev->what = PROC_EVENT_NONE;
 	ev->event_data.ack.err = err;
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = rcvd_ack + 1;
 	msg->len = sizeof(*ev);
+	msg->flags = 0; /* not used */
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
@@ -339,7 +369,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 		return;
 
 	/* Can only change if privileged. */
-	if (!capable(CAP_NET_ADMIN)) {
+	if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) {
 		err = EPERM;
 		goto out;
 	}
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 6ecfa758942c..0daa11e418b1 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -157,17 +157,18 @@ static int cn_call_callback(struct sk_buff *skb)
 static void cn_rx_skb(struct sk_buff *__skb)
 {
 	struct nlmsghdr *nlh;
-	int err;
 	struct sk_buff *skb;
+	int len, err;
 
 	skb = skb_get(__skb);
 
 	if (skb->len >= NLMSG_HDRLEN) {
 		nlh = nlmsg_hdr(skb);
+		len = nlmsg_len(nlh);
 
-		if (nlh->nlmsg_len < sizeof(struct cn_msg) ||
+		if (len < (int)sizeof(struct cn_msg) ||
 		    skb->len < nlh->nlmsg_len ||
-		    nlh->nlmsg_len > CONNECTOR_MAX_MSG_SIZE) {
+		    len > CONNECTOR_MAX_MSG_SIZE) {
 			kfree_skb(skb);
 			return;
 		}
diff --git a/drivers/coresight/Makefile b/drivers/coresight/Makefile
new file mode 100644
index 000000000000..4b4bec890ef5
--- /dev/null
+++ b/drivers/coresight/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for CoreSight drivers.
+#
+obj-$(CONFIG_CORESIGHT) += coresight.o
+obj-$(CONFIG_OF) += of_coresight.o
+obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o
+obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o
+obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o
+obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \
+					   coresight-replicator.o
+obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o
diff --git a/drivers/coresight/coresight-etb10.c b/drivers/coresight/coresight-etb10.c
new file mode 100644
index 000000000000..c922d4aded8a
--- /dev/null
+++ b/drivers/coresight/coresight-etb10.c
@@ -0,0 +1,537 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/seq_file.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define ETB_RAM_DEPTH_REG	0x004
+#define ETB_STATUS_REG		0x00c
+#define ETB_RAM_READ_DATA_REG	0x010
+#define ETB_RAM_READ_POINTER	0x014
+#define ETB_RAM_WRITE_POINTER	0x018
+#define ETB_TRG			0x01c
+#define ETB_CTL_REG		0x020
+#define ETB_RWD_REG		0x024
+#define ETB_FFSR		0x300
+#define ETB_FFCR		0x304
+#define ETB_ITMISCOP0		0xee0
+#define ETB_ITTRFLINACK		0xee4
+#define ETB_ITTRFLIN		0xee8
+#define ETB_ITATBDATA0		0xeeC
+#define ETB_ITATBCTR2		0xef0
+#define ETB_ITATBCTR1		0xef4
+#define ETB_ITATBCTR0		0xef8
+
+/* register description */
+/* STS - 0x00C */
+#define ETB_STATUS_RAM_FULL	BIT(0)
+/* CTL - 0x020 */
+#define ETB_CTL_CAPT_EN		BIT(0)
+/* FFCR - 0x304 */
+#define ETB_FFCR_EN_FTC		BIT(0)
+#define ETB_FFCR_FON_MAN	BIT(6)
+#define ETB_FFCR_STOP_FI	BIT(12)
+#define ETB_FFCR_STOP_TRIGGER	BIT(13)
+
+#define ETB_FFCR_BIT		6
+#define ETB_FFSR_BIT		1
+#define ETB_FRAME_SIZE_WORDS	4
+
+/**
+ * struct etb_drvdata - specifics associated to an ETB component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @in_use:	synchronise user space access to etb buffer.
+ * @buf:	area of memory where ETB buffer content gets sent.
+ * @buffer_depth: size of @buf.
+ * @enable:	this ETB is being used.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct etb_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	atomic_t		in_use;
+	u8			*buf;
+	u32			buffer_depth;
+	bool			enable;
+	u32			trigger_cntr;
+};
+
+static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
+{
+	int ret;
+	u32 depth = 0;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* RO registers don't need locking */
+	depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+
+	clk_disable_unprepare(drvdata->clk);
+	return depth;
+}
+
+static void etb_enable_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u32 depth;
+
+	CS_UNLOCK(drvdata->base);
+
+	depth = drvdata->buffer_depth;
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* clear entire RAM buffer */
+	for (i = 0; i < depth; i++)
+		writel_relaxed(0x0, drvdata->base + ETB_RWD_REG);
+
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* reset read RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + ETB_TRG);
+	writel_relaxed(ETB_FFCR_EN_FTC | ETB_FFCR_STOP_TRIGGER,
+		       drvdata->base + ETB_FFCR);
+	/* ETB trace capture enable */
+	writel_relaxed(ETB_CTL_CAPT_EN, drvdata->base + ETB_CTL_REG);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int etb_enable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_enable_hw(drvdata);
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB enabled\n");
+	return 0;
+}
+
+static void etb_disable_hw(struct etb_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	CS_UNLOCK(drvdata->base);
+
+	ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+	/* stop formatter when a stop has completed */
+	ffcr |= ETB_FFCR_STOP_FI;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+	/* manually generate a flush of the system */
+	ffcr |= ETB_FFCR_FON_MAN;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+
+	if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	/* disable trace capture */
+	writel_relaxed(0x0, drvdata->base + ETB_CTL_REG);
+
+	if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_dump_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u8 *buf_ptr;
+	u32 read_data, depth;
+	u32 read_ptr, write_ptr;
+	u32 frame_off, frame_endoff;
+
+	CS_UNLOCK(drvdata->base);
+
+	read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+
+	frame_off = write_ptr % ETB_FRAME_SIZE_WORDS;
+	frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off;
+	if (frame_off) {
+		dev_err(drvdata->dev,
+			"write_ptr: %lu not aligned to formatter frame size\n",
+			(unsigned long)write_ptr);
+		dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n",
+			(unsigned long)frame_off, (unsigned long)frame_endoff);
+		write_ptr += frame_endoff;
+	}
+
+	if ((readl_relaxed(drvdata->base + ETB_STATUS_REG)
+		      & ETB_STATUS_RAM_FULL) == 0)
+		writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+	else
+		writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	depth = drvdata->buffer_depth;
+	buf_ptr = drvdata->buf;
+	for (i = 0; i < depth; i++) {
+		read_data = readl_relaxed(drvdata->base +
+					  ETB_RAM_READ_DATA_REG);
+		*buf_ptr++ = read_data >> 0;
+		*buf_ptr++ = read_data >> 8;
+		*buf_ptr++ = read_data >> 16;
+		*buf_ptr++ = read_data >> 24;
+	}
+
+	if (frame_off) {
+		buf_ptr -= (frame_endoff * 4);
+		for (i = 0; i < frame_endoff; i++) {
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+		}
+	}
+
+	writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_disable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_disable_hw(drvdata);
+	etb_dump_hw(drvdata);
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETB disabled\n");
+}
+
+static const struct coresight_ops_sink etb_sink_ops = {
+	.enable		= etb_enable,
+	.disable	= etb_disable,
+};
+
+static const struct coresight_ops etb_cs_ops = {
+	.sink_ops	= &etb_sink_ops,
+};
+
+static void etb_dump(struct etb_drvdata *drvdata)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->enable) {
+		etb_disable_hw(drvdata);
+		etb_dump_hw(drvdata);
+		etb_enable_hw(drvdata);
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB dumped\n");
+}
+
+static int etb_open(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	if (atomic_cmpxchg(&drvdata->in_use, 0, 1))
+		return -EBUSY;
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t etb_read(struct file *file, char __user *data,
+				size_t len, loff_t *ppos)
+{
+	u32 depth;
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	etb_dump(drvdata);
+
+	depth = drvdata->buffer_depth;
+	if (*ppos + len > depth * 4)
+		len = depth * 4 - *ppos;
+
+	if (copy_to_user(data, drvdata->buf + *ppos, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+		__func__, len, (int) (depth * 4 - *ppos));
+	return len;
+}
+
+static int etb_release(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+	atomic_set(&drvdata->in_use, 0);
+
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations etb_fops = {
+	.owner		= THIS_MODULE,
+	.open		= etb_open,
+	.read		= etb_read,
+	.release	= etb_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	u32 etb_rdr, etb_sr, etb_rrp, etb_rwp;
+	u32 etb_trg, etb_cr, etb_ffsr, etb_ffcr;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	etb_rdr = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+	etb_sr = readl_relaxed(drvdata->base + ETB_STATUS_REG);
+	etb_rrp = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	etb_rwp = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+	etb_trg = readl_relaxed(drvdata->base + ETB_TRG);
+	etb_cr = readl_relaxed(drvdata->base + ETB_CTL_REG);
+	etb_ffsr = readl_relaxed(drvdata->base + ETB_FFSR);
+	etb_ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf,
+		       "Depth:\t\t0x%x\n"
+		       "Status:\t\t0x%x\n"
+		       "RAM read ptr:\t0x%x\n"
+		       "RAM wrt ptr:\t0x%x\n"
+		       "Trigger cnt:\t0x%x\n"
+		       "Control:\t0x%x\n"
+		       "Flush status:\t0x%x\n"
+		       "Flush ctrl:\t0x%x\n",
+		       etb_rdr, etb_sr, etb_rrp, etb_rwp,
+		       etb_trg, etb_cr, etb_ffsr, etb_ffcr);
+out:
+	return -EINVAL;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static int etb_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etb_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->buffer_depth =  etb_get_buffer_depth(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->buffer_depth < 0)
+		return -EINVAL;
+
+	drvdata->buf = devm_kzalloc(dev,
+				    drvdata->buffer_depth * 4, GFP_KERNEL);
+	if (!drvdata->buf)
+		return -ENOMEM;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+	desc->ops = &etb_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etb_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &etb_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "ETB initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+	return ret;
+}
+
+static int etb_remove(struct amba_device *adev)
+{
+	struct etb_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id etb_ids[] = {
+	{
+		.id	= 0x0003b907,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etb_driver = {
+	.drv = {
+		.name	= "coresight-etb10",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etb_probe,
+	.remove		= etb_remove,
+	.id_table	= etb_ids,
+};
+
+static int __init etb_init(void)
+{
+	return amba_driver_register(&etb_driver);
+}
+module_init(etb_init);
+
+static void __exit etb_exit(void)
+{
+	amba_driver_unregister(&etb_driver);
+}
+module_exit(etb_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver");
diff --git a/drivers/coresight/coresight-etm-cp14.c b/drivers/coresight/coresight-etm-cp14.c
new file mode 100644
index 000000000000..12a220682117
--- /dev/null
+++ b/drivers/coresight/coresight-etm-cp14.c
@@ -0,0 +1,591 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <asm/hardware/cp14.h>
+
+#include "coresight-etm.h"
+
+int etm_readl_cp14(u32 reg, unsigned int *val)
+{
+	switch (reg) {
+	case ETMCR:
+		*val = etm_read(ETMCR);
+		return 0;
+	case ETMCCR:
+		*val = etm_read(ETMCCR);
+		return 0;
+	case ETMTRIGGER:
+		*val = etm_read(ETMTRIGGER);
+		return 0;
+	case ETMSR:
+		*val = etm_read(ETMSR);
+		return 0;
+	case ETMSCR:
+		*val = etm_read(ETMSCR);
+		return 0;
+	case ETMTSSCR:
+		*val = etm_read(ETMTSSCR);
+		return 0;
+	case ETMTEEVR:
+		*val = etm_read(ETMTEEVR);
+		return 0;
+	case ETMTECR1:
+		*val = etm_read(ETMTECR1);
+		return 0;
+	case ETMFFLR:
+		*val = etm_read(ETMFFLR);
+		return 0;
+	case ETMACVRn(0):
+		*val = etm_read(ETMACVR0);
+		return 0;
+	case ETMACVRn(1):
+		*val = etm_read(ETMACVR1);
+		return 0;
+	case ETMACVRn(2):
+		*val = etm_read(ETMACVR2);
+		return 0;
+	case ETMACVRn(3):
+		*val = etm_read(ETMACVR3);
+		return 0;
+	case ETMACVRn(4):
+		*val = etm_read(ETMACVR4);
+		return 0;
+	case ETMACVRn(5):
+		*val = etm_read(ETMACVR5);
+		return 0;
+	case ETMACVRn(6):
+		*val = etm_read(ETMACVR6);
+		return 0;
+	case ETMACVRn(7):
+		*val = etm_read(ETMACVR7);
+		return 0;
+	case ETMACVRn(8):
+		*val = etm_read(ETMACVR8);
+		return 0;
+	case ETMACVRn(9):
+		*val = etm_read(ETMACVR9);
+		return 0;
+	case ETMACVRn(10):
+		*val = etm_read(ETMACVR10);
+		return 0;
+	case ETMACVRn(11):
+		*val = etm_read(ETMACVR11);
+		return 0;
+	case ETMACVRn(12):
+		*val = etm_read(ETMACVR12);
+		return 0;
+	case ETMACVRn(13):
+		*val = etm_read(ETMACVR13);
+		return 0;
+	case ETMACVRn(14):
+		*val = etm_read(ETMACVR14);
+		return 0;
+	case ETMACVRn(15):
+		*val = etm_read(ETMACVR15);
+		return 0;
+	case ETMACTRn(0):
+		*val = etm_read(ETMACTR0);
+		return 0;
+	case ETMACTRn(1):
+		*val = etm_read(ETMACTR1);
+		return 0;
+	case ETMACTRn(2):
+		*val = etm_read(ETMACTR2);
+		return 0;
+	case ETMACTRn(3):
+		*val = etm_read(ETMACTR3);
+		return 0;
+	case ETMACTRn(4):
+		*val = etm_read(ETMACTR4);
+		return 0;
+	case ETMACTRn(5):
+		*val = etm_read(ETMACTR5);
+		return 0;
+	case ETMACTRn(6):
+		*val = etm_read(ETMACTR6);
+		return 0;
+	case ETMACTRn(7):
+		*val = etm_read(ETMACTR7);
+		return 0;
+	case ETMACTRn(8):
+		*val = etm_read(ETMACTR8);
+		return 0;
+	case ETMACTRn(9):
+		*val = etm_read(ETMACTR9);
+		return 0;
+	case ETMACTRn(10):
+		*val = etm_read(ETMACTR10);
+		return 0;
+	case ETMACTRn(11):
+		*val = etm_read(ETMACTR11);
+		return 0;
+	case ETMACTRn(12):
+		*val = etm_read(ETMACTR12);
+		return 0;
+	case ETMACTRn(13):
+		*val = etm_read(ETMACTR13);
+		return 0;
+	case ETMACTRn(14):
+		*val = etm_read(ETMACTR14);
+		return 0;
+	case ETMACTRn(15):
+		*val = etm_read(ETMACTR15);
+		return 0;
+	case ETMCNTRLDVRn(0):
+		*val = etm_read(ETMCNTRLDVR0);
+		return 0;
+	case ETMCNTRLDVRn(1):
+		*val = etm_read(ETMCNTRLDVR1);
+		return 0;
+	case ETMCNTRLDVRn(2):
+		*val = etm_read(ETMCNTRLDVR2);
+		return 0;
+	case ETMCNTRLDVRn(3):
+		*val = etm_read(ETMCNTRLDVR3);
+		return 0;
+	case ETMCNTENRn(0):
+		*val = etm_read(ETMCNTENR0);
+		return 0;
+	case ETMCNTENRn(1):
+		*val = etm_read(ETMCNTENR1);
+		return 0;
+	case ETMCNTENRn(2):
+		*val = etm_read(ETMCNTENR2);
+		return 0;
+	case ETMCNTENRn(3):
+		*val = etm_read(ETMCNTENR3);
+		return 0;
+	case ETMCNTRLDEVRn(0):
+		*val = etm_read(ETMCNTRLDEVR0);
+		return 0;
+	case ETMCNTRLDEVRn(1):
+		*val = etm_read(ETMCNTRLDEVR1);
+		return 0;
+	case ETMCNTRLDEVRn(2):
+		*val = etm_read(ETMCNTRLDEVR2);
+		return 0;
+	case ETMCNTRLDEVRn(3):
+		*val = etm_read(ETMCNTRLDEVR3);
+		return 0;
+	case ETMCNTVRn(0):
+		*val = etm_read(ETMCNTVR0);
+		return 0;
+	case ETMCNTVRn(1):
+		*val = etm_read(ETMCNTVR1);
+		return 0;
+	case ETMCNTVRn(2):
+		*val = etm_read(ETMCNTVR2);
+		return 0;
+	case ETMCNTVRn(3):
+		*val = etm_read(ETMCNTVR3);
+		return 0;
+	case ETMSQ12EVR:
+		*val = etm_read(ETMSQ12EVR);
+		return 0;
+	case ETMSQ21EVR:
+		*val = etm_read(ETMSQ21EVR);
+		return 0;
+	case ETMSQ23EVR:
+		*val = etm_read(ETMSQ23EVR);
+		return 0;
+	case ETMSQ31EVR:
+		*val = etm_read(ETMSQ31EVR);
+		return 0;
+	case ETMSQ32EVR:
+		*val = etm_read(ETMSQ32EVR);
+		return 0;
+	case ETMSQ13EVR:
+		*val = etm_read(ETMSQ13EVR);
+		return 0;
+	case ETMSQR:
+		*val = etm_read(ETMSQR);
+		return 0;
+	case ETMEXTOUTEVRn(0):
+		*val = etm_read(ETMEXTOUTEVR0);
+		return 0;
+	case ETMEXTOUTEVRn(1):
+		*val = etm_read(ETMEXTOUTEVR1);
+		return 0;
+	case ETMEXTOUTEVRn(2):
+		*val = etm_read(ETMEXTOUTEVR2);
+		return 0;
+	case ETMEXTOUTEVRn(3):
+		*val = etm_read(ETMEXTOUTEVR3);
+		return 0;
+	case ETMCIDCVRn(0):
+		*val = etm_read(ETMCIDCVR0);
+		return 0;
+	case ETMCIDCVRn(1):
+		*val = etm_read(ETMCIDCVR1);
+		return 0;
+	case ETMCIDCVRn(2):
+		*val = etm_read(ETMCIDCVR2);
+		return 0;
+	case ETMCIDCMR:
+		*val = etm_read(ETMCIDCMR);
+		return 0;
+	case ETMIMPSPEC0:
+		*val = etm_read(ETMIMPSPEC0);
+		return 0;
+	case ETMIMPSPEC1:
+		*val = etm_read(ETMIMPSPEC1);
+		return 0;
+	case ETMIMPSPEC2:
+		*val = etm_read(ETMIMPSPEC2);
+		return 0;
+	case ETMIMPSPEC3:
+		*val = etm_read(ETMIMPSPEC3);
+		return 0;
+	case ETMIMPSPEC4:
+		*val = etm_read(ETMIMPSPEC4);
+		return 0;
+	case ETMIMPSPEC5:
+		*val = etm_read(ETMIMPSPEC5);
+		return 0;
+	case ETMIMPSPEC6:
+		*val = etm_read(ETMIMPSPEC6);
+		return 0;
+	case ETMIMPSPEC7:
+		*val = etm_read(ETMIMPSPEC7);
+		return 0;
+	case ETMSYNCFR:
+		*val = etm_read(ETMSYNCFR);
+		return 0;
+	case ETMIDR:
+		*val = etm_read(ETMIDR);
+		return 0;
+	case ETMCCER:
+		*val = etm_read(ETMCCER);
+		return 0;
+	case ETMEXTINSELR:
+		*val = etm_read(ETMEXTINSELR);
+		return 0;
+	case ETMTESSEICR:
+		*val = etm_read(ETMTESSEICR);
+		return 0;
+	case ETMEIBCR:
+		*val = etm_read(ETMEIBCR);
+		return 0;
+	case ETMTSEVR:
+		*val = etm_read(ETMTSEVR);
+		return 0;
+	case ETMAUXCR:
+		*val = etm_read(ETMAUXCR);
+		return 0;
+	case ETMTRACEIDR:
+		*val = etm_read(ETMTRACEIDR);
+		return 0;
+	case ETMVMIDCVR:
+		*val = etm_read(ETMVMIDCVR);
+		return 0;
+	case ETMOSLSR:
+		*val = etm_read(ETMOSLSR);
+		return 0;
+	case ETMOSSRR:
+		*val = etm_read(ETMOSSRR);
+		return 0;
+	case ETMPDCR:
+		*val = etm_read(ETMPDCR);
+		return 0;
+	case ETMPDSR:
+		*val = etm_read(ETMPDSR);
+		return 0;
+	default:
+		*val = 0;
+		return -EINVAL;
+	}
+}
+
+int etm_writel_cp14(u32 reg, u32 val)
+{
+	switch (reg) {
+	case ETMCR:
+		etm_write(val, ETMCR);
+		break;
+	case ETMTRIGGER:
+		etm_write(val, ETMTRIGGER);
+		break;
+	case ETMSR:
+		etm_write(val, ETMSR);
+		break;
+	case ETMTSSCR:
+		etm_write(val, ETMTSSCR);
+		break;
+	case ETMTEEVR:
+		etm_write(val, ETMTEEVR);
+		break;
+	case ETMTECR1:
+		etm_write(val, ETMTECR1);
+		break;
+	case ETMFFLR:
+		etm_write(val, ETMFFLR);
+		break;
+	case ETMACVRn(0):
+		etm_write(val, ETMACVR0);
+		break;
+	case ETMACVRn(1):
+		etm_write(val, ETMACVR1);
+		break;
+	case ETMACVRn(2):
+		etm_write(val, ETMACVR2);
+		break;
+	case ETMACVRn(3):
+		etm_write(val, ETMACVR3);
+		break;
+	case ETMACVRn(4):
+		etm_write(val, ETMACVR4);
+		break;
+	case ETMACVRn(5):
+		etm_write(val, ETMACVR5);
+		break;
+	case ETMACVRn(6):
+		etm_write(val, ETMACVR6);
+		break;
+	case ETMACVRn(7):
+		etm_write(val, ETMACVR7);
+		break;
+	case ETMACVRn(8):
+		etm_write(val, ETMACVR8);
+		break;
+	case ETMACVRn(9):
+		etm_write(val, ETMACVR9);
+		break;
+	case ETMACVRn(10):
+		etm_write(val, ETMACVR10);
+		break;
+	case ETMACVRn(11):
+		etm_write(val, ETMACVR11);
+		break;
+	case ETMACVRn(12):
+		etm_write(val, ETMACVR12);
+		break;
+	case ETMACVRn(13):
+		etm_write(val, ETMACVR13);
+		break;
+	case ETMACVRn(14):
+		etm_write(val, ETMACVR14);
+		break;
+	case ETMACVRn(15):
+		etm_write(val, ETMACVR15);
+		break;
+	case ETMACTRn(0):
+		etm_write(val, ETMACTR0);
+		break;
+	case ETMACTRn(1):
+		etm_write(val, ETMACTR1);
+		break;
+	case ETMACTRn(2):
+		etm_write(val, ETMACTR2);
+		break;
+	case ETMACTRn(3):
+		etm_write(val, ETMACTR3);
+		break;
+	case ETMACTRn(4):
+		etm_write(val, ETMACTR4);
+		break;
+	case ETMACTRn(5):
+		etm_write(val, ETMACTR5);
+		break;
+	case ETMACTRn(6):
+		etm_write(val, ETMACTR6);
+		break;
+	case ETMACTRn(7):
+		etm_write(val, ETMACTR7);
+		break;
+	case ETMACTRn(8):
+		etm_write(val, ETMACTR8);
+		break;
+	case ETMACTRn(9):
+		etm_write(val, ETMACTR9);
+		break;
+	case ETMACTRn(10):
+		etm_write(val, ETMACTR10);
+		break;
+	case ETMACTRn(11):
+		etm_write(val, ETMACTR11);
+		break;
+	case ETMACTRn(12):
+		etm_write(val, ETMACTR12);
+		break;
+	case ETMACTRn(13):
+		etm_write(val, ETMACTR13);
+		break;
+	case ETMACTRn(14):
+		etm_write(val, ETMACTR14);
+		break;
+	case ETMACTRn(15):
+		etm_write(val, ETMACTR15);
+		break;
+	case ETMCNTRLDVRn(0):
+		etm_write(val, ETMCNTRLDVR0);
+		break;
+	case ETMCNTRLDVRn(1):
+		etm_write(val, ETMCNTRLDVR1);
+		break;
+	case ETMCNTRLDVRn(2):
+		etm_write(val, ETMCNTRLDVR2);
+		break;
+	case ETMCNTRLDVRn(3):
+		etm_write(val, ETMCNTRLDVR3);
+		break;
+	case ETMCNTENRn(0):
+		etm_write(val, ETMCNTENR0);
+		break;
+	case ETMCNTENRn(1):
+		etm_write(val, ETMCNTENR1);
+		break;
+	case ETMCNTENRn(2):
+		etm_write(val, ETMCNTENR2);
+		break;
+	case ETMCNTENRn(3):
+		etm_write(val, ETMCNTENR3);
+		break;
+	case ETMCNTRLDEVRn(0):
+		etm_write(val, ETMCNTRLDEVR0);
+		break;
+	case ETMCNTRLDEVRn(1):
+		etm_write(val, ETMCNTRLDEVR1);
+		break;
+	case ETMCNTRLDEVRn(2):
+		etm_write(val, ETMCNTRLDEVR2);
+		break;
+	case ETMCNTRLDEVRn(3):
+		etm_write(val, ETMCNTRLDEVR3);
+		break;
+	case ETMCNTVRn(0):
+		etm_write(val, ETMCNTVR0);
+		break;
+	case ETMCNTVRn(1):
+		etm_write(val, ETMCNTVR1);
+		break;
+	case ETMCNTVRn(2):
+		etm_write(val, ETMCNTVR2);
+		break;
+	case ETMCNTVRn(3):
+		etm_write(val, ETMCNTVR3);
+		break;
+	case ETMSQ12EVR:
+		etm_write(val, ETMSQ12EVR);
+		break;
+	case ETMSQ21EVR:
+		etm_write(val, ETMSQ21EVR);
+		break;
+	case ETMSQ23EVR:
+		etm_write(val, ETMSQ23EVR);
+		break;
+	case ETMSQ31EVR:
+		etm_write(val, ETMSQ31EVR);
+		break;
+	case ETMSQ32EVR:
+		etm_write(val, ETMSQ32EVR);
+		break;
+	case ETMSQ13EVR:
+		etm_write(val, ETMSQ13EVR);
+		break;
+	case ETMSQR:
+		etm_write(val, ETMSQR);
+		break;
+	case ETMEXTOUTEVRn(0):
+		etm_write(val, ETMEXTOUTEVR0);
+		break;
+	case ETMEXTOUTEVRn(1):
+		etm_write(val, ETMEXTOUTEVR1);
+		break;
+	case ETMEXTOUTEVRn(2):
+		etm_write(val, ETMEXTOUTEVR2);
+		break;
+	case ETMEXTOUTEVRn(3):
+		etm_write(val, ETMEXTOUTEVR3);
+		break;
+	case ETMCIDCVRn(0):
+		etm_write(val, ETMCIDCVR0);
+		break;
+	case ETMCIDCVRn(1):
+		etm_write(val, ETMCIDCVR1);
+		break;
+	case ETMCIDCVRn(2):
+		etm_write(val, ETMCIDCVR2);
+		break;
+	case ETMCIDCMR:
+		etm_write(val, ETMCIDCMR);
+		break;
+	case ETMIMPSPEC0:
+		etm_write(val, ETMIMPSPEC0);
+		break;
+	case ETMIMPSPEC1:
+		etm_write(val, ETMIMPSPEC1);
+		break;
+	case ETMIMPSPEC2:
+		etm_write(val, ETMIMPSPEC2);
+		break;
+	case ETMIMPSPEC3:
+		etm_write(val, ETMIMPSPEC3);
+		break;
+	case ETMIMPSPEC4:
+		etm_write(val, ETMIMPSPEC4);
+		break;
+	case ETMIMPSPEC5:
+		etm_write(val, ETMIMPSPEC5);
+		break;
+	case ETMIMPSPEC6:
+		etm_write(val, ETMIMPSPEC6);
+		break;
+	case ETMIMPSPEC7:
+		etm_write(val, ETMIMPSPEC7);
+		break;
+	case ETMSYNCFR:
+		etm_write(val, ETMSYNCFR);
+		break;
+	case ETMEXTINSELR:
+		etm_write(val, ETMEXTINSELR);
+		break;
+	case ETMTESSEICR:
+		etm_write(val, ETMTESSEICR);
+		break;
+	case ETMEIBCR:
+		etm_write(val, ETMEIBCR);
+		break;
+	case ETMTSEVR:
+		etm_write(val, ETMTSEVR);
+		break;
+	case ETMAUXCR:
+		etm_write(val, ETMAUXCR);
+		break;
+	case ETMTRACEIDR:
+		etm_write(val, ETMTRACEIDR);
+		break;
+	case ETMVMIDCVR:
+		etm_write(val, ETMVMIDCVR);
+		break;
+	case ETMOSLAR:
+		etm_write(val, ETMOSLAR);
+		break;
+	case ETMOSSRR:
+		etm_write(val, ETMOSSRR);
+		break;
+	case ETMPDCR:
+		etm_write(val, ETMPDCR);
+		break;
+	case ETMPDSR:
+		etm_write(val, ETMPDSR);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/coresight/coresight-etm.h b/drivers/coresight/coresight-etm.h
new file mode 100644
index 000000000000..501c5fac8a45
--- /dev/null
+++ b/drivers/coresight/coresight-etm.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_CORESIGHT_ETM_H
+#define _CORESIGHT_CORESIGHT_ETM_H
+
+#include <linux/spinlock.h>
+#include "coresight-priv.h"
+
+/*
+ * Device registers:
+ * 0x000 - 0x2FC: Trace         registers
+ * 0x300 - 0x314: Management    registers
+ * 0x318 - 0xEFC: Trace         registers
+ *
+ * Coresight registers
+ * 0xF00 - 0xF9C: Management    registers
+ * 0xFA0 - 0xFA4: Management    registers in PFTv1.0
+ *                Trace         registers in PFTv1.1
+ * 0xFA8 - 0xFFC: Management    registers
+ */
+
+/* Trace registers (0x000-0x2FC) */
+#define ETMCR			0x000
+#define ETMCCR			0x004
+#define ETMTRIGGER		0x008
+#define ETMSR			0x010
+#define ETMSCR			0x014
+#define ETMTSSCR		0x018
+#define ETMTECR2		0x01c
+#define ETMTEEVR		0x020
+#define ETMTECR1		0x024
+#define ETMFFLR			0x02c
+#define ETMACVRn(n)		(0x040 + (n * 4))
+#define ETMACTRn(n)		(0x080 + (n * 4))
+#define ETMCNTRLDVRn(n)		(0x140 + (n * 4))
+#define ETMCNTENRn(n)		(0x150 + (n * 4))
+#define ETMCNTRLDEVRn(n)	(0x160 + (n * 4))
+#define ETMCNTVRn(n)		(0x170 + (n * 4))
+#define ETMSQ12EVR		0x180
+#define ETMSQ21EVR		0x184
+#define ETMSQ23EVR		0x188
+#define ETMSQ31EVR		0x18c
+#define ETMSQ32EVR		0x190
+#define ETMSQ13EVR		0x194
+#define ETMSQR			0x19c
+#define ETMEXTOUTEVRn(n)	(0x1a0 + (n * 4))
+#define ETMCIDCVRn(n)		(0x1b0 + (n * 4))
+#define ETMCIDCMR		0x1bc
+#define ETMIMPSPEC0		0x1c0
+#define ETMIMPSPEC1		0x1c4
+#define ETMIMPSPEC2		0x1c8
+#define ETMIMPSPEC3		0x1cc
+#define ETMIMPSPEC4		0x1d0
+#define ETMIMPSPEC5		0x1d4
+#define ETMIMPSPEC6		0x1d8
+#define ETMIMPSPEC7		0x1dc
+#define ETMSYNCFR		0x1e0
+#define ETMIDR			0x1e4
+#define ETMCCER			0x1e8
+#define ETMEXTINSELR		0x1ec
+#define ETMTESSEICR		0x1f0
+#define ETMEIBCR		0x1f4
+#define ETMTSEVR		0x1f8
+#define ETMAUXCR		0x1fc
+#define ETMTRACEIDR		0x200
+#define ETMVMIDCVR		0x240
+/* Management registers (0x300-0x314) */
+#define ETMOSLAR		0x300
+#define ETMOSLSR		0x304
+#define ETMOSSRR		0x308
+#define ETMPDCR			0x310
+#define ETMPDSR			0x314
+#define ETM_MAX_ADDR_CMP	16
+#define ETM_MAX_CNTR		4
+#define ETM_MAX_CTXID_CMP	3
+
+/* Register definition */
+/* ETMCR - 0x00 */
+#define ETMCR_PWD_DWN		BIT(0)
+#define ETMCR_STALL_MODE	BIT(7)
+#define ETMCR_ETM_PRG		BIT(10)
+#define ETMCR_ETM_EN		BIT(11)
+#define ETMCR_CYC_ACC		BIT(12)
+#define ETMCR_CTXID_SIZE	(BIT(14)|BIT(15))
+#define ETMCR_TIMESTAMP_EN	BIT(28)
+/* ETMCCR - 0x04 */
+#define ETMCCR_FIFOFULL		BIT(23)
+/* ETMPDCR - 0x310 */
+#define ETMPDCR_PWD_UP		BIT(3)
+/* ETMTECR1 - 0x024 */
+#define ETMTECR1_ADDR_COMP_1	BIT(0)
+#define ETMTECR1_INC_EXC	BIT(24)
+#define ETMTECR1_START_STOP	BIT(25)
+/* ETMCCER - 0x1E8 */
+#define ETMCCER_TIMESTAMP	BIT(22)
+
+#define ETM_MODE_EXCLUDE	BIT(0)
+#define ETM_MODE_CYCACC		BIT(1)
+#define ETM_MODE_STALL		BIT(2)
+#define ETM_MODE_TIMESTAMP	BIT(3)
+#define ETM_MODE_CTXID		BIT(4)
+#define ETM_MODE_ALL		0x1f
+
+#define ETM_SQR_MASK		0x3
+#define ETM_TRACEID_MASK	0x3f
+#define ETM_EVENT_MASK		0x1ffff
+#define ETM_SYNC_MASK		0xfff
+#define ETM_ALL_MASK		0xffffffff
+
+#define ETMSR_PROG_BIT		1
+#define ETM_SEQ_STATE_MAX_VAL	(0x2)
+#define PORT_SIZE_MASK		(GENMASK(21, 21) | GENMASK(6, 4))
+
+#define ETM_HARD_WIRE_RES_A	/* Hard wired, always true */	\
+				((0x0f << 0)	|		\
+				/* Resource index A */		\
+				(0x06 << 4))
+
+#define ETM_ADD_COMP_0		/* Single addr comparator 1 */	\
+				((0x00 << 7)	|		\
+				/* Resource index B */		\
+				(0x00 << 11))
+
+#define ETM_EVENT_NOT_A		BIT(14) /* NOT(A) */
+
+#define ETM_DEFAULT_EVENT_VAL	(ETM_HARD_WIRE_RES_A	|	\
+				 ETM_ADD_COMP_0		|	\
+				 ETM_EVENT_NOT_A)
+/**
+ * struct etm_drvdata - specifics associated to an ETM component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @cpu:	the cpu this component is affined to.
+ * @port_size:	port size as reported by ETMCR bit 4-6 and 21.
+ * @arch:	ETM/PTM version number.
+ * @use_cpu14:	true if management registers need to be accessed via CP14.
+ * @enable:	is this ETM/PTM currently tracing.
+ * @sticky_enable: true if ETM base configuration has been done.
+ * @boot_enable:true if we should start tracing at boot time.
+ * @os_unlock:	true if access to management registers is allowed.
+ * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
+ * @nr_cntr:	Number of counters as found in ETMCCR bit 13-15.
+ * @nr_ext_inp:	Number of external input as found in ETMCCR bit 17-19.
+ * @nr_ext_out:	Number of external output as found in ETMCCR bit 20-22.
+ * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
+ * @etmccr:	value of register ETMCCR.
+ * @etmccer:	value of register ETMCCER.
+ * @traceid:	value of the current ID for this component.
+ * @mode:	controls various modes supported by this ETM/PTM.
+ * @ctrl:	used in conjunction with @mode.
+ * @trigger_event: setting for register ETMTRIGGER.
+ * @startstop_ctrl: setting for register ETMTSSCR.
+ * @enable_event: setting for register ETMTEEVR.
+ * @enable_ctrl1: setting for register ETMTECR1.
+ * @fifofull_level: setting for register ETMFFLR.
+ * @addr_idx:	index for the address comparator selection.
+ * @addr_val:	value for address comparator register.
+ * @addr_acctype: access type for address comparator register.
+ * @addr_type:	current status of the comparator register.
+ * @cntr_idx:	index for the counter register selection.
+ * @cntr_rld_val: reload value of a counter register.
+ * @cntr_event:	control for counter enable register.
+ * @cntr_rld_event: value for counter reload event register.
+ * @cntr_val:	counter value register.
+ * @seq_12_event: event causing the transition from 1 to 2.
+ * @seq_21_event: event causing the transition from 2 to 1.
+ * @seq_23_event: event causing the transition from 2 to 3.
+ * @seq_31_event: event causing the transition from 3 to 1.
+ * @seq_32_event: event causing the transition from 3 to 2.
+ * @seq_13_event: event causing the transition from 1 to 3.
+ * @seq_curr_state: current value of the sequencer register.
+ * @ctxid_idx: index for the context ID registers.
+ * @ctxid_val: value for the context ID to trigger on.
+ * @ctxid_mask: mask applicable to all the context IDs.
+ * @sync_freq:	Synchronisation frequency.
+ * @timestamp_event: Defines an event that requests the insertion
+		     of a timestamp into the trace stream.
+ */
+struct etm_drvdata {
+	void __iomem			*base;
+	struct device			*dev;
+	struct coresight_device		*csdev;
+	struct clk			*clk;
+	spinlock_t			spinlock;
+	int				cpu;
+	int				port_size;
+	u8				arch;
+	bool				use_cp14;
+	bool				enable;
+	bool				sticky_enable;
+	bool				boot_enable;
+	bool				os_unlock;
+	u8				nr_addr_cmp;
+	u8				nr_cntr;
+	u8				nr_ext_inp;
+	u8				nr_ext_out;
+	u8				nr_ctxid_cmp;
+	u32				etmccr;
+	u32				etmccer;
+	u32				traceid;
+	u32				mode;
+	u32				ctrl;
+	u32				trigger_event;
+	u32				startstop_ctrl;
+	u32				enable_event;
+	u32				enable_ctrl1;
+	u32				fifofull_level;
+	u8				addr_idx;
+	u32				addr_val[ETM_MAX_ADDR_CMP];
+	u32				addr_acctype[ETM_MAX_ADDR_CMP];
+	u32				addr_type[ETM_MAX_ADDR_CMP];
+	u8				cntr_idx;
+	u32				cntr_rld_val[ETM_MAX_CNTR];
+	u32				cntr_event[ETM_MAX_CNTR];
+	u32				cntr_rld_event[ETM_MAX_CNTR];
+	u32				cntr_val[ETM_MAX_CNTR];
+	u32				seq_12_event;
+	u32				seq_21_event;
+	u32				seq_23_event;
+	u32				seq_31_event;
+	u32				seq_32_event;
+	u32				seq_13_event;
+	u32				seq_curr_state;
+	u8				ctxid_idx;
+	u32				ctxid_val[ETM_MAX_CTXID_CMP];
+	u32				ctxid_mask;
+	u32				sync_freq;
+	u32				timestamp_event;
+};
+
+enum etm_addr_type {
+	ETM_ADDR_TYPE_NONE,
+	ETM_ADDR_TYPE_SINGLE,
+	ETM_ADDR_TYPE_RANGE,
+	ETM_ADDR_TYPE_START,
+	ETM_ADDR_TYPE_STOP,
+};
+#endif
diff --git a/drivers/coresight/coresight-etm3x.c b/drivers/coresight/coresight-etm3x.c
new file mode 100644
index 000000000000..d9e3ed6aa857
--- /dev/null
+++ b/drivers/coresight/coresight-etm3x.c
@@ -0,0 +1,1928 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+
+#include "coresight-etm.h"
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM_DEFAULT_ENABLE
+static int boot_enable = 1;
+#else
+static int boot_enable;
+#endif
+module_param_named(
+	boot_enable, boot_enable, int, S_IRUGO
+);
+
+/* The number of ETM/PTM currently registered */
+static int etm_count;
+static struct etm_drvdata *etmdrvdata[NR_CPUS];
+
+static inline void etm_writel(struct etm_drvdata *drvdata,
+			      u32 val, u32 off)
+{
+	if (drvdata->use_cp14) {
+		if (etm_writel_cp14(off, val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		writel_relaxed(val, drvdata->base + off);
+	}
+}
+
+static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
+{
+	u32 val;
+
+	if (drvdata->use_cp14) {
+		if (etm_readl_cp14(off, &val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		val = readl_relaxed(drvdata->base + off);
+	}
+
+	return val;
+}
+
+/*
+ * Memory mapped writes to clear os lock are not supported on some processors
+ * and OS lock must be unlocked before any memory mapped access on such
+ * processors, otherwise memory mapped reads/writes will be invalid.
+ */
+static void etm_os_unlock(void *info)
+{
+	struct etm_drvdata *drvdata = (struct etm_drvdata *)info;
+	/* Writing any value to ETMOSLAR unlocks the trace registers */
+	etm_writel(drvdata, 0x0, ETMOSLAR);
+	isb();
+}
+
+static void etm_set_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	/* Ensure pending cp14 accesses complete before setting pwrdwn */
+	mb();
+	isb();
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+}
+
+static void etm_clr_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_set_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr |= ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_clr_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	/* Ensure pending cp14 accesses complete before clearing pwrup */
+	mb();
+	isb();
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr &= ~ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+}
+
+/**
+ * coresight_timeout_etm - loop until a bit has changed to a specific state.
+ * @drvdata: etm's private data structure.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Basically the same as @coresight_timeout except for the register access
+ * method where we have to account for CP14 configurations.
+
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+static int coresight_timeout_etm(struct etm_drvdata *drvdata, u32 offset,
+				  int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = etm_readl(drvdata, offset);
+		/* Waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* Waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+
+static void etm_set_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_clr_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_set_default(struct etm_drvdata *drvdata)
+{
+	int i;
+
+	drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->enable_event = ETM_HARD_WIRE_RES_A;
+
+	drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		drvdata->cntr_rld_val[i] = 0x0;
+		drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_val[i] = 0x0;
+	}
+
+	drvdata->seq_curr_state = 0x0;
+	drvdata->ctxid_idx = 0x0;
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		drvdata->ctxid_val[i] = 0x0;
+	drvdata->ctxid_mask = 0x0;
+}
+
+static void etm_enable_hw(void *info)
+{
+	int i;
+	u32 etmcr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Turn engine on */
+	etm_clr_pwrdwn(drvdata);
+	/* Apply power to trace registers */
+	etm_set_pwrup(drvdata);
+	/* Make sure all registers are accessible */
+	etm_os_unlock(drvdata);
+
+	etm_set_prog(drvdata);
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG);
+	etmcr |= drvdata->port_size;
+	etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR);
+	etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER);
+	etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR);
+	etm_writel(drvdata, drvdata->enable_event, ETMTEEVR);
+	etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1);
+	etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR);
+	for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+		etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i));
+		etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i));
+	}
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i));
+		etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i));
+		etm_writel(drvdata, drvdata->cntr_rld_event[i],
+			   ETMCNTRLDEVRn(i));
+		etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i));
+	}
+	etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR);
+	etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR);
+	etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR);
+	etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR);
+	etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR);
+	etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR);
+	etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR);
+	for (i = 0; i < drvdata->nr_ext_out; i++)
+		etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i));
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		etm_writel(drvdata, drvdata->ctxid_val[i], ETMCIDCVRn(i));
+	etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR);
+	etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR);
+	/* No external input selected */
+	etm_writel(drvdata, 0x0, ETMEXTINSELR);
+	etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR);
+	/* No auxiliary control selected */
+	etm_writel(drvdata, 0x0, ETMAUXCR);
+	etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR);
+	/* No VMID comparator value selected */
+	etm_writel(drvdata, 0x0, ETMVMIDCVR);
+
+	/* Ensures trace output is enabled from this ETM */
+	etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR);
+
+	etm_clr_prog(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
+}
+
+static int etm_trace_id_simple(struct etm_drvdata *drvdata)
+{
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	return (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+}
+
+static int etm_trace_id(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+	int trace_id = -1;
+
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	if (clk_prepare_enable(drvdata->clk))
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return trace_id;
+}
+
+static int etm_enable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto err_clk;
+
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Configure the ETM only if the CPU is online.  If it isn't online
+	 * hw configuration will take place when 'CPU_STARTING' is received
+	 * in @etm_cpu_callback.
+	 */
+	if (cpu_online(drvdata->cpu)) {
+		ret = smp_call_function_single(drvdata->cpu,
+					       etm_enable_hw, drvdata, 1);
+		if (ret)
+			goto err;
+	}
+
+	drvdata->enable = true;
+	drvdata->sticky_enable = true;
+
+	spin_unlock(&drvdata->spinlock);
+
+	dev_info(drvdata->dev, "ETM tracing enabled\n");
+	return 0;
+err:
+	spin_unlock(&drvdata->spinlock);
+	clk_disable_unprepare(drvdata->clk);
+err_clk:
+	return ret;
+}
+
+static void etm_disable_hw(void *info)
+{
+	int i;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+	etm_set_prog(drvdata);
+
+	/* Program trace enable to low by using always false event */
+	etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR);
+
+	/* Read back sequencer and counters for post trace analysis */
+	drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+
+	for (i = 0; i < drvdata->nr_cntr; i++)
+		drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
+
+	etm_set_pwrdwn(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+}
+
+static void etm_disable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	/*
+	 * Taking hotplug lock here protects from clocks getting disabled
+	 * with tracing being left on (crash scenario) if user disable occurs
+	 * after cpu online mask indicates the cpu is offline but before the
+	 * DYING hotplug callback is serviced by the ETM driver.
+	 */
+	get_online_cpus();
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Executing etm_disable_hw on the cpu whose ETM is being disabled
+	 * ensures that register writes occur when cpu is powered.
+	 */
+	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
+	drvdata->enable = false;
+
+	spin_unlock(&drvdata->spinlock);
+	put_online_cpus();
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETM tracing disabled\n");
+}
+
+static const struct coresight_ops_source etm_source_ops = {
+	.trace_id	= etm_trace_id,
+	.enable		= etm_enable,
+	.disable	= etm_disable,
+};
+
+static const struct coresight_ops etm_cs_ops = {
+	.source_ops	= &etm_source_ops,
+};
+
+static ssize_t nr_addr_cmp_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_addr_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_addr_cmp);
+
+static ssize_t nr_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_cntr;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_cntr);
+
+static ssize_t nr_ctxid_cmp_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_ctxid_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_ctxid_cmp);
+
+static ssize_t etmsr_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags, val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = etm_readl(drvdata, ETMSR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(etmsr);
+
+static ssize_t reset_store(struct device *dev,
+			   struct device_attribute *attr,
+			   const char *buf, size_t size)
+{
+	int i, ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		spin_lock(&drvdata->spinlock);
+		drvdata->mode = ETM_MODE_EXCLUDE;
+		drvdata->ctrl = 0x0;
+		drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+		drvdata->startstop_ctrl = 0x0;
+		drvdata->addr_idx = 0x0;
+		for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+			drvdata->addr_val[i] = 0x0;
+			drvdata->addr_acctype[i] = 0x0;
+			drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE;
+		}
+		drvdata->cntr_idx = 0x0;
+
+		etm_set_default(drvdata);
+		spin_unlock(&drvdata->spinlock);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t mode_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->mode;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t mode_store(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->mode = val & ETM_MODE_ALL;
+
+	if (drvdata->mode & ETM_MODE_EXCLUDE)
+		drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC;
+	else
+		drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
+
+	if (drvdata->mode & ETM_MODE_CYCACC)
+		drvdata->ctrl |= ETMCR_CYC_ACC;
+	else
+		drvdata->ctrl &= ~ETMCR_CYC_ACC;
+
+	if (drvdata->mode & ETM_MODE_STALL) {
+		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
+			dev_warn(drvdata->dev, "stall mode not supported\n");
+			return -EINVAL;
+		}
+		drvdata->ctrl |= ETMCR_STALL_MODE;
+	 } else
+		drvdata->ctrl &= ~ETMCR_STALL_MODE;
+
+	if (drvdata->mode & ETM_MODE_TIMESTAMP) {
+		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
+			dev_warn(drvdata->dev, "timestamp not supported\n");
+			return -EINVAL;
+		}
+		drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
+	} else
+		drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN;
+
+	if (drvdata->mode & ETM_MODE_CTXID)
+		drvdata->ctrl |= ETMCR_CTXID_SIZE;
+	else
+		drvdata->ctrl &= ~ETMCR_CTXID_SIZE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t trigger_event_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->trigger_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_event_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_event);
+
+static ssize_t enable_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->enable_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t enable_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->enable_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_event);
+
+static ssize_t fifofull_level_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->fifofull_level;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t fifofull_level_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->fifofull_level = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(fifofull_level);
+
+static ssize_t addr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->addr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_addr_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_idx);
+
+static ssize_t addr_single_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_single_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_single);
+
+static ssize_t addr_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val1 = drvdata->addr_val[idx];
+	val2 = drvdata->addr_val[idx + 1];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx %#lx\n", val1, val2);
+}
+
+static ssize_t addr_range_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+		return -EINVAL;
+	/* Lower address comparator cannot have a higher address value */
+	if (val1 > val2)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val1;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
+	drvdata->addr_val[idx + 1] = val2;
+	drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
+	drvdata->enable_ctrl1 |= (1 << (idx/2));
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_range);
+
+static ssize_t addr_start_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_start_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_START;
+	drvdata->startstop_ctrl |= (1 << idx);
+	drvdata->enable_ctrl1 |= BIT(25);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_start);
+
+static ssize_t addr_stop_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_stop_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP;
+	drvdata->startstop_ctrl |= (1 << (idx + 16));
+	drvdata->enable_ctrl1 |= ETMTECR1_START_STOP;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_stop);
+
+static ssize_t addr_acctype_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->addr_acctype[drvdata->addr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_acctype_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_acctype[drvdata->addr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_acctype);
+
+static ssize_t cntr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->cntr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_cntr)
+		return -EINVAL;
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_idx);
+
+static ssize_t cntr_rld_val_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_val[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_val_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_val);
+
+static ssize_t cntr_event_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_event_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_event);
+
+static ssize_t cntr_rld_event_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_event_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_event);
+
+static ssize_t cntr_val_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int i, ret = 0;
+	u32 val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		spin_lock(&drvdata->spinlock);
+		for (i = 0; i < drvdata->nr_cntr; i++)
+			ret += sprintf(buf, "counter %d: %x\n",
+				       i, drvdata->cntr_val[i]);
+		spin_unlock(&drvdata->spinlock);
+		return ret;
+	}
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		val = etm_readl(drvdata, ETMCNTVRn(i));
+		ret += sprintf(buf, "counter %d: %x\n", i, val);
+	}
+
+	return ret;
+}
+
+static ssize_t cntr_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_val);
+
+static ssize_t seq_12_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_12_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_12_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_12_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_12_event);
+
+static ssize_t seq_21_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_21_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_21_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_21_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_21_event);
+
+static ssize_t seq_23_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_23_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_23_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_23_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_23_event);
+
+static ssize_t seq_31_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_31_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_31_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_31_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_31_event);
+
+static ssize_t seq_32_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_32_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_32_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_32_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_32_event);
+
+static ssize_t seq_13_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_13_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_13_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_13_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_13_event);
+
+static ssize_t seq_curr_state_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->seq_curr_state;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_curr_state_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val > ETM_SEQ_STATE_MAX_VAL)
+		return -EINVAL;
+
+	drvdata->seq_curr_state = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(seq_curr_state);
+
+static ssize_t ctxid_idx_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_idx_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_ctxid_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_idx);
+
+static ssize_t ctxid_val_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->ctxid_val[drvdata->ctxid_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_val_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_val[drvdata->ctxid_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_val);
+
+static ssize_t ctxid_mask_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_mask;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_mask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->ctxid_mask = val;
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_mask);
+
+static ssize_t sync_freq_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->sync_freq;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t sync_freq_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->sync_freq = val & ETM_SYNC_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(sync_freq);
+
+static ssize_t timestamp_event_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->timestamp_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t timestamp_event_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->timestamp_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(timestamp_event);
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	ret = sprintf(buf,
+		      "ETMCCR: 0x%08x\n"
+		      "ETMCCER: 0x%08x\n"
+		      "ETMSCR: 0x%08x\n"
+		      "ETMIDR: 0x%08x\n"
+		      "ETMCR: 0x%08x\n"
+		      "ETMTRACEIDR: 0x%08x\n"
+		      "Enable event: 0x%08x\n"
+		      "Enable start/stop: 0x%08x\n"
+		      "Enable control: CR1 0x%08x CR2 0x%08x\n"
+		      "CPU affinity: %d\n",
+		      drvdata->etmccr, drvdata->etmccer,
+		      etm_readl(drvdata, ETMSCR), etm_readl(drvdata, ETMIDR),
+		      etm_readl(drvdata, ETMCR), etm_trace_id_simple(drvdata),
+		      etm_readl(drvdata, ETMTEEVR),
+		      etm_readl(drvdata, ETMTSSCR),
+		      etm_readl(drvdata, ETMTECR1),
+		      etm_readl(drvdata, ETMTECR2),
+		      drvdata->cpu);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return ret;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t traceid_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->traceid;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t traceid_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->traceid = val & ETM_TRACEID_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(traceid);
+
+static struct attribute *coresight_etm_attrs[] = {
+	&dev_attr_nr_addr_cmp.attr,
+	&dev_attr_nr_cntr.attr,
+	&dev_attr_nr_ctxid_cmp.attr,
+	&dev_attr_etmsr.attr,
+	&dev_attr_reset.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_trigger_event.attr,
+	&dev_attr_enable_event.attr,
+	&dev_attr_fifofull_level.attr,
+	&dev_attr_addr_idx.attr,
+	&dev_attr_addr_single.attr,
+	&dev_attr_addr_range.attr,
+	&dev_attr_addr_start.attr,
+	&dev_attr_addr_stop.attr,
+	&dev_attr_addr_acctype.attr,
+	&dev_attr_cntr_idx.attr,
+	&dev_attr_cntr_rld_val.attr,
+	&dev_attr_cntr_event.attr,
+	&dev_attr_cntr_rld_event.attr,
+	&dev_attr_cntr_val.attr,
+	&dev_attr_seq_12_event.attr,
+	&dev_attr_seq_21_event.attr,
+	&dev_attr_seq_23_event.attr,
+	&dev_attr_seq_31_event.attr,
+	&dev_attr_seq_32_event.attr,
+	&dev_attr_seq_13_event.attr,
+	&dev_attr_seq_curr_state.attr,
+	&dev_attr_ctxid_idx.attr,
+	&dev_attr_ctxid_val.attr,
+	&dev_attr_ctxid_mask.attr,
+	&dev_attr_sync_freq.attr,
+	&dev_attr_timestamp_event.attr,
+	&dev_attr_status.attr,
+	&dev_attr_traceid.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etm);
+
+static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
+			    void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	if (!etmdrvdata[cpu])
+		goto out;
+
+	switch (action & (~CPU_TASKS_FROZEN)) {
+	case CPU_STARTING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (!etmdrvdata[cpu]->os_unlock) {
+			etm_os_unlock(etmdrvdata[cpu]);
+			etmdrvdata[cpu]->os_unlock = true;
+		}
+
+		if (etmdrvdata[cpu]->enable)
+			etm_enable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+
+	case CPU_ONLINE:
+		if (etmdrvdata[cpu]->boot_enable &&
+		    !etmdrvdata[cpu]->sticky_enable)
+			coresight_enable(etmdrvdata[cpu]->csdev);
+		break;
+
+	case CPU_DYING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (etmdrvdata[cpu]->enable)
+			etm_disable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+	}
+out:
+	return NOTIFY_OK;
+}
+
+static struct notifier_block etm_cpu_notifier = {
+	.notifier_call = etm_cpu_callback,
+};
+
+static bool etm_arch_supported(u8 arch)
+{
+	switch (arch) {
+	case ETM_ARCH_V3_3:
+		break;
+	case ETM_ARCH_V3_5:
+		break;
+	case PFT_ARCH_V1_0:
+		break;
+	case PFT_ARCH_V1_1:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static void etm_init_arch_data(void *info)
+{
+	u32 etmidr;
+	u32 etmccr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* First dummy read */
+	(void)etm_readl(drvdata, ETMPDSR);
+	/* Provide power to ETM: ETMPDCR[3] == 1 */
+	etm_set_pwrup(drvdata);
+	/*
+	 * Clear power down bit since when this bit is set writes to
+	 * certain registers might be ignored.
+	 */
+	etm_clr_pwrdwn(drvdata);
+	/*
+	 * Set prog bit. It will be set from reset but this is included to
+	 * ensure it is set
+	 */
+	etm_set_prog(drvdata);
+
+	/* Find all capabilities */
+	etmidr = etm_readl(drvdata, ETMIDR);
+	drvdata->arch = BMVAL(etmidr, 4, 11);
+	drvdata->port_size = etm_readl(drvdata, ETMCR) & PORT_SIZE_MASK;
+
+	drvdata->etmccer = etm_readl(drvdata, ETMCCER);
+	etmccr = etm_readl(drvdata, ETMCCR);
+	drvdata->etmccr = etmccr;
+	drvdata->nr_addr_cmp = BMVAL(etmccr, 0, 3) * 2;
+	drvdata->nr_cntr = BMVAL(etmccr, 13, 15);
+	drvdata->nr_ext_inp = BMVAL(etmccr, 17, 19);
+	drvdata->nr_ext_out = BMVAL(etmccr, 20, 22);
+	drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25);
+
+	etm_set_pwrdwn(drvdata);
+	etm_clr_pwrup(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
+static void etm_init_default_data(struct etm_drvdata *drvdata)
+{
+	static int etm3x_traceid;
+
+	u32 flags = (1 << 0 | /* instruction execute*/
+		     3 << 3 | /* ARM instruction */
+		     0 << 5 | /* No data value comparison */
+		     0 << 7 | /* No exact mach */
+		     0 << 8 | /* Ignore context ID */
+		     0 << 10); /* Security ignored */
+
+	/*
+	 * Initial configuration only - guarantees sources handled by
+	 * this driver have a unique ID at startup time but not between
+	 * all other types of sources.  For that we lean on the core
+	 * framework.
+	 */
+	drvdata->traceid = etm3x_traceid++;
+	drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN);
+	drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
+	if (drvdata->nr_addr_cmp >= 2) {
+		drvdata->addr_val[0] = (u32) _stext;
+		drvdata->addr_val[1] = (u32) _etext;
+		drvdata->addr_acctype[0] = flags;
+		drvdata->addr_acctype[1] = flags;
+		drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE;
+		drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE;
+	}
+
+	etm_set_default(drvdata);
+}
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etm_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+
+		adev->dev.platform_data = pdata;
+		drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14");
+	}
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->cpu = pdata ? pdata->cpu : 0;
+
+	get_online_cpus();
+	etmdrvdata[drvdata->cpu] = drvdata;
+
+	if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1))
+		drvdata->os_unlock = true;
+
+	if (smp_call_function_single(drvdata->cpu,
+				     etm_init_arch_data,  drvdata, 1))
+		dev_err(dev, "ETM arch init failed\n");
+
+	if (!etm_count++)
+		register_hotcpu_notifier(&etm_cpu_notifier);
+
+	put_online_cpus();
+
+	if (etm_arch_supported(drvdata->arch) == false) {
+		ret = -EINVAL;
+		goto err_arch_supported;
+	}
+	etm_init_default_data(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc->type = CORESIGHT_DEV_TYPE_SOURCE;
+	desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
+	desc->ops = &etm_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etm_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_arch_supported;
+	}
+
+	dev_info(dev, "ETM initialized\n");
+
+	if (boot_enable) {
+		coresight_enable(drvdata->csdev);
+		drvdata->boot_enable = true;
+	}
+
+	return 0;
+
+err_arch_supported:
+	clk_disable_unprepare(drvdata->clk);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+	return ret;
+}
+
+static int etm_remove(struct amba_device *adev)
+{
+	struct etm_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+
+	return 0;
+}
+
+static struct amba_id etm_ids[] = {
+	{	/* ETM 3.3 */
+		.id	= 0x0003b921,
+		.mask	= 0x0003ffff,
+	},
+	{	/* ETM 3.5 */
+		.id	= 0x0003b956,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.0 */
+		.id	= 0x0003b950,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.1 */
+		.id	= 0x0003b95f,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etm_driver = {
+	.drv = {
+		.name	= "coresight-etm3x",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etm_probe,
+	.remove		= etm_remove,
+	.id_table	= etm_ids,
+};
+
+int __init etm_init(void)
+{
+	return amba_driver_register(&etm_driver);
+}
+module_init(etm_init);
+
+void __exit etm_exit(void)
+{
+	amba_driver_unregister(&etm_driver);
+}
+module_exit(etm_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Program Flow Trace driver");
diff --git a/drivers/coresight/coresight-funnel.c b/drivers/coresight/coresight-funnel.c
new file mode 100644
index 000000000000..2108edffe1f4
--- /dev/null
+++ b/drivers/coresight/coresight-funnel.c
@@ -0,0 +1,268 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define FUNNEL_FUNCTL		0x000
+#define FUNNEL_PRICTL		0x004
+
+#define FUNNEL_HOLDTIME_MASK	0xf00
+#define FUNNEL_HOLDTIME_SHFT	0x8
+#define FUNNEL_HOLDTIME		(0x7 << FUNNEL_HOLDTIME_SHFT)
+
+/**
+ * struct funnel_drvdata - specifics associated to a funnel component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @priority:	port selection order.
+ */
+struct funnel_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+	unsigned long		priority;
+};
+
+static void funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~FUNNEL_HOLDTIME_MASK;
+	functl |= FUNNEL_HOLDTIME;
+	functl |= (1 << port);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+	writel_relaxed(drvdata->priority, drvdata->base + FUNNEL_PRICTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int funnel_enable(struct coresight_device *csdev, int inport,
+			 int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	funnel_enable_hw(drvdata, inport);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+	return 0;
+}
+
+static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~(1 << inport);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void funnel_disable(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	funnel_disable_hw(drvdata, inport);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+}
+
+static const struct coresight_ops_link funnel_link_ops = {
+	.enable		= funnel_enable,
+	.disable	= funnel_disable,
+};
+
+static const struct coresight_ops funnel_cs_ops = {
+	.link_ops	= &funnel_link_ops,
+};
+
+static ssize_t priority_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->priority;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t priority_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->priority = val;
+	return size;
+}
+static DEVICE_ATTR_RW(priority);
+
+static u32 get_funnel_ctrl_hw(struct funnel_drvdata *drvdata)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	CS_LOCK(drvdata->base);
+
+	return functl;
+}
+
+static ssize_t funnel_ctrl_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int ret;
+	u32 val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	val = get_funnel_ctrl_hw(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#x\n", val);
+}
+static DEVICE_ATTR_RO(funnel_ctrl);
+
+static struct attribute *coresight_funnel_attrs[] = {
+	&dev_attr_funnel_ctrl.attr,
+	&dev_attr_priority.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_funnel);
+
+static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct funnel_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
+	desc->ops = &funnel_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_funnel_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "FUNNEL initialized\n");
+	return 0;
+}
+
+static int funnel_remove(struct amba_device *adev)
+{
+	struct funnel_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id funnel_ids[] = {
+	{
+		.id     = 0x0003b908,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver funnel_driver = {
+	.drv = {
+		.name	= "coresight-funnel",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= funnel_probe,
+	.remove		= funnel_remove,
+	.id_table	= funnel_ids,
+};
+
+static int __init funnel_init(void)
+{
+	return amba_driver_register(&funnel_driver);
+}
+module_init(funnel_init);
+
+static void __exit funnel_exit(void)
+{
+	amba_driver_unregister(&funnel_driver);
+}
+module_exit(funnel_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Funnel driver");
diff --git a/drivers/coresight/coresight-priv.h b/drivers/coresight/coresight-priv.h
new file mode 100644
index 000000000000..7b3372fca4f6
--- /dev/null
+++ b/drivers/coresight/coresight-priv.h
@@ -0,0 +1,63 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_PRIV_H
+#define _CORESIGHT_PRIV_H
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/coresight.h>
+
+/*
+ * Coresight management registers (0xf00-0xfcc)
+ * 0xfa0 - 0xfa4: Management	registers in PFTv1.0
+ *		  Trace		registers in PFTv1.1
+ */
+#define CORESIGHT_ITCTRL	0xf00
+#define CORESIGHT_CLAIMSET	0xfa0
+#define CORESIGHT_CLAIMCLR	0xfa4
+#define CORESIGHT_LAR		0xfb0
+#define CORESIGHT_LSR		0xfb4
+#define CORESIGHT_AUTHSTATUS	0xfb8
+#define CORESIGHT_DEVID		0xfc8
+#define CORESIGHT_DEVTYPE	0xfcc
+
+#define TIMEOUT_US		100
+#define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
+
+static inline void CS_LOCK(void __iomem *addr)
+{
+	do {
+		/* Wait for things to settle */
+		mb();
+		writel_relaxed(0x0, addr + CORESIGHT_LAR);
+	} while (0);
+}
+
+static inline void CS_UNLOCK(void __iomem *addr)
+{
+	do {
+		writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR);
+		/* Make sure everyone has seen this */
+		mb();
+	} while (0);
+}
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+extern int etm_readl_cp14(u32 off, unsigned int *val);
+extern int etm_writel_cp14(u32 off, u32 val);
+#else
+static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; }
+static inline int etm_writel_cp14(u32 val, u32 off) { return 0; }
+#endif
+
+#endif
diff --git a/drivers/coresight/coresight-replicator.c b/drivers/coresight/coresight-replicator.c
new file mode 100644
index 000000000000..a2dfcf903551
--- /dev/null
+++ b/drivers/coresight/coresight-replicator.c
@@ -0,0 +1,137 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+
+#include "coresight-priv.h"
+
+/**
+ * struct replicator_drvdata - specifics associated to a replicator component
+ * @dev:	the device entity associated with this component
+ * @csdev:	component vitals needed by the framework
+ */
+struct replicator_drvdata {
+	struct device		*dev;
+	struct coresight_device	*csdev;
+};
+
+static int replicator_enable(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR enabled\n");
+	return 0;
+}
+
+static void replicator_disable(struct coresight_device *csdev, int inport,
+			       int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR disabled\n");
+}
+
+static const struct coresight_ops_link replicator_link_ops = {
+	.enable		= replicator_enable,
+	.disable	= replicator_disable,
+};
+
+static const struct coresight_ops replicator_cs_ops = {
+	.link_ops	= &replicator_link_ops,
+};
+
+static int replicator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct replicator_drvdata *drvdata;
+	struct coresight_desc *desc;
+	struct device_node *np = pdev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		pdev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &pdev->dev;
+	platform_set_drvdata(pdev, drvdata);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
+	desc->ops = &replicator_cs_ops;
+	desc->pdata = pdev->dev.platform_data;
+	desc->dev = &pdev->dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "REPLICATOR initialized\n");
+	return 0;
+}
+
+static int replicator_remove(struct platform_device *pdev)
+{
+	struct replicator_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct of_device_id replicator_match[] = {
+	{.compatible = "arm,coresight-replicator"},
+	{}
+};
+
+static struct platform_driver replicator_driver = {
+	.probe          = replicator_probe,
+	.remove         = replicator_remove,
+	.driver         = {
+		.name   = "coresight-replicator",
+		.of_match_table = replicator_match,
+	},
+};
+
+static int __init replicator_init(void)
+{
+	return platform_driver_register(&replicator_driver);
+}
+module_init(replicator_init);
+
+static void __exit replicator_exit(void)
+{
+	platform_driver_unregister(&replicator_driver);
+}
+module_exit(replicator_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Replicator driver");
diff --git a/drivers/coresight/coresight-tmc.c b/drivers/coresight/coresight-tmc.c
new file mode 100644
index 000000000000..ce2c293f1707
--- /dev/null
+++ b/drivers/coresight/coresight-tmc.c
@@ -0,0 +1,776 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TMC_RSZ			0x004
+#define TMC_STS			0x00c
+#define TMC_RRD			0x010
+#define TMC_RRP			0x014
+#define TMC_RWP			0x018
+#define TMC_TRG			0x01c
+#define TMC_CTL			0x020
+#define TMC_RWD			0x024
+#define TMC_MODE		0x028
+#define TMC_LBUFLEVEL		0x02c
+#define TMC_CBUFLEVEL		0x030
+#define TMC_BUFWM		0x034
+#define TMC_RRPHI		0x038
+#define TMC_RWPHI		0x03c
+#define TMC_AXICTL		0x110
+#define TMC_DBALO		0x118
+#define TMC_DBAHI		0x11c
+#define TMC_FFSR		0x300
+#define TMC_FFCR		0x304
+#define TMC_PSCR		0x308
+#define TMC_ITMISCOP0		0xee0
+#define TMC_ITTRFLIN		0xee8
+#define TMC_ITATBDATA0		0xeec
+#define TMC_ITATBCTR2		0xef0
+#define TMC_ITATBCTR1		0xef4
+#define TMC_ITATBCTR0		0xef8
+
+/* register description */
+/* TMC_CTL - 0x020 */
+#define TMC_CTL_CAPT_EN		BIT(0)
+/* TMC_STS - 0x00C */
+#define TMC_STS_TRIGGERED	BIT(1)
+/* TMC_AXICTL - 0x110 */
+#define TMC_AXICTL_PROT_CTL_B0	BIT(0)
+#define TMC_AXICTL_PROT_CTL_B1	BIT(1)
+#define TMC_AXICTL_SCT_GAT_MODE	BIT(7)
+#define TMC_AXICTL_WR_BURST_LEN 0xF00
+/* TMC_FFCR - 0x304 */
+#define TMC_FFCR_EN_FMT		BIT(0)
+#define TMC_FFCR_EN_TI		BIT(1)
+#define TMC_FFCR_FON_FLIN	BIT(4)
+#define TMC_FFCR_FON_TRIG_EVT	BIT(5)
+#define TMC_FFCR_FLUSHMAN	BIT(6)
+#define TMC_FFCR_TRIGON_TRIGIN	BIT(8)
+#define TMC_FFCR_STOP_ON_FLUSH	BIT(12)
+
+#define TMC_STS_TRIGGERED_BIT	2
+#define TMC_FFCR_FLUSHMAN_BIT	6
+
+enum tmc_config_type {
+	TMC_CONFIG_TYPE_ETB,
+	TMC_CONFIG_TYPE_ETR,
+	TMC_CONFIG_TYPE_ETF,
+};
+
+enum tmc_mode {
+	TMC_MODE_CIRCULAR_BUFFER,
+	TMC_MODE_SOFTWARE_FIFO,
+	TMC_MODE_HARDWARE_FIFO,
+};
+
+enum tmc_mem_intf_width {
+	TMC_MEM_INTF_WIDTH_32BITS	= 0x2,
+	TMC_MEM_INTF_WIDTH_64BITS	= 0x3,
+	TMC_MEM_INTF_WIDTH_128BITS	= 0x4,
+	TMC_MEM_INTF_WIDTH_256BITS	= 0x5,
+};
+
+/**
+ * struct tmc_drvdata - specifics associated to an TMC component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.tmc" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @read_count:	manages preparation of buffer for reading.
+ * @buf:	area of memory where trace data get sent.
+ * @paddr:	DMA start location in RAM.
+ * @vaddr:	virtual representation of @paddr.
+ * @size:	@buf size.
+ * @enable:	this TMC is being used.
+ * @config_type: TMC variant, must be of type @tmc_config_type.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct tmc_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	int			read_count;
+	bool			reading;
+	char			*buf;
+	dma_addr_t		paddr;
+	void __iomem		*vaddr;
+	u32			size;
+	bool			enable;
+	enum tmc_config_type	config_type;
+	u32			trigger_cntr;
+};
+
+static void tmc_wait_for_ready(struct tmc_drvdata *drvdata)
+{
+	/* Ensure formatter, unformatter and hardware fifo are empty */
+	if (coresight_timeout(drvdata->base,
+			      TMC_STS, TMC_STS_TRIGGERED_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_STS);
+	}
+}
+
+static void tmc_flush_and_stop(struct tmc_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	ffcr = readl_relaxed(drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_STOP_ON_FLUSH;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_FLUSHMAN;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	/* Ensure flush completes */
+	if (coresight_timeout(drvdata->base,
+			      TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_FFCR);
+	}
+
+	tmc_wait_for_ready(drvdata);
+}
+
+static void tmc_enable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL);
+}
+
+static void tmc_disable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(0x0, drvdata->base + TMC_CTL);
+}
+
+static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
+{
+	/* Zero out the memory to help with debug */
+	memset(drvdata->buf, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
+{
+	u32 axictl;
+
+	/* Zero out the memory to help with debug */
+	memset(drvdata->vaddr, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(drvdata->size / 4, drvdata->base + TMC_RSZ);
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+
+	axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
+	axictl |= TMC_AXICTL_WR_BURST_LEN;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl &= ~TMC_AXICTL_SCT_GAT_MODE;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl = (axictl &
+		  ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
+		  TMC_AXICTL_PROT_CTL_B1;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+
+	writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO);
+	writel_relaxed(0x0, drvdata->base + TMC_DBAHI);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_enable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(0x0, drvdata->base + TMC_BUFWM);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		clk_disable_unprepare(drvdata->clk);
+		return -EBUSY;
+	}
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+		else
+			tmc_etf_enable_hw(drvdata);
+	}
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC enabled\n");
+	return 0;
+}
+
+static int tmc_enable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static int tmc_enable_link(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
+{
+	enum tmc_mem_intf_width memwidth;
+	u8 memwords;
+	char *bufp;
+	u32 read_data;
+	int i;
+
+	memwidth = BMVAL(readl_relaxed(drvdata->base + CORESIGHT_DEVID), 8, 10);
+	if (memwidth == TMC_MEM_INTF_WIDTH_32BITS)
+		memwords = 1;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_64BITS)
+		memwords = 2;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_128BITS)
+		memwords = 4;
+	else
+		memwords = 8;
+
+	bufp = drvdata->buf;
+	while (1) {
+		for (i = 0; i < memwords; i++) {
+			read_data = readl_relaxed(drvdata->base + TMC_RRD);
+			if (read_data == 0xFFFFFFFF)
+				return;
+			memcpy(bufp, &read_data, 4);
+			bufp += 4;
+		}
+	}
+}
+
+static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etb_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
+{
+	u32 rwp, val;
+
+	rwp = readl_relaxed(drvdata->base + TMC_RWP);
+	val = readl_relaxed(drvdata->base + TMC_STS);
+
+	/* How much memory do we still have */
+	if (val & BIT(0))
+		drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr;
+	else
+		drvdata->buf = drvdata->vaddr;
+}
+
+static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etr_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_disable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_disable_hw(drvdata);
+		else
+			tmc_etf_disable_hw(drvdata);
+	}
+out:
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TMC disabled\n");
+}
+
+static void tmc_disable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static void tmc_disable_link(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static const struct coresight_ops_sink tmc_sink_ops = {
+	.enable		= tmc_enable_sink,
+	.disable	= tmc_disable_sink,
+};
+
+static const struct coresight_ops_link tmc_link_ops = {
+	.enable		= tmc_enable_link,
+	.disable	= tmc_disable_link,
+};
+
+static const struct coresight_ops tmc_etb_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etr_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etf_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+	.link_ops	= &tmc_link_ops,
+};
+
+static int tmc_read_prepare(struct tmc_drvdata *drvdata)
+{
+	int ret;
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER) {
+			tmc_etb_disable_hw(drvdata);
+		} else {
+			ret = -ENODEV;
+			goto err;
+		}
+	}
+out:
+	drvdata->reading = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read start\n");
+	return 0;
+err:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return ret;
+}
+
+static void tmc_read_unprepare(struct tmc_drvdata *drvdata)
+{
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+	}
+out:
+	drvdata->reading = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read end\n");
+}
+
+static int tmc_open(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	int ret = 0;
+
+	if (drvdata->read_count++)
+		goto out;
+
+	ret = tmc_read_prepare(drvdata);
+	if (ret)
+		return ret;
+out:
+	nonseekable_open(inode, file);
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t tmc_read(struct file *file, char __user *data, size_t len,
+			loff_t *ppos)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	char *bufp = drvdata->buf + *ppos;
+
+	if (*ppos + len > drvdata->size)
+		len = drvdata->size - *ppos;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (bufp == (char *)(drvdata->vaddr + drvdata->size))
+			bufp = drvdata->vaddr;
+		else if (bufp > (char *)(drvdata->vaddr + drvdata->size))
+			bufp -= drvdata->size;
+		if ((bufp + len) > (char *)(drvdata->vaddr + drvdata->size))
+			len = (char *)(drvdata->vaddr + drvdata->size) - bufp;
+	}
+
+	if (copy_to_user(data, bufp, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+		__func__, len, (int) (drvdata->size - *ppos));
+	return len;
+}
+
+static int tmc_release(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+
+	if (--drvdata->read_count) {
+		if (drvdata->read_count < 0) {
+			dev_err(drvdata->dev, "mismatched close\n");
+			drvdata->read_count = 0;
+		}
+		goto out;
+	}
+
+	tmc_read_unprepare(drvdata);
+out:
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations tmc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= tmc_open,
+	.read		= tmc_read,
+	.release	= tmc_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static struct attribute *coresight_etr_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etr);
+
+static struct attribute *coresight_etf_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etf);
+
+static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret = 0;
+	u32 devid;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tmc_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
+	drvdata->config_type = BMVAL(devid, 6, 7);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (np)
+			ret = of_property_read_u32(np,
+						   "arm,buffer-size",
+						   &drvdata->size);
+		if (ret)
+			drvdata->size = SZ_1M;
+	} else {
+		drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
+	}
+
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		drvdata->vaddr = dma_alloc_coherent(dev, drvdata->size,
+						&drvdata->paddr, GFP_KERNEL);
+		if (!drvdata->vaddr)
+			return -ENOMEM;
+
+		memset(drvdata->vaddr, 0, drvdata->size);
+		drvdata->buf = drvdata->vaddr;
+	} else {
+		drvdata->buf = devm_kzalloc(dev, drvdata->size, GFP_KERNEL);
+		if (!drvdata->buf)
+			return -ENOMEM;
+	}
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto err_devm_kzalloc;
+	}
+
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etb_cs_ops;
+		desc->groups = coresight_etb_groups;
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etr_cs_ops;
+		desc->groups = coresight_etr_groups;
+	} else {
+		desc->type = CORESIGHT_DEV_TYPE_LINKSINK;
+		desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
+		desc->ops = &tmc_etf_cs_ops;
+		desc->groups = coresight_etf_groups;
+	}
+
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_devm_kzalloc;
+	}
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &tmc_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "TMC initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+err_devm_kzalloc:
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(dev, drvdata->size,
+				&drvdata->paddr, GFP_KERNEL);
+	return ret;
+}
+
+static int tmc_remove(struct amba_device *adev)
+{
+	struct tmc_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(drvdata->dev, drvdata->size,
+				  &drvdata->paddr, GFP_KERNEL);
+
+	return 0;
+}
+
+static struct amba_id tmc_ids[] = {
+	{
+		.id     = 0x0003b961,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tmc_driver = {
+	.drv = {
+		.name   = "coresight-tmc",
+		.owner  = THIS_MODULE,
+	},
+	.probe		= tmc_probe,
+	.remove		= tmc_remove,
+	.id_table	= tmc_ids,
+};
+
+static int __init tmc_init(void)
+{
+	return amba_driver_register(&tmc_driver);
+}
+module_init(tmc_init);
+
+static void __exit tmc_exit(void)
+{
+	amba_driver_unregister(&tmc_driver);
+}
+module_exit(tmc_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver");
diff --git a/drivers/coresight/coresight-tpiu.c b/drivers/coresight/coresight-tpiu.c
new file mode 100644
index 000000000000..ae101082791a
--- /dev/null
+++ b/drivers/coresight/coresight-tpiu.c
@@ -0,0 +1,217 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TPIU_SUPP_PORTSZ	0x000
+#define TPIU_CURR_PORTSZ	0x004
+#define TPIU_SUPP_TRIGMODES	0x100
+#define TPIU_TRIG_CNTRVAL	0x104
+#define TPIU_TRIG_MULT		0x108
+#define TPIU_SUPP_TESTPATM	0x200
+#define TPIU_CURR_TESTPATM	0x204
+#define TPIU_TEST_PATREPCNTR	0x208
+#define TPIU_FFSR		0x300
+#define TPIU_FFCR		0x304
+#define TPIU_FSYNC_CNTR		0x308
+#define TPIU_EXTCTL_INPORT	0x400
+#define TPIU_EXTCTL_OUTPORT	0x404
+#define TPIU_ITTRFLINACK	0xee4
+#define TPIU_ITTRFLIN		0xee8
+#define TPIU_ITATBDATA0		0xeec
+#define TPIU_ITATBCTR2		0xef0
+#define TPIU_ITATBCTR1		0xef4
+#define TPIU_ITATBCTR0		0xef8
+
+/** register definition **/
+/* FFCR - 0x304 */
+#define FFCR_FON_MAN		BIT(6)
+
+/**
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ */
+struct tpiu_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+};
+
+static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* TODO: fill this up */
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tpiu_enable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	tpiu_enable_hw(drvdata);
+
+	dev_info(drvdata->dev, "TPIU enabled\n");
+	return 0;
+}
+
+static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* Clear formatter controle reg. */
+	writel_relaxed(0x0, drvdata->base + TPIU_FFCR);
+	/* Generate manual flush */
+	writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tpiu_disable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TPIU disabled\n");
+}
+
+static const struct coresight_ops_sink tpiu_sink_ops = {
+	.enable		= tpiu_enable,
+	.disable	= tpiu_disable,
+};
+
+static const struct coresight_ops tpiu_cs_ops = {
+	.sink_ops	= &tpiu_sink_ops,
+};
+
+static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tpiu_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* Disable tpiu to support older devices */
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
+	desc->ops = &tpiu_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "TPIU initialized\n");
+	return 0;
+}
+
+static int tpiu_remove(struct amba_device *adev)
+{
+	struct tpiu_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id tpiu_ids[] = {
+	{
+		.id	= 0x0003b912,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tpiu_driver = {
+	.drv = {
+		.name	= "coresight-tpiu",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= tpiu_probe,
+	.remove		= tpiu_remove,
+	.id_table	= tpiu_ids,
+};
+
+static int __init tpiu_init(void)
+{
+	return amba_driver_register(&tpiu_driver);
+}
+module_init(tpiu_init);
+
+static void __exit tpiu_exit(void)
+{
+	amba_driver_unregister(&tpiu_driver);
+}
+module_exit(tpiu_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver");
diff --git a/drivers/coresight/coresight.c b/drivers/coresight/coresight.c
new file mode 100644
index 000000000000..6e0181f84425
--- /dev/null
+++ b/drivers/coresight/coresight.c
@@ -0,0 +1,717 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
+
+#include "coresight-priv.h"
+
+static DEFINE_MUTEX(coresight_mutex);
+
+static int coresight_id_match(struct device *dev, void *data)
+{
+	int trace_id, i_trace_id;
+	struct coresight_device *csdev, *i_csdev;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/*
+	 * No need to care about oneself and components that are not
+	 * sources or not enabled
+	 */
+	if (i_csdev == csdev || !i_csdev->enable ||
+	    i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE)
+		return 0;
+
+	/* Get the source ID for both compoment */
+	trace_id = source_ops(csdev)->trace_id(csdev);
+	i_trace_id = source_ops(i_csdev)->trace_id(i_csdev);
+
+	/* All you need is one */
+	if (trace_id == i_trace_id)
+		return 1;
+
+	return 0;
+}
+
+static int coresight_source_is_unique(struct coresight_device *csdev)
+{
+	int trace_id = source_ops(csdev)->trace_id(csdev);
+
+	/* this shouldn't happen */
+	if (trace_id < 0)
+		return 0;
+
+	return !bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_id_match);
+}
+
+static int coresight_find_link_inport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *parent;
+	struct coresight_connection *conn;
+
+	parent = container_of(csdev->path_link.next,
+			      struct coresight_device, path_link);
+
+	for (i = 0; i < parent->nr_outport; i++) {
+		conn = &parent->conns[i];
+		if (conn->child_dev == csdev)
+			return conn->child_port;
+	}
+
+	dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n",
+		dev_name(&parent->dev), dev_name(&csdev->dev));
+
+	return 0;
+}
+
+static int coresight_find_link_outport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *child;
+	struct coresight_connection *conn;
+
+	child = container_of(csdev->path_link.prev,
+			     struct coresight_device, path_link);
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		if (conn->child_dev == child)
+			return conn->outport;
+	}
+
+	dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n",
+		dev_name(&csdev->dev), dev_name(&child->dev));
+
+	return 0;
+}
+
+static int coresight_enable_sink(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!csdev->enable) {
+		if (sink_ops(csdev)->enable) {
+			ret = sink_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_sink(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (sink_ops(csdev)->disable) {
+			sink_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_link(struct coresight_device *csdev)
+{
+	int ret;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+		refport = inport;
+	else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+		refport = outport;
+	else
+		refport = 0;
+
+	if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
+		if (link_ops(csdev)->enable) {
+			ret = link_ops(csdev)->enable(csdev, inport, outport);
+			if (ret)
+				return ret;
+		}
+	}
+
+	csdev->enable = true;
+
+	return 0;
+}
+
+static void coresight_disable_link(struct coresight_device *csdev)
+{
+	int i, nr_conns;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
+		refport = inport;
+		nr_conns = csdev->nr_inport;
+	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
+		refport = outport;
+		nr_conns = csdev->nr_outport;
+	} else {
+		refport = 0;
+		nr_conns = 1;
+	}
+
+	if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
+		if (link_ops(csdev)->disable)
+			link_ops(csdev)->disable(csdev, inport, outport);
+	}
+
+	for (i = 0; i < nr_conns; i++)
+		if (atomic_read(&csdev->refcnt[i]) != 0)
+			return;
+
+	csdev->enable = false;
+}
+
+static int coresight_enable_source(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!coresight_source_is_unique(csdev)) {
+		dev_warn(&csdev->dev, "traceID %d not unique\n",
+			 source_ops(csdev)->trace_id(csdev));
+		return -EINVAL;
+	}
+
+	if (!csdev->enable) {
+		if (source_ops(csdev)->enable) {
+			ret = source_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_source(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (source_ops(csdev)->disable) {
+			source_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_path(struct list_head *path)
+{
+	int ret = 0;
+	struct coresight_device *cd;
+
+	list_for_each_entry(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			ret = coresight_enable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * Don't enable the source just yet - this needs to
+			 * happen at the very end when all links and sink
+			 * along the path have been configured properly.
+			 */
+			;
+		} else {
+			ret = coresight_enable_link(cd);
+		}
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	list_for_each_entry_continue_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return ret;
+}
+
+static int coresight_disable_path(struct list_head *path)
+{
+	struct coresight_device *cd;
+
+	list_for_each_entry_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * The source has already been stopped, no need
+			 * to do it again here.
+			 */
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return 0;
+}
+
+static int coresight_build_paths(struct coresight_device *csdev,
+				 struct list_head *path,
+				 bool enable)
+{
+	int i, ret = -EINVAL;
+	struct coresight_connection *conn;
+
+	list_add(&csdev->path_link, path);
+
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK && csdev->activated) {
+		if (enable)
+			ret = coresight_enable_path(path);
+		else
+			ret = coresight_disable_path(path);
+	} else {
+		for (i = 0; i < csdev->nr_outport; i++) {
+			conn = &csdev->conns[i];
+			if (coresight_build_paths(conn->child_dev,
+						    path, enable) == 0)
+				ret = 0;
+		}
+	}
+
+	if (list_first_entry(path, struct coresight_device, path_link) != csdev)
+		dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+
+	list_del(&csdev->path_link);
+
+	return ret;
+}
+
+int coresight_enable(struct coresight_device *csdev)
+{
+	int ret = 0;
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		ret = -EINVAL;
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (csdev->enable)
+		goto out;
+
+	if (coresight_build_paths(csdev, &path, true)) {
+		dev_err(&csdev->dev, "building path(s) failed\n");
+		goto out;
+	}
+
+	if (coresight_enable_source(csdev))
+		dev_err(&csdev->dev, "source enable failed\n");
+out:
+	mutex_unlock(&coresight_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(coresight_enable);
+
+void coresight_disable(struct coresight_device *csdev)
+{
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (!csdev->enable)
+		goto out;
+
+	coresight_disable_source(csdev);
+	if (coresight_build_paths(csdev, &path, false))
+		dev_err(&csdev->dev, "releasing path(s) failed\n");
+
+out:
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_disable);
+
+static ssize_t enable_sink_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated);
+}
+
+static ssize_t enable_sink_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		csdev->activated = true;
+	else
+		csdev->activated = false;
+
+	return size;
+
+}
+static DEVICE_ATTR_RW(enable_sink);
+
+static ssize_t enable_source_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable);
+}
+
+static ssize_t enable_source_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		ret = coresight_enable(csdev);
+		if (ret)
+			return ret;
+	} else {
+		coresight_disable(csdev);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_source);
+
+static struct attribute *coresight_sink_attrs[] = {
+	&dev_attr_enable_sink.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_sink);
+
+static struct attribute *coresight_source_attrs[] = {
+	&dev_attr_enable_source.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_source);
+
+static struct device_type coresight_dev_type[] = {
+	{
+		.name = "none",
+	},
+	{
+		.name = "sink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "link",
+	},
+	{
+		.name = "linksink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "source",
+		.groups = coresight_source_groups,
+	},
+};
+
+static void coresight_device_release(struct device *dev)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	kfree(csdev);
+}
+
+static int coresight_orphan_match(struct device *dev, void *data)
+{
+	int i;
+	bool still_orphan = false;
+	struct coresight_device *csdev, *i_csdev;
+	struct coresight_connection *conn;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/* No need to check oneself */
+	if (csdev == i_csdev)
+		return 0;
+
+	/* Move on to another component if no connection is orphan */
+	if (!i_csdev->orphan)
+		return 0;
+	/*
+	 * Circle throuch all the connection of that component.  If we find
+	 * an orphan connection whose name matches @csdev, link it.
+	 */
+	for (i = 0; i < i_csdev->nr_outport; i++)	{
+		conn = &i_csdev->conns[i];
+
+		/* We have found at least one orphan connection */
+		if (conn->child_dev == NULL) {
+			/* Does it match this newly added device? */
+			if (!strcmp(dev_name(&csdev->dev), conn->child_name))
+				conn->child_dev = csdev;
+		} else {
+			/* Too bad, this component still has an orphan */
+			still_orphan = true;
+		}
+	}
+
+	i_csdev->orphan = still_orphan;
+
+	/*
+	 * Returning '0' ensures that all known component on the
+	 * bus will be checked.
+	 */
+	return 0;
+}
+
+static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
+{
+	/*
+	 * No need to check for a return value as orphan connection(s)
+	 * are hooked-up with each newly added component.
+	 */
+	bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_orphan_match);
+}
+
+
+static int coresight_name_match(struct device *dev, void *data)
+{
+	char *to_match;
+	struct coresight_device *i_csdev;
+
+	to_match = data;
+	i_csdev = to_coresight_device(dev);
+
+	if (!strcmp(to_match, dev_name(&i_csdev->dev)))
+		return 1;
+
+	return 0;
+}
+
+static void coresight_fixup_device_conns(struct coresight_device *csdev)
+{
+	int i;
+	struct device *dev = NULL;
+	struct coresight_connection *conn;
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		dev = bus_find_device(&coresight_bustype, NULL,
+				      (void *)conn->child_name,
+				      coresight_name_match);
+
+		if (dev) {
+			conn->child_dev = to_coresight_device(dev);
+		} else {
+			csdev->orphan = true;
+			conn->child_dev = NULL;
+		}
+	}
+}
+
+/**
+ * coresight_timeout - loop until a bit has changed to a specific state.
+ * @addr: base address of the area of interest.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+int coresight_timeout(void __iomem *addr, u32 offset, int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = __raw_readl(addr + offset);
+		/* waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+struct bus_type coresight_bustype = {
+	.name	= "coresight",
+};
+
+static int __init coresight_init(void)
+{
+	return bus_register(&coresight_bustype);
+}
+postcore_initcall(coresight_init);
+
+struct coresight_device *coresight_register(struct coresight_desc *desc)
+{
+	int i;
+	int ret;
+	int link_subtype;
+	int nr_refcnts = 1;
+	atomic_t *refcnts = NULL;
+	struct coresight_device *csdev;
+	struct coresight_connection *conns;
+
+	csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
+	if (!csdev) {
+		ret = -ENOMEM;
+		goto err_kzalloc_csdev;
+	}
+
+	if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
+	    desc->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		link_subtype = desc->subtype.link_subtype;
+
+		if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+			nr_refcnts = desc->pdata->nr_inport;
+		else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+			nr_refcnts = desc->pdata->nr_outport;
+	}
+
+	refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
+	if (!refcnts) {
+		ret = -ENOMEM;
+		goto err_kzalloc_refcnts;
+	}
+
+	csdev->refcnt = refcnts;
+
+	csdev->nr_inport = desc->pdata->nr_inport;
+	csdev->nr_outport = desc->pdata->nr_outport;
+	conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
+	if (!conns) {
+		ret = -ENOMEM;
+		goto err_kzalloc_conns;
+	}
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conns[i].outport = desc->pdata->outports[i];
+		conns[i].child_name = desc->pdata->child_names[i];
+		conns[i].child_port = desc->pdata->child_ports[i];
+	}
+
+	csdev->conns = conns;
+
+	csdev->type = desc->type;
+	csdev->subtype = desc->subtype;
+	csdev->ops = desc->ops;
+	csdev->orphan = false;
+
+	csdev->dev.type = &coresight_dev_type[desc->type];
+	csdev->dev.groups = desc->groups;
+	csdev->dev.parent = desc->dev;
+	csdev->dev.release = coresight_device_release;
+	csdev->dev.bus = &coresight_bustype;
+	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+
+	ret = device_register(&csdev->dev);
+	if (ret)
+		goto err_device_register;
+
+	mutex_lock(&coresight_mutex);
+
+	coresight_fixup_device_conns(csdev);
+	coresight_fixup_orphan_conns(csdev);
+
+	mutex_unlock(&coresight_mutex);
+
+	return csdev;
+
+err_device_register:
+	kfree(conns);
+err_kzalloc_conns:
+	kfree(refcnts);
+err_kzalloc_refcnts:
+	kfree(csdev);
+err_kzalloc_csdev:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_register);
+
+void coresight_unregister(struct coresight_device *csdev)
+{
+	mutex_lock(&coresight_mutex);
+
+	kfree(csdev->conns);
+	device_unregister(&csdev->dev);
+
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_unregister);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/coresight/of_coresight.c b/drivers/coresight/of_coresight.c
new file mode 100644
index 000000000000..5030c0734508
--- /dev/null
+++ b/drivers/coresight/of_coresight.c
@@ -0,0 +1,204 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <asm/smp_plat.h>
+
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static struct device *
+of_coresight_get_endpoint_device(struct device_node *endpoint)
+{
+	struct device *dev = NULL;
+
+	/*
+	 * If we have a non-configuable replicator, it will be found on the
+	 * platform bus.
+	 */
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      endpoint, of_dev_node_match);
+	if (dev)
+		return dev;
+
+	/*
+	 * We have a configurable component - circle through the AMBA bus
+	 * looking for the device that matches the endpoint node.
+	 */
+	return bus_find_device(&amba_bustype, NULL,
+			       endpoint, of_dev_node_match);
+}
+
+static struct device_node *of_get_coresight_endpoint(
+		const struct device_node *parent, struct device_node *prev)
+{
+	struct device_node *node = of_graph_get_next_endpoint(parent, prev);
+
+	of_node_put(prev);
+	return node;
+}
+
+static void of_coresight_get_ports(struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *ep = NULL;
+	int in = 0, out = 0;
+
+	do {
+		ep = of_get_coresight_endpoint(node, ep);
+		if (!ep)
+			break;
+
+		if (of_property_read_bool(ep, "slave-mode"))
+			in++;
+		else
+			out++;
+
+	} while (ep);
+
+	*nr_inport = in;
+	*nr_outport = out;
+}
+
+static int of_coresight_alloc_memory(struct device *dev,
+			struct coresight_platform_data *pdata)
+{
+	/* List of output port on this component */
+	pdata->outports = devm_kzalloc(dev, pdata->nr_outport *
+				       sizeof(*pdata->outports),
+				       GFP_KERNEL);
+	if (!pdata->outports)
+		return -ENOMEM;
+
+	/* Children connected to this component via @outport */
+	 pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_names),
+					  GFP_KERNEL);
+	if (!pdata->child_names)
+		return -ENOMEM;
+
+	/* Port number on the child this component is connected to */
+	pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_ports),
+					  GFP_KERNEL);
+	if (!pdata->child_ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node)
+{
+	int i = 0, ret = 0;
+	struct coresight_platform_data *pdata;
+	struct of_endpoint endpoint, rendpoint;
+	struct device *rdev;
+	struct device_node *cpu;
+	struct device_node *ep = NULL;
+	struct device_node *rparent = NULL;
+	struct device_node *rport = NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	/* Use device name as debugfs handle */
+	pdata->name = dev_name(dev);
+
+	/* Get the number of input and output port for this component */
+	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+	if (pdata->nr_outport) {
+		ret = of_coresight_alloc_memory(dev, pdata);
+		if (ret)
+			return ERR_PTR(ret);
+
+		/* Iterate through each port to discover topology */
+		do {
+			/* Get a handle on a port */
+			ep = of_get_coresight_endpoint(node, ep);
+			if (!ep)
+				break;
+
+			/*
+			 * No need to deal with input ports, processing for as
+			 * processing for output ports will deal with them.
+			 */
+			if (of_find_property(ep, "slave-mode", NULL))
+				continue;
+
+			/* Get a handle on the local endpoint */
+			ret = of_graph_parse_endpoint(ep, &endpoint);
+
+			if (ret)
+				continue;
+
+			/* The local out port number */
+			pdata->outports[i] = endpoint.id;
+
+			/*
+			 * Get a handle on the remote port and parent
+			 * attached to it.
+			 */
+			rparent = of_graph_get_remote_port_parent(ep);
+			rport = of_graph_get_remote_port(ep);
+
+			if (!rparent || !rport)
+				continue;
+
+			if (of_graph_parse_endpoint(rport, &rendpoint))
+				continue;
+
+			rdev = of_coresight_get_endpoint_device(rparent);
+			if (!dev)
+				continue;
+
+			pdata->child_names[i] = dev_name(rdev);
+			pdata->child_ports[i] = rendpoint.id;
+
+			i++;
+		} while (ep);
+	}
+
+	/* Affinity defaults to CPU0 */
+	pdata->cpu = 0;
+	cpu = of_parse_phandle(node, "cpu", 0);
+	if (cpu) {
+		const u32 *mpidr;
+		int len, index;
+
+		mpidr = of_get_property(cpu, "reg", &len);
+		if (mpidr && len == 4) {
+			index = get_logical_index(be32_to_cpup(mpidr));
+			if (index != -EINVAL)
+				pdata->cpu = index;
+		}
+	}
+
+	return pdata;
+}
+EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 534fcb825153..a9c1324843eb 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -201,7 +201,7 @@ source "drivers/cpufreq/Kconfig.x86"
 endmenu
 
 menu "ARM CPU frequency scaling drivers"
-depends on ARM
+depends on ARM || ARM64
 source "drivers/cpufreq/Kconfig.arm"
 endmenu
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 6e57543fe0b9..22727792350b 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -4,7 +4,8 @@
 
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM_CPU_TOPOLOGY && PM_OPP && HAVE_CLK
+	depends on (ARM_CPU_TOPOLOGY && BIG_LITTLE) || (ARM64 && SMP)
+	depends on PM_OPP && HAVE_CLK
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
 
@@ -15,6 +16,14 @@ config ARM_DT_BL_CPUFREQ
 	  This enables probing via DT for Generic CPUfreq driver for ARM
 	  big.LITTLE platform. This gets frequency tables from DT.
 
+config ARM_VEXPRESS_BL_CPUFREQ
+	tristate "ARM Vexpress big LITTLE CPUfreq driver"
+	select ARM_BIG_LITTLE_CPUFREQ
+	depends on VEXPRESS_SPC
+	help
+	  This enables the CPUfreq driver for ARM Vexpress big.LITTLE platform.
+	  If in doubt, say N.
+
 config ARM_EXYNOS_CPUFREQ
 	bool "SAMSUNG EXYNOS SoCs"
 	depends on ARCH_EXYNOS
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 315b9231feb1..505c62bceb9d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -48,9 +48,10 @@ obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY)	+= amd_freq_sensitivity.o
 obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 # big LITTLE per platform glues. Keep DT_BL_CPUFREQ as the last entry in all big
 # LITTLE drivers, so that it is probed last.
+obj-$(CONFIG_ARM_VEXPRESS_BL_CPUFREQ)	+= vexpress_big_little.o
 obj-$(CONFIG_ARM_DT_BL_CPUFREQ)		+= arm_big_little_dt.o
 
-obj-$(CONFIG_ARCH_DAVINCI_DA850)	+= davinci-cpufreq.o
+obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= exynos-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 5d7f53fcd6f5..eaee6e222207 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -24,27 +24,148 @@
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
+#include <linux/mutex.h>
 #include <linux/of_platform.h>
 #include <linux/opp.h>
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
+#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
-/* Currently we support only two clusters */
-#define MAX_CLUSTERS	2
+#ifdef CONFIG_BL_SWITCHER
+bool bL_switching_enabled;
+#endif
+
+#define ACTUAL_FREQ(cluster, freq)	((cluster == A7_CLUSTER) ? freq << 1 : freq)
+#define VIRT_FREQ(cluster, freq)	((cluster == A7_CLUSTER) ? freq >> 1 : freq)
 
 static struct cpufreq_arm_bL_ops *arm_bL_ops;
 static struct clk *clk[MAX_CLUSTERS];
-static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS];
-static atomic_t cluster_usage[MAX_CLUSTERS] = {ATOMIC_INIT(0), ATOMIC_INIT(0)};
+static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
+static atomic_t cluster_usage[MAX_CLUSTERS + 1] = {ATOMIC_INIT(0),
+	ATOMIC_INIT(0)};
+
+static unsigned int clk_big_min;	/* (Big) clock frequencies */
+static unsigned int clk_little_max;	/* Maximum clock frequency (Little) */
+
+static DEFINE_PER_CPU(unsigned int, physical_cluster);
+static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
+
+static struct mutex cluster_lock[MAX_CLUSTERS];
+
+static unsigned int find_cluster_maxfreq(int cluster)
+{
+	int j;
+	u32 max_freq = 0, cpu_freq;
+
+	for_each_online_cpu(j) {
+		cpu_freq = per_cpu(cpu_last_req_freq, j);
+
+		if ((cluster == per_cpu(physical_cluster, j)) &&
+				(max_freq < cpu_freq))
+			max_freq = cpu_freq;
+	}
 
-static unsigned int bL_cpufreq_get(unsigned int cpu)
+	pr_debug("%s: cluster: %d, max freq: %d\n", __func__, cluster,
+			max_freq);
+
+	return max_freq;
+}
+
+static unsigned int clk_get_cpu_rate(unsigned int cpu)
 {
-	u32 cur_cluster = cpu_to_cluster(cpu);
+	u32 cur_cluster = per_cpu(physical_cluster, cpu);
+	u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
+
+	/* For switcher we use virtual A15 clock rates */
+	if (is_bL_switching_enabled())
+		rate = VIRT_FREQ(cur_cluster, rate);
+
+	pr_debug("%s: cpu: %d, cluster: %d, freq: %u\n", __func__, cpu,
+			cur_cluster, rate);
 
-	return clk_get_rate(clk[cur_cluster]) / 1000;
+	return rate;
+}
+
+static unsigned int bL_cpufreq_get_rate(unsigned int cpu)
+{
+	if (is_bL_switching_enabled()) {
+		pr_debug("%s: freq: %d\n", __func__, per_cpu(cpu_last_req_freq,
+					cpu));
+
+		return per_cpu(cpu_last_req_freq, cpu);
+	} else {
+		return clk_get_cpu_rate(cpu);
+	}
+}
+
+static unsigned int
+bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
+{
+	u32 new_rate, prev_rate;
+	int ret;
+	bool bLs = is_bL_switching_enabled();
+
+	mutex_lock(&cluster_lock[new_cluster]);
+
+	if (bLs) {
+		prev_rate = per_cpu(cpu_last_req_freq, cpu);
+		per_cpu(cpu_last_req_freq, cpu) = rate;
+		per_cpu(physical_cluster, cpu) = new_cluster;
+
+		new_rate = find_cluster_maxfreq(new_cluster);
+		new_rate = ACTUAL_FREQ(new_cluster, new_rate);
+	} else {
+		new_rate = rate;
+	}
+
+	pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d, freq: %d\n",
+			__func__, cpu, old_cluster, new_cluster, new_rate);
+
+	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+	if (WARN_ON(ret)) {
+		pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret,
+				new_cluster);
+		if (bLs) {
+			per_cpu(cpu_last_req_freq, cpu) = prev_rate;
+			per_cpu(physical_cluster, cpu) = old_cluster;
+		}
+
+		mutex_unlock(&cluster_lock[new_cluster]);
+
+		return ret;
+	}
+
+	mutex_unlock(&cluster_lock[new_cluster]);
+
+	/* Recalc freq for old cluster when switching clusters */
+	if (old_cluster != new_cluster) {
+		pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d\n",
+				__func__, cpu, old_cluster, new_cluster);
+
+		/* Switch cluster */
+		bL_switch_request(cpu, new_cluster);
+
+		mutex_lock(&cluster_lock[old_cluster]);
+
+		/* Set freq of old cluster if there are cpus left on it */
+		new_rate = find_cluster_maxfreq(old_cluster);
+		new_rate = ACTUAL_FREQ(old_cluster, new_rate);
+
+		if (new_rate) {
+			pr_debug("%s: Updating rate of old cluster: %d, to freq: %d\n",
+					__func__, old_cluster, new_rate);
+
+			if (clk_set_rate(clk[old_cluster], new_rate * 1000))
+				pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
+						__func__, ret, old_cluster);
+		}
+		mutex_unlock(&cluster_lock[old_cluster]);
+	}
+
+	return 0;
 }
 
 /* Validate policy frequency range */
@@ -60,12 +181,14 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 		unsigned int target_freq, unsigned int relation)
 {
 	struct cpufreq_freqs freqs;
-	u32 cpu = policy->cpu, freq_tab_idx, cur_cluster;
+	u32 cpu = policy->cpu, freq_tab_idx, cur_cluster, new_cluster,
+	    actual_cluster;
 	int ret = 0;
 
-	cur_cluster = cpu_to_cluster(policy->cpu);
+	cur_cluster = cpu_to_cluster(cpu);
+	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
 
-	freqs.old = bL_cpufreq_get(policy->cpu);
+	freqs.old = bL_cpufreq_get_rate(cpu);
 
 	/* Determine valid target frequency using freq_table */
 	cpufreq_frequency_table_target(policy, freq_table[cur_cluster],
@@ -79,13 +202,21 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 	if (freqs.old == freqs.new)
 		return 0;
 
+	if (is_bL_switching_enabled()) {
+		if ((actual_cluster == A15_CLUSTER) &&
+				(freqs.new < clk_big_min)) {
+			new_cluster = A7_CLUSTER;
+		} else if ((actual_cluster == A7_CLUSTER) &&
+				(freqs.new > clk_little_max)) {
+			new_cluster = A15_CLUSTER;
+		}
+	}
+
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	ret = clk_set_rate(clk[cur_cluster], freqs.new * 1000);
-	if (ret) {
-		pr_err("clk_set_rate failed: %d\n", ret);
+	ret = bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs.new);
+	if (ret)
 		return ret;
-	}
 
 	policy->cur = freqs.new;
 
@@ -94,7 +225,73 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 	return ret;
 }
 
-static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
+static inline u32 get_table_count(struct cpufreq_frequency_table *table)
+{
+	int count;
+
+	for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
+		;
+
+	return count;
+}
+
+/* get the minimum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_min(struct cpufreq_frequency_table *table)
+{
+	int i;
+	uint32_t min_freq = ~0;
+	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+		if (table[i].frequency < min_freq)
+			min_freq = table[i].frequency;
+	return min_freq;
+}
+
+/* get the maximum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_max(struct cpufreq_frequency_table *table)
+{
+	int i;
+	uint32_t max_freq = 0;
+	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+		if (table[i].frequency > max_freq)
+			max_freq = table[i].frequency;
+	return max_freq;
+}
+
+static int merge_cluster_tables(void)
+{
+	int i, j, k = 0, count = 1;
+	struct cpufreq_frequency_table *table;
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		count += get_table_count(freq_table[i]);
+
+	table = kzalloc(sizeof(*table) * count, GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	freq_table[MAX_CLUSTERS] = table;
+
+	/* Add in reverse order to get freqs in increasing order */
+	for (i = MAX_CLUSTERS - 1; i >= 0; i--) {
+		for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
+				j++) {
+			table[k].frequency = VIRT_FREQ(i,
+					freq_table[i][j].frequency);
+			pr_debug("%s: index: %d, freq: %d\n", __func__, k,
+					table[k].frequency);
+			k++;
+		}
+	}
+
+	table[k].index = k;
+	table[k].frequency = CPUFREQ_TABLE_END;
+
+	pr_debug("%s: End, table: %p, count: %d\n", __func__, table, k);
+
+	return 0;
+}
+
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
 
@@ -105,10 +302,35 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 	}
 }
 
-static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i;
+
+	if (cluster < MAX_CLUSTERS)
+		return _put_cluster_clk_and_freq_table(cpu_dev);
+
+	if (atomic_dec_return(&cluster_usage[MAX_CLUSTERS]))
+		return;
+
+	for (i = 0; i < MAX_CLUSTERS; i++) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return;
+		}
+
+		_put_cluster_clk_and_freq_table(cdev);
+	}
+
+	/* free virtual table */
+	kfree(freq_table[MAX_CLUSTERS]);
+}
+
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
+	char name[14] = "cpu-cluster.X";
 	int ret;
 
 	if (atomic_inc_return(&cluster_usage[cluster]) != 1)
@@ -149,6 +371,62 @@ atomic_dec:
 	return ret;
 }
 
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i, ret;
+
+	if (cluster < MAX_CLUSTERS)
+		return _get_cluster_clk_and_freq_table(cpu_dev);
+
+	if (atomic_inc_return(&cluster_usage[MAX_CLUSTERS]) != 1)
+		return 0;
+
+	/*
+	 * Get data for all clusters and fill virtual cluster with a merge of
+	 * both
+	 */
+	for (i = 0; i < MAX_CLUSTERS; i++) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return -ENODEV;
+		}
+
+		ret = _get_cluster_clk_and_freq_table(cdev);
+		if (ret)
+			goto put_clusters;
+	}
+
+	ret = merge_cluster_tables();
+	if (ret)
+		goto put_clusters;
+
+	/* Assuming 2 cluster, set clk_big_min and clk_little_max */
+	clk_big_min = get_table_min(freq_table[0]);
+	clk_little_max = VIRT_FREQ(1, get_table_max(freq_table[1]));
+
+	pr_debug("%s: cluster: %d, clk_big_min: %d, clk_little_max: %d\n",
+			__func__, cluster, clk_big_min, clk_little_max);
+
+	return 0;
+
+put_clusters:
+	while (i--) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return -ENODEV;
+		}
+
+		_put_cluster_clk_and_freq_table(cdev);
+	}
+
+	atomic_dec(&cluster_usage[MAX_CLUSTERS]);
+
+	return ret;
+}
+
 /* Per-CPU initialization */
 static int bL_cpufreq_init(struct cpufreq_policy *policy)
 {
@@ -177,37 +455,33 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 
 	cpufreq_frequency_table_get_attr(freq_table[cur_cluster], policy->cpu);
 
+	if (cur_cluster < MAX_CLUSTERS) {
+		int cpu;
+
+		cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+
+		for_each_cpu(cpu, policy->cpus)
+			per_cpu(physical_cluster, cpu) = cur_cluster;
+	} else {
+		/* Assumption: during init, we are always running on A15 */
+		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
+	}
+
 	if (arm_bL_ops->get_transition_latency)
 		policy->cpuinfo.transition_latency =
 			arm_bL_ops->get_transition_latency(cpu_dev);
 	else
 		policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 
-	policy->cur = bL_cpufreq_get(policy->cpu);
+	policy->cur = clk_get_cpu_rate(policy->cpu);
 
-	cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+	if (is_bL_switching_enabled())
+		per_cpu(cpu_last_req_freq, policy->cpu) = policy->cur;
 
 	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
 	return 0;
 }
 
-static int bL_cpufreq_exit(struct cpufreq_policy *policy)
-{
-	struct device *cpu_dev;
-
-	cpu_dev = get_cpu_device(policy->cpu);
-	if (!cpu_dev) {
-		pr_err("%s: failed to get cpu%d device\n", __func__,
-				policy->cpu);
-		return -ENODEV;
-	}
-
-	put_cluster_clk_and_freq_table(cpu_dev);
-	dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
-
-	return 0;
-}
-
 /* Export freq_table to sysfs */
 static struct freq_attr *bL_cpufreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
@@ -219,16 +493,47 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.flags			= CPUFREQ_STICKY,
 	.verify			= bL_cpufreq_verify_policy,
 	.target			= bL_cpufreq_set_target,
-	.get			= bL_cpufreq_get,
+	.get			= bL_cpufreq_get_rate,
 	.init			= bL_cpufreq_init,
-	.exit			= bL_cpufreq_exit,
 	.have_governor_per_policy = true,
 	.attr			= bL_cpufreq_attr,
 };
 
+static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	pr_debug("%s: action: %ld\n", __func__, action);
+
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_unregister_driver(&bL_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+		set_switching_enabled(true);
+		cpufreq_register_driver(&bL_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_DISABLE:
+		set_switching_enabled(false);
+		cpufreq_register_driver(&bL_cpufreq_driver);
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block bL_switcher_notifier = {
+	.notifier_call = bL_cpufreq_switcher_notifier,
+};
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
-	int ret;
+	int ret, i;
 
 	if (arm_bL_ops) {
 		pr_debug("%s: Already registered: %s, exiting\n", __func__,
@@ -243,16 +548,29 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
+	ret = bL_switcher_get_enabled();
+	set_switching_enabled(ret);
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		mutex_init(&cluster_lock[i]);
+
 	ret = cpufreq_register_driver(&bL_cpufreq_driver);
 	if (ret) {
 		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		pr_info("%s: Registered platform driver: %s\n", __func__,
-				ops->name);
+		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		if (ret) {
+			cpufreq_unregister_driver(&bL_cpufreq_driver);
+			arm_bL_ops = NULL;
+		} else {
+			pr_info("%s: Registered platform driver: %s\n",
+					__func__, ops->name);
+		}
 	}
 
+	bL_switcher_put_enabled();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(bL_cpufreq_register);
@@ -265,9 +583,31 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 		return;
 	}
 
+	bL_switcher_get_enabled();
+	bL_switcher_unregister_notifier(&bL_switcher_notifier);
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
+	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
 			arm_bL_ops->name);
+
+	/* For saving table get/put on every cpu in/out */
+	if (is_bL_switching_enabled()) {
+		put_cluster_clk_and_freq_table(get_cpu_device(0));
+	} else {
+		int i;
+
+		for (i = 0; i < MAX_CLUSTERS; i++) {
+			struct device *cdev = get_cpu_device(i);
+			if (!cdev) {
+				pr_err("%s: failed to get cpu%d device\n",
+						__func__, i);
+				return;
+			}
+
+			put_cluster_clk_and_freq_table(cdev);
+		}
+	}
+
 	arm_bL_ops = NULL;
 }
 EXPORT_SYMBOL_GPL(bL_cpufreq_unregister);
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index 79b2ce17884d..4f5a03d3aef6 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -23,6 +23,20 @@
 #include <linux/device.h>
 #include <linux/types.h>
 
+/* Currently we support only two clusters */
+#define A15_CLUSTER	0
+#define A7_CLUSTER	1
+#define MAX_CLUSTERS	2
+
+#ifdef CONFIG_BL_SWITCHER
+extern bool bL_switching_enabled;
+#define is_bL_switching_enabled()		bL_switching_enabled
+#define set_switching_enabled(x) 		(bL_switching_enabled = (x))
+#else
+#define is_bL_switching_enabled()		false
+#define set_switching_enabled(x) 		do { } while (0)
+#endif
+
 struct cpufreq_arm_bL_ops {
 	char name[CPUFREQ_NAME_LEN];
 	int (*get_transition_latency)(struct device *cpu_dev);
@@ -36,7 +50,8 @@ struct cpufreq_arm_bL_ops {
 
 static inline int cpu_to_cluster(int cpu)
 {
-	return topology_physical_package_id(cpu);
+	return is_bL_switching_enabled() ? MAX_CLUSTERS:
+		topology_physical_package_id(cpu);
 }
 
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 648554742a99..df9a2427c233 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -31,6 +31,8 @@
 #include <linux/completion.h>
 #include <linux/mutex.h>
 #include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/tick.h>
 
 #include <trace/events/power.h>
 
@@ -46,6 +48,15 @@ static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 #endif
 static DEFINE_RWLOCK(cpufreq_driver_lock);
+static DEFINE_MUTEX(cpufreq_governor_lock);
+
+/* Flag to suspend/resume CPUFreq governors */
+static bool cpufreq_suspended;
+
+static inline bool has_target(void)
+{
+	return cpufreq_driver->target;
+}
 
 /*
  * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
@@ -1274,82 +1285,71 @@ static struct subsys_interface cpufreq_interface = {
 
 
 /**
- * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
+ * cpufreq_suspend() - Suspend CPUFreq governors
  *
- * This function is only executed for the boot processor.  The other CPUs
- * have been put offline by means of CPU hotplug.
+ * Called during system wide Suspend/Hibernate cycles for suspending governors
+ * as some platforms can't change frequency after this point in suspend cycle.
+ * Because some of the devices (like: i2c, regulators, etc) they use for
+ * changing frequency are suspended quickly after this point.
  */
-static int cpufreq_bp_suspend(void)
+void cpufreq_suspend(void)
 {
-	int ret = 0;
+	struct cpufreq_policy *policy;
 
-	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	if (!cpufreq_driver)
+		return;
 
-	pr_debug("suspending cpu %u\n", cpu);
+	if (!has_target())
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
-		return 0;
+	pr_debug("%s: Suspending Governors\n", __func__);
 
-	if (cpufreq_driver->suspend) {
-		ret = cpufreq_driver->suspend(cpu_policy);
-		if (ret)
-			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
-					"step on CPU %u\n", cpu_policy->cpu);
-	}
+	policy = cpufreq_cpu_get(0);
 
-	cpufreq_cpu_put(cpu_policy);
-	return ret;
+	if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+		pr_err("%s: Failed to stop governor for policy: %p\n",
+			__func__, policy);
+	else if (cpufreq_driver->suspend
+	    && cpufreq_driver->suspend(policy))
+		pr_err("%s: Failed to suspend driver: %p\n", __func__,
+			policy);
+
+	cpufreq_suspended = true;
 }
 
 /**
- * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU.
+ * cpufreq_resume() - Resume CPUFreq governors
  *
- *	1.) resume CPUfreq hardware support (cpufreq_driver->resume())
- *	2.) schedule call cpufreq_update_policy() ASAP as interrupts are
- *	    restored. It will verify that the current freq is in sync with
- *	    what we believe it to be. This is a bit later than when it
- *	    should be, but nonethteless it's better than calling
- *	    cpufreq_driver->get() here which might re-enable interrupts...
- *
- * This function is only executed for the boot CPU.  The other CPUs have not
- * been turned on yet.
+ * Called during system wide Suspend/Hibernate cycle for resuming governors that
+ * are suspended with cpufreq_suspend().
  */
-static void cpufreq_bp_resume(void)
+void cpufreq_resume(void)
 {
-	int ret = 0;
-
-	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	struct cpufreq_policy *policy;
 
-	pr_debug("resuming cpu %u\n", cpu);
+	if (!cpufreq_driver)
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
+	if (!has_target())
 		return;
 
-	if (cpufreq_driver->resume) {
-		ret = cpufreq_driver->resume(cpu_policy);
-		if (ret) {
-			printk(KERN_ERR "cpufreq: resume failed in ->resume "
-					"step on CPU %u\n", cpu_policy->cpu);
-			goto fail;
-		}
-	}
+	pr_debug("%s: Resuming Governors\n", __func__);
 
-	schedule_work(&cpu_policy->update);
+	cpufreq_suspended = false;
 
-fail:
-	cpufreq_cpu_put(cpu_policy);
-}
+	policy = cpufreq_cpu_get(0);
 
-static struct syscore_ops cpufreq_syscore_ops = {
-	.suspend	= cpufreq_bp_suspend,
-	.resume		= cpufreq_bp_resume,
-};
+	if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
+	    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
+		pr_err("%s: Failed to start governor for policy: %p\n",
+			__func__, policy);
+	else if (cpufreq_driver->resume
+	    && cpufreq_driver->resume(policy))
+		pr_err("%s: Failed to resume driver: %p\n", __func__,
+			policy);
+
+	schedule_work(&policy->update);
+}
 
 /**
  *	cpufreq_get_current_driver - return current driver's name
@@ -1543,6 +1543,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	struct cpufreq_governor *gov = NULL;
 #endif
 
+	/* Don't start any governor operations if we are entering suspend */
+	if (cpufreq_suspended)
+		return 0;
+
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {
@@ -1563,6 +1567,21 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 
 	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
 						policy->cpu, event);
+
+	mutex_lock(&cpufreq_governor_lock);
+	if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) ||
+	    (policy->governor_enabled && (event == CPUFREQ_GOV_START))) {
+		mutex_unlock(&cpufreq_governor_lock);
+		return -EBUSY;
+	}
+
+	if (event == CPUFREQ_GOV_STOP)
+		policy->governor_enabled = false;
+	else if (event == CPUFREQ_GOV_START)
+		policy->governor_enabled = true;
+
+	mutex_unlock(&cpufreq_governor_lock);
+
 	ret = policy->governor->governor(policy, event);
 
 	if (!ret) {
@@ -1570,6 +1589,14 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 			policy->governor->initialized++;
 		else if (event == CPUFREQ_GOV_POLICY_EXIT)
 			policy->governor->initialized--;
+	} else {
+		/* Restore original values */
+		mutex_lock(&cpufreq_governor_lock);
+		if (event == CPUFREQ_GOV_STOP)
+			policy->governor_enabled = true;
+		else if (event == CPUFREQ_GOV_START)
+			policy->governor_enabled = false;
+		mutex_unlock(&cpufreq_governor_lock);
 	}
 
 	/* we keep one module reference alive for
@@ -1977,7 +2004,6 @@ static int __init cpufreq_core_init(void)
 
 	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
 	BUG_ON(!cpufreq_global_kobject);
-	register_syscore_ops(&cpufreq_syscore_ops);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index a86ff72141f3..27b0e2a295ea 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -97,7 +97,7 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 	policy = cdbs->cur_policy;
 
-	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_common_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;
@@ -148,14 +148,6 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 		load = 100 * (wall_time - idle_time) / wall_time;
 
-		if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-			int freq_avg = __cpufreq_driver_getavg(policy, j);
-			if (freq_avg <= 0)
-				freq_avg = policy->cur;
-
-			load *= freq_avg;
-		}
-
 		if (load > max_load)
 			max_load = load;
 	}
@@ -177,6 +169,9 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 {
 	int i;
 
+	if (!policy->governor_enabled)
+		return;
+
 	if (!all_cpus) {
 		__gov_queue_work(smp_processor_id(), dbs_data, delay);
 	} else {
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 0d9e6befe1d5..4a9058aeb57e 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -169,7 +169,6 @@ struct od_dbs_tuners {
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
-	unsigned int adj_up_threshold;
 	unsigned int powersave_bias;
 	unsigned int io_is_busy;
 };
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index c087347d6688..25438bbf96bb 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -29,11 +29,9 @@
 #include "cpufreq_governor.h"
 
 /* On-demand governor macros */
-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
-#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
@@ -161,14 +159,10 @@ static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
 
 /*
  * Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency. Every sampling_rate, we look
- * for the lowest frequency which can sustain the load while keeping idle time
- * over 30%. If such a frequency exist, we try to decrease to this frequency.
- *
- * Any frequency increase takes it to the maximum frequency. Frequency reduction
- * happens at minimum steps of 5% (default) of current frequency
+ * (default), then we try to increase frequency. Else, we adjust the frequency
+ * proportional to load.
  */
-static void od_check_cpu(int cpu, unsigned int load_freq)
+static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
@@ -178,29 +172,17 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load_freq > od_tuners->up_threshold * policy->cur) {
+	if (load > od_tuners->up_threshold) {
 		/* If switching to max speed, apply sampling_down_factor */
 		if (policy->cur < policy->max)
 			dbs_info->rate_mult =
 				od_tuners->sampling_down_factor;
 		dbs_freq_increase(policy, policy->max);
 		return;
-	}
-
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that can
-	 * support the current CPU usage without triggering the up policy. To be
-	 * safe, we focus 10 points under the threshold.
-	 */
-	if (load_freq < od_tuners->adj_up_threshold
-			* policy->cur) {
+	} else {
+		/* Calculate the next frequency proportional to load */
 		unsigned int freq_next;
-		freq_next = load_freq / od_tuners->adj_up_threshold;
+		freq_next = load * policy->cpuinfo.max_freq / 100;
 
 		/* No longer fully busy, reset rate_mult */
 		dbs_info->rate_mult = 1;
@@ -374,9 +356,6 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	/* Calculate the new adj_up_threshold */
-	od_tuners->adj_up_threshold += input;
-	od_tuners->adj_up_threshold -= od_tuners->up_threshold;
 
 	od_tuners->up_threshold = input;
 	return count;
@@ -525,8 +504,6 @@ static int od_init(struct dbs_data *dbs_data)
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
 		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
-			MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -535,8 +512,6 @@ static int od_init(struct dbs_data *dbs_data)
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
-			DEF_FREQUENCY_DOWN_DIFFERENTIAL;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index bfd6273fd873..9823037f194b 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -21,6 +21,9 @@
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
 #include <asm/cputime.h>
+#ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
+#endif
 
 static spinlock_t cpufreq_stats_lock;
 
@@ -81,7 +84,7 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	for (i = 0; i < stat->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
 			(unsigned long long)
-			cputime64_to_clock_t(stat->time_in_state[i]));
+			jiffies_64_to_clock_t(stat->time_in_state[i]));
 	}
 	return len;
 }
@@ -378,7 +381,7 @@ static struct notifier_block notifier_trans_block = {
 	.notifier_call = cpufreq_stat_notifier_trans
 };
 
-static int __init cpufreq_stats_init(void)
+static int cpufreq_stats_setup(void)
 {
 	int ret;
 	unsigned int cpu;
@@ -406,7 +409,8 @@ static int __init cpufreq_stats_init(void)
 
 	return 0;
 }
-static void __exit cpufreq_stats_exit(void)
+
+static void cpufreq_stats_cleanup(void)
 {
 	unsigned int cpu;
 
@@ -421,6 +425,54 @@ static void __exit cpufreq_stats_exit(void)
 	}
 }
 
+#ifdef CONFIG_BL_SWITCHER
+static int cpufreq_stats_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_stats_cleanup();
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+	case BL_NOTIFY_POST_DISABLE:
+		cpufreq_stats_setup();
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block switcher_notifier = {
+	.notifier_call = cpufreq_stats_switcher_notifier,
+};
+#endif
+
+static int __init cpufreq_stats_init(void)
+{
+	int ret;
+	spin_lock_init(&cpufreq_stats_lock);
+
+	ret = cpufreq_stats_setup();
+#ifdef CONFIG_BL_SWITCHER
+	if (!ret)
+		bL_switcher_register_notifier(&switcher_notifier);
+#endif
+	return ret;
+}
+
+static void __exit cpufreq_stats_exit(void)
+{
+#ifdef CONFIG_BL_SWITCHER
+	bL_switcher_unregister_notifier(&switcher_notifier);
+#endif
+	cpufreq_stats_cleanup();
+}
+
 MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_stats' - A driver to export cpufreq stats "
 				"through sysfs filesystem");
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index b61b5a3fad64..9216c2020ec1 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -19,7 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 #include <linux/platform_device.h>
 
 #define HB_CPUFREQ_CHANGE_NOTE	0x80000001
@@ -66,7 +66,8 @@ static int hb_cpufreq_driver_init(void)
 	struct device_node *np;
 	int ret;
 
-	if (!of_machine_is_compatible("calxeda,highbank"))
+	if ((!of_machine_is_compatible("calxeda,highbank")) &&
+		(!of_machine_is_compatible("calxeda,ecx-2000")))
 		return -ENODEV;
 
 	for_each_child_of_node(of_find_node_by_path("/cpus"), np)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6d6a0b48eb75..decf84e71943 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -48,7 +48,7 @@ static inline int32_t div_fp(int32_t x, int32_t y)
 }
 
 struct sample {
-	int core_pct_busy;
+	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
 	int freq;
@@ -68,7 +68,7 @@ struct _pid {
 	int32_t i_gain;
 	int32_t d_gain;
 	int deadband;
-	int last_err;
+	int32_t last_err;
 };
 
 struct cpudata {
@@ -153,16 +153,15 @@ static inline void pid_d_gain_set(struct _pid *pid, int percent)
 	pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
 }
 
-static signed int pid_calc(struct _pid *pid, int busy)
+static signed int pid_calc(struct _pid *pid, int32_t busy)
 {
-	signed int err, result;
+	signed int result;
 	int32_t pterm, dterm, fp_error;
 	int32_t integral_limit;
 
-	err = pid->setpoint - busy;
-	fp_error = int_tofp(err);
+	fp_error = int_tofp(pid->setpoint) - busy;
 
-	if (abs(err) <= pid->deadband)
+	if (abs(fp_error) <= int_tofp(pid->deadband))
 		return 0;
 
 	pterm = mul_fp(pid->p_gain, fp_error);
@@ -176,8 +175,8 @@ static signed int pid_calc(struct _pid *pid, int busy)
 	if (pid->integral < -integral_limit)
 		pid->integral = -integral_limit;
 
-	dterm = mul_fp(pid->d_gain, (err - pid->last_err));
-	pid->last_err = err;
+	dterm = mul_fp(pid->d_gain, fp_error - pid->last_err);
+	pid->last_err = fp_error;
 
 	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
 
@@ -367,12 +366,13 @@ static int intel_pstate_turbo_pstate(void)
 static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 {
 	int max_perf = cpu->pstate.turbo_pstate;
+	int max_perf_adj;
 	int min_perf;
 	if (limits.no_turbo)
 		max_perf = cpu->pstate.max_pstate;
 
-	max_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
-	*max = clamp_t(int, max_perf,
+	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
+	*max = clamp_t(int, max_perf_adj,
 			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
 	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
@@ -394,7 +394,10 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	trace_cpu_frequency(pstate * 100000, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
-	wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
+	if (limits.no_turbo)
+		wrmsrl(MSR_IA32_PERF_CTL, BIT(32) | (pstate << 8));
+	else
+		wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
 
 }
 
@@ -432,8 +435,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
 	u64 core_pct;
-	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
-	sample->freq = cpu->pstate.max_pstate * core_pct * 1000;
+	core_pct = div64_u64(int_tofp(sample->aperf * 100),
+			     sample->mperf);
+	sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
 
 	sample->core_pct_busy = core_pct;
 }
@@ -465,22 +469,19 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 	mod_timer_pinned(&cpu->timer, jiffies + delay);
 }
 
-static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
+static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
-	int32_t busy_scaled;
 	int32_t core_busy, max_pstate, current_pstate;
 
-	core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy);
+	core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
 	max_pstate = int_tofp(cpu->pstate.max_pstate);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
-	busy_scaled = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
-
-	return fp_toint(busy_scaled);
+	return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 {
-	int busy_scaled;
+	int32_t busy_scaled;
 	struct _pid *pid;
 	signed int ctl = 0;
 	int steps;
@@ -516,12 +517,18 @@ static void intel_pstate_timer_func(unsigned long __data)
 }
 
 #define ICPU(model, policy) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
+			(unsigned long)&policy }
 
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, default_policy),
 	ICPU(0x2d, default_policy),
 	ICPU(0x3a, default_policy),
+	ICPU(0x3c, default_policy),
+	ICPU(0x3e, default_policy),
+	ICPU(0x3f, default_policy),
+	ICPU(0x45, default_policy),
+	ICPU(0x46, default_policy),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -543,6 +550,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	intel_pstate_get_cpu_pstates(cpu);
+	if (!cpu->pstate.current_pstate) {
+		all_cpu_data[cpunum] = NULL;
+		kfree(cpu);
+		return -ENODATA;
+	}
 
 	cpu->cpu = cpunum;
 	cpu->pstate_policy =
@@ -587,6 +599,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits.min_perf_pct = 100;
 		limits.min_perf = int_tofp(1);
+		limits.max_policy_pct = 100;
 		limits.max_perf_pct = 100;
 		limits.max_perf = int_tofp(1);
 		limits.no_turbo = 0;
@@ -629,8 +642,8 @@ static int __cpuinit intel_pstate_cpu_exit(struct cpufreq_policy *policy)
 
 static int __cpuinit intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
-	int rc, min_pstate, max_pstate;
 	struct cpudata *cpu;
+	int rc;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -644,9 +657,8 @@ static int __cpuinit intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
-	policy->min = min_pstate * 100000;
-	policy->max = max_pstate * 100000;
+	policy->min = cpu->pstate.min_pstate * 100000;
+	policy->max = cpu->pstate.turbo_pstate * 100000;
 
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index ea0222a45b7b..b07ca0d3f56a 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -26,41 +26,108 @@
 static unsigned int                     busfreq;   /* FSB, in 10 kHz */
 static unsigned int                     max_multiplier;
 
+static unsigned int			param_busfreq = 0;
+static unsigned int			param_max_multiplier = 0;
+
+module_param_named(max_multiplier, param_max_multiplier, uint, S_IRUGO);
+MODULE_PARM_DESC(max_multiplier, "Maximum multiplier (allowed values: 20 30 35 40 45 50 55 60)");
+
+module_param_named(bus_frequency, param_busfreq, uint, S_IRUGO);
+MODULE_PARM_DESC(bus_frequency, "Bus frequency in kHz");
 
 /* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
 static struct cpufreq_frequency_table clock_ratio[] = {
-	{45,  /* 000 -> 4.5x */ 0},
+	{60,  /* 110 -> 6.0x */ 0},
+	{55,  /* 011 -> 5.5x */ 0},
 	{50,  /* 001 -> 5.0x */ 0},
+	{45,  /* 000 -> 4.5x */ 0},
 	{40,  /* 010 -> 4.0x */ 0},
-	{55,  /* 011 -> 5.5x */ 0},
-	{20,  /* 100 -> 2.0x */ 0},
-	{30,  /* 101 -> 3.0x */ 0},
-	{60,  /* 110 -> 6.0x */ 0},
 	{35,  /* 111 -> 3.5x */ 0},
+	{30,  /* 101 -> 3.0x */ 0},
+	{20,  /* 100 -> 2.0x */ 0},
 	{0, CPUFREQ_TABLE_END}
 };
 
+static const u8 index_to_register[8] = { 6, 3, 1, 0, 2, 7, 5, 4 };
+static const u8 register_to_index[8] = { 3, 2, 4, 1, 7, 6, 0, 5 };
+
+static const struct {
+	unsigned freq;
+	unsigned mult;
+} usual_frequency_table[] = {
+	{ 400000, 40 },	// 100   * 4
+	{ 450000, 45 }, // 100   * 4.5
+	{ 475000, 50 }, //  95   * 5
+	{ 500000, 50 }, // 100   * 5
+	{ 506250, 45 }, // 112.5 * 4.5
+	{ 533500, 55 }, //  97   * 5.5
+	{ 550000, 55 }, // 100   * 5.5
+	{ 562500, 50 }, // 112.5 * 5
+	{ 570000, 60 }, //  95   * 6
+	{ 600000, 60 }, // 100   * 6
+	{ 618750, 55 }, // 112.5 * 5.5
+	{ 660000, 55 }, // 120   * 5.5
+	{ 675000, 60 }, // 112.5 * 6
+	{ 720000, 60 }, // 120   * 6
+};
+
+#define FREQ_RANGE		3000
 
 /**
  * powernow_k6_get_cpu_multiplier - returns the current FSB multiplier
  *
- *   Returns the current setting of the frequency multiplier. Core clock
+ * Returns the current setting of the frequency multiplier. Core clock
  * speed is frequency of the Front-Side Bus multiplied with this value.
  */
 static int powernow_k6_get_cpu_multiplier(void)
 {
-	u64 invalue = 0;
+	unsigned long invalue = 0;
 	u32 msrval;
 
+	local_irq_disable();
+
 	msrval = POWERNOW_IOPORT + 0x1;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
 	invalue = inl(POWERNOW_IOPORT + 0x8);
 	msrval = POWERNOW_IOPORT + 0x0;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
 
-	return clock_ratio[(invalue >> 5)&7].index;
+	local_irq_enable();
+
+	return clock_ratio[register_to_index[(invalue >> 5)&7]].index;
 }
 
+static void powernow_k6_set_cpu_multiplier(unsigned int best_i)
+{
+	unsigned long outvalue, invalue;
+	unsigned long msrval;
+	unsigned long cr0;
+
+	/* we now need to transform best_i to the BVC format, see AMD#23446 */
+
+	/*
+	 * The processor doesn't respond to inquiry cycles while changing the
+	 * frequency, so we must disable cache.
+	 */
+	local_irq_disable();
+	cr0 = read_cr0();
+	write_cr0(cr0 | X86_CR0_CD);
+	wbinvd();
+
+	outvalue = (1<<12) | (1<<10) | (1<<9) | (index_to_register[best_i]<<5);
+
+	msrval = POWERNOW_IOPORT + 0x1;
+	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
+	invalue = inl(POWERNOW_IOPORT + 0x8);
+	invalue = invalue & 0x1f;
+	outvalue = outvalue | invalue;
+	outl(outvalue, (POWERNOW_IOPORT + 0x8));
+	msrval = POWERNOW_IOPORT + 0x0;
+	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+
+	write_cr0(cr0);
+	local_irq_enable();
+}
 
 /**
  * powernow_k6_set_state - set the PowerNow! multiplier
@@ -71,8 +138,6 @@ static int powernow_k6_get_cpu_multiplier(void)
 static void powernow_k6_set_state(struct cpufreq_policy *policy,
 		unsigned int best_i)
 {
-	unsigned long outvalue = 0, invalue = 0;
-	unsigned long msrval;
 	struct cpufreq_freqs freqs;
 
 	if (clock_ratio[best_i].index > max_multiplier) {
@@ -85,18 +150,7 @@ static void powernow_k6_set_state(struct cpufreq_policy *policy,
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	/* we now need to transform best_i to the BVC format, see AMD#23446 */
-
-	outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
-
-	msrval = POWERNOW_IOPORT + 0x1;
-	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
-	invalue = inl(POWERNOW_IOPORT + 0x8);
-	invalue = invalue & 0xf;
-	outvalue = outvalue | invalue;
-	outl(outvalue , (POWERNOW_IOPORT + 0x8));
-	msrval = POWERNOW_IOPORT + 0x0;
-	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+	powernow_k6_set_cpu_multiplier(best_i);
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
@@ -141,18 +195,57 @@ static int powernow_k6_target(struct cpufreq_policy *policy,
 	return 0;
 }
 
-
 static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 {
 	unsigned int i, f;
 	int result;
+	unsigned khz;
 
 	if (policy->cpu != 0)
 		return -ENODEV;
 
-	/* get frequencies */
-	max_multiplier = powernow_k6_get_cpu_multiplier();
-	busfreq = cpu_khz / max_multiplier;
+	max_multiplier = 0;
+	khz = cpu_khz;
+	for (i = 0; i < ARRAY_SIZE(usual_frequency_table); i++) {
+		if (khz >= usual_frequency_table[i].freq - FREQ_RANGE &&
+		    khz <= usual_frequency_table[i].freq + FREQ_RANGE) {
+			khz = usual_frequency_table[i].freq;
+			max_multiplier = usual_frequency_table[i].mult;
+			break;
+		}
+	}
+	if (param_max_multiplier) {
+		for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
+			if (clock_ratio[i].index == param_max_multiplier) {
+				max_multiplier = param_max_multiplier;
+				goto have_max_multiplier;
+			}
+		}
+		printk(KERN_ERR "powernow-k6: invalid max_multiplier parameter, valid parameters 20, 30, 35, 40, 45, 50, 55, 60\n");
+		return -EINVAL;
+	}
+
+	if (!max_multiplier) {
+		printk(KERN_WARNING "powernow-k6: unknown frequency %u, cannot determine current multiplier\n", khz);
+		printk(KERN_WARNING "powernow-k6: use module parameters max_multiplier and bus_frequency\n");
+		return -EOPNOTSUPP;
+	}
+
+have_max_multiplier:
+	param_max_multiplier = max_multiplier;
+
+	if (param_busfreq) {
+		if (param_busfreq >= 50000 && param_busfreq <= 150000) {
+			busfreq = param_busfreq / 10;
+			goto have_busfreq;
+		}
+		printk(KERN_ERR "powernow-k6: invalid bus_frequency parameter, allowed range 50000 - 150000 kHz\n");
+		return -EINVAL;
+	}
+
+	busfreq = khz / max_multiplier;
+have_busfreq:
+	param_busfreq = busfreq * 10;
 
 	/* table init */
 	for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
@@ -164,7 +257,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.transition_latency = 200000;
+	policy->cpuinfo.transition_latency = 500000;
 	policy->cur = busfreq * max_multiplier;
 
 	result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index b828efe4b2f8..9b963ceba5c4 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1100,7 +1100,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data;
 	struct init_on_cpu init_on_cpu;
-	int rc;
+	int rc, cpu;
 
 	smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
 	if (rc)
@@ -1169,7 +1169,9 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
 		 data->currfid, data->currvid);
 
-	per_cpu(powernow_data, pol->cpu) = data;
+	/* Point all the CPUs in this policy to the same data */
+	for_each_cpu(cpu, pol->cpus)
+		per_cpu(powernow_data, cpu) = data;
 
 	return 0;
 
@@ -1184,6 +1186,7 @@ err_out:
 static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+	int cpu;
 
 	if (!data)
 		return -EINVAL;
@@ -1194,7 +1197,8 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
 	kfree(data->powernow_table);
 	kfree(data);
-	per_cpu(powernow_data, pol->cpu) = NULL;
+	for_each_cpu(cpu, pol->cpus)
+		per_cpu(powernow_data, cpu) = NULL;
 
 	return 0;
 }
diff --git a/drivers/cpufreq/vexpress_big_little.c b/drivers/cpufreq/vexpress_big_little.c
new file mode 100644
index 000000000000..1abb883c051b
--- /dev/null
+++ b/drivers/cpufreq/vexpress_big_little.c
@@ -0,0 +1,86 @@
+/*
+ * Vexpress big.LITTLE CPUFreq Interface driver
+ *
+ * It provides necessary ops to arm_big_little cpufreq driver and gets
+ * Frequency information from Device Tree. Freq table in DT must be in KHz.
+ *
+ * Copyright (C) 2013 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/export.h>
+#include <linux/opp.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/vexpress.h>
+#include "arm_big_little.h"
+
+static int vexpress_init_opp_table(struct device *cpu_dev)
+{
+	int i = -1, count, cluster = cpu_to_cluster(cpu_dev->id);
+	u32 *table;
+	int ret;
+
+	count = vexpress_spc_get_freq_table(cluster, &table);
+	if (!table || !count) {
+		pr_err("SPC controller returned invalid freq table");
+		return -EINVAL;
+	}
+
+	while (++i < count) {
+		/* FIXME: Voltage value */
+		ret = opp_add(cpu_dev, table[i] * 1000, 900000);
+		if (ret) {
+			dev_warn(cpu_dev, "%s: Failed to add OPP %d, err: %d\n",
+				 __func__, table[i] * 1000, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int vexpress_get_transition_latency(struct device *cpu_dev)
+{
+	/* 1 ms */
+	return 1000000;
+}
+
+static struct cpufreq_arm_bL_ops vexpress_bL_ops = {
+	.name	= "vexpress-bL",
+	.get_transition_latency = vexpress_get_transition_latency,
+	.init_opp_table = vexpress_init_opp_table,
+};
+
+static int vexpress_bL_init(void)
+{
+	if (!vexpress_spc_check_loaded()) {
+		pr_info("%s: No SPC found\n", __func__);
+		return -ENOENT;
+	}
+
+	return bL_cpufreq_register(&vexpress_bL_ops);
+}
+module_init(vexpress_bL_init);
+
+static void vexpress_bL_exit(void)
+{
+	return bL_cpufreq_unregister(&vexpress_bL_ops);
+}
+module_exit(vexpress_bL_exit);
+
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_DESCRIPTION("ARM Vexpress big LITTLE cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index c4cc27e5c8a5..9625ce7ed5f8 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -31,8 +31,16 @@ config CPU_IDLE_GOV_MENU
 config ARCH_NEEDS_CPU_IDLE_COUPLED
 	def_bool n
 
+config DT_IDLE_STATES
+	bool
+
 if CPU_IDLE
 
+menu "ARM64 CPU Idle Drivers"
+depends on ARM64
+source "drivers/cpuidle/Kconfig.arm64"
+endmenu
+
 config CPU_IDLE_CALXEDA
 	bool "CPU Idle Driver for Calxeda processors"
 	depends on ARCH_HIGHBANK
diff --git a/drivers/cpuidle/Kconfig.arm64 b/drivers/cpuidle/Kconfig.arm64
new file mode 100644
index 000000000000..d0a08ed1b2ee
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.arm64
@@ -0,0 +1,14 @@
+#
+# ARM64 CPU Idle drivers
+#
+
+config ARM64_CPUIDLE
+	bool "Generic ARM64 CPU idle Driver"
+	select ARM64_CPU_SUSPEND
+	select DT_IDLE_STATES
+	help
+	  Select this to enable generic cpuidle driver for ARM64.
+	  It provides a generic idle driver whose idle states are configured
+	  at run-time through DT nodes. The CPUidle suspend backend is
+	  initialized by calling the CPU operations init idle hook
+	  provided by architecture code.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 0d8bd55e776f..0bd32cd03f0a 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -4,6 +4,12 @@
 
 obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
+obj-$(CONFIG_BIG_LITTLE) += arm_big_little.o
+obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 
 obj-$(CONFIG_CPU_IDLE_CALXEDA) += cpuidle-calxeda.o
 obj-$(CONFIG_ARCH_KIRKWOOD) += cpuidle-kirkwood.o
+
+###############################################################################
+# ARM64 drivers
+obj-$(CONFIG_ARM64_CPUIDLE)		+= cpuidle-arm64.o
diff --git a/drivers/cpuidle/arm_big_little.c b/drivers/cpuidle/arm_big_little.c
new file mode 100644
index 000000000000..e5378896a8cb
--- /dev/null
+++ b/drivers/cpuidle/arm_big_little.c
@@ -0,0 +1,183 @@
+/*
+ * big.LITTLE CPU idle driver.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/arm-cci.h>
+#include <linux/bitmap.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/clockchips.h>
+#include <linux/debugfs.h>
+#include <linux/hrtimer.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/tick.h>
+#include <linux/vexpress.h>
+#include <asm/mcpm.h>
+#include <asm/cpuidle.h>
+#include <asm/cputype.h>
+#include <asm/idmap.h>
+#include <asm/proc-fns.h>
+#include <asm/suspend.h>
+#include <linux/of.h>
+
+static int bl_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
+{
+	ktime_t time_start, time_end;
+	s64 diff;
+
+	time_start = ktime_get();
+
+	cpu_do_idle();
+
+	time_end = ktime_get();
+
+	local_irq_enable();
+
+	diff = ktime_to_us(ktime_sub(time_end, time_start));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+
+	dev->last_residency = (int) diff;
+
+	return index;
+}
+
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int idx);
+
+static struct cpuidle_state bl_cpuidle_set[] __initdata = {
+	[0] = {
+		.enter                  = bl_cpuidle_simple_enter,
+		.exit_latency           = 1,
+		.target_residency       = 1,
+		.power_usage		= UINT_MAX,
+		.flags                  = CPUIDLE_FLAG_TIME_VALID,
+		.name                   = "WFI",
+		.desc                   = "ARM WFI",
+	},
+	[1] = {
+		.enter			= bl_enter_powerdown,
+		.exit_latency		= 300,
+		.target_residency	= 1000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "C1",
+		.desc			= "ARM power down",
+	},
+};
+
+struct cpuidle_driver bl_idle_driver = {
+	.name = "bl_idle",
+	.owner = THIS_MODULE,
+	.safe_state_index = 0
+};
+
+static DEFINE_PER_CPU(struct cpuidle_device, bl_idle_dev);
+
+static int notrace bl_powerdown_finisher(unsigned long arg)
+{
+	unsigned int mpidr = read_cpuid_mpidr();
+	unsigned int cluster = (mpidr >> 8) & 0xf;
+	unsigned int cpu = mpidr & 0xf;
+
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	mcpm_cpu_suspend(0);  /* 0 should be replaced with better value here */
+	return 1;
+}
+
+/*
+ * bl_enter_powerdown - Programs CPU to enter the specified state
+ * @dev: cpuidle device
+ * @drv: The target state to be programmed
+ * @idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int idx)
+{
+	struct timespec ts_preidle, ts_postidle, ts_idle;
+	int ret;
+
+	/* Used to keep track of the total time in idle */
+	getnstimeofday(&ts_preidle);
+
+	BUG_ON(!irqs_disabled());
+
+	cpu_pm_enter();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+
+	ret = cpu_suspend((unsigned long) dev, bl_powerdown_finisher);
+	if (ret)
+		BUG();
+
+	mcpm_cpu_powered_up();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	cpu_pm_exit();
+
+	getnstimeofday(&ts_postidle);
+	local_irq_enable();
+	ts_idle = timespec_sub(ts_postidle, ts_preidle);
+
+	dev->last_residency = ts_idle.tv_nsec / NSEC_PER_USEC +
+					ts_idle.tv_sec * USEC_PER_SEC;
+	return idx;
+}
+
+/*
+ * bl_idle_init
+ *
+ * Registers the bl specific cpuidle driver with the cpuidle
+ * framework with the valid set of states.
+ */
+int __init bl_idle_init(void)
+{
+	struct cpuidle_device *dev;
+	int i, cpu_id;
+	struct cpuidle_driver *drv = &bl_idle_driver;
+
+	if (!of_find_compatible_node(NULL, NULL, "arm,generic")) {
+		pr_info("%s: No compatible node found\n", __func__);
+		return -ENODEV;
+	}
+
+	drv->state_count = (sizeof(bl_cpuidle_set) /
+				       sizeof(struct cpuidle_state));
+
+	for (i = 0; i < drv->state_count; i++) {
+		memcpy(&drv->states[i], &bl_cpuidle_set[i],
+				sizeof(struct cpuidle_state));
+	}
+
+	cpuidle_register_driver(drv);
+
+	for_each_cpu(cpu_id, cpu_online_mask) {
+		pr_err("CPUidle for CPU%d registered\n", cpu_id);
+		dev = &per_cpu(bl_idle_dev, cpu_id);
+		dev->cpu = cpu_id;
+
+		dev->state_count = drv->state_count;
+
+		if (cpuidle_register_device(dev)) {
+			printk(KERN_ERR "%s: Cpuidle register device failed\n",
+			       __func__);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+device_initcall(bl_idle_init);
diff --git a/drivers/cpuidle/cpuidle-arm64.c b/drivers/cpuidle/cpuidle-arm64.c
new file mode 100644
index 000000000000..50997ea942fc
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-arm64.c
@@ -0,0 +1,133 @@
+/*
+ * ARM64 generic CPU idle driver.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "CPUidle arm64: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_pm.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include <asm/cpuidle.h>
+#include <asm/suspend.h>
+
+#include "dt_idle_states.h"
+
+/*
+ * arm64_enter_idle_state - Programs CPU to enter the specified state
+ *
+ * dev: cpuidle device
+ * drv: cpuidle driver
+ * idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int arm64_enter_idle_state(struct cpuidle_device *dev,
+				  struct cpuidle_driver *drv, int idx)
+{
+	int ret;
+
+	if (!idx) {
+		cpu_do_idle();
+		return idx;
+	}
+
+	ret = cpu_pm_enter();
+	if (!ret) {
+		/*
+		 * Pass idle state index to cpu_suspend which in turn will
+		 * call the CPU ops suspend protocol with idle index as a
+		 * parameter.
+		 */
+		ret = cpu_suspend(idx);
+
+		cpu_pm_exit();
+	}
+
+	return ret ? -1 : idx;
+}
+
+static struct cpuidle_driver arm64_idle_driver = {
+	.name = "arm64_idle",
+	.owner = THIS_MODULE,
+	/*
+	 * State at index 0 is standby wfi and considered standard
+	 * on all ARM platforms. If in some platforms simple wfi
+	 * can't be used as "state 0", DT bindings must be implemented
+	 * to work around this issue and allow installing a special
+	 * handler for idle state index 0.
+	 */
+	.states[0] = {
+		.enter                  = arm64_enter_idle_state,
+		.exit_latency           = 1,
+		.target_residency       = 1,
+		.power_usage		= UINT_MAX,
+		.flags                  = CPUIDLE_FLAG_TIME_VALID,
+		.name                   = "WFI",
+		.desc                   = "ARM64 WFI",
+	}
+};
+
+static const struct of_device_id arm64_idle_state_match[] __initconst = {
+	{ .compatible = "arm,idle-state",
+	  .data = arm64_enter_idle_state },
+	{ },
+};
+
+/*
+ * arm64_idle_init
+ *
+ * Registers the arm64 specific cpuidle driver with the cpuidle
+ * framework. It relies on core code to parse the idle states
+ * and initialize them using driver data structures accordingly.
+ */
+static int __init arm64_idle_init(void)
+{
+	int cpu, ret;
+	struct cpuidle_driver *drv = &arm64_idle_driver;
+
+	/*
+	 * Initialize idle states data, starting at index 1.
+	 * This driver is DT only, if no DT idle states are detected (ret == 0)
+	 * let the driver initialization fail accordingly since there is no
+	 * reason to initialize the idle driver if only wfi is supported.
+	 */
+	ret = dt_init_idle_driver(drv, arm64_idle_state_match, 1);
+	if (ret <= 0) {
+		if (ret)
+			pr_err("failed to initialize idle states\n");
+		return ret ? : -ENODEV;
+	}
+
+	/*
+	 * Call arch CPU operations in order to initialize
+	 * idle states suspend back-end specific data
+	 */
+	for_each_possible_cpu(cpu) {
+		ret = cpu_init_idle(cpu);
+		if (ret) {
+			pr_err("CPU %d failed to init idle CPU ops\n", cpu);
+			return ret;
+		}
+	}
+
+	ret = cpuidle_register(drv, NULL);
+	if (ret) {
+		pr_err("failed to register cpuidle driver\n");
+		return ret;
+	}
+
+	return 0;
+}
+device_initcall(arm64_idle_init);
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 223379169cb0..0e6e408c0a63 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -37,20 +37,6 @@
 extern void highbank_set_cpu_jump(int cpu, void *jump_addr);
 extern void *scu_base_addr;
 
-static inline unsigned int get_auxcr(void)
-{
-	unsigned int val;
-	asm("mrc p15, 0, %0, c1, c0, 1	@ get AUXCR" : "=r" (val) : : "cc");
-	return val;
-}
-
-static inline void set_auxcr(unsigned int val)
-{
-	asm volatile("mcr p15, 0, %0, c1, c0, 1	@ set AUXCR"
-	  : : "r" (val) : "cc");
-	isb();
-}
-
 static noinline void calxeda_idle_restore(void)
 {
 	set_cr(get_cr() | CR_C);
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 8dfaaae94444..2253271b3fac 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -251,7 +251,8 @@ struct cpuidle_driver *cpuidle_driver_ref(void)
 	spin_lock(&cpuidle_driver_lock);
 
 	drv = cpuidle_get_driver();
-	drv->refcnt++;
+	if (drv)
+		drv->refcnt++;
 
 	spin_unlock(&cpuidle_driver_lock);
 	return drv;
diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c
new file mode 100644
index 000000000000..52f4d11bbf3f
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.c
@@ -0,0 +1,213 @@
+/*
+ * DT idle states parsing code.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "DT idle-states: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include "dt_idle_states.h"
+
+static int init_state_node(struct cpuidle_state *idle_state,
+			   const struct of_device_id *matches,
+			   struct device_node *state_node)
+{
+	int err;
+	const struct of_device_id *match_id;
+
+	match_id = of_match_node(matches, state_node);
+	if (!match_id)
+		return -ENODEV;
+	/*
+	 * CPUidle drivers are expected to initialize the const void *data
+	 * pointer of the passed in struct of_device_id array to the idle
+	 * state enter function.
+	 */
+	idle_state->enter = match_id->data;
+
+	err = of_property_read_u32(state_node, "wakeup-latency-us",
+				   &idle_state->exit_latency);
+	if (err) {
+		u32 entry_latency, exit_latency;
+
+		err = of_property_read_u32(state_node, "entry-latency-us",
+					   &entry_latency);
+		if (err) {
+			pr_debug(" * %s missing entry-latency-us property\n",
+				 state_node->full_name);
+			return -EINVAL;
+		}
+
+		err = of_property_read_u32(state_node, "exit-latency-us",
+					   &exit_latency);
+		if (err) {
+			pr_debug(" * %s missing exit-latency-us property\n",
+				 state_node->full_name);
+			return -EINVAL;
+		}
+		/*
+		 * If wakeup-latency-us is missing, default to entry+exit
+		 * latencies as defined in idle states bindings
+		 */
+		idle_state->exit_latency = entry_latency + exit_latency;
+	}
+
+	err = of_property_read_u32(state_node, "min-residency-us",
+				   &idle_state->target_residency);
+	if (err) {
+		pr_debug(" * %s missing min-residency-us property\n",
+			     state_node->full_name);
+		return -EINVAL;
+	}
+
+	idle_state->flags = CPUIDLE_FLAG_TIME_VALID;
+	if (of_property_read_bool(state_node, "local-timer-stop"))
+		idle_state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+	/*
+	 * TODO:
+	 *	replace with kstrdup and pointer assignment when name
+	 *	and desc become string pointers
+	 */
+	strncpy(idle_state->name, state_node->name, CPUIDLE_NAME_LEN - 1);
+	strncpy(idle_state->desc, state_node->name, CPUIDLE_DESC_LEN - 1);
+	return 0;
+}
+
+/*
+ * Check that the idle state is uniform across all CPUs in the CPUidle driver
+ * cpumask
+ */
+static bool idle_state_valid(struct device_node *state_node, unsigned int idx,
+			     const cpumask_t *cpumask)
+{
+	int cpu;
+	struct device_node *cpu_node, *curr_state_node;
+	bool valid = true;
+
+	/*
+	 * Compare idle state phandles for index idx on all CPUs in the
+	 * CPUidle driver cpumask. Start from next logical cpu following
+	 * cpumask_first(cpumask) since that's the CPU state_node was
+	 * retrieved from. If a mismatch is found bail out straight
+	 * away since we certainly hit a firmware misconfiguration.
+	 */
+	for (cpu = cpumask_next(cpumask_first(cpumask), cpumask);
+	     cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpumask)) {
+		cpu_node = of_cpu_device_node_get(cpu);
+		curr_state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+						   idx);
+		if (state_node != curr_state_node)
+			valid = false;
+
+		of_node_put(curr_state_node);
+		of_node_put(cpu_node);
+		if (!valid)
+			break;
+	}
+
+	return valid;
+}
+
+/**
+ * dt_init_idle_driver() - Parse the DT idle states and initialize the
+ *			   idle driver states array
+ * @drv:	  Pointer to CPU idle driver to be initialized
+ * @matches:	  Array of of_device_id match structures to search in for
+ *		  compatible idle state nodes. The data pointer for each valid
+ *		  struct of_device_id entry in the matches array must point to
+ *		  a function with the following signature, that corresponds to
+ *		  the CPUidle state enter function signature:
+ *
+ *		  int (*)(struct cpuidle_device *dev,
+ *			  struct cpuidle_driver *drv,
+ *			  int index);
+ *
+ * @start_idx:    First idle state index to be initialized
+ *
+ * If DT idle states are detected and are valid the state count and states
+ * array entries in the cpuidle driver are initialized accordingly starting
+ * from index start_idx.
+ *
+ * Return: number of valid DT idle states parsed, <0 on failure
+ */
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+			const struct of_device_id *matches,
+			unsigned int start_idx)
+{
+	struct cpuidle_state *idle_state;
+	struct device_node *state_node, *cpu_node;
+	int i, err = 0;
+	const cpumask_t *cpumask;
+	unsigned int state_idx = start_idx;
+
+	if (state_idx >= CPUIDLE_STATE_MAX)
+		return -EINVAL;
+	/*
+	 * We get the idle states for the first logical cpu in the
+	 * driver mask (or cpu_possible_mask if the driver cpumask is not set)
+	 * and we check through idle_state_valid() if they are uniform
+	 * across CPUs, otherwise we hit a firmware misconfiguration.
+	 */
+	cpumask = drv->cpumask ? : cpu_possible_mask;
+	cpu_node = of_cpu_device_node_get(cpumask_first(cpumask));
+
+	for (i = 0; ; i++) {
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+		if (!state_node)
+			break;
+
+		if (!idle_state_valid(state_node, i, cpumask)) {
+			pr_warn("%s idle state not valid, bailing out\n",
+				state_node->full_name);
+			err = -EINVAL;
+			break;
+		}
+
+		if (state_idx == CPUIDLE_STATE_MAX) {
+			pr_warn("State index reached static CPU idle driver states array size\n");
+			break;
+		}
+
+		idle_state = &drv->states[state_idx++];
+		err = init_state_node(idle_state, matches, state_node);
+		if (err) {
+			pr_err("Parsing idle state node %s failed with err %d\n",
+			       state_node->full_name, err);
+			err = -EINVAL;
+			break;
+		}
+		of_node_put(state_node);
+	}
+
+	of_node_put(state_node);
+	of_node_put(cpu_node);
+	if (err)
+		return err;
+	/*
+	 * Update the driver state count only if some valid DT idle states
+	 * were detected
+	 */
+	if (i)
+		drv->state_count = state_idx;
+
+	/*
+	 * Return the number of present and valid DT idle states, which can
+	 * also be 0 on platforms with missing DT idle states or legacy DT
+	 * configuration predating the DT idle states bindings.
+	 */
+	return i;
+}
+EXPORT_SYMBOL_GPL(dt_init_idle_driver);
diff --git a/drivers/cpuidle/dt_idle_states.h b/drivers/cpuidle/dt_idle_states.h
new file mode 100644
index 000000000000..4818134bc65b
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.h
@@ -0,0 +1,7 @@
+#ifndef __DT_IDLE_STATES
+#define __DT_IDLE_STATES
+
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+			const struct of_device_id *matches,
+			unsigned int start_idx);
+#endif
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 9f25f5296029..0eabd81e1a90 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -16,9 +16,13 @@
 	char *tmp;						\
 								\
 	tmp = kmalloc(sizeof(format) + max_alloc, GFP_ATOMIC);	\
-	sprintf(tmp, format, param);				\
-	strcat(str, tmp);					\
-	kfree(tmp);						\
+	if (likely(tmp)) {					\
+		sprintf(tmp, format, param);			\
+		strcat(str, tmp);				\
+		kfree(tmp);					\
+	} else {						\
+		strcat(str, "kmalloc failure in SPRINTFCAT");	\
+	}							\
 }
 
 static void report_jump_idx(u32 status, char *outstr)
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 32f480622b97..3833bd71cc5d 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx)
 static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 {
 	struct cryp_ctx *ctx;
-	int i;
+	int count;
 	struct cryp_device_data *device_data;
 
 	if (param == NULL) {
@@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	if (cryp_pending_irq_src(device_data,
 				 CRYP_IRQ_SRC_OUTPUT_FIFO)) {
 		if (ctx->outlen / ctx->blocksize > 0) {
-			for (i = 0; i < ctx->blocksize / 4; i++) {
-				*(ctx->outdata) = readl_relaxed(
-						&device_data->base->dout);
-				ctx->outdata += 4;
-				ctx->outlen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			readsl(&device_data->base->dout, ctx->outdata, count);
+			ctx->outdata += count;
+			ctx->outlen -= count;
 
 			if (ctx->outlen == 0) {
 				cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	} else if (cryp_pending_irq_src(device_data,
 					CRYP_IRQ_SRC_INPUT_FIFO)) {
 		if (ctx->datalen / ctx->blocksize > 0) {
-			for (i = 0 ; i < ctx->blocksize / 4; i++) {
-				writel_relaxed(ctx->indata,
-						&device_data->base->din);
-				ctx->indata += 4;
-				ctx->datalen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			writesl(&device_data->base->din, ctx->indata, count);
+
+			ctx->indata += count;
+			ctx->datalen -= count;
 
 			if (ctx->datalen == 0)
 				cryp_disable_irq_src(device_data,
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e9924898043a..0ba5a95199d3 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -333,6 +333,7 @@ config NET_DMA
 	bool "Network: TCP receive copy offload"
 	depends on DMA_ENGINE && NET
 	default (INTEL_IOATDMA || FSL_DMA)
+	depends on BROKEN
 	help
 	  This enables the use of DMA engines in the network stack to
 	  offload receive copy-to-user operations, freeing CPU cycles.
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index f28583370d00..617d17029065 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -414,17 +414,18 @@ static void dma_irq_handle_channel(struct imxdma_channel *imxdmac)
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	int chno = imxdmac->channel;
 	struct imxdma_desc *desc;
+	unsigned long flags;
 
-	spin_lock(&imxdma->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
 	if (list_empty(&imxdmac->ld_active)) {
-		spin_unlock(&imxdma->lock);
+		spin_unlock_irqrestore(&imxdma->lock, flags);
 		goto out;
 	}
 
 	desc = list_first_entry(&imxdmac->ld_active,
 				struct imxdma_desc,
 				node);
-	spin_unlock(&imxdma->lock);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 
 	if (desc->sg) {
 		u32 tmp;
@@ -496,7 +497,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
-	unsigned long flags;
 	int slot = -1;
 	int i;
 
@@ -504,7 +504,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 	switch (d->type) {
 	case IMXDMA_DESC_INTERLEAVED:
 		/* Try to get a free 2D slot */
-		spin_lock_irqsave(&imxdma->lock, flags);
 		for (i = 0; i < IMX_DMA_2D_SLOTS; i++) {
 			if ((imxdma->slots_2d[i].count > 0) &&
 			((imxdma->slots_2d[i].xsr != d->x) ||
@@ -514,10 +513,8 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 			slot = i;
 			break;
 		}
-		if (slot < 0) {
-			spin_unlock_irqrestore(&imxdma->lock, flags);
+		if (slot < 0)
 			return -EBUSY;
-		}
 
 		imxdma->slots_2d[slot].xsr = d->x;
 		imxdma->slots_2d[slot].ysr = d->y;
@@ -526,7 +523,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 
 		imxdmac->slot_2d = slot;
 		imxdmac->enabled_2d = true;
-		spin_unlock_irqrestore(&imxdma->lock, flags);
 
 		if (slot == IMX_DMA_2D_SLOT_A) {
 			d->config_mem &= ~CCR_MSEL_B;
@@ -602,18 +598,17 @@ static void imxdma_tasklet(unsigned long data)
 	struct imxdma_channel *imxdmac = (void *)data;
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct imxdma_desc *desc;
+	unsigned long flags;
 
-	spin_lock(&imxdma->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
 
 	if (list_empty(&imxdmac->ld_active)) {
 		/* Someone might have called terminate all */
-		goto out;
+		spin_unlock_irqrestore(&imxdma->lock, flags);
+		return;
 	}
 	desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc, node);
 
-	if (desc->desc.callback)
-		desc->desc.callback(desc->desc.callback_param);
-
 	/* If we are dealing with a cyclic descriptor, keep it on ld_active
 	 * and dont mark the descriptor as complete.
 	 * Only in non-cyclic cases it would be marked as complete
@@ -640,7 +635,11 @@ static void imxdma_tasklet(unsigned long data)
 				 __func__, imxdmac->channel);
 	}
 out:
-	spin_unlock(&imxdma->lock);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
+
+	if (desc->desc.callback)
+		desc->desc.callback(desc->desc.callback_param);
+
 }
 
 static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -862,7 +861,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	kfree(imxdmac->sg_list);
 
 	imxdmac->sg_list = kcalloc(periods + 1,
-			sizeof(struct scatterlist), GFP_KERNEL);
+			sizeof(struct scatterlist), GFP_ATOMIC);
 	if (!imxdmac->sg_list)
 		return NULL;
 
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 17a2393b3e25..533e1874e1d6 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
 		chan = ioat_chan_by_index(instance, bit);
-		tasklet_schedule(&chan->cleanup_task);
+		if (test_bit(IOAT_RUN, &chan->state))
+			tasklet_schedule(&chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@ static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
 {
 	struct ioat_chan_common *chan = data;
 
-	tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &chan->state))
+		tasklet_schedule(&chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
@@ -116,7 +118,6 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c
 	chan->timer.function = device->timer_fn;
 	chan->timer.data = data;
 	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
-	tasklet_disable(&chan->cleanup_task);
 }
 
 /**
@@ -354,13 +355,49 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
 	writel(((u64) chan->completion_dma) >> 32,
 	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	tasklet_enable(&chan->cleanup_task);
+	set_bit(IOAT_RUN, &chan->state);
 	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
 	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
 		__func__, ioat->desccount);
 	return ioat->desccount;
 }
 
+void ioat_stop(struct ioat_chan_common *chan)
+{
+	struct ioatdma_device *device = chan->device;
+	struct pci_dev *pdev = device->pdev;
+	int chan_id = chan_num(chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &chan->state);
+
+	/* flush inflight interrupts */
+	switch (device->irq_mode) {
+	case IOAT_MSIX:
+		msix = &device->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	device->cleanup_fn((unsigned long) &chan->common);
+}
+
 /**
  * ioat1_dma_free_chan_resources - release all the descriptors
  * @chan: the channel to be cleaned
@@ -379,9 +416,7 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c)
 	if (ioat->desccount == 0)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	ioat1_cleanup(ioat);
+	ioat_stop(chan);
 
 	/* Delay 100ms after reset to allow internal DMA logic to quiesce
 	 * before removing DMA descriptor resources.
@@ -526,8 +561,11 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 static void ioat1_cleanup_event(unsigned long data)
 {
 	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat1_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 54fb7b9ff9aa..a1d78847e5a5 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -370,6 +370,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
 void ioat_kobject_del(struct ioatdma_device *device);
 int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
 extern const struct sysfs_ops ioat_sysfs_ops;
 extern struct ioat_sysfs_entry ioat_version_attr;
 extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b1d139..1cd761026d84 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
 void ioat2_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat2_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
@@ -553,10 +556,10 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	ioat->issued = 0;
 	ioat->tail = 0;
 	ioat->alloc_order = order;
+	set_bit(IOAT_RUN, &chan->state);
 	spin_unlock_bh(&ioat->prep_lock);
 	spin_unlock_bh(&chan->cleanup_lock);
 
-	tasklet_enable(&chan->cleanup_task);
 	ioat2_start_null_desc(ioat);
 
 	/* check that we got off the ground */
@@ -566,7 +569,6 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
 
 	if (is_ioat_active(status) || is_ioat_idle(status)) {
-		set_bit(IOAT_RUN, &chan->state);
 		return 1 << ioat->alloc_order;
 	} else {
 		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@ void ioat2_free_chan_resources(struct dma_chan *c)
 	if (!ioat->ring)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	device->cleanup_fn((unsigned long) c);
+	ioat_stop(chan);
 	device->reset_hw(chan);
-	clear_bit(IOAT_RUN, &chan->state);
 
 	spin_lock_bh(&chan->cleanup_lock);
 	spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index ca6ea9b3551b..38b94b393c6c 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -87,13 +87,6 @@ static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 };
 static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
 					0, 1, 2, 3, 4, 5, 6 };
 
-/*
- * technically sources 1 and 2 do not require SED, but the op will have
- * at least 9 descriptors so that's irrelevant.
- */
-static const u8 pq16_idx_to_sed[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0,
-				      1, 1, 1, 1, 1, 1, 1 };
-
 static void ioat3_eh(struct ioat2_dma_chan *ioat);
 
 static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx)
@@ -135,12 +128,6 @@ static void pq_set_src(struct ioat_raw_descriptor *descs[2],
 	pq->coef[idx] = coef;
 }
 
-static int sed_get_pq16_pool_idx(int src_cnt)
-{
-
-	return pq16_idx_to_sed[src_cnt];
-}
-
 static bool is_jf_ioat(struct pci_dev *pdev)
 {
 	switch (pdev->device) {
@@ -648,8 +635,11 @@ static void ioat3_cleanup(struct ioat2_dma_chan *ioat)
 static void ioat3_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat3_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
@@ -1182,9 +1172,6 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
 	u8 op;
 	int i, s, idx, num_descs;
 
-	/* this function only handles src_cnt 9 - 16 */
-	BUG_ON(src_cnt < 9);
-
 	/* this function is only called with 9-16 sources */
 	op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
 
@@ -1212,8 +1199,7 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
 
 		descs[0] = (struct ioat_raw_descriptor *) pq;
 
-		desc->sed = ioat3_alloc_sed(device,
-					    sed_get_pq16_pool_idx(src_cnt));
+		desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3);
 		if (!desc->sed) {
 			dev_err(to_dev(chan),
 				"%s: no free sed entries\n", __func__);
@@ -1271,13 +1257,21 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
 	return &desc->txd;
 }
 
+static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
+{
+	if (dmaf_p_disabled_continue(flags))
+		return src_cnt + 1;
+	else if (dmaf_continue(flags))
+		return src_cnt + 3;
+	else
+		return src_cnt;
+}
+
 static struct dma_async_tx_descriptor *
 ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
 	      unsigned int src_cnt, const unsigned char *scf, size_t len,
 	      unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
-
 	/* specify valid address for disabled result */
 	if (flags & DMA_PREP_PQ_DISABLE_P)
 		dst[0] = dst[1];
@@ -1297,7 +1291,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
 		single_source_coef[0] = scf[0];
 		single_source_coef[1] = 0;
 
-		return (src_cnt > 8) && (dma->max_pq > 8) ?
+		return src_cnt_flags(src_cnt, flags) > 8 ?
 			__ioat3_prep_pq16_lock(chan, NULL, dst, single_source,
 					       2, single_source_coef, len,
 					       flags) :
@@ -1305,7 +1299,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
 					     single_source_coef, len, flags);
 
 	} else {
-		return (src_cnt > 8) && (dma->max_pq > 8) ?
+		return src_cnt_flags(src_cnt, flags) > 8 ?
 			__ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
 					       scf, len, flags) :
 			__ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt,
@@ -1318,8 +1312,6 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
 		  unsigned int src_cnt, const unsigned char *scf, size_t len,
 		  enum sum_check_flags *pqres, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
-
 	/* specify valid address for disabled result */
 	if (flags & DMA_PREP_PQ_DISABLE_P)
 		pq[0] = pq[1];
@@ -1331,7 +1323,7 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
 	 */
 	*pqres = 0;
 
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
 				       flags) :
 		__ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
@@ -1342,7 +1334,6 @@ static struct dma_async_tx_descriptor *
 ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
 		 unsigned int src_cnt, size_t len, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
 	unsigned char scf[src_cnt];
 	dma_addr_t pq[2];
 
@@ -1351,7 +1342,7 @@ ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
 	flags |= DMA_PREP_PQ_DISABLE_Q;
 	pq[1] = dst; /* specify valid address for disabled result */
 
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
 				       flags) :
 		__ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
@@ -1363,7 +1354,6 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
 		     unsigned int src_cnt, size_t len,
 		     enum sum_check_flags *result, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
 	unsigned char scf[src_cnt];
 	dma_addr_t pq[2];
 
@@ -1377,8 +1367,7 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
 	flags |= DMA_PREP_PQ_DISABLE_Q;
 	pq[1] = pq[0]; /* specify valid address for disabled result */
 
-
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
 				       scf, len, flags) :
 		__ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 71bf4ec300ea..ca78044df4b5 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1587,6 +1587,7 @@ static void dma_tasklet(unsigned long data)
 	struct d40_chan *d40c = (struct d40_chan *) data;
 	struct d40_desc *d40d;
 	unsigned long flags;
+	bool callback_active;
 	dma_async_tx_callback callback;
 	void *callback_param;
 
@@ -1614,6 +1615,7 @@ static void dma_tasklet(unsigned long data)
 	}
 
 	/* Callback to client */
+	callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
 	callback = d40d->txd.callback;
 	callback_param = d40d->txd.callback_param;
 
@@ -1636,7 +1638,7 @@ static void dma_tasklet(unsigned long data)
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+	if (callback_active && callback)
 		callback(callback_param);
 
 	return;
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index 7f3c57113ba1..1e08ce765f0c 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -562,7 +562,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci)
 
 	if (apiexcp & UECC_EXCP_DETECTED) {
 		cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n");
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     pfn, offset, 0,
 				     csrow, -1, -1,
 				     mci->ctl_name, "");
diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
index 644fec54681f..f1e9d7bd131f 100644
--- a/drivers/edac/e752x_edac.c
+++ b/drivers/edac/e752x_edac.c
@@ -1182,9 +1182,11 @@ static int e752x_get_devs(struct pci_dev *pdev, int dev_idx,
 	pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
 				pvt->dev_info->err_dev, pvt->bridge_ck);
 
-	if (pvt->bridge_ck == NULL)
+	if (pvt->bridge_ck == NULL) {
 		pvt->bridge_ck = pci_scan_single_device(pdev->bus,
 							PCI_DEVFN(0, 1));
+		pci_dev_get(pvt->bridge_ck);
+	}
 
 	if (pvt->bridge_ck == NULL) {
 		e752x_printk(KERN_ERR, "error reporting device not found:"
diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
index 1c4056a50383..2697deae3ab7 100644
--- a/drivers/edac/e7xxx_edac.c
+++ b/drivers/edac/e7xxx_edac.c
@@ -226,7 +226,7 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info)
 static void process_ce_no_info(struct mem_ctl_info *mci)
 {
 	edac_dbg(3, "\n");
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
 			     "e7xxx CE log register overflow", "");
 }
 
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 89e109022d78..a9d98cdd11f4 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -559,7 +559,8 @@ static void edac_mc_workq_function(struct work_struct *work_req)
  *
  *		called with the mem_ctls_mutex held
  */
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
+static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
+				bool init)
 {
 	edac_dbg(0, "\n");
 
@@ -567,7 +568,9 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
 	if (mci->op_state != OP_RUNNING_POLL)
 		return;
 
-	INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+	if (init)
+		INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+
 	mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec));
 }
 
@@ -601,7 +604,7 @@ static void edac_mc_workq_teardown(struct mem_ctl_info *mci)
  *	user space has updated our poll period value, need to
  *	reset our workq delays
  */
-void edac_mc_reset_delay_period(int value)
+void edac_mc_reset_delay_period(unsigned long value)
 {
 	struct mem_ctl_info *mci;
 	struct list_head *item;
@@ -611,7 +614,7 @@ void edac_mc_reset_delay_period(int value)
 	list_for_each(item, &mc_devices) {
 		mci = list_entry(item, struct mem_ctl_info, link);
 
-		edac_mc_workq_setup(mci, (unsigned long) value);
+		edac_mc_workq_setup(mci, value, false);
 	}
 
 	mutex_unlock(&mem_ctls_mutex);
@@ -782,7 +785,7 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
 		/* This instance is NOW RUNNING */
 		mci->op_state = OP_RUNNING_POLL;
 
-		edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
+		edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true);
 	} else {
 		mci->op_state = OP_RUNNING_INTERRUPT;
 	}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index c4d700a577d2..88cd940ece63 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -52,16 +52,20 @@ int edac_mc_get_poll_msec(void)
 
 static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
 {
-	long l;
+	unsigned long l;
 	int ret;
 
 	if (!val)
 		return -EINVAL;
 
-	ret = strict_strtol(val, 0, &l);
-	if (ret == -EINVAL || ((int)l != l))
+	ret = kstrtoul(val, 0, &l);
+	if (ret)
+		return ret;
+
+	if (l < 1000)
 		return -EINVAL;
-	*((int *)kp->arg) = l;
+
+	*((unsigned long *)kp->arg) = l;
 
 	/* notify edac_mc engine to reset the poll period */
 	edac_mc_reset_delay_period(l);
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 3d139c6e7fe3..f2118bfcf8df 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -52,7 +52,7 @@ extern void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
 extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev);
 extern void edac_device_reset_delay_period(struct edac_device_ctl_info
 					   *edac_dev, unsigned long value);
-extern void edac_mc_reset_delay_period(int value);
+extern void edac_mc_reset_delay_period(unsigned long value);
 
 extern void *edac_align_ptr(void **p, unsigned size, int n_elems);
 
diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c
index c2bd8c6a4349..10d3d298b640 100644
--- a/drivers/edac/highbank_l2_edac.c
+++ b/drivers/edac/highbank_l2_edac.c
@@ -90,28 +90,30 @@ static int highbank_l2_err_probe(struct platform_device *pdev)
 		goto err;
 	}
 
+	dci->mod_name = dev_name(&pdev->dev);
+	dci->dev_name = dev_name(&pdev->dev);
+
+	if (edac_device_add_device(dci))
+		goto err;
+
 	drvdata->db_irq = platform_get_irq(pdev, 0);
 	res = devm_request_irq(&pdev->dev, drvdata->db_irq,
 			       highbank_l2_err_handler,
 			       0, dev_name(&pdev->dev), dci);
 	if (res < 0)
-		goto err;
+		goto err2;
 
 	drvdata->sb_irq = platform_get_irq(pdev, 1);
 	res = devm_request_irq(&pdev->dev, drvdata->sb_irq,
 			       highbank_l2_err_handler,
 			       0, dev_name(&pdev->dev), dci);
 	if (res < 0)
-		goto err;
-
-	dci->mod_name = dev_name(&pdev->dev);
-	dci->dev_name = dev_name(&pdev->dev);
-
-	if (edac_device_add_device(dci))
-		goto err;
+		goto err2;
 
 	devres_close_group(&pdev->dev, NULL);
 	return 0;
+err2:
+	edac_device_del_device(&pdev->dev);
 err:
 	devres_release_group(&pdev->dev, NULL);
 	edac_device_free_ctl_info(dci);
diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c
index 4695dd2d71fd..7a78307588bc 100644
--- a/drivers/edac/highbank_mc_edac.c
+++ b/drivers/edac/highbank_mc_edac.c
@@ -189,14 +189,6 @@ static int highbank_mc_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq(pdev, 0);
-	res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler,
-			       0, dev_name(&pdev->dev), mci);
-	if (res < 0) {
-		dev_err(&pdev->dev, "Unable to request irq %d\n", irq);
-		goto err;
-	}
-
 	mci->mtype_cap = MEM_FLAG_DDR3;
 	mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
 	mci->edac_cap = EDAC_FLAG_SECDED;
@@ -217,10 +209,20 @@ static int highbank_mc_probe(struct platform_device *pdev)
 	if (res < 0)
 		goto err;
 
+	irq = platform_get_irq(pdev, 0);
+	res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler,
+			       0, dev_name(&pdev->dev), mci);
+	if (res < 0) {
+		dev_err(&pdev->dev, "Unable to request irq %d\n", irq);
+		goto err2;
+	}
+
 	highbank_mc_create_debugfs_nodes(mci);
 
 	devres_close_group(&pdev->dev, NULL);
 	return 0;
+err2:
+	edac_mc_del_mc(&pdev->dev);
 err:
 	devres_release_group(&pdev->dev, NULL);
 	edac_mc_free(mci);
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index aa44c1718f50..71b26513b93b 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -242,11 +242,11 @@ static void i3200_process_error_info(struct mem_ctl_info *mci,
 					     -1, -1,
 					     "i3000 UE", "");
 		} else if (log & I3200_ECCERRLOG_CE) {
-			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 					     0, 0, eccerrlog_syndrome(log),
 					     eccerrlog_row(channel, log),
 					     -1, -1,
-					     "i3000 UE", "");
+					     "i3000 CE", "");
 		}
 	}
 }
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 9004c64b169e..841eee387478 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -943,33 +943,35 @@ static int i7300_get_devices(struct mem_ctl_info *mci)
 
 	/* Attempt to 'get' the MCH register we want */
 	pdev = NULL;
-	while (!pvt->pci_dev_16_1_fsb_addr_map ||
-	       !pvt->pci_dev_16_2_fsb_err_regs) {
-		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
-				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev);
-		if (!pdev) {
-			/* End of list, leave */
-			i7300_printk(KERN_ERR,
-				"'system address,Process Bus' "
-				"device not found:"
-				"vendor 0x%x device 0x%x ERR funcs "
-				"(broken BIOS?)\n",
-				PCI_VENDOR_ID_INTEL,
-				PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
-			goto error;
-		}
-
+	while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR,
+				      pdev))) {
 		/* Store device 16 funcs 1 and 2 */
 		switch (PCI_FUNC(pdev->devfn)) {
 		case 1:
-			pvt->pci_dev_16_1_fsb_addr_map = pdev;
+			if (!pvt->pci_dev_16_1_fsb_addr_map)
+				pvt->pci_dev_16_1_fsb_addr_map =
+							pci_dev_get(pdev);
 			break;
 		case 2:
-			pvt->pci_dev_16_2_fsb_err_regs = pdev;
+			if (!pvt->pci_dev_16_2_fsb_err_regs)
+				pvt->pci_dev_16_2_fsb_err_regs =
+							pci_dev_get(pdev);
 			break;
 		}
 	}
 
+	if (!pvt->pci_dev_16_1_fsb_addr_map ||
+	    !pvt->pci_dev_16_2_fsb_err_regs) {
+		/* At least one device was not found */
+		i7300_printk(KERN_ERR,
+			"'system address,Process Bus' device not found:"
+			"vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n",
+			PCI_VENDOR_ID_INTEL,
+			PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
+		goto error;
+	}
+
 	edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s  %x:%x\n",
 		 pci_name(pvt->pci_dev_16_0_fsb_ctlr),
 		 pvt->pci_dev_16_0_fsb_ctlr->vendor,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 0ec3e95a12cd..271818a5a33a 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1334,14 +1334,19 @@ static int i7core_get_onedevice(struct pci_dev **prev,
 	 * is at addr 8086:2c40, instead of 8086:2c41. So, we need
 	 * to probe for the alternate address in case of failure
 	 */
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+	}
 
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE &&
+	    !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
 				      *prev);
+	}
 
 	if (!pdev) {
 		if (*prev) {
diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c
index 3e3e431c8301..b93b0d006ebb 100644
--- a/drivers/edac/i82860_edac.c
+++ b/drivers/edac/i82860_edac.c
@@ -124,7 +124,7 @@ static int i82860_process_error_info(struct mem_ctl_info *mci,
 				     dimm->location[0], dimm->location[1], -1,
 				     "i82860 UE", "");
 	else
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     info->eap, 0, info->derrsyn,
 				     dimm->location[0], dimm->location[1], -1,
 				     "i82860 CE", "");
diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c
index 272a3ec35957..0314dde18a5d 100644
--- a/drivers/eisa/eisa-bus.c
+++ b/drivers/eisa/eisa-bus.c
@@ -275,11 +275,13 @@ static int __init eisa_request_resources(struct eisa_root_device *root,
 		}
 		
 		if (slot) {
+			edev->res[i].name  = NULL;
 			edev->res[i].start = SLOT_ADDRESS(root, slot)
 					     + (i * 0x400);
 			edev->res[i].end   = edev->res[i].start + 0xff;
 			edev->res[i].flags = IORESOURCE_IO;
 		} else {
+			edev->res[i].name  = NULL;
 			edev->res[i].start = SLOT_ADDRESS(root, slot)
 					     + EISA_VENDOR_ID_OFFSET;
 			edev->res[i].end   = edev->res[i].start + 3;
@@ -326,19 +328,20 @@ static int __init eisa_probe(struct eisa_root_device *root)
 		return -ENOMEM;
 	}
 		
-	if (eisa_init_device(root, edev, 0)) {
+	if (eisa_request_resources(root, edev, 0)) {
+		dev_warn(root->dev,
+		         "EISA: Cannot allocate resource for mainboard\n");
 		kfree(edev);
 		if (!root->force_probe)
-			return -ENODEV;
+			return -EBUSY;
 		goto force_probe;
 	}
 
-	if (eisa_request_resources(root, edev, 0)) {
-		dev_warn(root->dev,
-		         "EISA: Cannot allocate resource for mainboard\n");
+	if (eisa_init_device(root, edev, 0)) {
+		eisa_release_resources(edev);
 		kfree(edev);
 		if (!root->force_probe)
-			return -EBUSY;
+			return -ENODEV;
 		goto force_probe;
 	}
 
@@ -361,11 +364,6 @@ static int __init eisa_probe(struct eisa_root_device *root)
 			continue;
 		}
 
-		if (eisa_init_device(root, edev, i)) {
-			kfree(edev);
-			continue;
-		}
-
 		if (eisa_request_resources(root, edev, i)) {
 			dev_warn(root->dev,
 			         "Cannot allocate resource for EISA slot %d\n",
@@ -374,6 +372,12 @@ static int __init eisa_probe(struct eisa_root_device *root)
 			continue;
 		}
 
+		if (eisa_init_device(root, edev, i)) {
+			eisa_release_resources(edev);
+			kfree(edev);
+			continue;
+		}
+
 		if (edev->state == (EISA_CONFIG_ENABLED | EISA_CONFIG_FORCED))
 			enabled_str = " (forced enabled)";
 		else if (edev->state == EISA_CONFIG_FORCED)
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index d0233cd18ffa..5985807e52c9 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -87,7 +87,8 @@ static irqreturn_t adc_jack_irq_thread(int irq, void *_data)
 {
 	struct adc_jack_data *data = _data;
 
-	schedule_delayed_work(&data->handler, data->handling_delay);
+	queue_delayed_work(system_power_efficient_wq,
+			   &data->handler, data->handling_delay);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index 02bec32adde4..f874c30ddbff 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -56,7 +56,7 @@ static irqreturn_t gpio_irq_handler(int irq, void *dev_id)
 {
 	struct gpio_extcon_data *extcon_data = dev_id;
 
-	schedule_delayed_work(&extcon_data->work,
+	queue_delayed_work(system_power_efficient_wq, &extcon_data->work,
 			      extcon_data->debounce_jiffies);
 	return IRQ_HANDLED;
 }
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index b56bdaa27d4b..9966fc0a527f 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -1180,7 +1180,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 
 
 	/* Initialize MUIC register by using platform data or default data */
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		init_data = pdata->muic_data->init_data;
 		num_init_data = pdata->muic_data->num_init_data;
 	} else {
@@ -1213,7 +1213,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 				= init_data[i].data;
 	}
 
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		struct max77693_muic_platform_data *muic_pdata = pdata->muic_data;
 
 		/*
diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index 67d6738d85a0..09f4a9374cf5 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -712,7 +712,7 @@ static int max8997_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
-	if (pdata->muic_pdata) {
+	if (pdata && pdata->muic_pdata) {
 		struct max8997_muic_platform_data *muic_pdata
 			= pdata->muic_pdata;
 
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index ac1b43a04285..4f73c727a97a 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client,
 	    _IOC_SIZE(cmd) > sizeof(buffer))
 		return -ENOTTY;
 
-	if (_IOC_DIR(cmd) == _IOC_READ)
-		memset(&buffer, 0, _IOC_SIZE(cmd));
+	memset(&buffer, 0, sizeof(buffer));
 
 	if (_IOC_DIR(cmd) & _IOC_WRITE)
 		if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd)))
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 664a6ff0a823..392ad513dc04 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -895,7 +895,7 @@ static int lookup_existing_device(struct device *dev, void *data)
 		old->config_rom_retries = 0;
 		fw_notice(card, "rediscovered device %s\n", dev_name(dev));
 
-		PREPARE_DELAYED_WORK(&old->work, fw_device_update);
+		old->workfn = fw_device_update;
 		fw_schedule_device_work(old, 0);
 
 		if (current_node == card->root_node)
@@ -1054,7 +1054,7 @@ static void fw_device_init(struct work_struct *work)
 	if (atomic_cmpxchg(&device->state,
 			   FW_DEVICE_INITIALIZING,
 			   FW_DEVICE_RUNNING) == FW_DEVICE_GONE) {
-		PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+		device->workfn = fw_device_shutdown;
 		fw_schedule_device_work(device, SHUTDOWN_DELAY);
 	} else {
 		fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n",
@@ -1175,13 +1175,20 @@ static void fw_device_refresh(struct work_struct *work)
 		  dev_name(&device->device), fw_rcode_string(ret));
  gone:
 	atomic_set(&device->state, FW_DEVICE_GONE);
-	PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+	device->workfn = fw_device_shutdown;
 	fw_schedule_device_work(device, SHUTDOWN_DELAY);
  out:
 	if (node_id == card->root_node->node_id)
 		fw_schedule_bm_work(card, 0);
 }
 
+static void fw_device_workfn(struct work_struct *work)
+{
+	struct fw_device *device = container_of(to_delayed_work(work),
+						struct fw_device, work);
+	device->workfn(work);
+}
+
 void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 {
 	struct fw_device *device;
@@ -1231,7 +1238,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		 * power-up after getting plugged in.  We schedule the
 		 * first config rom scan half a second after bus reset.
 		 */
-		INIT_DELAYED_WORK(&device->work, fw_device_init);
+		device->workfn = fw_device_init;
+		INIT_DELAYED_WORK(&device->work, fw_device_workfn);
 		fw_schedule_device_work(device, INITIAL_DELAY);
 		break;
 
@@ -1247,7 +1255,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		if (atomic_cmpxchg(&device->state,
 			    FW_DEVICE_RUNNING,
 			    FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_refresh);
+			device->workfn = fw_device_refresh;
 			fw_schedule_device_work(device,
 				device->is_local ? 0 : INITIAL_DELAY);
 		}
@@ -1262,7 +1270,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		smp_wmb();  /* update node_id before generation */
 		device->generation = card->generation;
 		if (atomic_read(&device->state) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_update);
+			device->workfn = fw_device_update;
 			fw_schedule_device_work(device, 0);
 		}
 		break;
@@ -1287,7 +1295,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		device = node->data;
 		if (atomic_xchg(&device->state,
 				FW_DEVICE_GONE) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+			device->workfn = fw_device_shutdown;
 			fw_schedule_device_work(device,
 				list_empty(&card->link) ? 0 : SHUTDOWN_DELAY);
 		}
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 815b0fcbe918..7bdb6fe63236 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -929,8 +929,6 @@ static void fwnet_write_complete(struct fw_card *card, int rcode,
 	if (rcode == RCODE_COMPLETE) {
 		fwnet_transmit_packet_done(ptask);
 	} else {
-		fwnet_transmit_packet_failed(ptask);
-
 		if (printk_timed_ratelimit(&j,  1000) || rcode != last_rcode) {
 			dev_err(&ptask->dev->netdev->dev,
 				"fwnet_write_complete failed: %x (skipped %d)\n",
@@ -938,8 +936,10 @@ static void fwnet_write_complete(struct fw_card *card, int rcode,
 
 			errors_skipped = 0;
 			last_rcode = rcode;
-		} else
+		} else {
 			errors_skipped++;
+		}
+		fwnet_transmit_packet_failed(ptask);
 	}
 }
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index afb701ec90ca..0f3e3047e29c 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -271,6 +271,7 @@ static inline struct fw_ohci *fw_ohci(struct fw_card *card)
 
 static char ohci_driver_name[] = KBUILD_MODNAME;
 
+#define PCI_VENDOR_ID_PINNACLE_SYSTEMS	0x11bd
 #define PCI_DEVICE_ID_AGERE_FW643	0x5901
 #define PCI_DEVICE_ID_CREATIVE_SB1394	0x4001
 #define PCI_DEVICE_ID_JMICRON_JMB38X_FW	0x2380
@@ -278,17 +279,15 @@ static char ohci_driver_name[] = KBUILD_MODNAME;
 #define PCI_DEVICE_ID_TI_TSB12LV26	0x8020
 #define PCI_DEVICE_ID_TI_TSB82AA2	0x8025
 #define PCI_DEVICE_ID_VIA_VT630X	0x3044
-#define PCI_VENDOR_ID_PINNACLE_SYSTEMS	0x11bd
 #define PCI_REV_ID_VIA_VT6306		0x46
 
-#define QUIRK_CYCLE_TIMER		1
-#define QUIRK_RESET_PACKET		2
-#define QUIRK_BE_HEADERS		4
-#define QUIRK_NO_1394A			8
-#define QUIRK_NO_MSI			16
-#define QUIRK_TI_SLLZ059		32
-#define QUIRK_IR_WAKE			64
-#define QUIRK_PHY_LCTRL_TIMEOUT		128
+#define QUIRK_CYCLE_TIMER		0x1
+#define QUIRK_RESET_PACKET		0x2
+#define QUIRK_BE_HEADERS		0x4
+#define QUIRK_NO_1394A			0x8
+#define QUIRK_NO_MSI			0x10
+#define QUIRK_TI_SLLZ059		0x20
+#define QUIRK_IR_WAKE			0x40
 
 /* In case of multiple matches in ohci_quirks[], only the first one is used. */
 static const struct {
@@ -301,10 +300,7 @@ static const struct {
 		QUIRK_BE_HEADERS},
 
 	{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
-		QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI},
-
-	{PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID,
-		QUIRK_PHY_LCTRL_TIMEOUT},
+		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
 		QUIRK_RESET_PACKET},
@@ -351,7 +347,6 @@ MODULE_PARM_DESC(quirks, "Chip quirks (default = 0"
 	", disable MSI = "		__stringify(QUIRK_NO_MSI)
 	", TI SLLZ059 erratum = "	__stringify(QUIRK_TI_SLLZ059)
 	", IR wake unreliable = "	__stringify(QUIRK_IR_WAKE)
-	", phy LCtrl timeout = "	__stringify(QUIRK_PHY_LCTRL_TIMEOUT)
 	")");
 
 #define OHCI_PARAM_DEBUG_AT_AR		1
@@ -2293,9 +2288,6 @@ static int ohci_enable(struct fw_card *card,
 	 * TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but
 	 * cannot actually use the phy at that time.  These need tens of
 	 * millisecods pause between LPS write and first phy access too.
-	 *
-	 * But do not wait for 50msec on Agere/LSI cards.  Their phy
-	 * arbitration state machine may time out during such a long wait.
 	 */
 
 	reg_write(ohci, OHCI1394_HCControlSet,
@@ -2303,11 +2295,8 @@ static int ohci_enable(struct fw_card *card,
 		  OHCI1394_HCControl_postedWriteEnable);
 	flush_writes(ohci);
 
-	if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT))
+	for (lps = 0, i = 0; !lps && i < 3; i++) {
 		msleep(50);
-
-	for (lps = 0, i = 0; !lps && i < 150; i++) {
-		msleep(1);
 		lps = reg_read(ohci, OHCI1394_HCControlSet) &
 		      OHCI1394_HCControl_LPS;
 	}
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 47674b913843..1b1c37dd830b 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -146,6 +146,7 @@ struct sbp2_logical_unit {
 	 */
 	int generation;
 	int retries;
+	work_func_t workfn;
 	struct delayed_work work;
 	bool has_sdev;
 	bool blocked;
@@ -864,7 +865,7 @@ static void sbp2_login(struct work_struct *work)
 	/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
 	sbp2_set_busy_timeout(lu);
 
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
+	lu->workfn = sbp2_reconnect;
 	sbp2_agent_reset(lu);
 
 	/* This was a re-login. */
@@ -918,7 +919,7 @@ static void sbp2_login(struct work_struct *work)
 	 * If a bus reset happened, sbp2_update will have requeued
 	 * lu->work already.  Reset the work from reconnect to login.
 	 */
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
 }
 
 static void sbp2_reconnect(struct work_struct *work)
@@ -952,7 +953,7 @@ static void sbp2_reconnect(struct work_struct *work)
 		    lu->retries++ >= 5) {
 			dev_err(tgt_dev(tgt), "failed to reconnect\n");
 			lu->retries = 0;
-			PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+			lu->workfn = sbp2_login;
 		}
 		sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
 
@@ -972,6 +973,13 @@ static void sbp2_reconnect(struct work_struct *work)
 	sbp2_conditionally_unblock(lu);
 }
 
+static void sbp2_lu_workfn(struct work_struct *work)
+{
+	struct sbp2_logical_unit *lu = container_of(to_delayed_work(work),
+						struct sbp2_logical_unit, work);
+	lu->workfn(work);
+}
+
 static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
 {
 	struct sbp2_logical_unit *lu;
@@ -998,7 +1006,8 @@ static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
 	lu->blocked  = false;
 	++tgt->dont_block;
 	INIT_LIST_HEAD(&lu->orb_list);
-	INIT_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
+	INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn);
 
 	list_add_tail(&lu->link, &tgt->lu_list);
 	return 0;
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index b95159b33c39..eb760a218da4 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -551,9 +551,15 @@ static bool dmi_matches(const struct dmi_system_id *dmi)
 		int s = dmi->matches[i].slot;
 		if (s == DMI_NONE)
 			break;
-		if (dmi_ident[s]
-		    && strstr(dmi_ident[s], dmi->matches[i].substr))
-			continue;
+		if (dmi_ident[s]) {
+			if (!dmi->matches[i].exact_match &&
+			    strstr(dmi_ident[s], dmi->matches[i].substr))
+				continue;
+			else if (dmi->matches[i].exact_match &&
+				 !strcmp(dmi_ident[s], dmi->matches[i].substr))
+				continue;
+		}
+
 		/* No match */
 		return false;
 	}
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index b0fc7c79dfbb..0d32596ad092 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -36,4 +36,11 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 	  backend for pstore by default. This setting can be overridden
 	  using the efivars module's pstore_disable parameter.
 
+config EFI_PARAMS_FROM_FDT
+	bool
+	help
+	  Select this config option from the architecture Kconfig if
+	  the EFI runtime support gets system table address, memory
+          map address, and other parameters from the device tree.
+
 endmenu
diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/arm-stub.c
new file mode 100644
index 000000000000..41114ce03b01
--- /dev/null
+++ b/drivers/firmware/efi/arm-stub.c
@@ -0,0 +1,278 @@
+/*
+ * EFI stub implementation that is shared by arm and arm64 architectures.
+ * This should be #included by the EFI stub implementation files.
+ *
+ * Copyright (C) 2013,2014 Linaro Limited
+ *     Roy Franz <roy.franz@linaro.org
+ * Copyright (C) 2013 Red Hat, Inc.
+ *     Mark Salter <msalter@redhat.com>
+ *
+ * This file is part of the Linux kernel, and is made available under the
+ * terms of the GNU General Public License version 2.
+ *
+ */
+
+static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg)
+{
+	static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID;
+	static efi_char16_t const var_name[] __initconst = {
+		'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 };
+
+	efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable;
+	unsigned long size = sizeof(u8);
+	efi_status_t status;
+	u8 val;
+
+	status = f_getvar((efi_char16_t *)var_name, (efi_guid_t *)&var_guid,
+			  NULL, &size, &val);
+
+	switch (status) {
+	case EFI_SUCCESS:
+		return val;
+	case EFI_NOT_FOUND:
+		return 0;
+	default:
+		return 1;
+	}
+}
+
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+				    void *__image, void **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_loaded_image_t *image = __image;
+	efi_file_handle_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)image->device_handle;
+
+	status = sys_table_arg->boottime->handle_protocol(handle,
+				 &fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	status = io->open_volume(io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to open volume\n");
+
+	*__fh = fh;
+	return status;
+}
+static efi_status_t efi_file_close(void *handle)
+{
+	efi_file_handle_t *fh = handle;
+
+	return fh->close(handle);
+}
+
+static efi_status_t
+efi_file_read(void *handle, unsigned long *size, void *addr)
+{
+	efi_file_handle_t *fh = handle;
+
+	return fh->read(handle, size, addr);
+}
+
+
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
+	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
+{
+	efi_file_handle_t *h, *fh = __fh;
+	efi_file_info_t *info;
+	efi_status_t status;
+	efi_guid_t info_guid = EFI_FILE_INFO_ID;
+	unsigned long info_sz;
+
+	status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to open file: ");
+		efi_char16_printk(sys_table_arg, filename_16);
+		efi_printk(sys_table_arg, "\n");
+		return status;
+	}
+
+	*handle = h;
+
+	info_sz = 0;
+	status = h->get_info(h, &info_guid, &info_sz, NULL);
+	if (status != EFI_BUFFER_TOO_SMALL) {
+		efi_printk(sys_table_arg, "Failed to get file info size\n");
+		return status;
+	}
+
+grow:
+	status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA,
+				 info_sz, (void **)&info);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
+		return status;
+	}
+
+	status = h->get_info(h, &info_guid, &info_sz,
+						   info);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		sys_table_arg->boottime->free_pool(info);
+		goto grow;
+	}
+
+	*file_sz = info->file_size;
+	sys_table_arg->boottime->free_pool(info);
+
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to get initrd info\n");
+
+	return status;
+}
+
+
+
+static void efi_char16_printk(efi_system_table_t *sys_table_arg,
+			      efi_char16_t *str)
+{
+	struct efi_simple_text_output_protocol *out;
+
+	out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out;
+	out->output_string(out, str);
+}
+
+
+/*
+ * This function handles the architcture specific differences between arm and
+ * arm64 regarding where the kernel image must be loaded and any memory that
+ * must be reserved. On failure it is required to free all
+ * all allocations it has made.
+ */
+static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+					unsigned long *image_addr,
+					unsigned long *image_size,
+					unsigned long *reserve_addr,
+					unsigned long *reserve_size,
+					unsigned long dram_base,
+					efi_loaded_image_t *image);
+/*
+ * EFI entry point for the arm/arm64 EFI stubs.  This is the entrypoint
+ * that is described in the PE/COFF header.  Most of the code is the same
+ * for both archictectures, with the arch-specific code provided in the
+ * handle_kernel_image() function.
+ */
+unsigned long __init efi_entry(void *handle, efi_system_table_t *sys_table,
+			       unsigned long *image_addr)
+{
+	efi_loaded_image_t *image;
+	efi_status_t status;
+	unsigned long image_size = 0;
+	unsigned long dram_base;
+	/* addr/point and size pairs for memory management*/
+	unsigned long initrd_addr;
+	u64 initrd_size = 0;
+	unsigned long fdt_addr = 0;  /* Original DTB */
+	u64 fdt_size = 0;  /* We don't get size from configuration table */
+	char *cmdline_ptr = NULL;
+	int cmdline_size = 0;
+	unsigned long new_fdt_addr;
+	efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID;
+	unsigned long reserve_addr = 0;
+	unsigned long reserve_size = 0;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		goto fail;
+
+	pr_efi(sys_table, "Booting Linux Kernel...\n");
+
+	/*
+	 * Get a handle to the loaded image protocol.  This is used to get
+	 * information about the running image, such as size and the command
+	 * line.
+	 */
+	status = sys_table->boottime->handle_protocol(handle,
+					&loaded_image_proto, (void *)&image);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Failed to get loaded image protocol\n");
+		goto fail;
+	}
+
+	dram_base = get_dram_base(sys_table);
+	if (dram_base == EFI_ERROR) {
+		pr_efi_err(sys_table, "Failed to find DRAM base\n");
+		goto fail;
+	}
+	status = handle_kernel_image(sys_table, image_addr, &image_size,
+				     &reserve_addr,
+				     &reserve_size,
+				     dram_base, image);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Failed to relocate kernel\n");
+		goto fail;
+	}
+
+	/*
+	 * Get the command line from EFI, using the LOADED_IMAGE
+	 * protocol. We are going to copy the command line into the
+	 * device tree, so this can be allocated anywhere.
+	 */
+	cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size);
+	if (!cmdline_ptr) {
+		pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n");
+		goto fail_free_image;
+	}
+
+	/*
+	 * Unauthenticated device tree data is a security hazard, so
+	 * ignore 'dtb=' unless UEFI Secure Boot is disabled.
+	 */
+	if (efi_secureboot_enabled(sys_table)) {
+		pr_efi(sys_table, "UEFI Secure Boot is enabled.\n");
+	} else {
+		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
+					      "dtb=",
+					      ~0UL, (unsigned long *)&fdt_addr,
+					      (unsigned long *)&fdt_size);
+
+		if (status != EFI_SUCCESS) {
+			pr_efi_err(sys_table, "Failed to load device tree!\n");
+			goto fail_free_cmdline;
+		}
+	}
+	if (!fdt_addr)
+		/* Look for a device tree configuration table entry. */
+		fdt_addr = (uintptr_t)get_fdt(sys_table);
+
+	status = handle_cmdline_files(sys_table, image, cmdline_ptr,
+				      "initrd=", dram_base + SZ_512M,
+				      (unsigned long *)&initrd_addr,
+				      (unsigned long *)&initrd_size);
+	if (status != EFI_SUCCESS)
+		pr_efi_err(sys_table, "Failed initrd from command line!\n");
+
+	new_fdt_addr = fdt_addr;
+	status = allocate_new_fdt_and_exit_boot(sys_table, handle,
+				&new_fdt_addr, dram_base + MAX_FDT_OFFSET,
+				initrd_addr, initrd_size, cmdline_ptr,
+				fdt_addr, fdt_size);
+
+	/*
+	 * If all went well, we need to return the FDT address to the
+	 * calling function so it can be passed to kernel as part of
+	 * the kernel boot protocol.
+	 */
+	if (status == EFI_SUCCESS)
+		return new_fdt_addr;
+
+	pr_efi_err(sys_table, "Failed to update FDT and exit boot services\n");
+
+	efi_free(sys_table, initrd_size, initrd_addr);
+	efi_free(sys_table, fdt_size, fdt_addr);
+
+fail_free_cmdline:
+	efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr);
+
+fail_free_image:
+	efi_free(sys_table, image_size, *image_addr);
+	efi_free(sys_table, reserve_size, reserve_addr);
+fail:
+	return EFI_ERROR;
+}
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 202d2c85ba2e..bf8dd3d5bee7 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -18,14 +18,12 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
 
 static int efi_pstore_open(struct pstore_info *psi)
 {
-	efivar_entry_iter_begin();
 	psi->data = NULL;
 	return 0;
 }
 
 static int efi_pstore_close(struct pstore_info *psi)
 {
-	efivar_entry_iter_end();
 	psi->data = NULL;
 	return 0;
 }
@@ -78,19 +76,124 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 	__efivar_entry_get(entry, &entry->var.Attributes,
 			   &entry->var.DataSize, entry->var.Data);
 	size = entry->var.DataSize;
+	memcpy(*cb_data->buf, entry->var.Data,
+	       (size_t)min_t(unsigned long, EFIVARS_DATA_SIZE_MAX, size));
 
-	*cb_data->buf = kmalloc(size, GFP_KERNEL);
-	if (*cb_data->buf == NULL)
-		return -ENOMEM;
-	memcpy(*cb_data->buf, entry->var.Data, size);
 	return size;
 }
 
+/**
+ * efi_pstore_scan_sysfs_enter
+ * @entry: scanning entry
+ * @next: next entry
+ * @head: list head
+ */
+static void efi_pstore_scan_sysfs_enter(struct efivar_entry *pos,
+					struct efivar_entry *next,
+					struct list_head *head)
+{
+	pos->scanning = true;
+	if (&next->list != head)
+		next->scanning = true;
+}
+
+/**
+ * __efi_pstore_scan_sysfs_exit
+ * @entry: deleting entry
+ * @turn_off_scanning: Check if a scanning flag should be turned off
+ */
+static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
+						bool turn_off_scanning)
+{
+	if (entry->deleting) {
+		list_del(&entry->list);
+		efivar_entry_iter_end();
+		efivar_unregister(entry);
+		efivar_entry_iter_begin();
+	} else if (turn_off_scanning)
+		entry->scanning = false;
+}
+
+/**
+ * efi_pstore_scan_sysfs_exit
+ * @pos: scanning entry
+ * @next: next entry
+ * @head: list head
+ * @stop: a flag checking if scanning will stop
+ */
+static void efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
+				       struct efivar_entry *next,
+				       struct list_head *head, bool stop)
+{
+	__efi_pstore_scan_sysfs_exit(pos, true);
+	if (stop)
+		__efi_pstore_scan_sysfs_exit(next, &next->list != head);
+}
+
+/**
+ * efi_pstore_sysfs_entry_iter
+ *
+ * @data: function-specific data to pass to callback
+ * @pos: entry to begin iterating from
+ *
+ * You MUST call efivar_enter_iter_begin() before this function, and
+ * efivar_entry_iter_end() afterwards.
+ *
+ * It is possible to begin iteration from an arbitrary entry within
+ * the list by passing @pos. @pos is updated on return to point to
+ * the next entry of the last one passed to efi_pstore_read_func().
+ * To begin iterating from the beginning of the list @pos must be %NULL.
+ */
+static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
+{
+	struct efivar_entry *entry, *n;
+	struct list_head *head = &efivar_sysfs_list;
+	int size = 0;
+
+	if (!*pos) {
+		list_for_each_entry_safe(entry, n, head, list) {
+			efi_pstore_scan_sysfs_enter(entry, n, head);
+
+			size = efi_pstore_read_func(entry, data);
+			efi_pstore_scan_sysfs_exit(entry, n, head, size < 0);
+			if (size)
+				break;
+		}
+		*pos = n;
+		return size;
+	}
+
+	list_for_each_entry_safe_from((*pos), n, head, list) {
+		efi_pstore_scan_sysfs_enter((*pos), n, head);
+
+		size = efi_pstore_read_func((*pos), data);
+		efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
+		if (size)
+			break;
+	}
+	*pos = n;
+	return size;
+}
+
+/**
+ * efi_pstore_read
+ *
+ * This function returns a size of NVRAM entry logged via efi_pstore_write().
+ * The meaning and behavior of efi_pstore/pstore are as below.
+ *
+ * size > 0: Got data of an entry logged via efi_pstore_write() successfully,
+ *           and pstore filesystem will continue reading subsequent entries.
+ * size == 0: Entry was not logged via efi_pstore_write(),
+ *            and efi_pstore driver will continue reading subsequent entries.
+ * size < 0: Failed to get data of entry logging via efi_pstore_write(),
+ *           and pstore will stop reading entry.
+ */
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 			       int *count, struct timespec *timespec,
 			       char **buf, struct pstore_info *psi)
 {
 	struct pstore_read_data data;
+	ssize_t size;
 
 	data.id = id;
 	data.type = type;
@@ -98,8 +201,17 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 	data.timespec = timespec;
 	data.buf = buf;
 
-	return __efivar_entry_iter(efi_pstore_read_func, &efivar_sysfs_list, &data,
-				   (struct efivar_entry **)&psi->data);
+	*data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
+	if (!*data.buf)
+		return -ENOMEM;
+
+	efivar_entry_iter_begin();
+	size = efi_pstore_sysfs_entry_iter(&data,
+					   (struct efivar_entry **)&psi->data);
+	efivar_entry_iter_end();
+	if (size <= 0)
+		kfree(*data.buf);
+	return size;
 }
 
 static int efi_pstore_write(enum pstore_type_id type,
@@ -170,9 +282,17 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data)
 			return 0;
 	}
 
+	if (entry->scanning) {
+		/*
+		 * Skip deletion because this entry will be deleted
+		 * after scanning is completed.
+		 */
+		entry->deleting = true;
+	} else
+		list_del(&entry->list);
+
 	/* found */
 	__efivar_entry_delete(entry);
-	list_del(&entry->list);
 
 	return 1;
 }
@@ -200,10 +320,12 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 
 	efivar_entry_iter_begin();
 	found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry);
-	efivar_entry_iter_end();
 
-	if (found)
+	if (found && !entry->scanning) {
+		efivar_entry_iter_end();
 		efivar_unregister(entry);
+	} else
+		efivar_entry_iter_end();
 
 	return 0;
 }
@@ -236,7 +358,11 @@ static __init int efivars_pstore_init(void)
 	efi_pstore_info.bufsize = 1024;
 	spin_lock_init(&efi_pstore_info.buf_lock);
 
-	pstore_register(&efi_pstore_info);
+	if (pstore_register(&efi_pstore_info)) {
+		kfree(efi_pstore_info.buf);
+		efi_pstore_info.buf = NULL;
+		efi_pstore_info.bufsize = 0;
+	}
 
 	return 0;
 }
diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c
new file mode 100644
index 000000000000..eb6d4be9e722
--- /dev/null
+++ b/drivers/firmware/efi/efi-stub-helper.c
@@ -0,0 +1,634 @@
+/*
+ * Helper functions used by the EFI stub on multiple
+ * architectures. This should be #included by the EFI stub
+ * implementation files.
+ *
+ * Copyright 2011 Intel Corporation; author Matt Fleming
+ *
+ * This file is part of the Linux kernel, and is made available
+ * under the terms of the GNU General Public License version 2.
+ *
+ */
+#define EFI_READ_CHUNK_SIZE	(1024 * 1024)
+
+/* error code which can't be mistaken for valid address */
+#define EFI_ERROR	(~0UL)
+
+
+struct file_info {
+	efi_file_handle_t *handle;
+	u64 size;
+};
+
+static void efi_printk(efi_system_table_t *sys_table_arg, char *str)
+{
+	char *s8;
+
+	for (s8 = str; *s8; s8++) {
+		efi_char16_t ch[2] = { 0 };
+
+		ch[0] = *s8;
+		if (*s8 == '\n') {
+			efi_char16_t nl[2] = { '\r', 0 };
+			efi_char16_printk(sys_table_arg, nl);
+		}
+
+		efi_char16_printk(sys_table_arg, ch);
+	}
+}
+
+#define pr_efi(sys_table, msg)     efi_printk(sys_table, "EFI stub: "msg)
+#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
+
+
+static efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
+				       efi_memory_desc_t **map,
+				       unsigned long *map_size,
+				       unsigned long *desc_size,
+				       u32 *desc_ver,
+				       unsigned long *key_ptr)
+{
+	efi_memory_desc_t *m = NULL;
+	efi_status_t status;
+	unsigned long key;
+	u32 desc_version;
+
+	*map_size = sizeof(*m) * 32;
+again:
+	/*
+	 * Add an additional efi_memory_desc_t because we're doing an
+	 * allocation which may be in a new descriptor region.
+	 */
+	*map_size += sizeof(*m);
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				*map_size, (void **)&m);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	*desc_size = 0;
+	key = 0;
+	status = efi_call_early(get_memory_map, map_size, m,
+				&key, desc_size, &desc_version);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		efi_call_early(free_pool, m);
+		goto again;
+	}
+
+	if (status != EFI_SUCCESS)
+		efi_call_early(free_pool, m);
+
+	if (key_ptr && status == EFI_SUCCESS)
+		*key_ptr = key;
+	if (desc_ver && status == EFI_SUCCESS)
+		*desc_ver = desc_version;
+
+fail:
+	*map = m;
+	return status;
+}
+
+
+static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg)
+{
+	efi_status_t status;
+	unsigned long map_size;
+	unsigned long membase  = EFI_ERROR;
+	struct efi_memory_map map;
+	efi_memory_desc_t *md;
+
+	status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
+				    &map_size, &map.desc_size, NULL, NULL);
+	if (status != EFI_SUCCESS)
+		return membase;
+
+	map.map_end = map.map + map_size;
+
+	for_each_efi_memory_desc(&map, md)
+		if (md->attribute & EFI_MEMORY_WB)
+			if (membase > md->phys_addr)
+				membase = md->phys_addr;
+
+	efi_call_early(free_pool, map.map);
+
+	return membase;
+}
+
+/*
+ * Allocate at the highest possible address that is not above 'max'.
+ */
+static efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
+			       unsigned long size, unsigned long align,
+			       unsigned long *addr, unsigned long max)
+{
+	unsigned long map_size, desc_size;
+	efi_memory_desc_t *map;
+	efi_status_t status;
+	unsigned long nr_pages;
+	u64 max_addr = 0;
+	int i;
+
+	status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
+				    NULL, NULL);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	/*
+	 * Enforce minimum alignment that EFI requires when requesting
+	 * a specific address.  We are doing page-based allocations,
+	 * so we must be aligned to a page.
+	 */
+	if (align < EFI_PAGE_SIZE)
+		align = EFI_PAGE_SIZE;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+again:
+	for (i = 0; i < map_size / desc_size; i++) {
+		efi_memory_desc_t *desc;
+		unsigned long m = (unsigned long)map;
+		u64 start, end;
+
+		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+		if (desc->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (desc->num_pages < nr_pages)
+			continue;
+
+		start = desc->phys_addr;
+		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+		if ((start + size) > end || (start + size) > max)
+			continue;
+
+		if (end - size > max)
+			end = max;
+
+		if (round_down(end - size, align) < start)
+			continue;
+
+		start = round_down(end - size, align);
+
+		/*
+		 * Don't allocate at 0x0. It will confuse code that
+		 * checks pointers against NULL.
+		 */
+		if (start == 0x0)
+			continue;
+
+		if (start > max_addr)
+			max_addr = start;
+	}
+
+	if (!max_addr)
+		status = EFI_NOT_FOUND;
+	else {
+		status = efi_call_early(allocate_pages,
+					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+					nr_pages, &max_addr);
+		if (status != EFI_SUCCESS) {
+			max = max_addr;
+			max_addr = 0;
+			goto again;
+		}
+
+		*addr = max_addr;
+	}
+
+	efi_call_early(free_pool, map);
+fail:
+	return status;
+}
+
+/*
+ * Allocate at the lowest possible address.
+ */
+static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
+			      unsigned long size, unsigned long align,
+			      unsigned long *addr)
+{
+	unsigned long map_size, desc_size;
+	efi_memory_desc_t *map;
+	efi_status_t status;
+	unsigned long nr_pages;
+	int i;
+
+	status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
+				    NULL, NULL);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	/*
+	 * Enforce minimum alignment that EFI requires when requesting
+	 * a specific address.  We are doing page-based allocations,
+	 * so we must be aligned to a page.
+	 */
+	if (align < EFI_PAGE_SIZE)
+		align = EFI_PAGE_SIZE;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	for (i = 0; i < map_size / desc_size; i++) {
+		efi_memory_desc_t *desc;
+		unsigned long m = (unsigned long)map;
+		u64 start, end;
+
+		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+
+		if (desc->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (desc->num_pages < nr_pages)
+			continue;
+
+		start = desc->phys_addr;
+		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+		/*
+		 * Don't allocate at 0x0. It will confuse code that
+		 * checks pointers against NULL. Skip the first 8
+		 * bytes so we start at a nice even number.
+		 */
+		if (start == 0x0)
+			start += 8;
+
+		start = round_up(start, align);
+		if ((start + size) > end)
+			continue;
+
+		status = efi_call_early(allocate_pages,
+					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+					nr_pages, &start);
+		if (status == EFI_SUCCESS) {
+			*addr = start;
+			break;
+		}
+	}
+
+	if (i == map_size / desc_size)
+		status = EFI_NOT_FOUND;
+
+	efi_call_early(free_pool, map);
+fail:
+	return status;
+}
+
+static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
+		     unsigned long addr)
+{
+	unsigned long nr_pages;
+
+	if (!size)
+		return;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	efi_call_early(free_pages, addr, nr_pages);
+}
+
+
+/*
+ * Check the cmdline for a LILO-style file= arguments.
+ *
+ * We only support loading a file from the same filesystem as
+ * the kernel image.
+ */
+static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
+					 efi_loaded_image_t *image,
+					 char *cmd_line, char *option_string,
+					 unsigned long max_addr,
+					 unsigned long *load_addr,
+					 unsigned long *load_size)
+{
+	struct file_info *files;
+	unsigned long file_addr;
+	u64 file_size_total;
+	efi_file_handle_t *fh = NULL;
+	efi_status_t status;
+	int nr_files;
+	char *str;
+	int i, j, k;
+
+	file_addr = 0;
+	file_size_total = 0;
+
+	str = cmd_line;
+
+	j = 0;			/* See close_handles */
+
+	if (!load_addr || !load_size)
+		return EFI_INVALID_PARAMETER;
+
+	*load_addr = 0;
+	*load_size = 0;
+
+	if (!str || !*str)
+		return EFI_SUCCESS;
+
+	for (nr_files = 0; *str; nr_files++) {
+		str = strstr(str, option_string);
+		if (!str)
+			break;
+
+		str += strlen(option_string);
+
+		/* Skip any leading slashes */
+		while (*str == '/' || *str == '\\')
+			str++;
+
+		while (*str && *str != ' ' && *str != '\n')
+			str++;
+	}
+
+	if (!nr_files)
+		return EFI_SUCCESS;
+
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				nr_files * sizeof(*files), (void **)&files);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table_arg, "Failed to alloc mem for file handle list\n");
+		goto fail;
+	}
+
+	str = cmd_line;
+	for (i = 0; i < nr_files; i++) {
+		struct file_info *file;
+		efi_char16_t filename_16[256];
+		efi_char16_t *p;
+
+		str = strstr(str, option_string);
+		if (!str)
+			break;
+
+		str += strlen(option_string);
+
+		file = &files[i];
+		p = filename_16;
+
+		/* Skip any leading slashes */
+		while (*str == '/' || *str == '\\')
+			str++;
+
+		while (*str && *str != ' ' && *str != '\n') {
+			if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16))
+				break;
+
+			if (*str == '/') {
+				*p++ = '\\';
+				str++;
+			} else {
+				*p++ = *str++;
+			}
+		}
+
+		*p = '\0';
+
+		/* Only open the volume once. */
+		if (!i) {
+			status = efi_open_volume(sys_table_arg, image,
+						 (void **)&fh);
+			if (status != EFI_SUCCESS)
+				goto free_files;
+		}
+
+		status = efi_file_size(sys_table_arg, fh, filename_16,
+				       (void **)&file->handle, &file->size);
+		if (status != EFI_SUCCESS)
+			goto close_handles;
+
+		file_size_total += file->size;
+	}
+
+	if (file_size_total) {
+		unsigned long addr;
+
+		/*
+		 * Multiple files need to be at consecutive addresses in memory,
+		 * so allocate enough memory for all the files.  This is used
+		 * for loading multiple files.
+		 */
+		status = efi_high_alloc(sys_table_arg, file_size_total, 0x1000,
+				    &file_addr, max_addr);
+		if (status != EFI_SUCCESS) {
+			pr_efi_err(sys_table_arg, "Failed to alloc highmem for files\n");
+			goto close_handles;
+		}
+
+		/* We've run out of free low memory. */
+		if (file_addr > max_addr) {
+			pr_efi_err(sys_table_arg, "We've run out of free low memory\n");
+			status = EFI_INVALID_PARAMETER;
+			goto free_file_total;
+		}
+
+		addr = file_addr;
+		for (j = 0; j < nr_files; j++) {
+			unsigned long size;
+
+			size = files[j].size;
+			while (size) {
+				unsigned long chunksize;
+				if (size > EFI_READ_CHUNK_SIZE)
+					chunksize = EFI_READ_CHUNK_SIZE;
+				else
+					chunksize = size;
+
+				status = efi_file_read(files[j].handle,
+						       &chunksize,
+						       (void *)addr);
+				if (status != EFI_SUCCESS) {
+					pr_efi_err(sys_table_arg, "Failed to read file\n");
+					goto free_file_total;
+				}
+				addr += chunksize;
+				size -= chunksize;
+			}
+
+			efi_file_close(files[j].handle);
+		}
+
+	}
+
+	efi_call_early(free_pool, files);
+
+	*load_addr = file_addr;
+	*load_size = file_size_total;
+
+	return status;
+
+free_file_total:
+	efi_free(sys_table_arg, file_size_total, file_addr);
+
+close_handles:
+	for (k = j; k < i; k++)
+		efi_file_close(files[k].handle);
+free_files:
+	efi_call_early(free_pool, files);
+fail:
+	*load_addr = 0;
+	*load_size = 0;
+
+	return status;
+}
+/*
+ * Relocate a kernel image, either compressed or uncompressed.
+ * In the ARM64 case, all kernel images are currently
+ * uncompressed, and as such when we relocate it we need to
+ * allocate additional space for the BSS segment. Any low
+ * memory that this function should avoid needs to be
+ * unavailable in the EFI memory map, as if the preferred
+ * address is not available the lowest available address will
+ * be used.
+ */
+static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
+					unsigned long *image_addr,
+					unsigned long image_size,
+					unsigned long alloc_size,
+					unsigned long preferred_addr,
+					unsigned long alignment)
+{
+	unsigned long cur_image_addr;
+	unsigned long new_addr = 0;
+	efi_status_t status;
+	unsigned long nr_pages;
+	efi_physical_addr_t efi_addr = preferred_addr;
+
+	if (!image_addr || !image_size || !alloc_size)
+		return EFI_INVALID_PARAMETER;
+	if (alloc_size < image_size)
+		return EFI_INVALID_PARAMETER;
+
+	cur_image_addr = *image_addr;
+
+	/*
+	 * The EFI firmware loader could have placed the kernel image
+	 * anywhere in memory, but the kernel has restrictions on the
+	 * max physical address it can run at.  Some architectures
+	 * also have a prefered address, so first try to relocate
+	 * to the preferred address.  If that fails, allocate as low
+	 * as possible while respecting the required alignment.
+	 */
+	nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	status = efi_call_early(allocate_pages,
+				EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+				nr_pages, &efi_addr);
+	new_addr = efi_addr;
+	/*
+	 * If preferred address allocation failed allocate as low as
+	 * possible.
+	 */
+	if (status != EFI_SUCCESS) {
+		status = efi_low_alloc(sys_table_arg, alloc_size, alignment,
+				       &new_addr);
+	}
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n");
+		return status;
+	}
+
+	/*
+	 * We know source/dest won't overlap since both memory ranges
+	 * have been allocated by UEFI, so we can safely use memcpy.
+	 */
+	memcpy((void *)new_addr, (void *)cur_image_addr, image_size);
+
+	/* Return the new address of the relocated image. */
+	*image_addr = new_addr;
+
+	return status;
+}
+
+/*
+ * Get the number of UTF-8 bytes corresponding to an UTF-16 character.
+ * This overestimates for surrogates, but that is okay.
+ */
+static int efi_utf8_bytes(u16 c)
+{
+	return 1 + (c >= 0x80) + (c >= 0x800);
+}
+
+/*
+ * Convert an UTF-16 string, not necessarily null terminated, to UTF-8.
+ */
+static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
+{
+	unsigned int c;
+
+	while (n--) {
+		c = *src++;
+		if (n && c >= 0xd800 && c <= 0xdbff &&
+		    *src >= 0xdc00 && *src <= 0xdfff) {
+			c = 0x10000 + ((c & 0x3ff) << 10) + (*src & 0x3ff);
+			src++;
+			n--;
+		}
+		if (c >= 0xd800 && c <= 0xdfff)
+			c = 0xfffd; /* Unmatched surrogate */
+		if (c < 0x80) {
+			*dst++ = c;
+			continue;
+		}
+		if (c < 0x800) {
+			*dst++ = 0xc0 + (c >> 6);
+			goto t1;
+		}
+		if (c < 0x10000) {
+			*dst++ = 0xe0 + (c >> 12);
+			goto t2;
+		}
+		*dst++ = 0xf0 + (c >> 18);
+		*dst++ = 0x80 + ((c >> 12) & 0x3f);
+	t2:
+		*dst++ = 0x80 + ((c >> 6) & 0x3f);
+	t1:
+		*dst++ = 0x80 + (c & 0x3f);
+	}
+
+	return dst;
+}
+
+/*
+ * Convert the unicode UEFI command line to ASCII to pass to kernel.
+ * Size of memory allocated return in *cmd_line_len.
+ * Returns NULL on error.
+ */
+static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
+				 efi_loaded_image_t *image,
+				 int *cmd_line_len)
+{
+	const u16 *s2;
+	u8 *s1 = NULL;
+	unsigned long cmdline_addr = 0;
+	int load_options_chars = image->load_options_size / 2; /* UTF-16 */
+	const u16 *options = image->load_options;
+	int options_bytes = 0;  /* UTF-8 bytes */
+	int options_chars = 0;  /* UTF-16 chars */
+	efi_status_t status;
+	u16 zero = 0;
+
+	if (options) {
+		s2 = options;
+		while (*s2 && *s2 != '\n'
+		       && options_chars < load_options_chars) {
+			options_bytes += efi_utf8_bytes(*s2++);
+			options_chars++;
+		}
+	}
+
+	if (!options_chars) {
+		/* No command line options, so return empty string*/
+		options = &zero;
+	}
+
+	options_bytes++;	/* NUL termination */
+
+	status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr);
+	if (status != EFI_SUCCESS)
+		return NULL;
+
+	s1 = (u8 *)cmdline_addr;
+	s2 = (const u16 *)options;
+
+	s1 = efi_utf16_to_utf8(s1, s2, options_chars);
+	*s1 = '\0';
+
+	*cmd_line_len = options_bytes;
+	return (char *)cmdline_addr;
+}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5145fa344ad5..87f2890974a4 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -13,11 +13,29 @@
  * This file is released under the GPLv2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kobject.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/efi.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/io.h>
+
+struct efi __read_mostly efi = {
+	.mps        = EFI_INVALID_TABLE_ADDR,
+	.acpi       = EFI_INVALID_TABLE_ADDR,
+	.acpi20     = EFI_INVALID_TABLE_ADDR,
+	.smbios     = EFI_INVALID_TABLE_ADDR,
+	.sal_systab = EFI_INVALID_TABLE_ADDR,
+	.boot_info  = EFI_INVALID_TABLE_ADDR,
+	.hcdp       = EFI_INVALID_TABLE_ADDR,
+	.uga        = EFI_INVALID_TABLE_ADDR,
+	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+};
+EXPORT_SYMBOL(efi);
 
 static struct kobject *efi_kobj;
 static struct kobject *efivars_kobj;
@@ -132,3 +150,212 @@ err_put:
 }
 
 subsys_initcall(efisubsys_init);
+
+
+/*
+ * We can't ioremap data in EFI boot services RAM, because we've already mapped
+ * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
+ * callable after efi_enter_virtual_mode and before efi_free_boot_services.
+ */
+void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
+{
+	struct efi_memory_map *map;
+	void *p;
+	map = efi.memmap;
+	if (!map)
+		return NULL;
+	if (WARN_ON(!map->map))
+		return NULL;
+	for (p = map->map; p < map->map_end; p += map->desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 end = md->phys_addr + size;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		if (!md->virt_addr)
+			continue;
+		if (phys_addr >= md->phys_addr && phys_addr < end) {
+			phys_addr += md->virt_addr - md->phys_addr;
+			return (__force void __iomem *)(unsigned long)phys_addr;
+		}
+	}
+	return NULL;
+}
+
+static __initdata efi_config_table_type_t common_tables[] = {
+	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
+	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
+	{HCDP_TABLE_GUID, "HCDP", &efi.hcdp},
+	{MPS_TABLE_GUID, "MPS", &efi.mps},
+	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab},
+	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
+	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+	{NULL_GUID, NULL, NULL},
+};
+
+static __init int match_config_table(efi_guid_t *guid,
+				     unsigned long table,
+				     efi_config_table_type_t *table_types)
+{
+	u8 str[EFI_VARIABLE_GUID_LEN + 1];
+	int i;
+
+	if (table_types) {
+		efi_guid_unparse(guid, str);
+
+		for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
+			efi_guid_unparse(&table_types[i].guid, str);
+
+			if (!efi_guidcmp(*guid, table_types[i].guid)) {
+				*(table_types[i].ptr) = table;
+				pr_cont(" %s=0x%lx ",
+					table_types[i].name, table);
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __init efi_config_init(efi_config_table_type_t *arch_tables)
+{
+	void *config_tables, *tablep;
+	int i, sz;
+
+	if (efi_enabled(EFI_64BIT))
+		sz = sizeof(efi_config_table_64_t);
+	else
+		sz = sizeof(efi_config_table_32_t);
+
+	/*
+	 * Let's see what config tables the firmware passed to us.
+	 */
+	config_tables = early_memremap(efi.systab->tables,
+				       efi.systab->nr_tables * sz);
+	if (config_tables == NULL) {
+		pr_err("Could not map Configuration table!\n");
+		return -ENOMEM;
+	}
+
+	tablep = config_tables;
+	pr_info("");
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+		unsigned long table;
+
+		if (efi_enabled(EFI_64BIT)) {
+			u64 table64;
+			guid = ((efi_config_table_64_t *)tablep)->guid;
+			table64 = ((efi_config_table_64_t *)tablep)->table;
+			table = table64;
+#ifndef CONFIG_64BIT
+			if (table64 >> 32) {
+				pr_cont("\n");
+				pr_err("Table located above 4GB, disabling EFI.\n");
+				early_iounmap(config_tables,
+					       efi.systab->nr_tables * sz);
+				return -EINVAL;
+			}
+#endif
+		} else {
+			guid = ((efi_config_table_32_t *)tablep)->guid;
+			table = ((efi_config_table_32_t *)tablep)->table;
+		}
+
+		if (!match_config_table(&guid, table, common_tables))
+			match_config_table(&guid, table, arch_tables);
+
+		tablep += sz;
+	}
+	pr_cont("\n");
+	early_iounmap(config_tables, efi.systab->nr_tables * sz);
+	return 0;
+}
+
+#ifdef CONFIG_EFI_PARAMS_FROM_FDT
+
+#define UEFI_PARAM(name, prop, field)			   \
+	{						   \
+		{ name },				   \
+		{ prop },				   \
+		offsetof(struct efi_fdt_params, field),    \
+		FIELD_SIZEOF(struct efi_fdt_params, field) \
+	}
+
+static __initdata struct {
+	const char name[32];
+	const char propname[32];
+	int offset;
+	int size;
+} dt_params[] = {
+	UEFI_PARAM("System Table", "linux,uefi-system-table", system_table),
+	UEFI_PARAM("MemMap Address", "linux,uefi-mmap-start", mmap),
+	UEFI_PARAM("MemMap Size", "linux,uefi-mmap-size", mmap_size),
+	UEFI_PARAM("MemMap Desc. Size", "linux,uefi-mmap-desc-size", desc_size),
+	UEFI_PARAM("MemMap Desc. Version", "linux,uefi-mmap-desc-ver", desc_ver)
+};
+
+struct param_info {
+	int verbose;
+	int found;
+	void *params;
+};
+
+static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
+				       int depth, void *data)
+{
+	struct param_info *info = data;
+	const void *prop;
+	void *dest;
+	u64 val;
+	int i, len;
+
+	if (depth != 1 ||
+	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
+		prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len);
+		if (!prop)
+			return 0;
+		dest = info->params + dt_params[i].offset;
+		info->found++;
+
+		val = of_read_number(prop, len / sizeof(u32));
+
+		if (dt_params[i].size == sizeof(u32))
+			*(u32 *)dest = val;
+		else
+			*(u64 *)dest = val;
+
+		if (info->verbose)
+			pr_info("  %s: 0x%0*llx\n", dt_params[i].name,
+				dt_params[i].size * 2, val);
+	}
+	return 1;
+}
+
+int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose)
+{
+	struct param_info info;
+	int ret;
+
+	pr_info("Getting EFI parameters from FDT:\n");
+
+	info.verbose = verbose;
+	info.found = 0;
+	info.params = params;
+
+	ret = of_scan_flat_dt(fdt_find_uefi_params, &info);
+	if (!info.found)
+		pr_info("UEFI not found.\n");
+	else if (!ret)
+		pr_err("Can't find '%s' in device tree!\n",
+		       dt_params[info.found].name);
+
+	return ret;
+}
+#endif /* CONFIG_EFI_PARAMS_FROM_FDT */
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 8bd1bb6dbe47..463c56545ae8 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -69,6 +69,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/ucs2_string.h>
+#include <linux/compat.h>
 
 #define EFIVARS_VERSION "0.08"
 #define EFIVARS_DATE "2004-May-17"
@@ -86,6 +87,15 @@ static struct kset *efivars_kset;
 static struct bin_attribute *efivars_new_var;
 static struct bin_attribute *efivars_del_var;
 
+struct compat_efi_variable {
+	efi_char16_t  VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)];
+	efi_guid_t    VendorGuid;
+	__u32         DataSize;
+	__u8          Data[1024];
+	__u32         Status;
+	__u32         Attributes;
+} __packed;
+
 struct efivar_attribute {
 	struct attribute attr;
 	ssize_t (*show) (struct efivar_entry *entry, char *buf);
@@ -189,45 +199,107 @@ efivar_data_read(struct efivar_entry *entry, char *buf)
 	memcpy(buf, var->Data, var->DataSize);
 	return var->DataSize;
 }
-/*
- * We allow each variable to be edited via rewriting the
- * entire efi variable structure.
- */
-static ssize_t
-efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count)
-{
-	struct efi_variable *new_var, *var = &entry->var;
-	int err;
-
-	if (count != sizeof(struct efi_variable))
-		return -EINVAL;
 
-	new_var = (struct efi_variable *)buf;
+static inline int
+sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
+	     unsigned long size, u32 attributes, u8 *data)
+{
 	/*
 	 * If only updating the variable data, then the name
 	 * and guid should remain the same
 	 */
-	if (memcmp(new_var->VariableName, var->VariableName, sizeof(var->VariableName)) ||
-		efi_guidcmp(new_var->VendorGuid, var->VendorGuid)) {
+	if (memcmp(name, var->VariableName, sizeof(var->VariableName)) ||
+		efi_guidcmp(vendor, var->VendorGuid)) {
 		printk(KERN_ERR "efivars: Cannot edit the wrong variable!\n");
 		return -EINVAL;
 	}
 
-	if ((new_var->DataSize <= 0) || (new_var->Attributes == 0)){
+	if ((size <= 0) || (attributes == 0)){
 		printk(KERN_ERR "efivars: DataSize & Attributes must be valid!\n");
 		return -EINVAL;
 	}
 
-	if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) {
+	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
+	    efivar_validate(name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
 
-	memcpy(&entry->var, new_var, count);
+	return 0;
+}
 
-	err = efivar_entry_set(entry, new_var->Attributes,
-			       new_var->DataSize, new_var->Data, false);
+static inline bool is_compat(void)
+{
+	if (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())
+		return true;
+
+	return false;
+}
+
+static void
+copy_out_compat(struct efi_variable *dst, struct compat_efi_variable *src)
+{
+	memcpy(dst->VariableName, src->VariableName, EFI_VAR_NAME_LEN);
+	memcpy(dst->Data, src->Data, sizeof(src->Data));
+
+	dst->VendorGuid = src->VendorGuid;
+	dst->DataSize = src->DataSize;
+	dst->Attributes = src->Attributes;
+}
+
+/*
+ * We allow each variable to be edited via rewriting the
+ * entire efi variable structure.
+ */
+static ssize_t
+efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count)
+{
+	struct efi_variable *new_var, *var = &entry->var;
+	efi_char16_t *name;
+	unsigned long size;
+	efi_guid_t vendor;
+	u32 attributes;
+	u8 *data;
+	int err;
+
+	if (is_compat()) {
+		struct compat_efi_variable *compat;
+
+		if (count != sizeof(*compat))
+			return -EINVAL;
+
+		compat = (struct compat_efi_variable *)buf;
+		attributes = compat->Attributes;
+		vendor = compat->VendorGuid;
+		name = compat->VariableName;
+		size = compat->DataSize;
+		data = compat->Data;
+
+		err = sanity_check(var, name, vendor, size, attributes, data);
+		if (err)
+			return err;
+
+		copy_out_compat(&entry->var, compat);
+	} else {
+		if (count != sizeof(struct efi_variable))
+			return -EINVAL;
+
+		new_var = (struct efi_variable *)buf;
+
+		attributes = new_var->Attributes;
+		vendor = new_var->VendorGuid;
+		name = new_var->VariableName;
+		size = new_var->DataSize;
+		data = new_var->Data;
+
+		err = sanity_check(var, name, vendor, size, attributes, data);
+		if (err)
+			return err;
+
+		memcpy(&entry->var, new_var, count);
+	}
+
+	err = efivar_entry_set(entry, attributes, size, data, NULL);
 	if (err) {
 		printk(KERN_WARNING "efivars: set_variable() failed: status=%d\n", err);
 		return -EIO;
@@ -240,6 +312,8 @@ static ssize_t
 efivar_show_raw(struct efivar_entry *entry, char *buf)
 {
 	struct efi_variable *var = &entry->var;
+	struct compat_efi_variable *compat;
+	size_t size;
 
 	if (!entry || !buf)
 		return 0;
@@ -249,9 +323,23 @@ efivar_show_raw(struct efivar_entry *entry, char *buf)
 			     &entry->var.DataSize, entry->var.Data))
 		return -EIO;
 
-	memcpy(buf, var, sizeof(*var));
+	if (is_compat()) {
+		compat = (struct compat_efi_variable *)buf;
 
-	return sizeof(*var);
+		size = sizeof(*compat);
+		memcpy(compat->VariableName, var->VariableName,
+			EFI_VAR_NAME_LEN);
+		memcpy(compat->Data, var->Data, sizeof(compat->Data));
+
+		compat->VendorGuid = var->VendorGuid;
+		compat->DataSize = var->DataSize;
+		compat->Attributes = var->Attributes;
+	} else {
+		size = sizeof(*var);
+		memcpy(buf, var, size);
+	}
+
+	return size;
 }
 
 /*
@@ -326,15 +414,39 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 			     struct bin_attribute *bin_attr,
 			     char *buf, loff_t pos, size_t count)
 {
+	struct compat_efi_variable *compat = (struct compat_efi_variable *)buf;
 	struct efi_variable *new_var = (struct efi_variable *)buf;
 	struct efivar_entry *new_entry;
+	bool need_compat = is_compat();
+	efi_char16_t *name;
+	unsigned long size;
+	u32 attributes;
+	u8 *data;
 	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) {
+	if (need_compat) {
+		if (count != sizeof(*compat))
+			return -EINVAL;
+
+		attributes = compat->Attributes;
+		name = compat->VariableName;
+		size = compat->DataSize;
+		data = compat->Data;
+	} else {
+		if (count != sizeof(*new_var))
+			return -EINVAL;
+
+		attributes = new_var->Attributes;
+		name = new_var->VariableName;
+		size = new_var->DataSize;
+		data = new_var->Data;
+	}
+
+	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
+	    efivar_validate(name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -343,10 +455,13 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	if (!new_entry)
 		return -ENOMEM;
 
-	memcpy(&new_entry->var, new_var, sizeof(*new_var));
+	if (need_compat)
+		copy_out_compat(&new_entry->var, compat);
+	else
+		memcpy(&new_entry->var, new_var, sizeof(*new_var));
 
-	err = efivar_entry_set(new_entry, new_var->Attributes, new_var->DataSize,
-			       new_var->Data, &efivar_sysfs_list);
+	err = efivar_entry_set(new_entry, attributes, size,
+			       data, &efivar_sysfs_list);
 	if (err) {
 		if (err == -EEXIST)
 			err = -EINVAL;
@@ -369,26 +484,47 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 			     char *buf, loff_t pos, size_t count)
 {
 	struct efi_variable *del_var = (struct efi_variable *)buf;
+	struct compat_efi_variable *compat;
 	struct efivar_entry *entry;
+	efi_char16_t *name;
+	efi_guid_t vendor;
 	int err = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
+	if (is_compat()) {
+		if (count != sizeof(*compat))
+			return -EINVAL;
+
+		compat = (struct compat_efi_variable *)buf;
+		name = compat->VariableName;
+		vendor = compat->VendorGuid;
+	} else {
+		if (count != sizeof(*del_var))
+			return -EINVAL;
+
+		name = del_var->VariableName;
+		vendor = del_var->VendorGuid;
+	}
+
 	efivar_entry_iter_begin();
-	entry = efivar_entry_find(del_var->VariableName, del_var->VendorGuid,
-				  &efivar_sysfs_list, true);
+	entry = efivar_entry_find(name, vendor, &efivar_sysfs_list, true);
 	if (!entry)
 		err = -EINVAL;
 	else if (__efivar_entry_delete(entry))
 		err = -EIO;
 
-	efivar_entry_iter_end();
-
-	if (err)
+	if (err) {
+		efivar_entry_iter_end();
 		return err;
+	}
 
-	efivar_unregister(entry);
+	if (!entry->scanning) {
+		efivar_entry_iter_end();
+		efivar_unregister(entry);
+	} else
+		efivar_entry_iter_end();
 
 	/* It's dead Jim.... */
 	return count;
@@ -564,7 +700,7 @@ static int efivar_sysfs_destroy(struct efivar_entry *entry, void *data)
 	return 0;
 }
 
-void efivars_sysfs_exit(void)
+static void efivars_sysfs_exit(void)
 {
 	/* Remove all entries and destroy */
 	__efivar_entry_iter(efivar_sysfs_destroy, &efivar_sysfs_list, NULL, NULL);
@@ -583,6 +719,9 @@ int efivars_sysfs_init(void)
 	struct kobject *parent_kobj = efivars_kobject();
 	int error = 0;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return -ENODEV;
+
 	/* No efivars has been registered yet */
 	if (!parent_kobj)
 		return 0;
diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/fdt.c
new file mode 100644
index 000000000000..507a3df46a5d
--- /dev/null
+++ b/drivers/firmware/efi/fdt.c
@@ -0,0 +1,275 @@
+/*
+ * FDT related Helper functions used by the EFI stub on multiple
+ * architectures. This should be #included by the EFI stub
+ * implementation files.
+ *
+ * Copyright 2013 Linaro Limited; author Roy Franz
+ *
+ * This file is part of the Linux kernel, and is made available
+ * under the terms of the GNU General Public License version 2.
+ *
+ */
+
+static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+			       unsigned long orig_fdt_size,
+			       void *fdt, int new_fdt_size, char *cmdline_ptr,
+			       u64 initrd_addr, u64 initrd_size,
+			       efi_memory_desc_t *memory_map,
+			       unsigned long map_size, unsigned long desc_size,
+			       u32 desc_ver)
+{
+	int node, prev;
+	int status;
+	u32 fdt_val32;
+	u64 fdt_val64;
+
+	/* Do some checks on provided FDT, if it exists*/
+	if (orig_fdt) {
+		if (fdt_check_header(orig_fdt)) {
+			pr_efi_err(sys_table, "Device Tree header not valid!\n");
+			return EFI_LOAD_ERROR;
+		}
+		/*
+		 * We don't get the size of the FDT if we get if from a
+		 * configuration table.
+		 */
+		if (orig_fdt_size && fdt_totalsize(orig_fdt) > orig_fdt_size) {
+			pr_efi_err(sys_table, "Truncated device tree! foo!\n");
+			return EFI_LOAD_ERROR;
+		}
+	}
+
+	if (orig_fdt)
+		status = fdt_open_into(orig_fdt, fdt, new_fdt_size);
+	else
+		status = fdt_create_empty_tree(fdt, new_fdt_size);
+
+	if (status != 0)
+		goto fdt_set_fail;
+
+	/*
+	 * Delete any memory nodes present. We must delete nodes which
+	 * early_init_dt_scan_memory may try to use.
+	 */
+	prev = 0;
+	for (;;) {
+		const char *type;
+		int len;
+
+		node = fdt_next_node(fdt, prev, NULL);
+		if (node < 0)
+			break;
+
+		type = fdt_getprop(fdt, node, "device_type", &len);
+		if (type && strncmp(type, "memory", len) == 0) {
+			fdt_del_node(fdt, node);
+			continue;
+		}
+
+		prev = node;
+	}
+
+	node = fdt_subnode_offset(fdt, 0, "chosen");
+	if (node < 0) {
+		node = fdt_add_subnode(fdt, 0, "chosen");
+		if (node < 0) {
+			status = node; /* node is error code when negative */
+			goto fdt_set_fail;
+		}
+	}
+
+	if ((cmdline_ptr != NULL) && (strlen(cmdline_ptr) > 0)) {
+		status = fdt_setprop(fdt, node, "bootargs", cmdline_ptr,
+				     strlen(cmdline_ptr) + 1);
+		if (status)
+			goto fdt_set_fail;
+	}
+
+	/* Set initrd address/end in device tree, if present */
+	if (initrd_size != 0) {
+		u64 initrd_image_end;
+		u64 initrd_image_start = cpu_to_fdt64(initrd_addr);
+
+		status = fdt_setprop(fdt, node, "linux,initrd-start",
+				     &initrd_image_start, sizeof(u64));
+		if (status)
+			goto fdt_set_fail;
+		initrd_image_end = cpu_to_fdt64(initrd_addr + initrd_size);
+		status = fdt_setprop(fdt, node, "linux,initrd-end",
+				     &initrd_image_end, sizeof(u64));
+		if (status)
+			goto fdt_set_fail;
+	}
+
+	/* Add FDT entries for EFI runtime services in chosen node. */
+	node = fdt_subnode_offset(fdt, 0, "chosen");
+	fdt_val64 = cpu_to_fdt64((u64)(unsigned long)sys_table);
+	status = fdt_setprop(fdt, node, "linux,uefi-system-table",
+			     &fdt_val64, sizeof(fdt_val64));
+	if (status)
+		goto fdt_set_fail;
+
+	fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map);
+	status = fdt_setprop(fdt, node, "linux,uefi-mmap-start",
+			     &fdt_val64,  sizeof(fdt_val64));
+	if (status)
+		goto fdt_set_fail;
+
+	fdt_val32 = cpu_to_fdt32(map_size);
+	status = fdt_setprop(fdt, node, "linux,uefi-mmap-size",
+			     &fdt_val32,  sizeof(fdt_val32));
+	if (status)
+		goto fdt_set_fail;
+
+	fdt_val32 = cpu_to_fdt32(desc_size);
+	status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size",
+			     &fdt_val32, sizeof(fdt_val32));
+	if (status)
+		goto fdt_set_fail;
+
+	fdt_val32 = cpu_to_fdt32(desc_ver);
+	status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver",
+			     &fdt_val32, sizeof(fdt_val32));
+	if (status)
+		goto fdt_set_fail;
+
+	/*
+	 * Add kernel version banner so stub/kernel match can be
+	 * verified.
+	 */
+	status = fdt_setprop_string(fdt, node, "linux,uefi-stub-kern-ver",
+			     linux_banner);
+	if (status)
+		goto fdt_set_fail;
+
+	return EFI_SUCCESS;
+
+fdt_set_fail:
+	if (status == -FDT_ERR_NOSPACE)
+		return EFI_BUFFER_TOO_SMALL;
+
+	return EFI_LOAD_ERROR;
+}
+
+#ifndef EFI_FDT_ALIGN
+#define EFI_FDT_ALIGN EFI_PAGE_SIZE
+#endif
+
+/*
+ * Allocate memory for a new FDT, then add EFI, commandline, and
+ * initrd related fields to the FDT.  This routine increases the
+ * FDT allocation size until the allocated memory is large
+ * enough.  EFI allocations are in EFI_PAGE_SIZE granules,
+ * which are fixed at 4K bytes, so in most cases the first
+ * allocation should succeed.
+ * EFI boot services are exited at the end of this function.
+ * There must be no allocations between the get_memory_map()
+ * call and the exit_boot_services() call, so the exiting of
+ * boot services is very tightly tied to the creation of the FDT
+ * with the final memory map in it.
+ */
+
+efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
+					    void *handle,
+					    unsigned long *new_fdt_addr,
+					    unsigned long max_addr,
+					    u64 initrd_addr, u64 initrd_size,
+					    char *cmdline_ptr,
+					    unsigned long fdt_addr,
+					    unsigned long fdt_size)
+{
+	unsigned long map_size, desc_size;
+	u32 desc_ver;
+	unsigned long mmap_key;
+	efi_memory_desc_t *memory_map;
+	unsigned long new_fdt_size;
+	efi_status_t status;
+
+	/*
+	 * Estimate size of new FDT, and allocate memory for it. We
+	 * will allocate a bigger buffer if this ends up being too
+	 * small, so a rough guess is OK here.
+	 */
+	new_fdt_size = fdt_size + EFI_PAGE_SIZE;
+	while (1) {
+		status = efi_high_alloc(sys_table, new_fdt_size, EFI_FDT_ALIGN,
+					new_fdt_addr, max_addr);
+		if (status != EFI_SUCCESS) {
+			pr_efi_err(sys_table, "Unable to allocate memory for new device tree.\n");
+			goto fail;
+		}
+
+		/*
+		 * Now that we have done our final memory allocation (and free)
+		 * we can get the memory map key  needed for
+		 * exit_boot_services().
+		 */
+		status = efi_get_memory_map(sys_table, &memory_map, &map_size,
+					    &desc_size, &desc_ver, &mmap_key);
+		if (status != EFI_SUCCESS)
+			goto fail_free_new_fdt;
+
+		status = update_fdt(sys_table,
+				    (void *)fdt_addr, fdt_size,
+				    (void *)*new_fdt_addr, new_fdt_size,
+				    cmdline_ptr, initrd_addr, initrd_size,
+				    memory_map, map_size, desc_size, desc_ver);
+
+		/* Succeeding the first time is the expected case. */
+		if (status == EFI_SUCCESS)
+			break;
+
+		if (status == EFI_BUFFER_TOO_SMALL) {
+			/*
+			 * We need to allocate more space for the new
+			 * device tree, so free existing buffer that is
+			 * too small.  Also free memory map, as we will need
+			 * to get new one that reflects the free/alloc we do
+			 * on the device tree buffer.
+			 */
+			efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+			sys_table->boottime->free_pool(memory_map);
+			new_fdt_size += EFI_PAGE_SIZE;
+		} else {
+			pr_efi_err(sys_table, "Unable to constuct new device tree.\n");
+			goto fail_free_mmap;
+		}
+	}
+
+	/* Now we are ready to exit_boot_services.*/
+	status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+
+
+	if (status == EFI_SUCCESS)
+		return status;
+
+	pr_efi_err(sys_table, "Exit boot services failed.\n");
+
+fail_free_mmap:
+	sys_table->boottime->free_pool(memory_map);
+
+fail_free_new_fdt:
+	efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+
+fail:
+	return EFI_LOAD_ERROR;
+}
+
+static void *get_fdt(efi_system_table_t *sys_table)
+{
+	efi_guid_t fdt_guid = DEVICE_TREE_GUID;
+	efi_config_table_t *tables;
+	void *fdt;
+	int i;
+
+	tables = (efi_config_table_t *) sys_table->tables;
+	fdt = NULL;
+
+	for (i = 0; i < sys_table->nr_tables; i++)
+		if (efi_guidcmp(tables[i].guid, fdt_guid) == 0) {
+			fdt = (void *) tables[i].table;
+			break;
+	 }
+
+	return fdt;
+}
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 391c67b182d9..5abe943e3404 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -42,7 +42,7 @@ DECLARE_WORK(efivar_work, NULL);
 EXPORT_SYMBOL_GPL(efivar_work);
 
 static bool
-validate_device_path(struct efi_variable *var, int match, u8 *buffer,
+validate_device_path(efi_char16_t *var_name, int match, u8 *buffer,
 		     unsigned long len)
 {
 	struct efi_generic_dev_path *node;
@@ -75,7 +75,7 @@ validate_device_path(struct efi_variable *var, int match, u8 *buffer,
 }
 
 static bool
-validate_boot_order(struct efi_variable *var, int match, u8 *buffer,
+validate_boot_order(efi_char16_t *var_name, int match, u8 *buffer,
 		    unsigned long len)
 {
 	/* An array of 16-bit integers */
@@ -86,18 +86,18 @@ validate_boot_order(struct efi_variable *var, int match, u8 *buffer,
 }
 
 static bool
-validate_load_option(struct efi_variable *var, int match, u8 *buffer,
+validate_load_option(efi_char16_t *var_name, int match, u8 *buffer,
 		     unsigned long len)
 {
 	u16 filepathlength;
 	int i, desclength = 0, namelen;
 
-	namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName));
+	namelen = ucs2_strnlen(var_name, EFI_VAR_NAME_LEN);
 
 	/* Either "Boot" or "Driver" followed by four digits of hex */
 	for (i = match; i < match+4; i++) {
-		if (var->VariableName[i] > 127 ||
-		    hex_to_bin(var->VariableName[i] & 0xff) < 0)
+		if (var_name[i] > 127 ||
+		    hex_to_bin(var_name[i] & 0xff) < 0)
 			return true;
 	}
 
@@ -132,12 +132,12 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer,
 	/*
 	 * And, finally, check the filepath
 	 */
-	return validate_device_path(var, match, buffer + desclength + 6,
+	return validate_device_path(var_name, match, buffer + desclength + 6,
 				    filepathlength);
 }
 
 static bool
-validate_uint16(struct efi_variable *var, int match, u8 *buffer,
+validate_uint16(efi_char16_t *var_name, int match, u8 *buffer,
 		unsigned long len)
 {
 	/* A single 16-bit integer */
@@ -148,7 +148,7 @@ validate_uint16(struct efi_variable *var, int match, u8 *buffer,
 }
 
 static bool
-validate_ascii_string(struct efi_variable *var, int match, u8 *buffer,
+validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
 		      unsigned long len)
 {
 	int i;
@@ -166,7 +166,7 @@ validate_ascii_string(struct efi_variable *var, int match, u8 *buffer,
 
 struct variable_validate {
 	char *name;
-	bool (*validate)(struct efi_variable *var, int match, u8 *data,
+	bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
 			 unsigned long len);
 };
 
@@ -189,10 +189,10 @@ static const struct variable_validate variable_validate[] = {
 };
 
 bool
-efivar_validate(struct efi_variable *var, u8 *data, unsigned long len)
+efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
 {
 	int i;
-	u16 *unicode_name = var->VariableName;
+	u16 *unicode_name = var_name;
 
 	for (i = 0; variable_validate[i].validate != NULL; i++) {
 		const char *name = variable_validate[i].name;
@@ -208,7 +208,7 @@ efivar_validate(struct efi_variable *var, u8 *data, unsigned long len)
 
 			/* Wildcard in the matching name means we've matched */
 			if (c == '*')
-				return variable_validate[i].validate(var,
+				return variable_validate[i].validate(var_name,
 							     match, data, len);
 
 			/* Case sensitive match */
@@ -217,7 +217,7 @@ efivar_validate(struct efi_variable *var, u8 *data, unsigned long len)
 
 			/* Reached the end of the string while matching */
 			if (!c)
-				return variable_validate[i].validate(var,
+				return variable_validate[i].validate(var_name,
 							     match, data, len);
 		}
 	}
@@ -481,7 +481,7 @@ EXPORT_SYMBOL_GPL(efivar_entry_remove);
  */
 static void efivar_entry_list_del_unlock(struct efivar_entry *entry)
 {
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	list_del(&entry->list);
 	spin_unlock_irq(&__efivars->lock);
@@ -507,7 +507,7 @@ int __efivar_entry_delete(struct efivar_entry *entry)
 	const struct efivar_operations *ops = __efivars->ops;
 	efi_status_t status;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	status = ops->set_variable(entry->var.VariableName,
 				   &entry->var.VendorGuid,
@@ -667,7 +667,7 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 	int strsize1, strsize2;
 	bool found = false;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	list_for_each_entry_safe(entry, n, head, list) {
 		strsize1 = ucs2_strsize(name, 1024);
@@ -683,8 +683,16 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 	if (!found)
 		return NULL;
 
-	if (remove)
-		list_del(&entry->list);
+	if (remove) {
+		if (entry->scanning) {
+			/*
+			 * The entry will be deleted
+			 * after scanning is completed.
+			 */
+			entry->deleting = true;
+		} else
+			list_del(&entry->list);
+	}
 
 	return entry;
 }
@@ -731,7 +739,7 @@ int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes,
 	const struct efivar_operations *ops = __efivars->ops;
 	efi_status_t status;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	status = ops->get_variable(entry->var.VariableName,
 				   &entry->var.VendorGuid,
@@ -797,7 +805,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 
 	*set = false;
 
-	if (efivar_validate(&entry->var, data, *size) == false)
+	if (efivar_validate(name, data, *size) == false)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/gator/Kconfig b/drivers/gator/Kconfig
new file mode 100644
index 000000000000..b2358bbc1293
--- /dev/null
+++ b/drivers/gator/Kconfig
@@ -0,0 +1,39 @@
+config GATOR
+	tristate "Gator module for ARM's Streamline Performance Analyzer"
+	default m if (ARM || ARM64)
+	depends on PROFILING
+	depends on HIGH_RES_TIMERS
+	depends on LOCAL_TIMERS || !(ARM && SMP)
+	depends on PERF_EVENTS
+	depends on HW_PERF_EVENTS || !(ARM || ARM64)
+	select TRACING
+	help
+	  Gator module for ARM's Streamline Performance Analyzer
+
+config GATOR_WITH_MALI_SUPPORT
+	bool
+
+choice
+	prompt "Enable Mali GPU support in Gator"
+	depends on GATOR
+	optional
+	help
+	  Enable Mali GPU support in Gator
+
+config GATOR_MALI_4XXMP
+	bool "Mali-400MP or Mali-450MP"
+	select GATOR_WITH_MALI_SUPPORT
+
+config GATOR_MALI_MIDGARD
+	bool "Mali-T60x, Mali-T62x, Mali-T72x or Mali-T76x"
+	select GATOR_WITH_MALI_SUPPORT
+
+endchoice
+
+config GATOR_MALI_PATH
+	string "Path to Mali driver"
+	depends on GATOR_WITH_MALI_SUPPORT
+	default "drivers/gpu/arm/mali400mp"
+	help
+	  The gator code adds this to its include path so it can get the Mali
+	  trace headers with: #include "linux/mali_linux_trace.h"
diff --git a/drivers/gator/LICENSE b/drivers/gator/LICENSE
new file mode 100644
index 000000000000..d159169d1050
--- /dev/null
+++ b/drivers/gator/LICENSE
@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/drivers/gator/Makefile b/drivers/gator/Makefile
new file mode 100644
index 000000000000..28d2070b11d5
--- /dev/null
+++ b/drivers/gator/Makefile
@@ -0,0 +1,79 @@
+ifneq ($(KERNELRELEASE),)
+
+# Uncomment the following line to enable kernel stack unwinding within gator, or update gator_backtrace.c
+# EXTRA_CFLAGS +=	-DGATOR_KERNEL_STACK_UNWINDING
+
+CONFIG_GATOR ?= m
+obj-$(CONFIG_GATOR) := gator.o
+
+gator-y :=	gator_main.o \
+		gator_events_block.o \
+		gator_events_irq.o \
+		gator_events_meminfo.o \
+		gator_events_mmapped.o \
+		gator_events_net.o \
+		gator_events_perf_pmu.o \
+		gator_events_sched.o \
+
+# Convert the old GATOR_WITH_MALI_SUPPORT to the new kernel flags
+ifneq ($(GATOR_WITH_MALI_SUPPORT),)
+  CONFIG_GATOR_WITH_MALI_SUPPORT := y
+  ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_MIDGARD)
+    CONFIG_GATOR_MALI_4XXMP := n
+    CONFIG_GATOR_MALI_MIDGARD := y
+  else
+    CONFIG_GATOR_MALI_4XXMP := y
+    CONFIG_GATOR_MALI_MIDGARD := n
+  endif
+  EXTRA_CFLAGS += -DMALI_SUPPORT=$(GATOR_WITH_MALI_SUPPORT)
+  ifneq ($(GATOR_MALI_INTERFACE_STYLE),)
+    EXTRA_CFLAGS += -DGATOR_MALI_INTERFACE_STYLE=$(GATOR_MALI_INTERFACE_STYLE)
+  endif
+endif
+
+ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y)
+  ifeq ($(CONFIG_GATOR_MALI_MIDGARD),y)
+    gator-y +=	gator_events_mali_midgard.o \
+		gator_events_mali_midgard_hw.o
+    include $(src)/mali_midgard.mk
+  else
+    gator-y +=	gator_events_mali_4xx.o
+  endif
+  gator-y +=	gator_events_mali_common.o
+
+  ifneq ($(CONFIG_GATOR_MALI_PATH),)
+    ccflags-y += -I$(CONFIG_GATOR_MALI_PATH)
+  endif
+  ccflags-$(CONFIG_GATOR_MALI_4XXMP) += -DMALI_SUPPORT=MALI_4xx
+  ccflags-$(CONFIG_GATOR_MALI_MIDGARD) += -DMALI_SUPPORT=MALI_MIDGARD
+endif
+
+# GATOR_TEST controls whether to include (=1) or exclude (=0) test code.
+GATOR_TEST ?= 0
+EXTRA_CFLAGS +=	-DGATOR_TEST=$(GATOR_TEST)
+
+# Should the original or new block_rq_complete API be used?
+OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete $(srctree)/include/trace/events/block.h | grep nr_bytes -q; echo $$?)
+EXTRA_CFLAGS += -DOLD_BLOCK_RQ_COMPLETE=$(OLD_BLOCK_RQ_COMPLETE)
+
+gator-$(CONFIG_ARM) +=	gator_events_armv6.o \
+			gator_events_armv7.o \
+			gator_events_l2c-310.o \
+			gator_events_scorpion.o
+
+gator-$(CONFIG_ARM64) +=
+
+else
+
+all:
+	@echo
+	@echo "usage:"
+	@echo "      make -C <kernel_build_dir> M=\`pwd\` ARCH=arm CROSS_COMPILE=<...> modules"
+	@echo
+	$(error)
+
+clean:
+	rm -f *.o .*.cmd modules.order Module.symvers gator.ko gator.mod.c
+	rm -rf .tmp_versions
+
+endif
diff --git a/drivers/gator/gator.h b/drivers/gator/gator.h
new file mode 100644
index 000000000000..5cc73a388c4f
--- /dev/null
+++ b/drivers/gator/gator.h
@@ -0,0 +1,152 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef GATOR_H_
+#define GATOR_H_
+
+#include <linux/version.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+
+#define GATOR_PERF_SUPPORT      (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0))
+#define GATOR_PERF_PMU_SUPPORT  (GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS)))
+#define GATOR_NO_PERF_SUPPORT   (!(GATOR_PERF_SUPPORT))
+#define GATOR_CPU_FREQ_SUPPORT  ((LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ))
+#define GATOR_IKS_SUPPORT       defined(CONFIG_BL_SWITCHER)
+
+/* cpu ids */
+#define ARM1136     0xb36
+#define ARM1156     0xb56
+#define ARM1176     0xb76
+#define ARM11MPCORE 0xb02
+#define CORTEX_A5   0xc05
+#define CORTEX_A7   0xc07
+#define CORTEX_A8   0xc08
+#define CORTEX_A9   0xc09
+#define CORTEX_A15  0xc0f
+#define CORTEX_A17  0xc0e
+#define SCORPION    0x00f
+#define SCORPIONMP  0x02d
+#define KRAITSIM    0x049
+#define KRAIT       0x04d
+#define KRAIT_S4_PRO 0x06f
+#define CORTEX_A53  0xd03
+#define CORTEX_A57  0xd07
+#define AARCH64     0xd0f
+#define OTHER       0xfff
+
+/* gpu enums */
+#define MALI_4xx     1
+#define MALI_MIDGARD 2
+
+#define MAXSIZE_CORE_NAME 32
+
+struct gator_cpu {
+	const int cpuid;
+	/* Human readable name */
+	const char core_name[MAXSIZE_CORE_NAME];
+	/* gatorfs event and Perf PMU name */
+	const char *const pmnc_name;
+	/* compatible from Documentation/devicetree/bindings/arm/cpus.txt */
+	const char *const dt_name;
+	const int pmnc_counters;
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid);
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name);
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+struct dentry *gatorfs_mkdir(struct super_block *sb, struct dentry *root,
+			     char const *name);
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val);
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val);
+
+/******************************************************************************
+ * Tracepoints
+ ******************************************************************************/
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#	error Kernels prior to 2.6.32 not supported
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name)
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name, NULL)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name, NULL)
+#else
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		extern struct tracepoint *gator_tracepoint_##probe_name; \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		((gator_tracepoint_##probe_name == NULL) || tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL))
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		tracepoint_probe_unregister(gator_tracepoint_##probe_name, probe_##probe_name, NULL)
+#endif
+
+/******************************************************************************
+ * Events
+ ******************************************************************************/
+struct gator_interface {
+	/* Complementary function to init */
+	void (*shutdown)(void);
+	int (*create_files)(struct super_block *sb, struct dentry *root);
+	int (*start)(void);
+	/* Complementary function to start */
+	void (*stop)(void);
+	int (*online)(int **buffer, bool migrate);
+	int (*offline)(int **buffer, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*online_dispatch)(int cpu, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*offline_dispatch)(int cpu, bool migrate);
+	int (*read)(int **buffer, bool sched_switch);
+	int (*read64)(long long **buffer);
+	int (*read_proc)(long long **buffer, struct task_struct *);
+	struct list_head list;
+};
+
+int gator_events_install(struct gator_interface *interface);
+int gator_events_get_key(void);
+u32 gator_cpuid(void);
+
+void gator_backtrace_handler(struct pt_regs *const regs);
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid);
+
+#if !GATOR_IKS_SUPPORT
+
+#define get_physical_cpu() smp_processor_id()
+#define lcpu_to_pcpu(lcpu) lcpu
+#define pcpu_to_lcpu(pcpu) pcpu
+
+#else
+
+#define get_physical_cpu() lcpu_to_pcpu(get_logical_cpu())
+int lcpu_to_pcpu(const int lcpu);
+int pcpu_to_lcpu(const int pcpu);
+
+#endif
+
+#define get_logical_cpu() smp_processor_id()
+#define on_primary_core() (get_logical_cpu() == 0)
+
+#endif /* GATOR_H_ */
diff --git a/drivers/gator/gator_annotate.c b/drivers/gator/gator_annotate.c
new file mode 100644
index 000000000000..ff9a3cef7b2e
--- /dev/null
+++ b/drivers/gator/gator_annotate.c
@@ -0,0 +1,189 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/current.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(annotate_lock);
+static bool collect_annotations;
+
+static int annotate_copy(struct file *file, char const __user *buf, size_t count)
+{
+	int cpu = 0;
+	int write = per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF];
+
+	if (file == NULL) {
+		/* copy from kernel */
+		memcpy(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count);
+	} else {
+		/* copy from user space */
+		if (copy_from_user(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count) != 0)
+			return -1;
+	}
+	per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF] = (write + count) & gator_buffer_mask[ANNOTATE_BUF];
+
+	return 0;
+}
+
+static ssize_t annotate_write(struct file *file, char const __user *buf, size_t count_orig, loff_t *offset)
+{
+	int pid, cpu, header_size, available, contiguous, length1, length2, size, count = count_orig & 0x7fffffff;
+	bool interrupt_context;
+
+	if (*offset)
+		return -EINVAL;
+
+	interrupt_context = in_interrupt();
+	/* Annotations are not supported in interrupt context, but may work
+	 * if you comment out the the next four lines of code. By doing so,
+	 * annotations in interrupt context can result in deadlocks and lost
+	 * data.
+	 */
+	if (interrupt_context) {
+		pr_warning("gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n");
+		return -EINVAL;
+	}
+
+ retry:
+	/* synchronize between cores and with collect_annotations */
+	spin_lock(&annotate_lock);
+
+	if (!collect_annotations) {
+		/* Not collecting annotations, tell the caller everything was written */
+		size = count_orig;
+		goto annotate_write_out;
+	}
+
+	/* Annotation only uses a single per-cpu buffer as the data must be in order to the engine */
+	cpu = 0;
+
+	if (current == NULL)
+		pid = 0;
+	else
+		pid = current->pid;
+
+	/* determine total size of the payload */
+	header_size = MAXSIZE_PACK32 * 3 + MAXSIZE_PACK64;
+	available = buffer_bytes_available(cpu, ANNOTATE_BUF) - header_size;
+	size = count < available ? count : available;
+
+	if (size <= 0) {
+		/* Buffer is full, wait until space is available */
+		spin_unlock(&annotate_lock);
+
+		/* Drop the annotation as blocking is not allowed in interrupt context */
+		if (interrupt_context)
+			return -EINVAL;
+
+		wait_event_interruptible(gator_annotate_wait, buffer_bytes_available(cpu, ANNOTATE_BUF) > header_size || !collect_annotations);
+
+		/* Check to see if a signal is pending */
+		if (signal_pending(current))
+			return -EINTR;
+
+		goto retry;
+	}
+
+	/* synchronize shared variables annotateBuf and annotatePos */
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF]) {
+		u64 time = gator_get_time();
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, time);
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, size);
+
+		/* determine the sizes to capture, length1 + length2 will equal size */
+		contiguous = contiguous_space_available(cpu, ANNOTATE_BUF);
+		if (size < contiguous) {
+			length1 = size;
+			length2 = 0;
+		} else {
+			length1 = contiguous;
+			length2 = size - contiguous;
+		}
+
+		if (annotate_copy(file, buf, length1) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		if (length2 > 0 && annotate_copy(file, &buf[length1], length2) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, ANNOTATE_BUF, time);
+	}
+
+annotate_write_out:
+	spin_unlock(&annotate_lock);
+
+	/* return the number of bytes written */
+	return size;
+}
+
+#include "gator_annotate_kernel.c"
+
+static int annotate_release(struct inode *inode, struct file *file)
+{
+	int cpu = 0;
+
+	/* synchronize between cores */
+	spin_lock(&annotate_lock);
+
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF] && buffer_check_space(cpu, ANNOTATE_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		uint32_t pid = current->pid;
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		/* time */
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0);
+		/* size */
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0);
+	}
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ANNOTATE_BUF, gator_get_time());
+
+	spin_unlock(&annotate_lock);
+
+	return 0;
+}
+
+static const struct file_operations annotate_fops = {
+	.write = annotate_write,
+	.release = annotate_release
+};
+
+static int gator_annotate_create_files(struct super_block *sb, struct dentry *root)
+{
+	return gatorfs_create_file_perm(sb, root, "annotate", &annotate_fops, 0666);
+}
+
+static int gator_annotate_start(void)
+{
+	collect_annotations = true;
+	return 0;
+}
+
+static void gator_annotate_stop(void)
+{
+	/* the spinlock here will ensure that when this function exits, we are not in the middle of an annotation */
+	spin_lock(&annotate_lock);
+	collect_annotations = false;
+	wake_up(&gator_annotate_wait);
+	spin_unlock(&annotate_lock);
+}
diff --git a/drivers/gator/gator_annotate_kernel.c b/drivers/gator/gator_annotate_kernel.c
new file mode 100644
index 000000000000..69471f99e5fb
--- /dev/null
+++ b/drivers/gator/gator_annotate_kernel.c
@@ -0,0 +1,200 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define ESCAPE_CODE 0x1c
+#define STRING_ANNOTATION 0x06
+#define NAME_CHANNEL_ANNOTATION 0x07
+#define NAME_GROUP_ANNOTATION 0x08
+#define VISUAL_ANNOTATION 0x04
+#define MARKER_ANNOTATION 0x05
+
+static void kannotate_write(const char *ptr, unsigned int size)
+{
+	int retval;
+	int pos = 0;
+	loff_t offset = 0;
+
+	while (pos < size) {
+		retval = annotate_write(NULL, &ptr[pos], size - pos, &offset);
+		if (retval < 0) {
+			pr_warning("gator: kannotate_write failed with return value %d\n", retval);
+			return;
+		}
+		pos += retval;
+	}
+}
+
+static void marshal_u16(char *buf, u16 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+}
+
+static void marshal_u32(char *buf, u32 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+	buf[2] = (val >> 16) & 0xff;
+	buf[3] = (val >> 24) & 0xff;
+}
+
+void gator_annotate_channel(int channel, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_channel);
+
+void gator_annotate(const char *str)
+{
+	gator_annotate_channel(0, str);
+}
+EXPORT_SYMBOL(gator_annotate);
+
+void gator_annotate_channel_color(int channel, int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	marshal_u32(header + 8, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_channel_color);
+
+void gator_annotate_color(int color, const char *str)
+{
+	gator_annotate_channel_color(0, color, str);
+}
+EXPORT_SYMBOL(gator_annotate_color);
+
+void gator_annotate_channel_end(int channel)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_channel_end);
+
+void gator_annotate_end(void)
+{
+	gator_annotate_channel_end(0);
+}
+EXPORT_SYMBOL(gator_annotate_end);
+
+void gator_annotate_name_channel(int channel, int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_CHANNEL_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u32(header + 6, group);
+	marshal_u16(header + 10, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_channel);
+
+void gator_annotate_name_group(int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_GROUP_ANNOTATION;
+	marshal_u32(header + 2, group);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_group);
+
+void gator_annotate_visual(const char *data, unsigned int length, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+	char header_length[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = VISUAL_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header_length, length);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+	kannotate_write(header_length, sizeof(header_length));
+	kannotate_write(data, length);
+}
+EXPORT_SYMBOL(gator_annotate_visual);
+
+void gator_annotate_marker(void)
+{
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker);
+
+void gator_annotate_marker_str(const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_marker_str);
+
+void gator_annotate_marker_color(int color)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 4);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker_color);
+
+void gator_annotate_marker_color_str(int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_marker_color_str);
diff --git a/drivers/gator/gator_backtrace.c b/drivers/gator/gator_backtrace.c
new file mode 100644
index 000000000000..76c941d009a9
--- /dev/null
+++ b/drivers/gator/gator_backtrace.c
@@ -0,0 +1,208 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * EABI backtrace stores {fp,lr} on the stack.
+ */
+struct stack_frame_eabi {
+	union {
+		struct {
+			unsigned long fp;
+			/* May be the fp in the case of a leaf function or clang */
+			unsigned long lr;
+			/* If lr is really the fp, lr2 is the corresponding lr */
+			unsigned long lr2;
+		};
+		/* Used to read 32 bit fp/lr from a 64 bit kernel */
+		struct {
+			u32 fp_32;
+			/* same as lr above */
+			u32 lr_32;
+			/* same as lr2 above */
+			u32 lr2_32;
+		};
+	};
+};
+
+static void gator_add_trace(int cpu, unsigned long address)
+{
+	off_t offset = 0;
+	unsigned long cookie = get_address_cookie(cpu, current, address & ~1, &offset);
+
+	if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE)
+		offset = address;
+
+	marshal_backtrace(offset & ~1, cookie, 0);
+}
+
+static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int depth)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	struct stack_frame_eabi *curr;
+	struct stack_frame_eabi bufcurr;
+#if defined(__arm__)
+	const bool is_compat = false;
+	unsigned long fp = regs->ARM_fp;
+	unsigned long sp = regs->ARM_sp;
+	unsigned long lr = regs->ARM_lr;
+	const int gcc_frame_offset = sizeof(unsigned long);
+#else
+	/* Is userspace aarch32 (32 bit) */
+	const bool is_compat = compat_user_mode(regs);
+	unsigned long fp = (is_compat ? regs->regs[11] : regs->regs[29]);
+	unsigned long sp = (is_compat ? regs->compat_sp : regs->sp);
+	unsigned long lr = (is_compat ? regs->compat_lr : regs->regs[30]);
+	const int gcc_frame_offset = (is_compat ? sizeof(u32) : 0);
+#endif
+	/* clang frame offset is always zero */
+	int is_user_mode = user_mode(regs);
+
+	/* pc (current function) has already been added */
+
+	if (!is_user_mode)
+		return;
+
+	/* Add the lr (parent function), entry preamble may not have
+	 * executed
+	 */
+	gator_add_trace(cpu, lr);
+
+	/* check fp is valid */
+	if (fp == 0 || fp < sp)
+		return;
+
+	/* Get the current stack frame */
+	curr = (struct stack_frame_eabi *)(fp - gcc_frame_offset);
+	if ((unsigned long)curr & 3)
+		return;
+
+	while (depth-- && curr) {
+		if (!access_ok(VERIFY_READ, curr, sizeof(struct stack_frame_eabi)) ||
+				__copy_from_user_inatomic(&bufcurr, curr, sizeof(struct stack_frame_eabi))) {
+			return;
+		}
+
+		fp = (is_compat ? bufcurr.fp_32 : bufcurr.fp);
+		lr = (is_compat ? bufcurr.lr_32 : bufcurr.lr);
+
+#define calc_next(reg) ((reg) - gcc_frame_offset)
+		/* Returns true if reg is a valid fp */
+#define validate_next(reg, curr) \
+		((reg) != 0 && (calc_next(reg) & 3) == 0 && (unsigned long)(curr) < calc_next(reg))
+
+		/* Try lr from the stack as the fp because gcc leaf functions do
+		 * not push lr. If gcc_frame_offset is non-zero, the lr will also
+		 * be the clang fp. This assumes code is at a lower address than
+		 * the stack
+		 */
+		if (validate_next(lr, curr)) {
+			fp = lr;
+			lr = (is_compat ? bufcurr.lr2_32 : bufcurr.lr2);
+		}
+
+		gator_add_trace(cpu, lr);
+
+		if (!validate_next(fp, curr))
+			return;
+
+		/* Move to the next stack frame */
+		curr = (struct stack_frame_eabi *)calc_next(fp);
+	}
+#endif
+}
+
+#if defined(__arm__) || defined(__aarch64__)
+static int report_trace(struct stackframe *frame, void *d)
+{
+	unsigned int *depth = d, cookie = NO_COOKIE;
+	unsigned long addr = frame->pc;
+
+	if (*depth) {
+#if defined(MODULE)
+		unsigned int cpu = get_physical_cpu();
+		struct module *mod = __module_address(addr);
+
+		if (mod) {
+			cookie = get_cookie(cpu, current, mod->name, false);
+			addr = addr - (unsigned long)mod->module_core;
+		}
+#endif
+		marshal_backtrace(addr & ~1, cookie, 1);
+		(*depth)--;
+	}
+
+	return *depth == 0;
+}
+#endif
+
+/* Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile */
+/* #define GATOR_KERNEL_STACK_UNWINDING */
+
+#if (defined(__arm__) || defined(__aarch64__)) && !defined(GATOR_KERNEL_STACK_UNWINDING)
+/* Disabled by default */
+MODULE_PARM_DESC(kernel_stack_unwinding, "Allow kernel stack unwinding.");
+static bool kernel_stack_unwinding;
+module_param(kernel_stack_unwinding, bool, 0644);
+#endif
+
+static void kernel_backtrace(int cpu, struct pt_regs *const regs)
+{
+#if defined(__arm__) || defined(__aarch64__)
+#ifdef GATOR_KERNEL_STACK_UNWINDING
+	int depth = gator_backtrace_depth;
+#else
+	int depth = (kernel_stack_unwinding ? gator_backtrace_depth : 1);
+#endif
+	struct stackframe frame;
+
+	if (depth == 0)
+		depth = 1;
+#if defined(__arm__)
+	frame.fp = regs->ARM_fp;
+	frame.sp = regs->ARM_sp;
+	frame.lr = regs->ARM_lr;
+	frame.pc = regs->ARM_pc;
+#else
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+#endif
+	walk_stackframe(&frame, report_trace, &depth);
+#else
+	marshal_backtrace(PC_REG & ~1, NO_COOKIE, 1);
+#endif
+}
+
+static void gator_add_sample(int cpu, struct pt_regs *const regs, u64 time)
+{
+	bool in_kernel;
+	unsigned long exec_cookie;
+
+	if (!regs)
+		return;
+
+	in_kernel = !user_mode(regs);
+	exec_cookie = get_exec_cookie(cpu, current);
+
+	if (!marshal_backtrace_header(exec_cookie, current->tgid, current->pid, time))
+		return;
+
+	if (in_kernel) {
+		kernel_backtrace(cpu, regs);
+	} else {
+		/* Cookie+PC */
+		gator_add_trace(cpu, PC_REG);
+
+		/* Backtrace */
+		if (gator_backtrace_depth)
+			arm_backtrace_eabi(cpu, regs, gator_backtrace_depth);
+	}
+
+	marshal_backtrace_footer(time);
+}
diff --git a/drivers/gator/gator_buffer.c b/drivers/gator/gator_buffer.c
new file mode 100644
index 000000000000..910d5aa15066
--- /dev/null
+++ b/drivers/gator/gator_buffer.c
@@ -0,0 +1,171 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void marshal_frame(int cpu, int buftype)
+{
+	int frame;
+	bool write_cpu;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	switch (buftype) {
+	case SUMMARY_BUF:
+		write_cpu = false;
+		frame = FRAME_SUMMARY;
+		break;
+	case BACKTRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_BACKTRACE;
+		break;
+	case NAME_BUF:
+		write_cpu = true;
+		frame = FRAME_NAME;
+		break;
+	case COUNTER_BUF:
+		write_cpu = false;
+		frame = FRAME_COUNTER;
+		break;
+	case BLOCK_COUNTER_BUF:
+		write_cpu = true;
+		frame = FRAME_BLOCK_COUNTER;
+		break;
+	case ANNOTATE_BUF:
+		write_cpu = false;
+		frame = FRAME_ANNOTATE;
+		break;
+	case SCHED_TRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_SCHED_TRACE;
+		break;
+	case IDLE_BUF:
+		write_cpu = false;
+		frame = FRAME_IDLE;
+		break;
+	case ACTIVITY_BUF:
+		write_cpu = false;
+		frame = FRAME_ACTIVITY;
+		break;
+	default:
+		write_cpu = false;
+		frame = -1;
+		break;
+	}
+
+	/* add response type */
+	if (gator_response_type > 0)
+		gator_buffer_write_packed_int(cpu, buftype, gator_response_type);
+
+	/* leave space for 4-byte unpacked length */
+	per_cpu(gator_buffer_write, cpu)[buftype] = (per_cpu(gator_buffer_write, cpu)[buftype] + sizeof(s32)) & gator_buffer_mask[buftype];
+
+	/* add frame type and core number */
+	gator_buffer_write_packed_int(cpu, buftype, frame);
+	if (write_cpu)
+		gator_buffer_write_packed_int(cpu, buftype, cpu);
+}
+
+static int buffer_bytes_available(int cpu, int buftype)
+{
+	int remaining, filled;
+
+	filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_read, cpu)[buftype];
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+
+	remaining = gator_buffer_size[buftype] - filled;
+
+	if (per_cpu(buffer_space_available, cpu)[buftype])
+		/* Give some extra room; also allows space to insert the overflow error packet */
+		remaining -= 200;
+	else
+		/* Hysteresis, prevents multiple overflow messages */
+		remaining -= 2000;
+
+	return remaining;
+}
+
+static bool buffer_check_space(int cpu, int buftype, int bytes)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+
+	if (remaining < bytes)
+		per_cpu(buffer_space_available, cpu)[buftype] = false;
+	else
+		per_cpu(buffer_space_available, cpu)[buftype] = true;
+
+	return per_cpu(buffer_space_available, cpu)[buftype];
+}
+
+static int contiguous_space_available(int cpu, int buftype)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+	int contiguous = gator_buffer_size[buftype] - per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (remaining < contiguous)
+		return remaining;
+	return contiguous;
+}
+
+static void gator_commit_buffer(int cpu, int buftype, u64 time)
+{
+	int type_length, commit, length, byte;
+	unsigned long flags;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	/* post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload */
+	local_irq_save(flags);
+	type_length = gator_response_type ? 1 : 0;
+	commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+	length = per_cpu(gator_buffer_write, cpu)[buftype] - commit;
+	if (length < 0)
+		length += gator_buffer_size[buftype];
+	length = length - type_length - sizeof(s32);
+
+	if (length <= FRAME_HEADER_SIZE) {
+		/* Nothing to write, only the frame header is present */
+		local_irq_restore(flags);
+		return;
+	}
+
+	for (byte = 0; byte < sizeof(s32); byte++)
+		per_cpu(gator_buffer, cpu)[buftype][(commit + type_length + byte) & gator_buffer_mask[buftype]] = (length >> byte * 8) & 0xFF;
+
+	per_cpu(gator_buffer_commit, cpu)[buftype] = per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (gator_live_rate > 0) {
+		while (time > per_cpu(gator_buffer_commit_time, cpu))
+			per_cpu(gator_buffer_commit_time, cpu) += gator_live_rate;
+	}
+
+	marshal_frame(cpu, buftype);
+	local_irq_restore(flags);
+
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	if (per_cpu(in_scheduler_context, cpu)) {
+#ifndef CONFIG_PREEMPT_RT_FULL
+		/* mod_timer can not be used in interrupt context in RT-Preempt full */
+		mod_timer(&gator_buffer_wake_up_timer, jiffies + 1);
+#endif
+	} else {
+		up(&gator_buffer_wake_sem);
+	}
+}
+
+static void buffer_check(int cpu, int buftype, u64 time)
+{
+	int filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_commit, cpu)[buftype];
+
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+	if (filled >= ((gator_buffer_size[buftype] * 3) / 4))
+		gator_commit_buffer(cpu, buftype, time);
+}
diff --git a/drivers/gator/gator_buffer_write.c b/drivers/gator/gator_buffer_write.c
new file mode 100644
index 000000000000..654ec606cfad
--- /dev/null
+++ b/drivers/gator/gator_buffer_write.c
@@ -0,0 +1,83 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void gator_buffer_write_packed_int(int cpu, int buftype, int x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_packed_int64(int cpu, int buftype, long long x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_bytes(int cpu, int buftype, const char *x, int len)
+{
+	int i;
+	u32 write = per_cpu(gator_buffer_write, cpu)[buftype];
+	u32 mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+
+	for (i = 0; i < len; i++) {
+		buffer[write] = x[i];
+		write = (write + 1) & mask;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = write;
+}
+
+static void gator_buffer_write_string(int cpu, int buftype, const char *x)
+{
+	int len = strlen(x);
+
+	gator_buffer_write_packed_int(cpu, buftype, len);
+	gator_buffer_write_bytes(cpu, buftype, x, len);
+}
diff --git a/drivers/gator/gator_cookies.c b/drivers/gator/gator_cookies.c
new file mode 100644
index 000000000000..c43cce815226
--- /dev/null
+++ b/drivers/gator/gator_cookies.c
@@ -0,0 +1,446 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* must be power of 2 */
+#define COOKIEMAP_ENTRIES	1024
+/* must be a power of 2 - 512/4 = 128 entries */
+#define TRANSLATE_BUFFER_SIZE 512
+#define TRANSLATE_TEXT_SIZE		256
+#define MAX_COLLISIONS		2
+
+static uint32_t *gator_crc32_table;
+static unsigned int translate_buffer_mask;
+
+struct cookie_args {
+	struct task_struct *task;
+	const char *text;
+};
+
+static DEFINE_PER_CPU(char *, translate_text);
+static DEFINE_PER_CPU(uint32_t, cookie_next_key);
+static DEFINE_PER_CPU(uint64_t *, cookie_keys);
+static DEFINE_PER_CPU(uint32_t *, cookie_values);
+static DEFINE_PER_CPU(int, translate_buffer_read);
+static DEFINE_PER_CPU(int, translate_buffer_write);
+static DEFINE_PER_CPU(struct cookie_args *, translate_buffer);
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq);
+static void wq_cookie_handler(struct work_struct *unused);
+static DECLARE_WORK(cookie_work, wq_cookie_handler);
+static struct timer_list app_process_wake_up_timer;
+static void app_process_wake_up_handler(unsigned long unused_data);
+
+static uint32_t cookiemap_code(uint64_t value64)
+{
+	uint32_t value = (uint32_t)((value64 >> 32) + value64);
+	uint32_t cookiecode = (value >> 24) & 0xff;
+
+	cookiecode = cookiecode * 31 + ((value >> 16) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 8) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 0) & 0xff);
+	cookiecode &= (COOKIEMAP_ENTRIES - 1);
+	return cookiecode * MAX_COLLISIONS;
+}
+
+static uint32_t gator_chksum_crc32(const char *data)
+{
+	register unsigned long crc;
+	const unsigned char *block = data;
+	int i, length = strlen(data);
+
+	crc = 0xFFFFFFFF;
+	for (i = 0; i < length; i++)
+		crc = ((crc >> 8) & 0x00FFFFFF) ^ gator_crc32_table[(crc ^ *block++) & 0xFF];
+
+	return (crc ^ 0xFFFFFFFF);
+}
+
+/*
+ * Exists
+ *  Pre:  [0][1][v][3]..[n-1]
+ *  Post: [v][0][1][3]..[n-1]
+ */
+static uint32_t cookiemap_exists(uint64_t key)
+{
+	unsigned long x, flags, retval = 0;
+	int cpu = get_physical_cpu();
+	uint32_t cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+
+	/* Can be called from interrupt handler or from work queue */
+	local_irq_save(flags);
+	for (x = 0; x < MAX_COLLISIONS; x++) {
+		if (keys[x] == key) {
+			uint32_t value = values[x];
+
+			for (; x > 0; x--) {
+				keys[x] = keys[x - 1];
+				values[x] = values[x - 1];
+			}
+			keys[0] = key;
+			values[0] = value;
+			retval = value;
+			break;
+		}
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+/*
+ * Add
+ *  Pre:  [0][1][2][3]..[n-1]
+ *  Post: [v][0][1][2]..[n-2]
+ */
+static void cookiemap_add(uint64_t key, uint32_t value)
+{
+	int cpu = get_physical_cpu();
+	int cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+	int x;
+
+	for (x = MAX_COLLISIONS - 1; x > 0; x--) {
+		keys[x] = keys[x - 1];
+		values[x] = values[x - 1];
+	}
+	keys[0] = key;
+	values[0] = value;
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+static void translate_buffer_write_args(int cpu, struct task_struct *task, const char *text)
+{
+	unsigned long flags;
+	int write;
+	int next_write;
+	struct cookie_args *args;
+
+	local_irq_save(flags);
+
+	write = per_cpu(translate_buffer_write, cpu);
+	next_write = (write + 1) & translate_buffer_mask;
+
+	/* At least one entry must always remain available as when read == write, the queue is empty not full */
+	if (next_write != per_cpu(translate_buffer_read, cpu)) {
+		args = &per_cpu(translate_buffer, cpu)[write];
+		args->task = task;
+		args->text = text;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+		get_task_struct(task);
+#endif
+		per_cpu(translate_buffer_write, cpu) = next_write;
+	}
+
+	local_irq_restore(flags);
+}
+#endif
+
+static void translate_buffer_read_args(int cpu, struct cookie_args *args)
+{
+	unsigned long flags;
+	int read;
+
+	local_irq_save(flags);
+
+	read = per_cpu(translate_buffer_read, cpu);
+	*args = per_cpu(translate_buffer, cpu)[read];
+	per_cpu(translate_buffer_read, cpu) = (read + 1) & translate_buffer_mask;
+
+	local_irq_restore(flags);
+}
+
+static void wq_cookie_handler(struct work_struct *unused)
+{
+	struct cookie_args args;
+	int cpu = get_physical_cpu(), cookie;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started != 0) {
+		while (per_cpu(translate_buffer_read, cpu) != per_cpu(translate_buffer_write, cpu)) {
+			translate_buffer_read_args(cpu, &args);
+			cookie = get_cookie(cpu, args.task, args.text, true);
+			marshal_link(cookie, args.task->tgid, args.task->pid);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+			put_task_struct(args.task);
+#endif
+		}
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void app_process_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&cookie_work);
+}
+
+/* Retrieve full name from proc/pid/cmdline for java processes on Android */
+static int translate_app_process(const char **text, int cpu, struct task_struct *task, bool from_wq)
+{
+	void *maddr;
+	unsigned int len;
+	unsigned long addr;
+	struct mm_struct *mm;
+	struct page *page = NULL;
+	struct vm_area_struct *page_vma;
+	int bytes, offset, retval = 0;
+	char *buf = per_cpu(translate_text, cpu);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+	/* Push work into a work queue if in atomic context as the kernel
+	 * functions below might sleep. Rely on the in_interrupt variable
+	 * rather than in_irq() or in_interrupt() kernel functions, as the
+	 * value of these functions seems inconsistent during a context
+	 * switch between android/linux versions
+	 */
+	if (!from_wq) {
+		/* Check if already in buffer */
+		int pos = per_cpu(translate_buffer_read, cpu);
+
+		while (pos != per_cpu(translate_buffer_write, cpu)) {
+			if (per_cpu(translate_buffer, cpu)[pos].task == task)
+				goto out;
+			pos = (pos + 1) & translate_buffer_mask;
+		}
+
+		translate_buffer_write_args(cpu, task, *text);
+
+		/* Not safe to call in RT-Preempt full in schedule switch context */
+		mod_timer(&app_process_wake_up_timer, jiffies + 1);
+		goto out;
+	}
+#endif
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto outmm;
+	addr = mm->arg_start;
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > TRANSLATE_TEXT_SIZE)
+		len = TRANSLATE_TEXT_SIZE;
+
+	down_read(&mm->mmap_sem);
+	while (len) {
+		if (get_user_pages(task, mm, addr, 1, 0, 1, &page, &page_vma) <= 0)
+			goto outsem;
+
+		maddr = kmap(page);
+		offset = addr & (PAGE_SIZE - 1);
+		bytes = len;
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		copy_from_user_page(page_vma, page, addr, buf, maddr + offset, bytes);
+
+		/* release page allocated by get_user_pages() */
+		kunmap(page);
+		page_cache_release(page);
+
+		len -= bytes;
+		buf += bytes;
+		addr += bytes;
+
+		*text = per_cpu(translate_text, cpu);
+		retval = 1;
+	}
+
+	/* On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period */
+	if (strcmp(*text, "zygote") == 0 || strcmp(*text, "<pre-initialized>") == 0)
+		retval = 0;
+
+outsem:
+	up_read(&mm->mmap_sem);
+outmm:
+	mmput(mm);
+out:
+	return retval;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq)
+{
+	unsigned long flags, cookie;
+	uint64_t key;
+
+	key = gator_chksum_crc32(text);
+	key = (key << 32) | (uint32_t)task->tgid;
+
+	cookie = cookiemap_exists(key);
+	if (cookie)
+		return cookie;
+
+	/* On 64-bit android app_process can be app_process32 or app_process64 */
+	if (strncmp(text, APP_PROCESS, sizeof(APP_PROCESS) - 1) == 0) {
+		if (!translate_app_process(&text, cpu, task, from_wq))
+			return UNRESOLVED_COOKIE;
+	}
+
+	/* Can be called from interrupt handler or from work queue or from scheduler trace */
+	local_irq_save(flags);
+
+	cookie = UNRESOLVED_COOKIE;
+	if (marshal_cookie_header(text)) {
+		cookie = per_cpu(cookie_next_key, cpu) += nr_cpu_ids;
+		cookiemap_add(key, cookie);
+		marshal_cookie(cookie, text);
+	}
+
+	local_irq_restore(flags);
+
+	return cookie;
+}
+
+static int get_exec_cookie(int cpu, struct task_struct *task)
+{
+	struct mm_struct *mm = task->mm;
+	const char *text;
+
+	/* kernel threads have no address space */
+	if (!mm)
+		return NO_COOKIE;
+
+	if (task && task->mm && task->mm->exe_file) {
+		text = task->mm->exe_file->f_path.dentry->d_name.name;
+		return get_cookie(cpu, task, text, false);
+	}
+
+	return UNRESOLVED_COOKIE;
+}
+
+static unsigned long get_address_cookie(int cpu, struct task_struct *task, unsigned long addr, off_t *offset)
+{
+	unsigned long cookie = NO_COOKIE;
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	const char *text;
+
+	if (!mm)
+		return cookie;
+
+	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+		if (addr < vma->vm_start || addr >= vma->vm_end)
+			continue;
+
+		if (vma->vm_file) {
+			text = vma->vm_file->f_path.dentry->d_name.name;
+			cookie = get_cookie(cpu, task, text, false);
+			*offset = (vma->vm_pgoff << PAGE_SHIFT) + addr - vma->vm_start;
+		} else {
+			/* must be an anonymous map */
+			*offset = addr;
+		}
+
+		break;
+	}
+
+	if (!vma)
+		cookie = UNRESOLVED_COOKIE;
+
+	return cookie;
+}
+
+static int cookies_initialize(void)
+{
+	uint32_t crc, poly;
+	int i, j, cpu, size, err = 0;
+
+	translate_buffer_mask = TRANSLATE_BUFFER_SIZE / sizeof(per_cpu(translate_buffer, 0)[0]) - 1;
+
+	for_each_present_cpu(cpu) {
+		per_cpu(cookie_next_key, cpu) = nr_cpu_ids + cpu;
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(cookie_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_keys, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_keys, cpu), 0, size);
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint32_t);
+		per_cpu(cookie_values, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_values, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_values, cpu), 0, size);
+
+		per_cpu(translate_buffer, cpu) = kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_buffer, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+
+		per_cpu(translate_buffer_write, cpu) = 0;
+		per_cpu(translate_buffer_read, cpu) = 0;
+
+		per_cpu(translate_text, cpu) = kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_text, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+	}
+
+	/* build CRC32 table */
+	poly = 0x04c11db7;
+	gator_crc32_table = kmalloc(256 * sizeof(*gator_crc32_table), GFP_KERNEL);
+	if (!gator_crc32_table) {
+		err = -ENOMEM;
+		goto cookie_setup_error;
+	}
+	for (i = 0; i < 256; i++) {
+		crc = i;
+		for (j = 8; j > 0; j--) {
+			if (crc & 1)
+				crc = (crc >> 1) ^ poly;
+			else
+				crc >>= 1;
+		}
+		gator_crc32_table[i] = crc;
+	}
+
+	setup_timer(&app_process_wake_up_timer, app_process_wake_up_handler, 0);
+
+cookie_setup_error:
+	return err;
+}
+
+static void cookies_release(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(cookie_keys, cpu));
+		per_cpu(cookie_keys, cpu) = NULL;
+
+		kfree(per_cpu(cookie_values, cpu));
+		per_cpu(cookie_values, cpu) = NULL;
+
+		kfree(per_cpu(translate_buffer, cpu));
+		per_cpu(translate_buffer, cpu) = NULL;
+		per_cpu(translate_buffer_read, cpu) = 0;
+		per_cpu(translate_buffer_write, cpu) = 0;
+
+		kfree(per_cpu(translate_text, cpu));
+		per_cpu(translate_text, cpu) = NULL;
+	}
+
+	del_timer_sync(&app_process_wake_up_timer);
+	kfree(gator_crc32_table);
+	gator_crc32_table = NULL;
+}
diff --git a/drivers/gator/gator_events_armv6.c b/drivers/gator/gator_events_armv6.c
new file mode 100644
index 000000000000..a157a0013302
--- /dev/null
+++ b/drivers/gator/gator_events_armv6.c
@@ -0,0 +1,234 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+
+/*
+ * Per-CPU PMCR
+ */
+#define PMCR_E			(1 << 0)	/* Enable */
+#define PMCR_P			(1 << 1)	/* Count reset */
+#define PMCR_C			(1 << 2)	/* Cycle counter reset */
+#define PMCR_OFL_PMN0	(1 << 8)	/* Count reg 0 overflow */
+#define PMCR_OFL_PMN1	(1 << 9)	/* Count reg 1 overflow */
+#define PMCR_OFL_CCNT	(1 << 10)	/* Cycle counter overflow */
+
+#define PMN0 0
+#define PMN1 1
+#define CCNT 2
+#define CNTMAX	(CCNT+1)
+
+static int pmnc_counters;
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+static inline void armv6_pmnc_write(u32 val)
+{
+	/* upper 4bits and 7, 11 are write-as-0 */
+	val &= 0x0ffff77f;
+	asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r" (val));
+}
+
+static inline u32 armv6_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r" (val));
+	return val;
+}
+
+static void armv6_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	switch (cnt) {
+	case CCNT:
+		asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r" (val));
+		break;
+	case PMN0:
+		asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r" (val));
+		break;
+	case PMN1:
+		asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r" (val));
+		break;
+	}
+}
+
+int gator_events_armv6_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	pmnc_counters = 3;
+
+	for (i = PMN0; i <= CCNT; i++) {
+		char buf[40];
+
+		if (i == CCNT)
+			snprintf(buf, sizeof(buf), "ARM_%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_%s_cnt%d", pmnc_name, i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i != CCNT)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv6_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+	u32 pmnc;
+
+	if (armv6_pmnc_read() & PMCR_E)
+		armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+
+	/* initialize PMNC, reset overflow, D bit, C bit and P bit. */
+	armv6_pmnc_write(PMCR_OFL_PMN0 | PMCR_OFL_PMN1 | PMCR_OFL_CCNT |
+			 PMCR_C | PMCR_P);
+
+	/* configure control register */
+	for (pmnc = 0, cnt = PMN0; cnt <= CCNT; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters) */
+		if (cnt == PMN0)
+			pmnc |= event << 20;
+		else if (cnt == PMN1)
+			pmnc |= event << 12;
+
+		/* Reset counter */
+		armv6_pmnc_reset_counter(cnt);
+	}
+	armv6_pmnc_write(pmnc | PMCR_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv6_offline(int **buffer, bool migrate)
+{
+	unsigned int cnt;
+
+	armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+	for (cnt = PMN0; cnt <= CCNT; cnt++)
+		armv6_pmnc_reset_counter(cnt);
+
+	return 0;
+}
+
+static void gator_events_armv6_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv6_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv6_pmnc_read() & PMCR_E))
+		return 0;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			u32 value = 0;
+
+			switch (cnt) {
+			case CCNT:
+				asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r" (value));
+				break;
+			case PMN0:
+				asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r" (value));
+				break;
+			case PMN1:
+				asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r" (value));
+				break;
+			}
+			armv6_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv6_interface = {
+	.create_files = gator_events_armv6_create_files,
+	.stop = gator_events_armv6_stop,
+	.online = gator_events_armv6_online,
+	.offline = gator_events_armv6_offline,
+	.read = gator_events_armv6_read,
+};
+
+int gator_events_armv6_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case ARM1136:
+	case ARM1156:
+	case ARM1176:
+		pmnc_name = "ARM11";
+		break;
+	case ARM11MPCORE:
+		pmnc_name = "ARM11MPCore";
+		break;
+	default:
+		return -1;
+	}
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv6_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_armv7.c b/drivers/gator/gator_events_armv7.c
new file mode 100644
index 000000000000..09c94220114c
--- /dev/null
+++ b/drivers/gator/gator_events_armv7.c
@@ -0,0 +1,314 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*  Disabling interrupts
+ *    Many of the functions below disable interrupts via local_irq_save(). This disabling of interrupts is done to prevent any race conditions
+ *    between multiple entities (e.g. hrtimer interrupts and event based interrupts) calling the same functions. As accessing the pmu involves
+ *    several steps (disable, select, read, enable), these steps must be performed atomically. Normal synchronization routines cannot be used
+ *    as these functions are being called from interrupt context.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(6+1)
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+inline void armv7_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+inline u32 armv7_ccnt_read(u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 den = CCNT_REG;
+	u32 val;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return val;
+}
+
+inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 sel = (cnt - CNT0);
+	u32 den = 1 << sel;
+	u32 oldval;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel));	/* select */
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return oldval;
+}
+
+static inline void armv7_pmnc_disable_interrupt(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : (1 << 31);
+
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_reset_interrupt(void)
+{
+	/* Get and reset overflow status flags */
+	u32 flags;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (flags));
+	flags &= 0x8000003f;
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (flags));
+	return flags;
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+	return cnt;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val = (cnt - CNT0);
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	return cnt;
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (armv7_pmnc_select_counter(cnt) == cnt)
+		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+}
+
+static int gator_events_armv7_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv7_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (armv7_pmnc_read() & PMNC_E)
+		armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	armv7_pmnc_write(PMNC_P | PMNC_C);
+
+	/* Reset overflow flags */
+	armv7_pmnc_reset_interrupt();
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* Disable counter */
+		armv7_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			armv7_pmnc_write_evtsel(cnt, event);
+
+		armv7_pmnc_disable_interrupt(cnt);
+
+		/* Reset counter */
+		cnt ? armv7_cntn_read(cnt, 0) : armv7_ccnt_read(0);
+
+		/* Enable counter */
+		armv7_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	armv7_pmnc_write(armv7_pmnc_read() | PMNC_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv7_offline(int **buffer, bool migrate)
+{
+	/* disable all counters, including PMCCNTR; overflow IRQs will not be signaled */
+	armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	return 0;
+}
+
+static void gator_events_armv7_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv7_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv7_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = armv7_ccnt_read(0);
+			else
+				value = armv7_cntn_read(cnt, 0);
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv7_interface = {
+	.create_files = gator_events_armv7_create_files,
+	.stop = gator_events_armv7_stop,
+	.online = gator_events_armv7_online,
+	.offline = gator_events_armv7_offline,
+	.read = gator_events_armv7_read,
+};
+
+int gator_events_armv7_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case CORTEX_A5:
+		pmnc_name = "ARMv7_Cortex_A5";
+		pmnc_counters = 2;
+		break;
+	case CORTEX_A7:
+		pmnc_name = "ARMv7_Cortex_A7";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A8:
+		pmnc_name = "ARMv7_Cortex_A8";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A9:
+		pmnc_name = "ARMv7_Cortex_A9";
+		pmnc_counters = 6;
+		break;
+	case CORTEX_A15:
+		pmnc_name = "ARMv7_Cortex_A15";
+		pmnc_counters = 6;
+		break;
+	/* ARM Cortex A17 is not supported by version of Linux before 3.0 */
+	default:
+		return -1;
+	}
+
+	pmnc_counters++;	/* CNT[n] + CCNT */
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv7_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_block.c b/drivers/gator/gator_events_block.c
new file mode 100644
index 000000000000..a352a54afa02
--- /dev/null
+++ b/drivers/gator/gator_events_block.c
@@ -0,0 +1,160 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/block.h>
+
+#define BLOCK_RQ_WR		0
+#define BLOCK_RQ_RD		1
+
+#define BLOCK_TOTAL		(BLOCK_RQ_RD+1)
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+#define EVENTWRITE REQ_RW
+#else
+#define EVENTWRITE REQ_WRITE
+#endif
+
+static ulong block_rq_wr_enabled;
+static ulong block_rq_rd_enabled;
+static ulong block_rq_wr_key;
+static ulong block_rq_rd_key;
+static atomic_t blockCnt[BLOCK_TOTAL];
+static int blockGet[BLOCK_TOTAL * 4];
+
+/* Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below */
+#if OLD_BLOCK_RQ_COMPLETE
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq))
+#else
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq, unsigned int nr_bytes))
+#endif
+{
+	int write;
+	unsigned int size;
+
+	if (!rq)
+		return;
+
+	write = rq->cmd_flags & EVENTWRITE;
+#if OLD_BLOCK_RQ_COMPLETE
+	size = rq->resid_len;
+#else
+	size = nr_bytes;
+#endif
+
+	if (!size)
+		return;
+
+	if (write) {
+		if (block_rq_wr_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_WR]);
+	} else {
+		if (block_rq_rd_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_RD]);
+	}
+}
+
+static int gator_events_block_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* block_complete_wr */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_wr");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_wr_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_wr_key);
+
+	/* block_complete_rd */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_rd");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_rd_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_rd_key);
+
+	return 0;
+}
+
+static int gator_events_block_start(void)
+{
+	/* register tracepoints */
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		if (GATOR_REGISTER_TRACE(block_rq_complete))
+			goto fail_block_rq_exit;
+	pr_debug("gator: registered block event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_block_rq_exit:
+	pr_err("gator: block event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_block_stop(void)
+{
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		GATOR_UNREGISTER_TRACE(block_rq_complete);
+	pr_debug("gator: unregistered block event tracepoints\n");
+
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+}
+
+static int gator_events_block_read(int **buffer, bool sched_switch)
+{
+	int len, value, data = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	len = 0;
+	if (block_rq_wr_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_WR])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_WR]);
+		blockGet[len++] = block_rq_wr_key;
+		/* Indicates to Streamline that value bytes were written now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_wr_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+	if (block_rq_rd_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_RD])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_RD]);
+		blockGet[len++] = block_rq_rd_key;
+		/* Indicates to Streamline that value bytes were read now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_rd_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+
+	if (buffer)
+		*buffer = blockGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_block_interface = {
+	.create_files = gator_events_block_create_files,
+	.start = gator_events_block_start,
+	.stop = gator_events_block_stop,
+	.read = gator_events_block_read,
+};
+
+int gator_events_block_init(void)
+{
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+
+	block_rq_wr_key = gator_events_get_key();
+	block_rq_rd_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_block_interface);
+}
diff --git a/drivers/gator/gator_events_irq.c b/drivers/gator/gator_events_irq.c
new file mode 100644
index 000000000000..5221aac581b3
--- /dev/null
+++ b/drivers/gator/gator_events_irq.c
@@ -0,0 +1,163 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/irq.h>
+
+#define HARDIRQ		0
+#define SOFTIRQ		1
+#define TOTALIRQ	(SOFTIRQ+1)
+
+static ulong hardirq_enabled;
+static ulong softirq_enabled;
+static ulong hardirq_key;
+static ulong softirq_key;
+static DEFINE_PER_CPU(atomic_t[TOTALIRQ], irqCnt);
+static DEFINE_PER_CPU(int[TOTALIRQ * 2], irqGet);
+
+GATOR_DEFINE_PROBE(irq_handler_exit,
+		   TP_PROTO(int irq, struct irqaction *action, int ret))
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[HARDIRQ]);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 37)
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(struct softirq_action *h, struct softirq_action *vec))
+#else
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(unsigned int vec_nr))
+#endif
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[SOFTIRQ]);
+}
+
+static int gator_events_irq_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_irq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &hardirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &hardirq_key);
+
+	/* soft irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_softirq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &softirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &softirq_key);
+
+	return 0;
+}
+
+static int gator_events_irq_online(int **buffer, bool migrate)
+{
+	int len = 0, cpu = get_physical_cpu();
+
+	/* synchronization with the irq_exit functions is not necessary as the values are being reset */
+	if (hardirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[HARDIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (softirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[SOFTIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static int gator_events_irq_start(void)
+{
+	/* register tracepoints */
+	if (hardirq_enabled)
+		if (GATOR_REGISTER_TRACE(irq_handler_exit))
+			goto fail_hardirq_exit;
+	if (softirq_enabled)
+		if (GATOR_REGISTER_TRACE(softirq_exit))
+			goto fail_softirq_exit;
+	pr_debug("gator: registered irq tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_softirq_exit:
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+fail_hardirq_exit:
+	pr_err("gator: irq tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_irq_stop(void)
+{
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+	if (softirq_enabled)
+		GATOR_UNREGISTER_TRACE(softirq_exit);
+	pr_debug("gator: unregistered irq tracepoints\n");
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+}
+
+static int gator_events_irq_read(int **buffer, bool sched_switch)
+{
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (hardirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[HARDIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[HARDIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (softirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[SOFTIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[SOFTIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_irq_interface = {
+	.create_files = gator_events_irq_create_files,
+	.online = gator_events_irq_online,
+	.start = gator_events_irq_start,
+	.stop = gator_events_irq_stop,
+	.read = gator_events_irq_read,
+};
+
+int gator_events_irq_init(void)
+{
+	hardirq_key = gator_events_get_key();
+	softirq_key = gator_events_get_key();
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+
+	return gator_events_install(&gator_events_irq_interface);
+}
diff --git a/drivers/gator/gator_events_l2c-310.c b/drivers/gator/gator_events_l2c-310.c
new file mode 100644
index 000000000000..73aaac32327e
--- /dev/null
+++ b/drivers/gator/gator_events_l2c-310.c
@@ -0,0 +1,208 @@
+/**
+ * l2c310 (L2 Cache Controller) event counters for gator
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#if defined(CONFIG_OF)
+#include <linux/of.h>
+#include <linux/of_address.h>
+#endif
+#include <asm/hardware/cache-l2x0.h>
+
+#include "gator.h"
+
+#define L2C310_COUNTERS_NUM 2
+
+static struct {
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long key;
+} l2c310_counters[L2C310_COUNTERS_NUM];
+
+static int l2c310_buffer[L2C310_COUNTERS_NUM * 2];
+
+static void __iomem *l2c310_base;
+
+static void gator_events_l2c310_reset_counters(void)
+{
+	u32 val = readl(l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	val |= ((1 << L2C310_COUNTERS_NUM) - 1) << 1;
+
+	writel(val, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_create_files(struct super_block *sb,
+					    struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "L2C-310_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &l2c310_counters[i].enabled);
+		gatorfs_create_ulong(sb, dir, "event",
+				     &l2c310_counters[i].event);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&l2c310_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_l2c310_start(void)
+{
+	static const unsigned long l2x0_event_cntx_cfg[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_CFG,
+		L2X0_EVENT_CNT1_CFG,
+	};
+	int i;
+
+	/* Counter event sources */
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++)
+		writel((l2c310_counters[i].event & 0xf) << 2,
+		       l2c310_base + l2x0_event_cntx_cfg[i]);
+
+	gator_events_l2c310_reset_counters();
+
+	/* Event counter enable */
+	writel(1, l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	return 0;
+}
+
+static void gator_events_l2c310_stop(void)
+{
+	/* Event counter disable */
+	writel(0, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_read(int **buffer, bool sched_switch)
+{
+	static const unsigned long l2x0_event_cntx_val[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_VAL,
+		L2X0_EVENT_CNT1_VAL,
+	};
+	int i;
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		if (l2c310_counters[i].enabled) {
+			l2c310_buffer[len++] = l2c310_counters[i].key;
+			l2c310_buffer[len++] = readl(l2c310_base +
+						     l2x0_event_cntx_val[i]);
+		}
+	}
+
+	/* l2c310 counters are saturating, not wrapping in case of overflow */
+	gator_events_l2c310_reset_counters();
+
+	if (buffer)
+		*buffer = l2c310_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_l2c310_interface = {
+	.create_files = gator_events_l2c310_create_files,
+	.start = gator_events_l2c310_start,
+	.stop = gator_events_l2c310_stop,
+	.read = gator_events_l2c310_read,
+};
+
+#define L2C310_ADDR_PROBE (~0)
+
+MODULE_PARM_DESC(l2c310_addr, "L2C310 physical base address (0 to disable)");
+static unsigned long l2c310_addr = L2C310_ADDR_PROBE;
+module_param(l2c310_addr, ulong, 0444);
+
+static void __iomem *gator_events_l2c310_probe(void)
+{
+	phys_addr_t variants[] = {
+#if defined(CONFIG_ARCH_EXYNOS4) || defined(CONFIG_ARCH_S5PV310)
+		0x10502000,
+#endif
+#if defined(CONFIG_ARCH_OMAP4)
+		0x48242000,
+#endif
+#if defined(CONFIG_ARCH_TEGRA)
+		0x50043000,
+#endif
+#if defined(CONFIG_ARCH_U8500)
+		0xa0412000,
+#endif
+#if defined(CONFIG_ARCH_VEXPRESS)
+		0x1e00a000, /* A9x4 core tile (HBI-0191) */
+		0x2c0f0000, /* New memory map tiles */
+#endif
+	};
+	int i;
+	void __iomem *base;
+#if defined(CONFIG_OF)
+	struct device_node *node = of_find_all_nodes(NULL);
+
+	if (node) {
+		of_node_put(node);
+
+		node = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+		base = of_iomap(node, 0);
+		of_node_put(node);
+
+		return base;
+	}
+#endif
+
+	for (i = 0; i < ARRAY_SIZE(variants); i++) {
+		base = ioremap(variants[i], SZ_4K);
+		if (base) {
+			u32 cache_id = readl(base + L2X0_CACHE_ID);
+
+			if ((cache_id & 0xff0003c0) == 0x410000c0)
+				return base;
+
+			iounmap(base);
+		}
+	}
+
+	return NULL;
+}
+
+int gator_events_l2c310_init(void)
+{
+	int i;
+
+	if (gator_cpuid() != CORTEX_A5 && gator_cpuid() != CORTEX_A9)
+		return -1;
+
+	if (l2c310_addr == L2C310_ADDR_PROBE)
+		l2c310_base = gator_events_l2c310_probe();
+	else if (l2c310_addr)
+		l2c310_base = ioremap(l2c310_addr, SZ_4K);
+
+	if (!l2c310_base)
+		return -1;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		l2c310_counters[i].enabled = 0;
+		l2c310_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_l2c310_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.c b/drivers/gator/gator_events_mali_4xx.c
new file mode 100644
index 000000000000..9cf43fe2c29b
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.c
@@ -0,0 +1,622 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#include "linux/mali_linux_trace.h"
+
+#include "gator_events_mali_common.h"
+#include "gator_events_mali_4xx.h"
+
+/*
+* There have been four different variants of the comms between gator and Mali depending on driver version:
+* # | DDK vsn range             | Support                                                             | Notes
+*
+* 1 | (obsolete)                | No software counter support                                         | Obsolete patches
+* 2 | (obsolete)                | Tracepoint called for each separate s/w counter value as it appears | Obsolete patches
+* 3 | r3p0-04rel0 - r3p2-01rel2 | Single tracepoint for all s/w counters in a bundle.                 |
+* 4 | r3p2-01rel3 - date        | As above but with extensions for MP devices (Mali-450)              | At least r4p0-00rel1
+*/
+
+#if !defined(GATOR_MALI_INTERFACE_STYLE)
+#define GATOR_MALI_INTERFACE_STYLE (4)
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE == 1
+#error GATOR_MALI_INTERFACE_STYLE 1 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE == 2
+#error GATOR_MALI_INTERFACE_STYLE 2 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE >= 3
+/* Valid GATOR_MALI_INTERFACE_STYLE */
+#else
+#error Unknown GATOR_MALI_INTERFACE_STYLE option.
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE < 4
+#include "mali/mali_mjollnir_profiling_gator_api.h"
+#else
+#include "mali/mali_utgard_profiling_gator_api.h"
+#endif
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_4xx)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_4xx
+#endif
+
+static const char mali_name[] = "4xx";
+
+/* gatorfs variables for counter enable state,
+ * the event the counter should count and the
+ * 'key' (a unique id set by gatord and returned
+ * by gator.ko)
+ */
+static unsigned long counter_enabled[NUMBER_OF_EVENTS];
+static unsigned long counter_event[NUMBER_OF_EVENTS];
+static unsigned long counter_key[NUMBER_OF_EVENTS];
+
+/* The data we have recorded */
+static u32 counter_data[NUMBER_OF_EVENTS];
+/* The address to sample (or 0 if samples are sent to us) */
+static u32 *counter_address[NUMBER_OF_EVENTS];
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+static int counter_prev[NUMBER_OF_EVENTS];
+static bool prev_set[NUMBER_OF_EVENTS];
+
+/* Note whether tracepoints have been registered */
+static int trace_registered;
+
+/*
+ * These numbers define the actual numbers of each block type that exist in the system. Initially
+ * these are set to the maxima defined above; if the driver is capable of being queried (newer
+ * drivers only) then the values may be revised.
+ */
+static unsigned int n_vp_cores = MAX_NUM_VP_CORES;
+static unsigned int n_l2_cores = MAX_NUM_L2_CACHE_CORES;
+static unsigned int n_fp_cores = MAX_NUM_FP_CORES;
+
+extern struct mali_counter mali_activity[2];
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+};
+
+/**
+ * Returns non-zero if the given counter ID is an activity counter.
+ */
+static inline int is_activity_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_ACTIVITY_EVENT &&
+		event_id <= LAST_ACTIVITY_EVENT);
+}
+
+/**
+ * Returns non-zero if the given counter ID is a hardware counter.
+ */
+static inline int is_hw_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_HW_COUNTER && event_id <= LAST_HW_COUNTER);
+}
+
+/* Probe for hardware counter events */
+GATOR_DEFINE_PROBE(mali_hw_counter, TP_PROTO(unsigned int event_id, unsigned int value))
+{
+	if (is_hw_counter(event_id))
+		counter_data[event_id] = value;
+}
+
+GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surface_id, unsigned int *counters))
+{
+	u32 i;
+
+	/* Copy over the values for those counters which are enabled. */
+	for (i = FIRST_SW_COUNTER; i <= LAST_SW_COUNTER; i++) {
+		if (counter_enabled[i])
+			counter_data[i] = (u32)(counters[i - FIRST_SW_COUNTER]);
+	}
+}
+
+/**
+ * Create a single filesystem entry for a specified event.
+ * @param sb the superblock
+ * @param root Filesystem root
+ * @param name The name of the entry to create
+ * @param event The ID of the event
+ * @param create_event_item boolean indicating whether to create an 'event' filesystem entry. True to create.
+ *
+ * @return 0 if ok, non-zero if the create failed.
+ */
+static int create_fs_entry(struct super_block *sb, struct dentry *root, const char *name, int event, int create_event_item)
+{
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, name);
+
+	if (!dir)
+		return -1;
+
+	if (create_event_item)
+		gatorfs_create_ulong(sb, dir, "event", &counter_event[event]);
+
+	gatorfs_create_ulong(sb, dir, "enabled", &counter_enabled[event]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &counter_key[event]);
+
+	return 0;
+}
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+/*
+ * Read the version info structure if available
+ */
+static void initialise_version_info(void)
+{
+	void (*mali_profiling_get_mali_version_symbol)(struct _mali_profiling_mali_version *values);
+
+	mali_profiling_get_mali_version_symbol = symbol_get(_mali_profiling_get_mali_version);
+
+	if (mali_profiling_get_mali_version_symbol) {
+		struct _mali_profiling_mali_version version_info;
+
+		pr_debug("gator: mali online _mali_profiling_get_mali_version symbol @ %p\n",
+				mali_profiling_get_mali_version_symbol);
+
+		/*
+		 * Revise the number of each different core type using information derived from the DDK.
+		 */
+		mali_profiling_get_mali_version_symbol(&version_info);
+
+		n_fp_cores = version_info.num_of_fp_cores;
+		n_vp_cores = version_info.num_of_vp_cores;
+		n_l2_cores = version_info.num_of_l2_cores;
+
+		/* Release the function - we're done with it. */
+		symbol_put(_mali_profiling_get_mali_version);
+	} else {
+		pr_err("gator: mali online _mali_profiling_get_mali_version symbol not found\n");
+		pr_err("gator:  check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n");
+	}
+}
+#endif
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+
+	char buf[40];
+	int core_id;
+	int counter_number;
+
+	pr_debug("gator: Initialising counters with style = %d\n", GATOR_MALI_INTERFACE_STYLE);
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+	/*
+	 * Initialise first: this sets up the number of cores available (on compatible DDK versions).
+	 * Ideally this would not need guarding but other parts of the code depend on the interface style being set
+	 * correctly; if it is not then the system can enter an inconsistent state.
+	 */
+	initialise_version_info();
+#endif
+
+	mali_activity[0].cores = n_fp_cores;
+	mali_activity[1].cores = n_vp_cores;
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	/* Vertex processor counters */
+	for (core_id = 0; core_id < n_vp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_VP_0;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_VP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Fragment processors' counters */
+	for (core_id = 0; core_id < n_fp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_FP_0 + core_id;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_FP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* L2 Cache counters */
+	for (core_id = 0; core_id < n_l2_cores; core_id++) {
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_L2_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_L2_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Now set up the software counter entries */
+	for (event = FIRST_SW_COUNTER; event <= LAST_SW_COUNTER; event++) {
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_SW_%d", mali_name, event - FIRST_SW_COUNTER);
+
+		if (create_fs_entry(sb, root, buf, event, 0) != 0)
+			return -1;
+	}
+
+	/* Now set up the special counter entries */
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Filmstrip_cnt0", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0)
+		return -1;
+
+#ifdef DVFS_REPORTED_BY_DDK
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Frequency", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0)
+		return -1;
+
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Voltage", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0)
+		return -1;
+#endif
+
+	return 0;
+}
+
+/*
+ * Local store for the get_counters entry point into the DDK.
+ * This is stored here since it is used very regularly.
+ */
+static void (*mali_get_counters)(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+static u32 (*mali_get_l2_counters)(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * Examine list of counters between two index limits and determine if any one is enabled.
+ * Returns 1 if any counter is enabled, 0 if none is.
+ */
+static int is_any_counter_enabled(unsigned int first_counter, unsigned int last_counter)
+{
+	unsigned int i;
+
+	for (i = first_counter; i <= last_counter; i++) {
+		if (counter_enabled[i])
+			return 1;	/* At least one counter is enabled */
+	}
+
+	return 0;		/* No s/w counters enabled */
+}
+
+static void init_counters(unsigned int from_counter, unsigned int to_counter)
+{
+	unsigned int counter_id;
+
+	/* If a Mali driver is present and exporting the appropriate symbol
+	 * then we can request the HW counters (of which there are only 2)
+	 * be configured to count the desired events
+	 */
+	mali_profiling_set_event_type *mali_set_hw_event;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		pr_debug("gator: mali online _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+
+		for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+			if (counter_enabled[counter_id])
+				mali_set_hw_event(counter_id, counter_event[counter_id]);
+			else
+				mali_set_hw_event(counter_id, 0xFFFFFFFF);
+		}
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali online _mali_profiling_set_event symbol not found\n");
+	}
+}
+
+static void mali_counter_initialize(void)
+{
+	int i;
+
+	mali_profiling_control_type *mali_control;
+
+	init_counters(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores) - 1);
+	init_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1);
+	init_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1);
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int rate = counter_event[COUNTER_FILMSTRIP] & 0xff;
+		unsigned int resize_factor = (counter_event[COUNTER_FILMSTRIP] >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(SW_COUNTER_ENABLE, (is_any_counter_enabled(FIRST_SW_COUNTER, LAST_SW_COUNTER) ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_ENABLE, (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d\n", (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0), rate);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	mali_get_counters = symbol_get(_mali_profiling_get_counters);
+	if (mali_get_counters)
+		pr_debug("gator: mali online _mali_profiling_get_counters symbol @ %p\n", mali_get_counters);
+	else
+		pr_debug("gator WARNING: mali _mali_profiling_get_counters symbol not defined\n");
+
+	mali_get_l2_counters = symbol_get(_mali_profiling_get_l2_counters);
+	if (mali_get_l2_counters)
+		pr_debug("gator: mali online _mali_profiling_get_l2_counters symbol @ %p\n", mali_get_l2_counters);
+	else
+		pr_debug("gator WARNING: mali _mali_profiling_get_l2_counters symbol not defined\n");
+
+	if (!mali_get_counters && !mali_get_l2_counters) {
+		pr_debug("gator: WARNING: no L2 counters available\n");
+		n_l2_cores = 0;
+	}
+
+	/* Clear counters in the start */
+	for (i = 0; i < NUMBER_OF_EVENTS; i++) {
+		counter_data[i] = 0;
+		prev_set[i] = false;
+	}
+}
+
+static void mali_counter_deinitialize(void)
+{
+	mali_profiling_set_event_type *mali_set_hw_event;
+	mali_profiling_control_type *mali_control;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		int i;
+
+		pr_debug("gator: mali offline _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+		for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++)
+			mali_set_hw_event(i, 0xFFFFFFFF);
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_set_event symbol not found\n");
+	}
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		/* Reset the DDK state - disable counter collection */
+		mali_control(SW_COUNTER_ENABLE, 0);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+
+	if (mali_get_counters)
+		symbol_put(_mali_profiling_get_counters);
+
+	if (mali_get_l2_counters)
+		symbol_put(_mali_profiling_get_l2_counters);
+}
+
+static int start(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(mali_hw_counter)) {
+		pr_err("gator: mali_hw_counter tracepoint failed to activate\n");
+		return -1;
+	}
+
+	/* For Mali drivers with built-in support. */
+	if (GATOR_REGISTER_TRACE(mali_sw_counters)) {
+		pr_err("gator: mali_sw_counters tracepoint failed to activate\n");
+		return -1;
+	}
+
+	trace_registered = 1;
+
+	mali_counter_initialize();
+	return 0;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali stop\n");
+
+	if (trace_registered) {
+		GATOR_UNREGISTER_TRACE(mali_hw_counter);
+
+		/* For Mali drivers with built-in support. */
+		GATOR_UNREGISTER_TRACE(mali_sw_counters);
+
+		pr_debug("gator: mali timeline tracepoint deactivated\n");
+
+		trace_registered = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+		counter_address[cnt] = NULL;
+	}
+
+	mali_counter_deinitialize();
+}
+
+static void dump_counters(unsigned int from_counter, unsigned int to_counter, unsigned int *len)
+{
+	unsigned int counter_id;
+
+	for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+		if (counter_enabled[counter_id]) {
+			counter_dump[(*len)++] = counter_key[counter_id];
+			counter_dump[(*len)++] = counter_data[counter_id];
+
+			counter_data[counter_id] = 0;
+		}
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Read the L2 C0 and C1 here. */
+	if (n_l2_cores > 0 && is_any_counter_enabled(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores))) {
+		unsigned int unavailable_l2_caches = 0;
+		struct _mali_profiling_l2_counter_values cache_values;
+		unsigned int cache_id;
+		struct _mali_profiling_core_counters *per_core;
+
+		/* Poke the driver to get the counter values - older style; only one L2 cache */
+		if (mali_get_l2_counters) {
+			unavailable_l2_caches = mali_get_l2_counters(&cache_values);
+		} else if (mali_get_counters) {
+			per_core = &cache_values.cores[0];
+			mali_get_counters(&per_core->source0, &per_core->value0, &per_core->source1, &per_core->value1);
+		} else {
+			/* This should never happen, as n_l2_caches is only set > 0 if one of the above functions is found. */
+		}
+
+		/* Fill in the two cache counter values for each cache block. */
+		for (cache_id = 0; cache_id < n_l2_cores; cache_id++) {
+			unsigned int counter_id_0 = COUNTER_L2_0_C0 + (2 * cache_id);
+			unsigned int counter_id_1 = counter_id_0 + 1;
+
+			if ((1 << cache_id) & unavailable_l2_caches)
+				continue; /* This cache is unavailable (powered-off, possibly). */
+
+			per_core = &cache_values.cores[cache_id];
+
+			if (counter_enabled[counter_id_0] && prev_set[counter_id_0]) {
+				/* Calculate and save src0's counter val0 */
+				counter_dump[len++] = counter_key[counter_id_0];
+				counter_dump[len++] = per_core->value0 - counter_prev[counter_id_0];
+			}
+
+			if (counter_enabled[counter_id_1] && prev_set[counter_id_1]) {
+				/* Calculate and save src1's counter val1 */
+				counter_dump[len++] = counter_key[counter_id_1];
+				counter_dump[len++] = per_core->value1 - counter_prev[counter_id_1];
+			}
+
+			/* Save the previous values for the counters. */
+			counter_prev[counter_id_0] = per_core->value0;
+			prev_set[counter_id_0] = true;
+			counter_prev[counter_id_1] = per_core->value1;
+			prev_set[counter_id_1] = true;
+		}
+	}
+
+	/* Process other (non-timeline) counters. */
+	dump_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1, &len);
+	dump_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1, &len);
+
+	dump_counters(FIRST_SW_COUNTER, LAST_SW_COUNTER, &len);
+
+#ifdef DVFS_REPORTED_BY_DDK
+	{
+		int cnt;
+		/*
+		 * Add in the voltage and frequency counters if enabled. Note
+		 * that, since these are actually passed as events, the counter
+		 * value should not be cleared.
+		 */
+		cnt = COUNTER_FREQUENCY;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = counter_data[cnt];
+		}
+
+		cnt = COUNTER_VOLTAGE;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = counter_data[cnt];
+		}
+	}
+#endif
+
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_interface = {
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read,
+};
+
+extern void gator_events_mali_log_dvfs_event(unsigned int frequency_mhz, unsigned int voltage_mv)
+{
+#ifdef DVFS_REPORTED_BY_DDK
+	counter_data[COUNTER_FREQUENCY] = frequency_mhz;
+	counter_data[COUNTER_VOLTAGE] = voltage_mv;
+#endif
+}
+
+int gator_events_mali_init(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali init\n");
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+		counter_key[cnt] = gator_events_get_key();
+		counter_address[cnt] = NULL;
+		counter_data[cnt] = 0;
+	}
+
+	trace_registered = 0;
+
+	return gator_events_install(&gator_events_mali_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.h b/drivers/gator/gator_events_mali_4xx.h
new file mode 100644
index 000000000000..976ca8c4cfa1
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * Header contains common definitions for the Mali-4xx processors.
+ */
+#if !defined(GATOR_EVENTS_MALI_4xx_H)
+#define GATOR_EVENTS_MALI_4xx_H
+
+extern void gator_events_mali_log_dvfs_event(unsigned int d0, unsigned int d1);
+
+#endif /* GATOR_EVENTS_MALI_4xx_H */
diff --git a/drivers/gator/gator_events_mali_common.c b/drivers/gator/gator_events_mali_common.c
new file mode 100644
index 000000000000..1af87d649afe
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.c
@@ -0,0 +1,72 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include "gator_events_mali_common.h"
+
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event)
+{
+	int err;
+	char buf[255];
+	struct dentry *dir;
+
+	/* If the counter name is empty ignore it */
+	if (strlen(event_name) != 0) {
+		/* Set up the filesystem entry for this event. */
+		if (mali_name == NULL)
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s", event_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_%s", mali_name, event_name);
+
+		dir = gatorfs_mkdir(sb, root, buf);
+
+		if (dir == NULL) {
+			pr_debug("gator: %s: error creating file system for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+
+		err = gatorfs_create_ulong(sb, dir, "enabled", &counter->enabled);
+		if (err != 0) {
+			pr_debug("gator: %s: error calling gatorfs_create_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		err = gatorfs_create_ro_ulong(sb, dir, "key", &counter->key);
+		if (err != 0) {
+			pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		if (counter->cores != -1) {
+			err = gatorfs_create_ro_ulong(sb, dir, "cores", &counter->cores);
+			if (err != 0) {
+				pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+		if (event != NULL) {
+			err = gatorfs_create_ulong(sb, dir, "event", event);
+			if (err != 0) {
+				pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters)
+{
+	unsigned int cnt;
+
+	for (cnt = 0; cnt < n_counters; cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		counter->key = gator_events_get_key();
+		counter->enabled = 0;
+		counter->cores = -1;
+	}
+}
diff --git a/drivers/gator/gator_events_mali_common.h b/drivers/gator/gator_events_mali_common.h
new file mode 100644
index 000000000000..e7082e62fe88
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.h
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if !defined(GATOR_EVENTS_MALI_COMMON_H)
+#define GATOR_EVENTS_MALI_COMMON_H
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Ensure that MALI_SUPPORT has been defined to something. */
+#ifndef MALI_SUPPORT
+#error MALI_SUPPORT not defined!
+#endif
+
+/* Values for the supported activity event types */
+#define ACTIVITY_START  (1)
+#define ACTIVITY_STOP   (2)
+
+/*
+ * Runtime state information for a counter.
+ */
+struct mali_counter {
+	/* 'key' (a unique id set by gatord and returned by gator.ko) */
+	unsigned long key;
+	/* counter enable state */
+	unsigned long enabled;
+	/* for activity counters, the number of cores, otherwise -1 */
+	unsigned long cores;
+};
+
+/*
+ * Mali-4xx
+ */
+typedef int mali_profiling_set_event_type(unsigned int, int);
+typedef void mali_profiling_control_type(unsigned int, unsigned int);
+
+/*
+ * Driver entry points for functions called directly by gator.
+ */
+extern int _mali_profiling_set_event(unsigned int, int);
+extern void _mali_profiling_control(unsigned int, unsigned int);
+extern void _mali_profiling_get_counters(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+
+/**
+ * Creates a filesystem entry under /dev/gator relating to the specified event name and key, and
+ * associate the key/enable values with this entry point.
+ *
+ * @param event_name The name of the event.
+ * @param sb Linux super block
+ * @param root Directory under which the entry will be created.
+ * @param counter_key Ptr to location which will be associated with the counter key.
+ * @param counter_enabled Ptr to location which will be associated with the counter enable state.
+ *
+ * @return 0 if entry point was created, non-zero if not.
+ */
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event);
+
+/**
+ * Initializes the counter array.
+ *
+ * @param keys The array of counters
+ * @param n_counters The number of entries in each of the arrays.
+ */
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters);
+
+#endif /* GATOR_EVENTS_MALI_COMMON_H  */
diff --git a/drivers/gator/gator_events_mali_midgard.c b/drivers/gator/gator_events_mali_midgard.c
new file mode 100644
index 000000000000..0aec906d7ae5
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard.c
@@ -0,0 +1,562 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_MIDGARD)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_MIDGARD
+#endif
+
+static const char mali_name[] = "Midgard";
+
+/* Counters for Mali-Midgard:
+ *
+ *  - Timeline events
+ *    They are tracepoints, but instead of reporting a number they report a START/STOP event.
+ *    They are reported in Streamline as number of microseconds while that particular counter was active.
+ *
+ *  - SW counters
+ *    They are tracepoints reporting a particular number.
+ *    They are accumulated in sw_counter_data array until they are passed to Streamline, then they are zeroed.
+ *
+ *  - Accumulators
+ *    They are the same as software counters but their value is not zeroed.
+ */
+
+/* Timeline (start/stop) activity */
+static const char *const timeline_event_names[] = {
+	"PM_SHADER_0",
+	"PM_SHADER_1",
+	"PM_SHADER_2",
+	"PM_SHADER_3",
+	"PM_SHADER_4",
+	"PM_SHADER_5",
+	"PM_SHADER_6",
+	"PM_SHADER_7",
+	"PM_TILER_0",
+	"PM_L2_0",
+	"PM_L2_1",
+	"MMU_AS_0",
+	"MMU_AS_1",
+	"MMU_AS_2",
+	"MMU_AS_3"
+};
+
+enum {
+	PM_SHADER_0 = 0,
+	PM_SHADER_1,
+	PM_SHADER_2,
+	PM_SHADER_3,
+	PM_SHADER_4,
+	PM_SHADER_5,
+	PM_SHADER_6,
+	PM_SHADER_7,
+	PM_TILER_0,
+	PM_L2_0,
+	PM_L2_1,
+	MMU_AS_0,
+	MMU_AS_1,
+	MMU_AS_2,
+	MMU_AS_3
+};
+/* The number of shader blocks in the enum above */
+#define NUM_PM_SHADER (8)
+
+/* Software Counters */
+static const char *const software_counter_names[] = {
+	"MMU_PAGE_FAULT_0",
+	"MMU_PAGE_FAULT_1",
+	"MMU_PAGE_FAULT_2",
+	"MMU_PAGE_FAULT_3"
+};
+
+enum {
+	MMU_PAGE_FAULT_0 = 0,
+	MMU_PAGE_FAULT_1,
+	MMU_PAGE_FAULT_2,
+	MMU_PAGE_FAULT_3
+};
+
+/* Software Counters */
+static const char *const accumulators_names[] = {
+	"TOTAL_ALLOC_PAGES"
+};
+
+enum {
+	TOTAL_ALLOC_PAGES = 0
+};
+
+#define FIRST_TIMELINE_EVENT (0)
+#define NUMBER_OF_TIMELINE_EVENTS (sizeof(timeline_event_names) / sizeof(timeline_event_names[0]))
+#define FIRST_SOFTWARE_COUNTER (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS)
+#define NUMBER_OF_SOFTWARE_COUNTERS (sizeof(software_counter_names) / sizeof(software_counter_names[0]))
+#define FIRST_ACCUMULATOR (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS)
+#define NUMBER_OF_ACCUMULATORS (sizeof(accumulators_names) / sizeof(accumulators_names[0]))
+#define FILMSTRIP (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS)
+#define NUMBER_OF_EVENTS (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS + 1)
+
+/*
+ * gatorfs variables for counter enable state
+ */
+static struct mali_counter counters[NUMBER_OF_EVENTS];
+static unsigned long filmstrip_event;
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+
+/*
+ * Array holding counter start times (in ns) for each counter. A zero
+ * here indicates that the activity monitored by this counter is not
+ * running.
+ */
+static struct timespec timeline_event_starttime[NUMBER_OF_TIMELINE_EVENTS];
+
+/* The data we have recorded */
+static unsigned int timeline_data[NUMBER_OF_TIMELINE_EVENTS];
+static unsigned int sw_counter_data[NUMBER_OF_SOFTWARE_COUNTERS];
+static unsigned int accumulators_data[NUMBER_OF_ACCUMULATORS];
+
+/* Hold the previous timestamp, used to calculate the sample interval. */
+static struct timespec prev_timestamp;
+
+/**
+ * Returns the timespan (in microseconds) between the two specified timestamps.
+ *
+ * @param start Ptr to the start timestamp
+ * @param end Ptr to the end timestamp
+ *
+ * @return Number of microseconds between the two timestamps (can be negative if start follows end).
+ */
+static inline long get_duration_us(const struct timespec *start, const struct timespec *end)
+{
+	long event_duration_us = (end->tv_nsec - start->tv_nsec) / 1000;
+
+	event_duration_us += (end->tv_sec - start->tv_sec) * 1000000;
+
+	return event_duration_us;
+}
+
+static void record_timeline_event(unsigned int timeline_index, unsigned int type)
+{
+	struct timespec event_timestamp;
+	struct timespec *event_start = &timeline_event_starttime[timeline_index];
+
+	switch (type) {
+	case ACTIVITY_START:
+		/* Get the event time... */
+		getnstimeofday(&event_timestamp);
+
+		/* Remember the start time if the activity is not already started */
+		if (event_start->tv_sec == 0)
+			*event_start = event_timestamp;	/* Structure copy */
+		break;
+
+	case ACTIVITY_STOP:
+		/* if the counter was started... */
+		if (event_start->tv_sec != 0) {
+			/* Get the event time... */
+			getnstimeofday(&event_timestamp);
+
+			/* Accumulate the duration in us */
+			timeline_data[timeline_index] += get_duration_us(event_start, &event_timestamp);
+
+			/* Reset the start time to indicate the activity is stopped. */
+			event_start->tv_sec = 0;
+		}
+		break;
+
+	default:
+		/* Other activity events are ignored. */
+		break;
+	}
+}
+
+/*
+ * Documentation about the following tracepoints is in mali_linux_trace.h
+ */
+
+GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long long value))
+{
+#define SHADER_PRESENT_LO       0x100	/* (RO) Shader core present bitmap, low word */
+#define TILER_PRESENT_LO        0x110	/* (RO) Tiler core present bitmap, low word */
+#define L2_PRESENT_LO           0x120	/* (RO) Level 2 cache present bitmap, low word */
+#define BIT_AT(value, pos) ((value >> pos) & 1)
+
+	static unsigned long long previous_shader_bitmask;
+	static unsigned long long previous_tiler_bitmask;
+	static unsigned long long previous_l2_bitmask;
+
+	switch (event_id) {
+	case SHADER_PRESENT_LO:
+		{
+			unsigned long long changed_bitmask = previous_shader_bitmask ^ value;
+			int pos;
+
+			for (pos = 0; pos < NUM_PM_SHADER; ++pos) {
+				if (BIT_AT(changed_bitmask, pos))
+					record_timeline_event(PM_SHADER_0 + pos, BIT_AT(value, pos) ? ACTIVITY_START : ACTIVITY_STOP);
+			}
+
+			previous_shader_bitmask = value;
+			break;
+		}
+
+	case TILER_PRESENT_LO:
+		{
+			unsigned long long changed = previous_tiler_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_TILER_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_tiler_bitmask = value;
+			break;
+		}
+
+	case L2_PRESENT_LO:
+		{
+			unsigned long long changed = previous_l2_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_L2_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+			if (BIT_AT(changed, 4))
+				record_timeline_event(PM_L2_1, BIT_AT(value, 4) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_l2_bitmask = value;
+			break;
+		}
+
+	default:
+		/* No other blocks are supported at present */
+		break;
+	}
+
+#undef SHADER_PRESENT_LO
+#undef TILER_PRESENT_LO
+#undef L2_PRESENT_LO
+#undef BIT_AT
+}
+
+GATOR_DEFINE_PROBE(mali_page_fault_insert_pages, TP_PROTO(int event_id, unsigned long value))
+{
+	/* We add to the previous since we may receive many tracepoints in one sample period */
+	sw_counter_data[MMU_PAGE_FAULT_0 + event_id] += value;
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_in_use, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_START);
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_released, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_STOP);
+}
+
+GATOR_DEFINE_PROBE(mali_total_alloc_pages_change, TP_PROTO(long long int event_id))
+{
+	accumulators_data[TOTAL_ALLOC_PAGES] = event_id;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	int counter_index = 0;
+	mali_profiling_control_type *mali_control;
+
+	for (event = FIRST_TIMELINE_EVENT; event < FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS; event++) {
+		if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_SOFTWARE_COUNTER; event < FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS; event++) {
+		if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_ACCUMULATOR; event < FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS; event++) {
+		if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0)
+			return -1;
+		symbol_put(_mali_profiling_control);
+	}
+
+	return 0;
+}
+
+static int register_tracepoints(void)
+{
+	if (GATOR_REGISTER_TRACE(mali_pm_status)) {
+		pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_page_fault_insert_pages)) {
+		pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_in_use)) {
+		pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_released)) {
+		pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_total_alloc_pages_change)) {
+		pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint failed to activate\n");
+		return 0;
+	}
+
+	pr_debug("gator: Mali-Midgard: start\n");
+	pr_debug("gator: Mali-Midgard: mali_pm_status probe is at %p\n", &probe_mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change);
+
+	return 1;
+}
+
+static int start(void)
+{
+	unsigned int cnt;
+	mali_profiling_control_type *mali_control;
+
+	/* Clean all data for the next capture */
+	for (cnt = 0; cnt < NUMBER_OF_TIMELINE_EVENTS; cnt++) {
+		timeline_event_starttime[cnt].tv_sec = timeline_event_starttime[cnt].tv_nsec = 0;
+		timeline_data[cnt] = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++)
+		sw_counter_data[cnt] = 0;
+
+	for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++)
+		accumulators_data[cnt] = 0;
+
+	/* Register tracepoints */
+	if (register_tracepoints() == 0)
+		return -1;
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int enabled = counters[FILMSTRIP].enabled ? 1 : 0;
+		unsigned int rate = filmstrip_event & 0xff;
+		unsigned int resize_factor = (filmstrip_event >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+		mali_control(FBDUMP_CONTROL_ENABLE, enabled);
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d, resize_factor=%d\n", enabled, rate, resize_factor);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	/*
+	 * Set the first timestamp for calculating the sample interval. The first interval could be quite long,
+	 * since it will be the time between 'start' and the first 'read'.
+	 * This means that timeline values will be divided by a big number for the first sample.
+	 */
+	getnstimeofday(&prev_timestamp);
+
+	return 0;
+}
+
+static void stop(void)
+{
+	mali_profiling_control_type *mali_control;
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/*
+	 * It is safe to unregister traces even if they were not successfully
+	 * registered, so no need to check.
+	 */
+	GATOR_UNREGISTER_TRACE(mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_total_alloc_pages_change);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint deactivated\n");
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	long sample_interval_us = 0;
+	struct timespec read_timestamp;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Get the start of this sample period. */
+	getnstimeofday(&read_timestamp);
+
+	/*
+	 * Calculate the sample interval if the previous sample time is valid.
+	 * We use tv_sec since it will not be 0.
+	 */
+	if (prev_timestamp.tv_sec != 0)
+		sample_interval_us = get_duration_us(&prev_timestamp, &read_timestamp);
+
+	/* Structure copy. Update the previous timestamp. */
+	prev_timestamp = read_timestamp;
+
+	/*
+	 * Report the timeline counters (ACTIVITY_START/STOP)
+	 */
+	for (cnt = FIRST_TIMELINE_EVENT; cnt < (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS); cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_TIMELINE_EVENT;
+			unsigned int value;
+
+			/* If the activity is still running, reset its start time to the
+			 * start of this sample period to correct the count. Add the
+			 * time up to the end of the sample onto the count.
+			 */
+			if (timeline_event_starttime[index].tv_sec != 0) {
+				const long event_duration = get_duration_us(&timeline_event_starttime[index], &read_timestamp);
+
+				timeline_data[index] += event_duration;
+				timeline_event_starttime[index] = read_timestamp;	/* Activity is still running. */
+			}
+
+			if (sample_interval_us != 0) {
+				/* Convert the counter to a percent-of-sample value */
+				value = (timeline_data[index] * 100) / sample_interval_us;
+			} else {
+				pr_debug("gator: Mali-Midgard: setting value to zero\n");
+				value = 0;
+			}
+
+			/* Clear the counter value ready for the next sample. */
+			timeline_data[index] = 0;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = value;
+		}
+	}
+
+	/* Report the software counters */
+	for (cnt = FIRST_SOFTWARE_COUNTER; cnt < (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_SOFTWARE_COUNTER;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = sw_counter_data[index];
+			/* Set the value to zero for the next time */
+			sw_counter_data[index] = 0;
+		}
+	}
+
+	/* Report the accumulators */
+	for (cnt = FIRST_ACCUMULATOR; cnt < (FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_ACCUMULATOR;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = accumulators_data[index];
+			/* Do not zero the accumulator */
+		}
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read
+};
+
+extern int gator_events_mali_midgard_init(void)
+{
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+	gator_mali_initialise_counters(counters, NUMBER_OF_EVENTS);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw.c b/drivers/gator/gator_events_mali_midgard_hw.c
new file mode 100644
index 000000000000..c8065da56815
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw.c
@@ -0,0 +1,977 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Mali Midgard DDK includes */
+#if defined(MALI_SIMPLE_API)
+/* Header with wrapper functions to kbase structures and functions */
+#include "mali/mali_kbase_gator_api.h"
+#elif defined(MALI_DIR_MIDGARD)
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard */
+#include "mali_linux_trace.h"
+#include "mali_kbase.h"
+#include "mali_kbase_mem_linux.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx */
+#include "linux/mali_linux_trace.h"
+#include "kbase/src/common/mali_kbase.h"
+#include "kbase/src/linux/mali_kbase_mem_linux.h"
+#endif
+
+/* If API version is not specified then assume API version 1. */
+#ifndef MALI_DDK_GATOR_API_VERSION
+#define MALI_DDK_GATOR_API_VERSION 1
+#endif
+
+#if (MALI_DDK_GATOR_API_VERSION != 1) && (MALI_DDK_GATOR_API_VERSION != 2) && (MALI_DDK_GATOR_API_VERSION != 3)
+#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3/r4 DDK, or 3 for r5 and later DDK).
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Mali-Midgard
+ */
+#if MALI_DDK_GATOR_API_VERSION == 3
+static uint32_t (*kbase_gator_instr_hwcnt_dump_irq_symbol)(struct kbase_gator_hwcnt_handles *);
+static uint32_t (*kbase_gator_instr_hwcnt_dump_complete_symbol)(struct kbase_gator_hwcnt_handles *, uint32_t *const);
+static struct kbase_gator_hwcnt_handles *(*kbase_gator_hwcnt_init_symbol)(struct kbase_gator_hwcnt_info *);
+static void (*kbase_gator_hwcnt_term_symbol)(struct kbase_gator_hwcnt_info *, struct kbase_gator_hwcnt_handles *);
+
+#else
+static struct kbase_device *(*kbase_find_device_symbol)(int);
+static struct kbase_context *(*kbase_create_context_symbol)(struct kbase_device *);
+static void (*kbase_destroy_context_symbol)(struct kbase_context *);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32);
+static void (*kbase_va_free_symbol)(struct kbase_context *, void *);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32, struct kbase_hwc_dma_mapping *);
+static void (*kbase_va_free_symbol)(struct kbase_context *, struct kbase_hwc_dma_mapping *);
+#endif
+
+static mali_error (*kbase_instr_hwcnt_enable_symbol)(struct kbase_context *, struct kbase_uk_hwcnt_setup *);
+static mali_error (*kbase_instr_hwcnt_disable_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_clear_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_dump_irq_symbol)(struct kbase_context *);
+static mali_bool (*kbase_instr_hwcnt_dump_complete_symbol)(struct kbase_context *, mali_bool *);
+
+static long shader_present_low;
+#endif
+
+/** The interval between reads, in ns.
+ *
+ * Earlier we introduced a 'hold off for 1ms after last read' to
+ * resolve MIDBASE-2178 and MALINE-724. However, the 1ms hold off is
+ * too long if no context switches occur as there is a race between
+ * this value and the tick of the read clock in gator which is also
+ * 1ms. If we 'miss' the current read, the counter values are
+ * effectively 'spread' over 2ms and the values seen are half what
+ * they should be (since Streamline averages over sample time). In the
+ * presence of context switches this spread can vary and markedly
+ * affect the counters. Currently there is no 'proper' solution to
+ * this, but empirically we have found that reducing the minimum read
+ * interval to 950us causes the counts to be much more stable.
+ */
+static const int READ_INTERVAL_NSEC = 950000;
+
+#if GATOR_TEST
+#include "gator_events_mali_midgard_hw_test.c"
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION != 3
+/* Blocks for HW counters */
+enum {
+	JM_BLOCK = 0,
+	TILER_BLOCK,
+	SHADER_BLOCK,
+	MMU_BLOCK
+};
+#endif
+
+static const char *mali_name;
+
+/* Counters for Mali-Midgard:
+ *
+ *    For HW counters we need strings to create /dev/gator/events files.
+ *    Enums are not needed because the position of the HW name in the array is the same
+ *    of the corresponding value in the received block of memory.
+ *    HW counters are requested by calculating a bitmask, passed then to the driver.
+ *    Every millisecond a HW counters dump is requested, and if the previous has been completed they are read.
+ */
+
+/* Hardware Counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+
+static const char *const *hardware_counter_names;
+static int number_of_hardware_counters;
+
+#else
+
+static const char *const hardware_counter_names[] = {
+	/* Job Manager */
+	"",
+	"",
+	"",
+	"",
+	"MESSAGES_SENT",
+	"MESSAGES_RECEIVED",
+	"GPU_ACTIVE",		/* 6 */
+	"IRQ_ACTIVE",
+	"JS0_JOBS",
+	"JS0_TASKS",
+	"JS0_ACTIVE",
+	"",
+	"JS0_WAIT_READ",
+	"JS0_WAIT_ISSUE",
+	"JS0_WAIT_DEPEND",
+	"JS0_WAIT_FINISH",
+	"JS1_JOBS",
+	"JS1_TASKS",
+	"JS1_ACTIVE",
+	"",
+	"JS1_WAIT_READ",
+	"JS1_WAIT_ISSUE",
+	"JS1_WAIT_DEPEND",
+	"JS1_WAIT_FINISH",
+	"JS2_JOBS",
+	"JS2_TASKS",
+	"JS2_ACTIVE",
+	"",
+	"JS2_WAIT_READ",
+	"JS2_WAIT_ISSUE",
+	"JS2_WAIT_DEPEND",
+	"JS2_WAIT_FINISH",
+	"JS3_JOBS",
+	"JS3_TASKS",
+	"JS3_ACTIVE",
+	"",
+	"JS3_WAIT_READ",
+	"JS3_WAIT_ISSUE",
+	"JS3_WAIT_DEPEND",
+	"JS3_WAIT_FINISH",
+	"JS4_JOBS",
+	"JS4_TASKS",
+	"JS4_ACTIVE",
+	"",
+	"JS4_WAIT_READ",
+	"JS4_WAIT_ISSUE",
+	"JS4_WAIT_DEPEND",
+	"JS4_WAIT_FINISH",
+	"JS5_JOBS",
+	"JS5_TASKS",
+	"JS5_ACTIVE",
+	"",
+	"JS5_WAIT_READ",
+	"JS5_WAIT_ISSUE",
+	"JS5_WAIT_DEPEND",
+	"JS5_WAIT_FINISH",
+	"JS6_JOBS",
+	"JS6_TASKS",
+	"JS6_ACTIVE",
+	"",
+	"JS6_WAIT_READ",
+	"JS6_WAIT_ISSUE",
+	"JS6_WAIT_DEPEND",
+	"JS6_WAIT_FINISH",
+
+	/*Tiler */
+	"",
+	"",
+	"",
+	"JOBS_PROCESSED",
+	"TRIANGLES",
+	"QUADS",
+	"POLYGONS",
+	"POINTS",
+	"LINES",
+	"VCACHE_HIT",
+	"VCACHE_MISS",
+	"FRONT_FACING",
+	"BACK_FACING",
+	"PRIM_VISIBLE",
+	"PRIM_CULLED",
+	"PRIM_CLIPPED",
+	"LEVEL0",
+	"LEVEL1",
+	"LEVEL2",
+	"LEVEL3",
+	"LEVEL4",
+	"LEVEL5",
+	"LEVEL6",
+	"LEVEL7",
+	"COMMAND_1",
+	"COMMAND_2",
+	"COMMAND_3",
+	"COMMAND_4",
+	"COMMAND_4_7",
+	"COMMAND_8_15",
+	"COMMAND_16_63",
+	"COMMAND_64",
+	"COMPRESS_IN",
+	"COMPRESS_OUT",
+	"COMPRESS_FLUSH",
+	"TIMESTAMPS",
+	"PCACHE_HIT",
+	"PCACHE_MISS",
+	"PCACHE_LINE",
+	"PCACHE_STALL",
+	"WRBUF_HIT",
+	"WRBUF_MISS",
+	"WRBUF_LINE",
+	"WRBUF_PARTIAL",
+	"WRBUF_STALL",
+	"ACTIVE",
+	"LOADING_DESC",
+	"INDEX_WAIT",
+	"INDEX_RANGE_WAIT",
+	"VERTEX_WAIT",
+	"PCACHE_WAIT",
+	"WRBUF_WAIT",
+	"BUS_READ",
+	"BUS_WRITE",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_STALL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_NEW_MISS",
+	"UTLB_HIT",
+
+	/* Shader Core */
+	"",
+	"",
+	"",
+	"SHADER_CORE_ACTIVE",
+	"FRAG_ACTIVE",
+	"FRAG_PRIMATIVES",
+	"FRAG_PRIMATIVES_DROPPED",
+	"FRAG_CYCLE_DESC",
+	"FRAG_CYCLES_PLR",
+	"FRAG_CYCLES_VERT",
+	"FRAG_CYCLES_TRISETUP",
+	"FRAG_CYCLES_RAST",
+	"FRAG_THREADS",
+	"FRAG_DUMMY_THREADS",
+	"FRAG_QUADS_RAST",
+	"FRAG_QUADS_EZS_TEST",
+	"FRAG_QUADS_EZS_KILLED",
+	"FRAG_QUADS_LZS_TEST",
+	"FRAG_QUADS_LZS_KILLED",
+	"FRAG_CYCLE_NO_TILE",
+	"FRAG_NUM_TILES",
+	"FRAG_TRANS_ELIM",
+	"COMPUTE_ACTIVE",
+	"COMPUTE_TASKS",
+	"COMPUTE_THREADS",
+	"COMPUTE_CYCLES_DESC",
+	"TRIPIPE_ACTIVE",
+	"ARITH_WORDS",
+	"ARITH_CYCLES_REG",
+	"ARITH_CYCLES_L0",
+	"ARITH_FRAG_DEPEND",
+	"LS_WORDS",
+	"LS_ISSUES",
+	"LS_RESTARTS",
+	"LS_REISSUES_MISS",
+	"LS_REISSUES_VD",
+	"LS_REISSUE_ATTRIB_MISS",
+	"LS_NO_WB",
+	"TEX_WORDS",
+	"TEX_BUBBLES",
+	"TEX_WORDS_L0",
+	"TEX_WORDS_DESC",
+	"TEX_THREADS",
+	"TEX_RECIRC_FMISS",
+	"TEX_RECIRC_DESC",
+	"TEX_RECIRC_MULTI",
+	"TEX_RECIRC_PMISS",
+	"TEX_RECIRC_CONF",
+	"LSC_READ_HITS",
+	"LSC_READ_MISSES",
+	"LSC_WRITE_HITS",
+	"LSC_WRITE_MISSES",
+	"LSC_ATOMIC_HITS",
+	"LSC_ATOMIC_MISSES",
+	"LSC_LINE_FETCHES",
+	"LSC_DIRTY_LINE",
+	"LSC_SNOOPS",
+	"AXI_TLB_STALL",
+	"AXI_TLB_MIESS",
+	"AXI_TLB_TRANSACTION",
+	"LS_TLB_MISS",
+	"LS_TLB_HIT",
+	"AXI_BEATS_READ",
+	"AXI_BEATS_WRITTEN",
+
+	/*L2 and MMU */
+	"",
+	"",
+	"",
+	"",
+	"MMU_HIT",
+	"MMU_NEW_MISS",
+	"MMU_REPLAY_FULL",
+	"MMU_REPLAY_MISS",
+	"MMU_TABLE_WALK",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_HIT",
+	"UTLB_NEW_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_STALL",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"L2_WRITE_BEATS",
+	"L2_READ_BEATS",
+	"L2_ANY_LOOKUP",
+	"L2_READ_LOOKUP",
+	"L2_SREAD_LOOKUP",
+	"L2_READ_REPLAY",
+	"L2_READ_SNOOP",
+	"L2_READ_HIT",
+	"L2_CLEAN_MISS",
+	"L2_WRITE_LOOKUP",
+	"L2_SWRITE_LOOKUP",
+	"L2_WRITE_REPLAY",
+	"L2_WRITE_SNOOP",
+	"L2_WRITE_HIT",
+	"L2_EXT_READ_FULL",
+	"L2_EXT_READ_HALF",
+	"L2_EXT_WRITE_FULL",
+	"L2_EXT_WRITE_HALF",
+	"L2_EXT_READ",
+	"L2_EXT_READ_LINE",
+	"L2_EXT_WRITE",
+	"L2_EXT_WRITE_LINE",
+	"L2_EXT_WRITE_SMALL",
+	"L2_EXT_BARRIER",
+	"L2_EXT_AR_STALL",
+	"L2_EXT_R_BUF_FULL",
+	"L2_EXT_RD_BUF_FULL",
+	"L2_EXT_R_RAW",
+	"L2_EXT_W_STALL",
+	"L2_EXT_W_BUF_FULL",
+	"L2_EXT_R_W_HAZARD",
+	"L2_TAG_HAZARD",
+	"L2_SNOOP_FULL",
+	"L2_REPLAY_FULL"
+};
+
+static const int number_of_hardware_counters = ARRAY_SIZE(hardware_counter_names);
+
+#endif
+
+#define GET_HW_BLOCK(c) (((c) >> 6) & 0x3)
+#define GET_COUNTER_OFFSET(c) ((c) & 0x3f)
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+/* Opaque handles for kbase_context and kbase_hwc_dma_mapping */
+static struct kbase_gator_hwcnt_handles *handles;
+
+/* Information about hardware counters */
+static struct kbase_gator_hwcnt_info *in_out_info;
+
+#else
+/* Memory to dump hardware counters into */
+static void *kernel_dump_buffer;
+
+#if MALI_DDK_GATOR_API_VERSION == 2
+/* DMA state used to manage lifetime of the buffer */
+struct kbase_hwc_dma_mapping kernel_dump_buffer_handle;
+#endif
+
+/* kbase context and device */
+static struct kbase_context *kbcontext;
+static struct kbase_device *kbdevice;
+
+/*
+ * The following function has no external prototype in older DDK
+ * revisions. When the DDK is updated then this should be removed.
+ */
+struct kbase_device *kbase_find_device(int minor);
+#endif
+
+static volatile bool kbase_device_busy;
+static unsigned int num_hardware_counters_enabled;
+
+/* gatorfs variables for counter enable state */
+static struct mali_counter *counters;
+
+/* An array used to return the data we recorded as key,value pairs */
+static int *counter_dump;
+
+extern struct mali_counter mali_activity[3];
+
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+	"opencl",
+};
+
+#define SYMBOL_GET(FUNCTION, ERROR_COUNT) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			pr_err("gator: mali " #FUNCTION " symbol was already registered\n"); \
+			(ERROR_COUNT)++; \
+		} else { \
+			FUNCTION ## _symbol = symbol_get(FUNCTION); \
+			if (!FUNCTION ## _symbol) { \
+				pr_err("gator: mali online " #FUNCTION " symbol not found\n"); \
+				(ERROR_COUNT)++; \
+			} \
+		} \
+	} while (0)
+
+#define SYMBOL_CLEANUP(FUNCTION) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			symbol_put(FUNCTION); \
+			FUNCTION ## _symbol = NULL; \
+		} \
+	} while (0)
+
+/**
+ * Execute symbol_get for all the Mali symbols and check for success.
+ * @return the number of symbols not loaded.
+ */
+static int init_symbols(void)
+{
+	int error_count = 0;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_init, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_term, error_count);
+#else
+	SYMBOL_GET(kbase_find_device, error_count);
+	SYMBOL_GET(kbase_create_context, error_count);
+	SYMBOL_GET(kbase_va_alloc, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_enable, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_clear, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_disable, error_count);
+	SYMBOL_GET(kbase_va_free, error_count);
+	SYMBOL_GET(kbase_destroy_context, error_count);
+#endif
+
+	return error_count;
+}
+
+/**
+ * Execute symbol_put for all the registered Mali symbols.
+ */
+static void clean_symbols(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term);
+#else
+	SYMBOL_CLEANUP(kbase_find_device);
+	SYMBOL_CLEANUP(kbase_create_context);
+	SYMBOL_CLEANUP(kbase_va_alloc);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_enable);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_clear);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_disable);
+	SYMBOL_CLEANUP(kbase_va_free);
+	SYMBOL_CLEANUP(kbase_destroy_context);
+#endif
+}
+
+/**
+ * Determines whether a read should take place
+ * @param current_time The current time, obtained from getnstimeofday()
+ * @param prev_time_s The number of seconds at the previous read attempt.
+ * @param next_read_time_ns The time (in ns) when the next read should be allowed.
+ *
+ * Note that this function has been separated out here to allow it to be tested.
+ */
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns)
+{
+	/* If the current ns count rolls over a second, roll the next read time too. */
+	if (current_time->tv_sec != *prev_time_s)
+		*next_read_time_ns = *next_read_time_ns - NSEC_PER_SEC;
+
+	/* Abort the read if the next read time has not arrived. */
+	if (current_time->tv_nsec < *next_read_time_ns)
+		return 0;
+
+	/* Set the next read some fixed time after this one, and update the read timestamp. */
+	*next_read_time_ns = current_time->tv_nsec + READ_INTERVAL_NSEC;
+
+	*prev_time_s = current_time->tv_sec;
+	return 1;
+}
+
+static int start(void)
+{
+#if MALI_DDK_GATOR_API_VERSION != 3
+	struct kbase_uk_hwcnt_setup setup;
+	unsigned long long shadersPresent = 0;
+	u16 bitmask[] = { 0, 0, 0, 0 };
+	mali_error err;
+#endif
+	int cnt;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Declare and initialise kbase_gator_hwcnt_info structure */
+	in_out_info = kmalloc(sizeof(*in_out_info), GFP_KERNEL);
+	for (cnt = 0; cnt < ARRAY_SIZE(in_out_info->bitmask); cnt++)
+		in_out_info->bitmask[cnt] = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		if (counters[cnt].enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			in_out_info->bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		handles = kbase_gator_hwcnt_init_symbol(in_out_info);
+
+		if (handles == NULL)
+			goto out;
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+#else
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		kbdevice = kbase_find_device_symbol(-1);
+
+		/* If we already got a context, fail */
+		if (kbcontext) {
+			pr_debug("gator: Mali-Midgard: error context already present\n");
+			goto out;
+		}
+
+		/* kbcontext will only be valid after all the Mali symbols are loaded successfully */
+		kbcontext = kbase_create_context_symbol(kbdevice);
+		if (!kbcontext) {
+			pr_debug("gator: Mali-Midgard: error creating kbase context\n");
+			goto out;
+		}
+
+		/* See if we can get the number of shader cores */
+		shadersPresent = kbdevice->shader_present_bitmap;
+		shader_present_low = (unsigned long)shadersPresent;
+
+		/*
+		 * The amount of memory needed to store the dump (bytes)
+		 * DUMP_SIZE = number of core groups
+		 *             * number of blocks (always 8 for midgard)
+		 *             * number of counters per block (always 64 for midgard)
+		 *             * number of bytes per counter (always 4 in midgard)
+		 * For a Mali-Midgard with a single core group = 1 * 8 * 64 * 4 = 2048
+		 * For a Mali-Midgard with a dual core group   = 2 * 8 * 64 * 4 = 4096
+		 */
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096, &kernel_dump_buffer_handle);
+#endif
+		if (!kernel_dump_buffer) {
+			pr_debug("gator: Mali-Midgard: error trying to allocate va\n");
+			goto destroy_context;
+		}
+
+		setup.dump_buffer = (uintptr_t)kernel_dump_buffer;
+		setup.jm_bm = bitmask[JM_BLOCK];
+		setup.tiler_bm = bitmask[TILER_BLOCK];
+		setup.shader_bm = bitmask[SHADER_BLOCK];
+		setup.mmu_l2_bm = bitmask[MMU_BLOCK];
+		/* These counters do not exist on Mali-T60x */
+		setup.l3_cache_bm = 0;
+
+		/* Use kbase API to enable hardware counters and provide dump buffer */
+		err = kbase_instr_hwcnt_enable_symbol(kbcontext, &setup);
+		if (err != MALI_ERROR_NONE) {
+			pr_debug("gator: Mali-Midgard: can't setup hardware counters\n");
+			goto free_buffer;
+		}
+		pr_debug("gator: Mali-Midgard: hardware counters enabled\n");
+		kbase_instr_hwcnt_clear_symbol(kbcontext);
+		pr_debug("gator: Mali-Midgard: hardware counters cleared\n");
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+
+free_buffer:
+#if MALI_DDK_GATOR_API_VERSION == 1
+	kbase_va_free_symbol(kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+	kbase_va_free_symbol(kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+destroy_context:
+	kbase_destroy_context_symbol(kbcontext);
+#endif
+
+out:
+	clean_symbols();
+	return -1;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	struct kbase_gator_hwcnt_handles *temp_hand;
+#else
+	struct kbase_context *temp_kbcontext;
+#endif
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/* Set all counters as disabled */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++)
+		counters[cnt].enabled = 0;
+
+	/* Destroy the context for HW counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+	if (num_hardware_counters_enabled > 0 && handles != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_hand = handles;
+		handles = NULL;
+
+		kbase_gator_hwcnt_term_symbol(in_out_info, temp_hand);
+
+		kfree(in_out_info);
+
+#else
+	if (num_hardware_counters_enabled > 0 && kbcontext != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_kbcontext = kbcontext;
+		kbcontext = NULL;
+
+		kbase_instr_hwcnt_disable_symbol(temp_kbcontext);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kbase_va_free_symbol(temp_kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kbase_va_free_symbol(temp_kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+		kbase_destroy_context_symbol(temp_kbcontext);
+#endif
+
+		pr_debug("gator: Mali-Midgard: hardware counters stopped\n");
+
+		clean_symbols();
+	}
+}
+
+static int read_counter(const int cnt, const int len, const struct mali_counter *counter)
+{
+	const int block = GET_HW_BLOCK(cnt);
+	const int counter_offset = GET_COUNTER_OFFSET(cnt);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *block_base_address = (char *)in_out_info->kernel_dump_buffer;
+	int i;
+	int shader_core_count = 0;
+	u32 value = 0;
+
+	for (i = 0; i < in_out_info->nr_hwc_blocks; i++) {
+		if (block == in_out_info->hwc_layout[i]) {
+			value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+			if (block == SHADER_BLOCK)
+				++shader_core_count;
+		}
+	}
+
+	if (shader_core_count > 1)
+		value /= shader_core_count;
+#else
+	const char *block_base_address = (char *)kernel_dump_buffer + vithar_blocks[block];
+
+	/* If counter belongs to shader block need to take into account all cores */
+	if (block == SHADER_BLOCK) {
+		int i = 0;
+		int shader_core_count = 0;
+
+		value = 0;
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> i) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> (i+4)) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i) + 0x800) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		/* Need to total by number of cores to produce an average */
+		if (shader_core_count != 0)
+			value /= shader_core_count;
+	} else {
+		value = *((u32 *)block_base_address + counter_offset);
+	}
+#endif
+
+	counter_dump[len + 0] = counter->key;
+	counter_dump[len + 1] = value;
+
+	return 2;
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	uint32_t success;
+
+	struct timespec current_time;
+	static u32 prev_time_s;
+	static s32 next_read_time_ns;
+
+	if (!on_primary_core() || sched_switch)
+		return 0;
+
+	getnstimeofday(&current_time);
+
+	/*
+	 * Discard reads unless a respectable time has passed. This
+	 * reduces the load on the GPU without sacrificing accuracy on
+	 * the Streamline display.
+	 */
+	if (!is_read_scheduled(&current_time, &prev_time_s, &next_read_time_ns))
+		return 0;
+
+	/*
+	 * Report the HW counters
+	 * Only process hardware counters if at least one of the hardware counters is enabled.
+	 */
+	if (num_hardware_counters_enabled > 0) {
+#if MALI_DDK_GATOR_API_VERSION != 3
+		const unsigned int vithar_blocks[] = {
+			0x700,	/* VITHAR_JOB_MANAGER,     Block 0 */
+			0x400,	/* VITHAR_TILER,           Block 1 */
+			0x000,	/* VITHAR_SHADER_CORE,     Block 2 */
+			0x500	/* VITHAR_MEMORY_SYSTEM,   Block 3 */
+		};
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+		if (!handles)
+			return -1;
+
+		/* Mali symbols can be called safely since a kbcontext is valid */
+		if (kbase_gator_instr_hwcnt_dump_complete_symbol(handles, &success) == MALI_TRUE) {
+#else
+		if (!kbcontext)
+			return -1;
+
+		/* Mali symbols can be called safely since a kbcontext is valid */
+		if (kbase_instr_hwcnt_dump_complete_symbol(kbcontext, &success) == MALI_TRUE) {
+#endif
+			kbase_device_busy = false;
+
+			if (success == MALI_TRUE) {
+				/* Cycle through hardware counters and accumulate totals */
+				for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+					const struct mali_counter *counter = &counters[cnt];
+
+					if (counter->enabled)
+						len += read_counter(cnt, len, counter);
+				}
+			}
+		}
+
+		if (!kbase_device_busy) {
+			kbase_device_busy = true;
+#if MALI_DDK_GATOR_API_VERSION == 3
+			kbase_gator_instr_hwcnt_dump_irq_symbol(handles);
+#else
+			kbase_instr_hwcnt_dump_irq_symbol(kbcontext);
+#endif
+		}
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	unsigned int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system("Midgard", mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	for (event = 0; event < number_of_hardware_counters; event++) {
+		if (gator_mali_create_file_system(mali_name, hardware_counter_names[event], sb, root, &counters[event], NULL) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void shutdown(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	void (*kbase_gator_hwcnt_term_names_symbol)(void) = NULL;
+	int error_count = 0;
+#endif
+
+	kfree(counters);
+	kfree(counter_dump);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_term_names, error_count);
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = NULL;
+	if (kbase_gator_hwcnt_term_names_symbol != NULL) {
+		kbase_gator_hwcnt_term_names_symbol();
+		pr_err("Released symbols\n");
+	}
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term_names);
+#endif
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.shutdown = shutdown,
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read
+};
+
+int gator_events_mali_midgard_hw_init(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *const *(*kbase_gator_hwcnt_init_names_symbol)(uint32_t *) = NULL;
+	int error_count = 0;
+#endif
+
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+#if GATOR_TEST
+	test_all_is_read_scheduled();
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_init_names, error_count);
+	if (error_count > 0) {
+		SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+		return 1;
+	}
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = kbase_gator_hwcnt_init_names_symbol(&number_of_hardware_counters);
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+
+	if ((hardware_counter_names == NULL) || (number_of_hardware_counters <= 0)) {
+		pr_err("gator: Error reading hardware counters names: got %d names\n", number_of_hardware_counters);
+		return -1;
+	}
+#else
+	mali_name = "Midgard";
+#endif
+
+	counters = kmalloc(sizeof(*counters)*number_of_hardware_counters, GFP_KERNEL);
+	counter_dump = kmalloc(sizeof(*counter_dump)*number_of_hardware_counters*2, GFP_KERNEL);
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+	gator_mali_initialise_counters(counters, number_of_hardware_counters);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw_test.c b/drivers/gator/gator_events_mali_midgard_hw_test.c
new file mode 100644
index 000000000000..31a91e1c72b2
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw_test.c
@@ -0,0 +1,55 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/**
+ * Test functions for mali_t600_hw code.
+ */
+
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns);
+
+static int test_is_read_scheduled(u32 s, u32 ns, u32 prev_s, s32 next_ns, int expected_result, s32 expected_next_ns)
+{
+	struct timespec current_time;
+	u32 prev_time_s = prev_s;
+	s32 next_read_time_ns = next_ns;
+
+	current_time.tv_sec = s;
+	current_time.tv_nsec = ns;
+
+	if (is_read_scheduled(&current_time, &prev_time_s, &next_read_time_ns) != expected_result) {
+		pr_err("Failed do_read(%u, %u, %u, %d): expected %d\n", s, ns, prev_s, next_ns, expected_result);
+		return 0;
+	}
+
+	if (next_read_time_ns != expected_next_ns) {
+		pr_err("Failed: next_read_ns expected=%d, actual=%d\n", expected_next_ns, next_read_time_ns);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void test_all_is_read_scheduled(void)
+{
+	const int HIGHEST_NS = 999999999;
+	int n_tests_passed = 0;
+
+	pr_err("gator: running tests on %s\n", __FILE__);
+
+	n_tests_passed += test_is_read_scheduled(0, 0, 0, 0, 1, READ_INTERVAL_NSEC);	/* Null time */
+	n_tests_passed += test_is_read_scheduled(100, 1000, 0, 0, 1, READ_INTERVAL_NSEC + 1000);	/* Initial values */
+
+	n_tests_passed += test_is_read_scheduled(100, HIGHEST_NS, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500);
+	n_tests_passed += test_is_read_scheduled(101, 0001, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500 - NSEC_PER_SEC);
+	n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500 - NSEC_PER_SEC, 1, 600 + READ_INTERVAL_NSEC);
+
+	n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500, 1, 600 + READ_INTERVAL_NSEC);
+
+	pr_err("gator: %d tests passed\n", n_tests_passed);
+}
diff --git a/drivers/gator/gator_events_meminfo.c b/drivers/gator/gator_events_meminfo.c
new file mode 100644
index 000000000000..c625ac5af9cd
--- /dev/null
+++ b/drivers/gator/gator_events_meminfo.c
@@ -0,0 +1,470 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/hardirq.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
+#include <trace/events/kmem.h>
+
+#define USE_THREAD defined(CONFIG_PREEMPT_RT_FULL)
+
+enum {
+	MEMINFO_MEMFREE,
+	MEMINFO_MEMUSED,
+	MEMINFO_BUFFERRAM,
+	MEMINFO_TOTAL,
+};
+
+enum {
+	PROC_SIZE,
+	PROC_SHARE,
+	PROC_TEXT,
+	PROC_DATA,
+	PROC_COUNT,
+};
+
+static const char * const meminfo_names[] = {
+	"Linux_meminfo_memfree",
+	"Linux_meminfo_memused",
+	"Linux_meminfo_bufferram",
+};
+
+static const char * const proc_names[] = {
+	"Linux_proc_statm_size",
+	"Linux_proc_statm_share",
+	"Linux_proc_statm_text",
+	"Linux_proc_statm_data",
+};
+
+static bool meminfo_global_enabled;
+static ulong meminfo_enabled[MEMINFO_TOTAL];
+static ulong meminfo_keys[MEMINFO_TOTAL];
+static long long meminfo_buffer[2 * (MEMINFO_TOTAL + 2)];
+static int meminfo_length;
+static bool new_data_avail;
+
+static bool proc_global_enabled;
+static ulong proc_enabled[PROC_COUNT];
+static ulong proc_keys[PROC_COUNT];
+static DEFINE_PER_CPU(long long, proc_buffer[2 * (PROC_COUNT + 3)]);
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data);
+static bool gator_meminfo_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_meminfo_sem);
+#else
+static DEFINE_SEMAPHORE(gator_meminfo_sem);
+#endif
+
+static void notify(void)
+{
+	up(&gator_meminfo_sem);
+}
+
+#else
+
+static unsigned int mem_event;
+static void wq_sched_handler(struct work_struct *wsptr);
+DECLARE_WORK(work, wq_sched_handler);
+static struct timer_list meminfo_wake_up_timer;
+static void meminfo_wake_up_handler(unsigned long unused_data);
+
+static void notify(void)
+{
+	mem_event++;
+}
+
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_page_free_direct, TP_PROTO(struct page *page, unsigned int order))
+#else
+GATOR_DEFINE_PROBE(mm_page_free, TP_PROTO(struct page *page, unsigned int order))
+#endif
+{
+	notify();
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_pagevec_free, TP_PROTO(struct page *page, int cold))
+#else
+GATOR_DEFINE_PROBE(mm_page_free_batched, TP_PROTO(struct page *page, int cold))
+#endif
+{
+	notify();
+}
+
+GATOR_DEFINE_PROBE(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype))
+{
+	notify();
+}
+
+static int gator_events_meminfo_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		dir = gatorfs_mkdir(sb, root, meminfo_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &meminfo_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &meminfo_keys[i]);
+	}
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		dir = gatorfs_mkdir(sb, root, proc_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &proc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &proc_keys[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_meminfo_start(void)
+{
+	int i;
+
+	new_data_avail = false;
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			meminfo_global_enabled = 1;
+			break;
+		}
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			proc_global_enabled = 1;
+			break;
+		}
+	}
+	if (meminfo_enabled[MEMINFO_MEMUSED])
+		proc_global_enabled = 1;
+
+	if (meminfo_global_enabled == 0)
+		return 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_page_free_direct))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free))
+#endif
+		goto mm_page_free_exit;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_pagevec_free))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free_batched))
+#endif
+		goto mm_page_free_batched_exit;
+	if (GATOR_REGISTER_TRACE(mm_page_alloc))
+		goto mm_page_alloc_exit;
+
+#if USE_THREAD
+	/* Start worker thread */
+	gator_meminfo_run = true;
+	/* Since the mutex starts unlocked, memory values will be initialized */
+	if (IS_ERR(kthread_run(gator_meminfo_func, NULL, "gator_meminfo")))
+		goto kthread_run_exit;
+#else
+	setup_timer(&meminfo_wake_up_timer, meminfo_wake_up_handler, 0);
+#endif
+
+	return 0;
+
+#if USE_THREAD
+kthread_run_exit:
+	GATOR_UNREGISTER_TRACE(mm_page_alloc);
+#endif
+mm_page_alloc_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+mm_page_free_batched_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free);
+#endif
+mm_page_free_exit:
+	return -1;
+}
+
+static void gator_events_meminfo_stop(void)
+{
+	if (meminfo_global_enabled) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+		GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+		GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+		GATOR_UNREGISTER_TRACE(mm_page_free);
+		GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+		GATOR_UNREGISTER_TRACE(mm_page_alloc);
+
+#if USE_THREAD
+		/* Stop worker thread */
+		gator_meminfo_run = false;
+		up(&gator_meminfo_sem);
+#else
+		del_timer_sync(&meminfo_wake_up_timer);
+#endif
+	}
+}
+
+static void do_read(void)
+{
+	struct sysinfo info;
+	int i, len;
+	unsigned long long value;
+
+	meminfo_length = len = 0;
+
+	si_meminfo(&info);
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			switch (i) {
+			case MEMINFO_MEMFREE:
+				value = info.freeram * PAGE_SIZE;
+				break;
+			case MEMINFO_MEMUSED:
+				/* pid -1 means system wide */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = -1;
+				/* Emit value */
+				meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED];
+				meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE;
+				/* Clear pid */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = 0;
+				continue;
+			case MEMINFO_BUFFERRAM:
+				value = info.bufferram * PAGE_SIZE;
+				break;
+			default:
+				value = 0;
+				break;
+			}
+			meminfo_buffer[len++] = meminfo_keys[i];
+			meminfo_buffer[len++] = value;
+		}
+	}
+
+	meminfo_length = len;
+	new_data_avail = true;
+}
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_meminfo_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_meminfo_sem))
+			;
+
+		if (!gator_meminfo_run)
+			break;
+
+		do_read();
+	}
+
+	return 0;
+}
+
+#else
+
+/* Must be run in process context as the kernel function si_meminfo() can sleep */
+static void wq_sched_handler(struct work_struct *wsptr)
+{
+	do_read();
+}
+
+static void meminfo_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&work);
+}
+
+#endif
+
+static int gator_events_meminfo_read(long long **buffer)
+{
+#if !USE_THREAD
+	static unsigned int last_mem_event;
+#endif
+
+	if (!on_primary_core() || !meminfo_global_enabled)
+		return 0;
+
+#if !USE_THREAD
+	if (last_mem_event != mem_event) {
+		last_mem_event = mem_event;
+		mod_timer(&meminfo_wake_up_timer, jiffies + 1);
+	}
+#endif
+
+	if (!new_data_avail)
+		return 0;
+
+	new_data_avail = false;
+
+	if (buffer)
+		*buffer = meminfo_buffer;
+
+	return meminfo_length;
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 34) && LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+
+static inline unsigned long gator_get_mm_counter(struct mm_struct *mm, int member)
+{
+#ifdef SPLIT_RSS_COUNTING
+	long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+	if (val < 0)
+		val = 0;
+	return (unsigned long)val;
+#else
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 0, 0)
+	return mm->rss_stat.count[member];
+#else
+	return atomic_long_read(&mm->rss_stat.count[member]);
+#endif
+#endif
+}
+
+#define get_mm_counter(mm, member) gator_get_mm_counter(mm, member)
+
+#endif
+
+static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct *task)
+{
+	struct mm_struct *mm;
+	u64 share = 0;
+	int i;
+	long long value;
+	int len = 0;
+	int cpu = get_physical_cpu();
+	long long *buf = per_cpu(proc_buffer, cpu);
+
+	if (!proc_global_enabled)
+		return 0;
+
+	/* Collect the memory stats of the process instead of the thread */
+	if (task->group_leader != NULL)
+		task = task->group_leader;
+
+	/* get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch */
+	mm = task->mm;
+	if (mm == NULL)
+		return 0;
+
+	/* Derived from task_statm in fs/proc/task_mmu.c */
+	if (meminfo_enabled[MEMINFO_MEMUSED] || proc_enabled[PROC_SHARE]) {
+		share = get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+							   file_rss
+#else
+							   MM_FILEPAGES
+#endif
+							   );
+	}
+
+	/* key of 1 indicates a pid */
+	buf[len++] = 1;
+	buf[len++] = task->pid;
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			switch (i) {
+			case PROC_SIZE:
+				value = mm->total_vm;
+				break;
+			case PROC_SHARE:
+				value = share;
+				break;
+			case PROC_TEXT:
+				value = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT;
+				break;
+			case PROC_DATA:
+				value = mm->total_vm - mm->shared_vm;
+				break;
+			}
+
+			buf[len++] = proc_keys[i];
+			buf[len++] = value * PAGE_SIZE;
+		}
+	}
+
+	if (meminfo_enabled[MEMINFO_MEMUSED]) {
+		value = share + get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+									   anon_rss
+#else
+									   MM_ANONPAGES
+#endif
+									   );
+		/* Send resident for this pid */
+		buf[len++] = meminfo_keys[MEMINFO_MEMUSED];
+		buf[len++] = value * PAGE_SIZE;
+	}
+
+	/* Clear pid */
+	buf[len++] = 1;
+	buf[len++] = 0;
+
+	if (buffer)
+		*buffer = buf;
+
+	return len;
+}
+
+static struct gator_interface gator_events_meminfo_interface = {
+	.create_files = gator_events_meminfo_create_files,
+	.start = gator_events_meminfo_start,
+	.stop = gator_events_meminfo_stop,
+	.read64 = gator_events_meminfo_read,
+	.read_proc = gator_events_meminfo_read_proc,
+};
+
+int gator_events_meminfo_init(void)
+{
+	int i;
+
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		meminfo_enabled[i] = 0;
+		meminfo_keys[i] = gator_events_get_key();
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		proc_enabled[i] = 0;
+		proc_keys[i] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_meminfo_interface);
+}
diff --git a/drivers/gator/gator_events_mmapped.c b/drivers/gator/gator_events_mmapped.c
new file mode 100644
index 000000000000..6b2af995ed41
--- /dev/null
+++ b/drivers/gator/gator_events_mmapped.c
@@ -0,0 +1,209 @@
+/*
+ * Example events provider
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Similar entries to those below must be present in the events.xml file.
+ * To add them to the events.xml, create an events-mmap.xml with the
+ * following contents and rebuild gatord:
+ *
+ * <category name="mmapped">
+ *   <event counter="mmapped_cnt0" title="Simulated1" name="Sine" display="maximum" class="absolute" description="Sort-of-sine"/>
+ *   <event counter="mmapped_cnt1" title="Simulated2" name="Triangle" display="maximum" class="absolute" description="Triangular wave"/>
+ *   <event counter="mmapped_cnt2" title="Simulated3" name="PWM" display="maximum" class="absolute" description="PWM Signal"/>
+ * </category>
+ *
+ * When adding custom events, be sure to do the following:
+ * - add any needed .c files to the gator driver Makefile
+ * - call gator_events_install in the events init function
+ * - add the init function to GATOR_EVENTS_LIST in gator_main.c
+ * - add a new events-*.xml file to the gator daemon and rebuild
+ *
+ * Troubleshooting:
+ * - verify the new events are part of events.xml, which is created when building the daemon
+ * - verify the new events exist at /dev/gator/events/ once gatord is launched
+ * - verify the counter name in the XML matches the name at /dev/gator/events
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ratelimit.h>
+
+#include "gator.h"
+
+#define MMAPPED_COUNTERS_NUM 3
+
+static int mmapped_global_enabled;
+
+static struct {
+	unsigned long enabled;
+	unsigned long key;
+} mmapped_counters[MMAPPED_COUNTERS_NUM];
+
+static int mmapped_buffer[MMAPPED_COUNTERS_NUM * 2];
+
+static s64 prev_time;
+
+/* Adds mmapped_cntX directories and enabled, event, and key files to /dev/gator/events */
+static int gator_events_mmapped_create_files(struct super_block *sb,
+					     struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "mmapped_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &mmapped_counters[i].enabled);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&mmapped_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_mmapped_start(void)
+{
+	int i;
+	struct timespec ts;
+
+	getnstimeofday(&ts);
+	prev_time = timespec_to_ns(&ts);
+
+	mmapped_global_enabled = 0;
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_global_enabled = 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void gator_events_mmapped_stop(void)
+{
+}
+
+/* This function "simulates" counters, generating values of fancy
+ * functions like sine or triangle... */
+static int mmapped_simulate(int counter, int delta_in_us)
+{
+	int result = 0;
+
+	switch (counter) {
+	case 0:		/* sort-of-sine */
+		{
+			static int t;
+			int x;
+
+			t += delta_in_us;
+			if (t > 2048000)
+				t = 0;
+
+			if (t % 1024000 < 512000)
+				x = 512000 - (t % 512000);
+			else
+				x = t % 512000;
+
+			result = 32 * x / 512000;
+			result = result * result;
+
+			if (t < 1024000)
+				result = 1922 - result;
+		}
+		break;
+	case 1:		/* triangle */
+		{
+			static int v, d = 1;
+
+			v = v + d * delta_in_us;
+			if (v < 0) {
+				v = 0;
+				d = 1;
+			} else if (v > 1000000) {
+				v = 1000000;
+				d = -1;
+			}
+
+			result = v;
+		}
+		break;
+	case 2:		/* PWM signal */
+		{
+			static int dc, x, t;
+
+			t += delta_in_us;
+			if (t > 1000000)
+				t = 0;
+			if (x / 1000000 != (x + delta_in_us) / 1000000)
+				dc = (dc + 100000) % 1000000;
+			x += delta_in_us;
+
+			result = t < dc ? 0 : 10;
+		}
+		break;
+	}
+
+	return result;
+}
+
+static int gator_events_mmapped_read(int **buffer, bool sched_switch)
+{
+	int i;
+	int len = 0;
+	int delta_in_us;
+	struct timespec ts;
+	s64 time;
+
+	/* System wide counters - read from one core only */
+	if (!on_primary_core() || !mmapped_global_enabled)
+		return 0;
+
+	getnstimeofday(&ts);
+	time = timespec_to_ns(&ts);
+	delta_in_us = (int)(time - prev_time) / 1000;
+	prev_time = time;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_buffer[len++] = mmapped_counters[i].key;
+			mmapped_buffer[len++] =
+			    mmapped_simulate(i, delta_in_us);
+		}
+	}
+
+	if (buffer)
+		*buffer = mmapped_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mmapped_interface = {
+	.create_files = gator_events_mmapped_create_files,
+	.start = gator_events_mmapped_start,
+	.stop = gator_events_mmapped_stop,
+	.read = gator_events_mmapped_read,
+};
+
+/* Must not be static! */
+int __init gator_events_mmapped_init(void)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		mmapped_counters[i].enabled = 0;
+		mmapped_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_mmapped_interface);
+}
diff --git a/drivers/gator/gator_events_net.c b/drivers/gator/gator_events_net.c
new file mode 100644
index 000000000000..d21b4db7b77c
--- /dev/null
+++ b/drivers/gator/gator_events_net.c
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <linux/netdevice.h>
+#include <linux/hardirq.h>
+
+#define NETRX		0
+#define NETTX		1
+#define TOTALNET	2
+
+static ulong netrx_enabled;
+static ulong nettx_enabled;
+static ulong netrx_key;
+static ulong nettx_key;
+static int rx_total, tx_total;
+static ulong netPrev[TOTALNET];
+static int netGet[TOTALNET * 4];
+
+static struct timer_list net_wake_up_timer;
+
+/* Must be run in process context as the kernel function dev_get_stats() can sleep */
+static void get_network_stats(struct work_struct *wsptr)
+{
+	int rx = 0, tx = 0;
+	struct net_device *dev;
+
+	for_each_netdev(&init_net, dev) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+		const struct net_device_stats *stats = dev_get_stats(dev);
+#else
+		struct rtnl_link_stats64 temp;
+		const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+#endif
+		rx += stats->rx_bytes;
+		tx += stats->tx_bytes;
+	}
+	rx_total = rx;
+	tx_total = tx;
+}
+
+DECLARE_WORK(wq_get_stats, get_network_stats);
+
+static void net_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&wq_get_stats);
+}
+
+static void calculate_delta(int *rx, int *tx)
+{
+	int rx_calc, tx_calc;
+
+	rx_calc = (int)(rx_total - netPrev[NETRX]);
+	if (rx_calc < 0)
+		rx_calc = 0;
+	netPrev[NETRX] += rx_calc;
+
+	tx_calc = (int)(tx_total - netPrev[NETTX]);
+	if (tx_calc < 0)
+		tx_calc = 0;
+	netPrev[NETTX] += tx_calc;
+
+	*rx = rx_calc;
+	*tx = tx_calc;
+}
+
+static int gator_events_net_create_files(struct super_block *sb, struct dentry *root)
+{
+	/* Network counters are not currently supported in RT-Preempt full because mod_timer is used */
+#ifndef CONFIG_PREEMPT_RT_FULL
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_rx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &netrx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &netrx_key);
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_tx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &nettx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &nettx_key);
+#endif
+
+	return 0;
+}
+
+static int gator_events_net_start(void)
+{
+	get_network_stats(0);
+	netPrev[NETRX] = rx_total;
+	netPrev[NETTX] = tx_total;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+	setup_timer(&net_wake_up_timer, net_wake_up_handler, 0);
+#else
+	setup_deferrable_timer_on_stack(&net_wake_up_timer, net_wake_up_handler, 0);
+#endif
+	return 0;
+}
+
+static void gator_events_net_stop(void)
+{
+	del_timer_sync(&net_wake_up_timer);
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+}
+
+static int gator_events_net_read(int **buffer, bool sched_switch)
+{
+	int len, rx_delta, tx_delta;
+	static int last_rx_delta, last_tx_delta;
+
+	if (!on_primary_core())
+		return 0;
+
+	if (!netrx_enabled && !nettx_enabled)
+		return 0;
+
+	mod_timer(&net_wake_up_timer, jiffies + 1);
+
+	calculate_delta(&rx_delta, &tx_delta);
+
+	len = 0;
+	if (netrx_enabled && last_rx_delta != rx_delta) {
+		last_rx_delta = rx_delta;
+		netGet[len++] = netrx_key;
+		/* indicates to Streamline that rx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = netrx_key;
+		netGet[len++] = rx_delta;
+	}
+
+	if (nettx_enabled && last_tx_delta != tx_delta) {
+		last_tx_delta = tx_delta;
+		netGet[len++] = nettx_key;
+		/* indicates to Streamline that tx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = nettx_key;
+		netGet[len++] = tx_delta;
+	}
+
+	if (buffer)
+		*buffer = netGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_net_interface = {
+	.create_files = gator_events_net_create_files,
+	.start = gator_events_net_start,
+	.stop = gator_events_net_stop,
+	.read = gator_events_net_read,
+};
+
+int gator_events_net_init(void)
+{
+	netrx_key = gator_events_get_key();
+	nettx_key = gator_events_get_key();
+
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+
+	return gator_events_install(&gator_events_net_interface);
+}
diff --git a/drivers/gator/gator_events_perf_pmu.c b/drivers/gator/gator_events_perf_pmu.c
new file mode 100644
index 000000000000..47cf278e508b
--- /dev/null
+++ b/drivers/gator/gator_events_perf_pmu.c
@@ -0,0 +1,574 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_armvX.c is used for Linux 2.6.x */
+#if GATOR_PERF_PMU_SUPPORT
+
+#include <linux/io.h>
+#ifdef CONFIG_OF
+#include <linux/of_address.h>
+#endif
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+
+extern bool event_based_sampling;
+
+/* Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE */
+#define CNTMAX 16
+#define CCI_400 4
+#define CCN_5XX 8
+/* Maximum number of uncore counters */
+/* + 1 for the cci-400 cycles counter */
+/* + 1 for the CCN-5xx cycles counter */
+#define UCCNT (CCI_400 + 1 + CCN_5XX + 1)
+
+/* Default to 0 if unable to probe the revision which was the previous behavior */
+#define DEFAULT_CCI_REVISION 0
+
+/* A gator_attr is needed for every counter */
+struct gator_attr {
+	/* Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs */
+	char name[40];
+	/* Exposed in gatorfs - set by gatord to enable this counter */
+	unsigned long enabled;
+	/* Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. */
+	unsigned long type;
+	/* Exposed in gatorfs - set by gatord to select the event to collect */
+	unsigned long event;
+	/* Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter */
+	unsigned long count;
+	/* Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data */
+	unsigned long key;
+};
+
+/* Per-core counter attributes */
+static struct gator_attr attrs[CNTMAX];
+/* Number of initialized per-core counters */
+static int attr_count;
+/* Uncore counter attributes */
+static struct gator_attr uc_attrs[UCCNT];
+/* Number of initialized uncore counters */
+static int uc_attr_count;
+
+struct gator_event {
+	int curr;
+	int prev;
+	int prev_delta;
+	bool zero;
+	struct perf_event *pevent;
+	struct perf_event_attr *pevent_attr;
+};
+
+static DEFINE_PER_CPU(struct gator_event[CNTMAX], events);
+static struct gator_event uc_events[UCCNT];
+static DEFINE_PER_CPU(int[(CNTMAX + UCCNT)*2], perf_cnt);
+
+static void gator_events_perf_pmu_stop(void);
+
+static int __create_files(struct super_block *sb, struct dentry *root, struct gator_attr *const attr)
+{
+	struct dentry *dir;
+
+	if (attr->name[0] == '\0')
+		return 0;
+	dir = gatorfs_mkdir(sb, root, attr->name);
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &attr->enabled);
+	gatorfs_create_ulong(sb, dir, "count", &attr->count);
+	gatorfs_create_ro_ulong(sb, dir, "key", &attr->key);
+	gatorfs_create_ulong(sb, dir, "event", &attr->event);
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_create_files(struct super_block *sb, struct dentry *root)
+{
+	int cnt;
+
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__create_files(sb, root, &attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__create_files(sb, root, &uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void ebs_overflow_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void ebs_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	gator_backtrace_handler(regs);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void dummy_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void dummy_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	/* Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll */
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch);
+
+static int gator_events_perf_pmu_online(int **buffer, bool migrate)
+{
+	return gator_events_perf_pmu_read(buffer, false);
+}
+
+static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const attr, struct gator_event *const event)
+{
+	perf_overflow_handler_t handler;
+
+	event->zero = true;
+
+	if (event->pevent != NULL || event->pevent_attr == 0 || migrate)
+		return;
+
+	if (attr->count > 0)
+		handler = ebs_overflow_handler;
+	else
+		handler = dummy_handler;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+	event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler);
+#else
+	event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler, 0);
+#endif
+	if (IS_ERR(event->pevent)) {
+		pr_debug("gator: unable to online a counter on cpu %d\n", cpu);
+		event->pevent = NULL;
+		return;
+	}
+
+	if (event->pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		pr_debug("gator: inactive counter on cpu %d\n", cpu);
+		perf_event_release_kernel(event->pevent);
+		event->pevent = NULL;
+		return;
+	}
+}
+
+static void gator_events_perf_pmu_online_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__online_dispatch(cpu, migrate, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__online_dispatch(cpu, migrate, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+}
+
+static void __offline_dispatch(int cpu, struct gator_event *const event)
+{
+	struct perf_event *pe = NULL;
+
+	if (event->pevent) {
+		pe = event->pevent;
+		event->pevent = NULL;
+	}
+
+	if (pe)
+		perf_event_release_kernel(pe);
+}
+
+static void gator_events_perf_pmu_offline_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	if (migrate)
+		return;
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__offline_dispatch(cpu, &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__offline_dispatch(cpu, &uc_events[cnt]);
+	}
+}
+
+static int __check_ebs(struct gator_attr *const attr)
+{
+	if (attr->count > 0) {
+		if (!event_based_sampling) {
+			event_based_sampling = true;
+		} else {
+			pr_warning("gator: Only one ebs counter is allowed\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int __start(struct gator_attr *const attr, struct gator_event *const event)
+{
+	u32 size = sizeof(struct perf_event_attr);
+
+	event->pevent = NULL;
+	/* Skip disabled counters */
+	if (!attr->enabled)
+		return 0;
+
+	event->prev = 0;
+	event->curr = 0;
+	event->prev_delta = 0;
+	event->pevent_attr = kmalloc(size, GFP_KERNEL);
+	if (!event->pevent_attr) {
+		gator_events_perf_pmu_stop();
+		return -1;
+	}
+
+	memset(event->pevent_attr, 0, size);
+	event->pevent_attr->type = attr->type;
+	event->pevent_attr->size = size;
+	event->pevent_attr->config = attr->event;
+	event->pevent_attr->sample_period = attr->count;
+	event->pevent_attr->pinned = 1;
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_start(void)
+{
+	int cnt, cpu;
+
+	event_based_sampling = false;
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__check_ebs(&attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__check_ebs(&uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++) {
+			if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0)
+				return -1;
+		}
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void __event_stop(struct gator_event *const event)
+{
+	kfree(event->pevent_attr);
+	event->pevent_attr = NULL;
+}
+
+static void __attr_stop(struct gator_attr *const attr)
+{
+	attr->enabled = 0;
+	attr->event = 0;
+	attr->count = 0;
+}
+
+static void gator_events_perf_pmu_stop(void)
+{
+	unsigned int cnt, cpu;
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++)
+			__event_stop(&per_cpu(events, cpu)[cnt]);
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__event_stop(&uc_events[cnt]);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__attr_stop(&attrs[cnt]);
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__attr_stop(&uc_attrs[cnt]);
+}
+
+static void __read(int *const len, int cpu, struct gator_attr *const attr, struct gator_event *const event)
+{
+	int delta;
+	struct perf_event *const ev = event->pevent;
+
+	if (ev != NULL && ev->state == PERF_EVENT_STATE_ACTIVE) {
+		/* After creating the perf counter in __online_dispatch, there
+		 * is a race condition between gator_events_perf_pmu_online and
+		 * gator_events_perf_pmu_read. So have
+		 * gator_events_perf_pmu_online call gator_events_perf_pmu_read
+		 * and in __read check to see if it's the first call after
+		 * __online_dispatch and if so, run the online code.
+		 */
+		if (event->zero) {
+			ev->pmu->read(ev);
+			event->prev = event->curr = local64_read(&ev->count);
+			event->prev_delta = 0;
+			per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+			per_cpu(perf_cnt, cpu)[(*len)++] = 0;
+			event->zero = false;
+		} else {
+			ev->pmu->read(ev);
+			event->curr = local64_read(&ev->count);
+			delta = event->curr - event->prev;
+			if (delta != 0 || delta != event->prev_delta) {
+				event->prev_delta = delta;
+				event->prev = event->curr;
+				per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+				if (delta < 0)
+					delta *= -1;
+				per_cpu(perf_cnt, cpu)[(*len)++] = delta;
+			}
+		}
+	}
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	const int cpu = get_logical_cpu();
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__read(&len, cpu, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__read(&len, cpu, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perf_cnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_perf_pmu_interface = {
+	.create_files = gator_events_perf_pmu_create_files,
+	.start = gator_events_perf_pmu_start,
+	.stop = gator_events_perf_pmu_stop,
+	.online = gator_events_perf_pmu_online,
+	.online_dispatch = gator_events_perf_pmu_online_dispatch,
+	.offline_dispatch = gator_events_perf_pmu_offline_dispatch,
+	.read = gator_events_perf_pmu_read,
+};
+
+static void __attr_init(struct gator_attr *const attr)
+{
+	attr->name[0] = '\0';
+	attr->enabled = 0;
+	attr->type = 0;
+	attr->event = 0;
+	attr->count = 0;
+	attr->key = gator_events_get_key();
+}
+
+#ifdef CONFIG_OF
+
+static const struct of_device_id arm_cci_matches[] = {
+	{.compatible = "arm,cci-400" },
+	{},
+};
+
+static int probe_cci_revision(void)
+{
+	struct device_node *np;
+	struct resource res;
+	void __iomem *cci_ctrl_base;
+	int rev;
+	int ret = DEFAULT_CCI_REVISION;
+
+	np = of_find_matching_node(NULL, arm_cci_matches);
+	if (!np)
+		return ret;
+
+	if (of_address_to_resource(np, 0, &res))
+		goto node_put;
+
+	cci_ctrl_base = ioremap(res.start, resource_size(&res));
+
+	rev = (readl_relaxed(cci_ctrl_base + 0xfe8) >> 4) & 0xf;
+
+	if (rev <= 4)
+		ret = 0;
+	else if (rev <= 6)
+		ret = 1;
+
+	iounmap(cci_ctrl_base);
+
+ node_put:
+	of_node_put(np);
+
+	return ret;
+}
+
+#else
+
+static int probe_cci_revision(void)
+{
+	return DEFAULT_CCI_REVISION;
+}
+
+#endif
+
+static void gator_events_perf_pmu_uncore_init(const char *const name, const int type, const int count)
+{
+	int cnt;
+
+	snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", name);
+	uc_attrs[uc_attr_count].type = type;
+	++uc_attr_count;
+
+	for (cnt = 0; cnt < count; ++cnt, ++uc_attr_count) {
+		struct gator_attr *const attr = &uc_attrs[uc_attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", name, cnt);
+		attr->type = type;
+	}
+}
+
+static void gator_events_perf_pmu_cci_init(const int type)
+{
+	const char *cci_name;
+
+	switch (probe_cci_revision()) {
+	case 0:
+		cci_name = "CCI_400";
+		break;
+	case 1:
+		cci_name = "CCI_400-r1";
+		break;
+	default:
+		pr_debug("gator: unrecognized cci-400 revision\n");
+		return;
+	}
+
+	gator_events_perf_pmu_uncore_init(cci_name, type, CCI_400);
+}
+
+static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_cpu, const int type)
+{
+	int cnt;
+
+	snprintf(attrs[attr_count].name, sizeof(attrs[attr_count].name), "%s_ccnt", gator_cpu->pmnc_name);
+	attrs[attr_count].type = type;
+	++attr_count;
+
+	for (cnt = 0; cnt < gator_cpu->pmnc_counters; ++cnt, ++attr_count) {
+		struct gator_attr *const attr = &attrs[attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", gator_cpu->pmnc_name, cnt);
+		attr->type = type;
+	}
+}
+
+int gator_events_perf_pmu_init(void)
+{
+	struct perf_event_attr pea;
+	struct perf_event *pe;
+	const struct gator_cpu *gator_cpu;
+	int type;
+	int cpu;
+	int cnt;
+	bool found_cpu = false;
+
+	for (cnt = 0; cnt < CNTMAX; cnt++)
+		__attr_init(&attrs[cnt]);
+	for (cnt = 0; cnt < UCCNT; cnt++)
+		__attr_init(&uc_attrs[cnt]);
+
+	memset(&pea, 0, sizeof(pea));
+	pea.size = sizeof(pea);
+	pea.config = 0xFF;
+	attr_count = 0;
+	uc_attr_count = 0;
+	for (type = PERF_TYPE_MAX; type < 0x20; ++type) {
+		pea.type = type;
+
+		/* A particular PMU may work on some but not all cores, so try on each core */
+		pe = NULL;
+		for_each_present_cpu(cpu) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler, 0);
+#endif
+			if (!IS_ERR(pe))
+				break;
+		}
+		/* Assume that valid PMUs are contiguous */
+		if (IS_ERR(pe)) {
+			pea.config = 0xff00;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler, 0);
+#endif
+			if (IS_ERR(pe))
+				break;
+		}
+
+		if (pe->pmu != NULL && type == pe->pmu->type) {
+			if (strcmp("CCI", pe->pmu->name) == 0 || strcmp("CCI_400", pe->pmu->name) == 0 || strcmp("CCI_400-r1", pe->pmu->name) == 0) {
+				gator_events_perf_pmu_cci_init(type);
+			} else if (strcmp("ccn", pe->pmu->name) == 0) {
+				gator_events_perf_pmu_uncore_init("ARM_CCN_5XX", type, CCN_5XX);
+			} else if ((gator_cpu = gator_find_cpu_by_pmu_name(pe->pmu->name)) != NULL) {
+				found_cpu = true;
+				gator_events_perf_pmu_cpu_init(gator_cpu, type);
+			}
+			/* Initialize gator_attrs for dynamic PMUs here */
+		}
+
+		perf_event_release_kernel(pe);
+	}
+
+	if (!found_cpu) {
+		const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(gator_cpuid());
+
+		if (gator_cpu == NULL)
+			return -1;
+		gator_events_perf_pmu_cpu_init(gator_cpu, PERF_TYPE_RAW);
+	}
+
+	/* Initialize gator_attrs for non-dynamic PMUs here */
+
+	if (attr_count > CNTMAX) {
+		pr_err("gator: Too many perf counters\n");
+		return -1;
+	}
+
+	if (uc_attr_count > UCCNT) {
+		pr_err("gator: Too many perf uncore counters\n");
+		return -1;
+	}
+
+	return gator_events_install(&gator_events_perf_pmu_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_sched.c b/drivers/gator/gator_events_sched.c
new file mode 100644
index 000000000000..637107d6af1d
--- /dev/null
+++ b/drivers/gator/gator_events_sched.c
@@ -0,0 +1,113 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/sched.h>
+
+#define SCHED_SWITCH	0
+#define SCHED_TOTAL		(SCHED_SWITCH+1)
+
+static ulong sched_switch_enabled;
+static ulong sched_switch_key;
+static DEFINE_PER_CPU(int[SCHED_TOTAL], schedCnt);
+static DEFINE_PER_CPU(int[SCHED_TOTAL * 2], schedGet);
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	unsigned long flags;
+
+	/* disable interrupts to synchronize with gator_events_sched_read()
+	 * spinlocks not needed since percpu buffers are used
+	 */
+	local_irq_save(flags);
+	per_cpu(schedCnt, get_physical_cpu())[SCHED_SWITCH]++;
+	local_irq_restore(flags);
+}
+
+static int gator_events_sched_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* switch */
+	dir = gatorfs_mkdir(sb, root, "Linux_sched_switch");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &sched_switch_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_switch_key);
+
+	return 0;
+}
+
+static int gator_events_sched_start(void)
+{
+	/* register tracepoints */
+	if (sched_switch_enabled)
+		if (GATOR_REGISTER_TRACE(sched_switch))
+			goto sched_switch_exit;
+	pr_debug("gator: registered scheduler event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+sched_switch_exit:
+	pr_err("gator: scheduler event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_sched_stop(void)
+{
+	if (sched_switch_enabled)
+		GATOR_UNREGISTER_TRACE(sched_switch);
+	pr_debug("gator: unregistered scheduler event tracepoints\n");
+
+	sched_switch_enabled = 0;
+}
+
+static int gator_events_sched_read(int **buffer, bool sched_switch)
+{
+	unsigned long flags;
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (sched_switch_enabled) {
+		local_irq_save(flags);
+		value = per_cpu(schedCnt, cpu)[SCHED_SWITCH];
+		per_cpu(schedCnt, cpu)[SCHED_SWITCH] = 0;
+		local_irq_restore(flags);
+		per_cpu(schedGet, cpu)[len++] = sched_switch_key;
+		per_cpu(schedGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(schedGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_sched_interface = {
+	.create_files = gator_events_sched_create_files,
+	.start = gator_events_sched_start,
+	.stop = gator_events_sched_stop,
+	.read = gator_events_sched_read,
+};
+
+int gator_events_sched_init(void)
+{
+	sched_switch_enabled = 0;
+
+	sched_switch_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_sched_interface);
+}
diff --git a/drivers/gator/gator_events_scorpion.c b/drivers/gator/gator_events_scorpion.c
new file mode 100644
index 000000000000..49219362db09
--- /dev/null
+++ b/drivers/gator/gator_events_scorpion.c
@@ -0,0 +1,674 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define PMNC_D		(1 << 3)	/* CCNT counts every 64th cpu cycle */
+#define PMNC_X		(1 << 4)	/* Export to ETM */
+#define PMNC_DP		(1 << 5)	/* Disable CCNT if non-invasive debug */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(4+1)
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+enum scorpion_perf_types {
+	SCORPION_ICACHE_EXPL_INV = 0x4c,
+	SCORPION_ICACHE_MISS = 0x4d,
+	SCORPION_ICACHE_ACCESS = 0x4e,
+	SCORPION_ICACHE_CACHEREQ_L2 = 0x4f,
+	SCORPION_ICACHE_NOCACHE_L2 = 0x50,
+	SCORPION_HIQUP_NOPED = 0x51,
+	SCORPION_DATA_ABORT = 0x52,
+	SCORPION_IRQ = 0x53,
+	SCORPION_FIQ = 0x54,
+	SCORPION_ALL_EXCPT = 0x55,
+	SCORPION_UNDEF = 0x56,
+	SCORPION_SVC = 0x57,
+	SCORPION_SMC = 0x58,
+	SCORPION_PREFETCH_ABORT = 0x59,
+	SCORPION_INDEX_CHECK = 0x5a,
+	SCORPION_NULL_CHECK = 0x5b,
+	SCORPION_EXPL_ICIALLU = 0x5c,
+	SCORPION_IMPL_ICIALLU = 0x5d,
+	SCORPION_NONICIALLU_BTAC_INV = 0x5e,
+	SCORPION_ICIMVAU_IMPL_ICIALLU = 0x5f,
+	SCORPION_SPIPE_ONLY_CYCLES = 0x60,
+	SCORPION_XPIPE_ONLY_CYCLES = 0x61,
+	SCORPION_DUAL_CYCLES = 0x62,
+	SCORPION_DISPATCH_ANY_CYCLES = 0x63,
+	SCORPION_FIFO_FULLBLK_CMT = 0x64,
+	SCORPION_FAIL_COND_INST = 0x65,
+	SCORPION_PASS_COND_INST = 0x66,
+	SCORPION_ALLOW_VU_CLK = 0x67,
+	SCORPION_VU_IDLE = 0x68,
+	SCORPION_ALLOW_L2_CLK = 0x69,
+	SCORPION_L2_IDLE = 0x6a,
+	SCORPION_DTLB_IMPL_INV_SCTLR_DACR = 0x6b,
+	SCORPION_DTLB_EXPL_INV = 0x6c,
+	SCORPION_DTLB_MISS = 0x6d,
+	SCORPION_DTLB_ACCESS = 0x6e,
+	SCORPION_ITLB_MISS = 0x6f,
+	SCORPION_ITLB_IMPL_INV = 0x70,
+	SCORPION_ITLB_EXPL_INV = 0x71,
+	SCORPION_UTLB_D_MISS = 0x72,
+	SCORPION_UTLB_D_ACCESS = 0x73,
+	SCORPION_UTLB_I_MISS = 0x74,
+	SCORPION_UTLB_I_ACCESS = 0x75,
+	SCORPION_UTLB_INV_ASID = 0x76,
+	SCORPION_UTLB_INV_MVA = 0x77,
+	SCORPION_UTLB_INV_ALL = 0x78,
+	SCORPION_S2_HOLD_RDQ_UNAVAIL = 0x79,
+	SCORPION_S2_HOLD = 0x7a,
+	SCORPION_S2_HOLD_DEV_OP = 0x7b,
+	SCORPION_S2_HOLD_ORDER = 0x7c,
+	SCORPION_S2_HOLD_BARRIER = 0x7d,
+	SCORPION_VIU_DUAL_CYCLE = 0x7e,
+	SCORPION_VIU_SINGLE_CYCLE = 0x7f,
+	SCORPION_VX_PIPE_WAR_STALL_CYCLES = 0x80,
+	SCORPION_VX_PIPE_WAW_STALL_CYCLES = 0x81,
+	SCORPION_VX_PIPE_RAW_STALL_CYCLES = 0x82,
+	SCORPION_VX_PIPE_LOAD_USE_STALL = 0x83,
+	SCORPION_VS_PIPE_WAR_STALL_CYCLES = 0x84,
+	SCORPION_VS_PIPE_WAW_STALL_CYCLES = 0x85,
+	SCORPION_VS_PIPE_RAW_STALL_CYCLES = 0x86,
+	SCORPION_EXCEPTIONS_INV_OPERATION = 0x87,
+	SCORPION_EXCEPTIONS_DIV_BY_ZERO = 0x88,
+	SCORPION_COND_INST_FAIL_VX_PIPE = 0x89,
+	SCORPION_COND_INST_FAIL_VS_PIPE = 0x8a,
+	SCORPION_EXCEPTIONS_OVERFLOW = 0x8b,
+	SCORPION_EXCEPTIONS_UNDERFLOW = 0x8c,
+	SCORPION_EXCEPTIONS_DENORM = 0x8d,
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	SCORPIONMP_NUM_BARRIERS = 0x8e,
+	SCORPIONMP_BARRIER_CYCLES = 0x8f,
+#else
+	SCORPION_BANK_AB_HIT = 0x8e,
+	SCORPION_BANK_AB_ACCESS = 0x8f,
+	SCORPION_BANK_CD_HIT = 0x90,
+	SCORPION_BANK_CD_ACCESS = 0x91,
+	SCORPION_BANK_AB_DSIDE_HIT = 0x92,
+	SCORPION_BANK_AB_DSIDE_ACCESS = 0x93,
+	SCORPION_BANK_CD_DSIDE_HIT = 0x94,
+	SCORPION_BANK_CD_DSIDE_ACCESS = 0x95,
+	SCORPION_BANK_AB_ISIDE_HIT = 0x96,
+	SCORPION_BANK_AB_ISIDE_ACCESS = 0x97,
+	SCORPION_BANK_CD_ISIDE_HIT = 0x98,
+	SCORPION_BANK_CD_ISIDE_ACCESS = 0x99,
+	SCORPION_ISIDE_RD_WAIT = 0x9a,
+	SCORPION_DSIDE_RD_WAIT = 0x9b,
+	SCORPION_BANK_BYPASS_WRITE = 0x9c,
+	SCORPION_BANK_AB_NON_CASTOUT = 0x9d,
+	SCORPION_BANK_AB_L2_CASTOUT = 0x9e,
+	SCORPION_BANK_CD_NON_CASTOUT = 0x9f,
+	SCORPION_BANK_CD_L2_CASTOUT = 0xa0,
+#endif
+	MSM_MAX_EVT
+};
+
+struct scorp_evt {
+	u32 evt_type;
+	u32 val;
+	u8 grp;
+	u32 evt_type_act;
+};
+
+static const struct scorp_evt sc_evt[] = {
+	{SCORPION_ICACHE_EXPL_INV, 0x80000500, 0, 0x4d},
+	{SCORPION_ICACHE_MISS, 0x80050000, 0, 0x4e},
+	{SCORPION_ICACHE_ACCESS, 0x85000000, 0, 0x4f},
+	{SCORPION_ICACHE_CACHEREQ_L2, 0x86000000, 0, 0x4f},
+	{SCORPION_ICACHE_NOCACHE_L2, 0x87000000, 0, 0x4f},
+	{SCORPION_HIQUP_NOPED, 0x80080000, 0, 0x4e},
+	{SCORPION_DATA_ABORT, 0x8000000a, 0, 0x4c},
+	{SCORPION_IRQ, 0x80000a00, 0, 0x4d},
+	{SCORPION_FIQ, 0x800a0000, 0, 0x4e},
+	{SCORPION_ALL_EXCPT, 0x8a000000, 0, 0x4f},
+	{SCORPION_UNDEF, 0x8000000b, 0, 0x4c},
+	{SCORPION_SVC, 0x80000b00, 0, 0x4d},
+	{SCORPION_SMC, 0x800b0000, 0, 0x4e},
+	{SCORPION_PREFETCH_ABORT, 0x8b000000, 0, 0x4f},
+	{SCORPION_INDEX_CHECK, 0x8000000c, 0, 0x4c},
+	{SCORPION_NULL_CHECK, 0x80000c00, 0, 0x4d},
+	{SCORPION_EXPL_ICIALLU, 0x8000000d, 0, 0x4c},
+	{SCORPION_IMPL_ICIALLU, 0x80000d00, 0, 0x4d},
+	{SCORPION_NONICIALLU_BTAC_INV, 0x800d0000, 0, 0x4e},
+	{SCORPION_ICIMVAU_IMPL_ICIALLU, 0x8d000000, 0, 0x4f},
+
+	{SCORPION_SPIPE_ONLY_CYCLES, 0x80000600, 1, 0x51},
+	{SCORPION_XPIPE_ONLY_CYCLES, 0x80060000, 1, 0x52},
+	{SCORPION_DUAL_CYCLES, 0x86000000, 1, 0x53},
+	{SCORPION_DISPATCH_ANY_CYCLES, 0x89000000, 1, 0x53},
+	{SCORPION_FIFO_FULLBLK_CMT, 0x8000000d, 1, 0x50},
+	{SCORPION_FAIL_COND_INST, 0x800d0000, 1, 0x52},
+	{SCORPION_PASS_COND_INST, 0x8d000000, 1, 0x53},
+	{SCORPION_ALLOW_VU_CLK, 0x8000000e, 1, 0x50},
+	{SCORPION_VU_IDLE, 0x80000e00, 1, 0x51},
+	{SCORPION_ALLOW_L2_CLK, 0x800e0000, 1, 0x52},
+	{SCORPION_L2_IDLE, 0x8e000000, 1, 0x53},
+
+	{SCORPION_DTLB_IMPL_INV_SCTLR_DACR, 0x80000001, 2, 0x54},
+	{SCORPION_DTLB_EXPL_INV, 0x80000100, 2, 0x55},
+	{SCORPION_DTLB_MISS, 0x80010000, 2, 0x56},
+	{SCORPION_DTLB_ACCESS, 0x81000000, 2, 0x57},
+	{SCORPION_ITLB_MISS, 0x80000200, 2, 0x55},
+	{SCORPION_ITLB_IMPL_INV, 0x80020000, 2, 0x56},
+	{SCORPION_ITLB_EXPL_INV, 0x82000000, 2, 0x57},
+	{SCORPION_UTLB_D_MISS, 0x80000003, 2, 0x54},
+	{SCORPION_UTLB_D_ACCESS, 0x80000300, 2, 0x55},
+	{SCORPION_UTLB_I_MISS, 0x80030000, 2, 0x56},
+	{SCORPION_UTLB_I_ACCESS, 0x83000000, 2, 0x57},
+	{SCORPION_UTLB_INV_ASID, 0x80000400, 2, 0x55},
+	{SCORPION_UTLB_INV_MVA, 0x80040000, 2, 0x56},
+	{SCORPION_UTLB_INV_ALL, 0x84000000, 2, 0x57},
+	{SCORPION_S2_HOLD_RDQ_UNAVAIL, 0x80000800, 2, 0x55},
+	{SCORPION_S2_HOLD, 0x88000000, 2, 0x57},
+	{SCORPION_S2_HOLD_DEV_OP, 0x80000900, 2, 0x55},
+	{SCORPION_S2_HOLD_ORDER, 0x80090000, 2, 0x56},
+	{SCORPION_S2_HOLD_BARRIER, 0x89000000, 2, 0x57},
+
+	{SCORPION_VIU_DUAL_CYCLE, 0x80000001, 4, 0x5c},
+	{SCORPION_VIU_SINGLE_CYCLE, 0x80000100, 4, 0x5d},
+	{SCORPION_VX_PIPE_WAR_STALL_CYCLES, 0x80000005, 4, 0x5c},
+	{SCORPION_VX_PIPE_WAW_STALL_CYCLES, 0x80000500, 4, 0x5d},
+	{SCORPION_VX_PIPE_RAW_STALL_CYCLES, 0x80050000, 4, 0x5e},
+	{SCORPION_VX_PIPE_LOAD_USE_STALL, 0x80000007, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAR_STALL_CYCLES, 0x80000008, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAW_STALL_CYCLES, 0x80000800, 4, 0x5d},
+	{SCORPION_VS_PIPE_RAW_STALL_CYCLES, 0x80080000, 4, 0x5e},
+	{SCORPION_EXCEPTIONS_INV_OPERATION, 0x8000000b, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_DIV_BY_ZERO, 0x80000b00, 4, 0x5d},
+	{SCORPION_COND_INST_FAIL_VX_PIPE, 0x800b0000, 4, 0x5e},
+	{SCORPION_COND_INST_FAIL_VS_PIPE, 0x8b000000, 4, 0x5f},
+	{SCORPION_EXCEPTIONS_OVERFLOW, 0x8000000c, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_UNDERFLOW, 0x80000c00, 4, 0x5d},
+	{SCORPION_EXCEPTIONS_DENORM, 0x8c000000, 4, 0x5f},
+
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	{SCORPIONMP_NUM_BARRIERS, 0x80000e00, 3, 0x59},
+	{SCORPIONMP_BARRIER_CYCLES, 0x800e0000, 3, 0x5a},
+#else
+	{SCORPION_BANK_AB_HIT, 0x80000001, 3, 0x58},
+	{SCORPION_BANK_AB_ACCESS, 0x80000100, 3, 0x59},
+	{SCORPION_BANK_CD_HIT, 0x80010000, 3, 0x5a},
+	{SCORPION_BANK_CD_ACCESS, 0x81000000, 3, 0x5b},
+	{SCORPION_BANK_AB_DSIDE_HIT, 0x80000002, 3, 0x58},
+	{SCORPION_BANK_AB_DSIDE_ACCESS, 0x80000200, 3, 0x59},
+	{SCORPION_BANK_CD_DSIDE_HIT, 0x80020000, 3, 0x5a},
+	{SCORPION_BANK_CD_DSIDE_ACCESS, 0x82000000, 3, 0x5b},
+	{SCORPION_BANK_AB_ISIDE_HIT, 0x80000003, 3, 0x58},
+	{SCORPION_BANK_AB_ISIDE_ACCESS, 0x80000300, 3, 0x59},
+	{SCORPION_BANK_CD_ISIDE_HIT, 0x80030000, 3, 0x5a},
+	{SCORPION_BANK_CD_ISIDE_ACCESS, 0x83000000, 3, 0x5b},
+	{SCORPION_ISIDE_RD_WAIT, 0x80000009, 3, 0x58},
+	{SCORPION_DSIDE_RD_WAIT, 0x80090000, 3, 0x5a},
+	{SCORPION_BANK_BYPASS_WRITE, 0x8000000a, 3, 0x58},
+	{SCORPION_BANK_AB_NON_CASTOUT, 0x8000000c, 3, 0x58},
+	{SCORPION_BANK_AB_L2_CASTOUT, 0x80000c00, 3, 0x59},
+	{SCORPION_BANK_CD_NON_CASTOUT, 0x800c0000, 3, 0x5a},
+	{SCORPION_BANK_CD_L2_CASTOUT, 0x8c000000, 3, 0x5b},
+#endif
+};
+
+static inline void scorpion_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+static inline u32 scorpion_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_ccnt_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_cntn_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u enabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 scorpion_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u disabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+	return cnt;
+}
+
+static inline int scorpion_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if ((cnt == CCNT) || (cnt >= CNTMAX)) {
+		pr_err("gator: CPU%u selecting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	val = (cnt - CNT0);
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+	return cnt;
+}
+
+static u32 scorpion_read_lpm0(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm0(u32 val)
+{
+	asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm1(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm1(u32 val)
+{
+	asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm2(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm2(u32 val)
+{
+	asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_l2lpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_l2lpm(u32 val)
+{
+	asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_vlpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_vlpm(u32 val)
+{
+	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+struct scorpion_access_funcs {
+	u32 (*read)(void);
+	void (*write)(u32);
+};
+
+struct scorpion_access_funcs scor_func[] = {
+	{scorpion_read_lpm0, scorpion_write_lpm0},
+	{scorpion_read_lpm1, scorpion_write_lpm1},
+	{scorpion_read_lpm2, scorpion_write_lpm2},
+	{scorpion_read_l2lpm, scorpion_write_l2lpm},
+	{scorpion_read_vlpm, scorpion_write_vlpm},
+};
+
+u32 venum_orig_val;
+u32 fp_orig_val;
+
+static void scorpion_pre_vlpm(void)
+{
+	u32 venum_new_val;
+	u32 fp_new_val;
+
+	/* CPACR Enable CP10 access */
+	asm volatile("mrc p15, 0, %0, c1, c0, 2" : "=r" (venum_orig_val));
+	venum_new_val = venum_orig_val | 0x00300000;
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_new_val));
+	/* Enable FPEXC */
+	asm volatile("mrc p10, 7, %0, c8, c0, 0" : "=r" (fp_orig_val));
+	fp_new_val = fp_orig_val | 0x40000000;
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_new_val));
+}
+
+static void scorpion_post_vlpm(void)
+{
+	/* Restore FPEXC */
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_orig_val));
+	/* Restore CPACR */
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_orig_val));
+}
+
+#define COLMN0MASK 0x000000ff
+#define COLMN1MASK 0x0000ff00
+#define COLMN2MASK 0x00ff0000
+static u32 scorpion_get_columnmask(u32 setval)
+{
+	if (setval & COLMN0MASK)
+		return 0xffffff00;
+	if (setval & COLMN1MASK)
+		return 0xffff00ff;
+	if (setval & COLMN2MASK)
+		return 0xff00ffff;
+	return 0x80ffffff;
+}
+
+static void scorpion_evt_setup(u32 gr, u32 setval)
+{
+	u32 val;
+
+	if (gr == 4)
+		scorpion_pre_vlpm();
+	val = scorpion_get_columnmask(setval) & scor_func[gr].read();
+	val = val | setval;
+	scor_func[gr].write(val);
+	if (gr == 4)
+		scorpion_post_vlpm();
+}
+
+static int get_scorpion_evtinfo(unsigned int evt_type, struct scorp_evt *evtinfo)
+{
+	u32 idx;
+
+	if ((evt_type < 0x4c) || (evt_type >= MSM_MAX_EVT))
+		return 0;
+	idx = evt_type - 0x4c;
+	if (sc_evt[idx].evt_type == evt_type) {
+		evtinfo->val = sc_evt[idx].val;
+		evtinfo->grp = sc_evt[idx].grp;
+		evtinfo->evt_type_act = sc_evt[idx].evt_type_act;
+		return 1;
+	}
+	return 0;
+}
+
+static inline void scorpion_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (scorpion_pmnc_select_counter(cnt) == cnt) {
+		if (val < 0x40) {
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+		} else {
+			u32 zero = 0;
+			struct scorp_evt evtinfo;
+			/* extract evtinfo.grp and evtinfo.tevt_type_act from val */
+			if (get_scorpion_evtinfo(val, &evtinfo) == 0)
+				return;
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (evtinfo.evt_type_act));
+			asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (zero));
+			scorpion_evt_setup(evtinfo.grp, val);
+		}
+	}
+}
+
+static void scorpion_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	if (cnt == CCNT) {
+		scorpion_pmnc_disable_counter(cnt);
+
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+
+	} else if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u resetting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+	} else {
+		scorpion_pmnc_disable_counter(cnt);
+
+		if (scorpion_pmnc_select_counter(cnt) == cnt)
+			asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+	}
+}
+
+static int gator_events_scorpion_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_scorpion_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (scorpion_pmnc_read() & PMNC_E)
+		scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	scorpion_pmnc_write(PMNC_P | PMNC_C);
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* disable counter */
+		scorpion_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			scorpion_pmnc_write_evtsel(cnt, event);
+
+		/* reset counter */
+		scorpion_pmnc_reset_counter(cnt);
+
+		/* Enable counter, do not enable interrupt for this counter */
+		scorpion_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	scorpion_pmnc_write(scorpion_pmnc_read() | PMNC_E);
+
+	/* read the counters and toss the invalid data, return zero instead */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			if (cnt == CCNT)
+				scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				scorpion_cntn_read();
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_scorpion_offline(int **buffer, bool migrate)
+{
+	scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+	return 0;
+}
+
+static void gator_events_scorpion_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_scorpion_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(scorpion_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				value = scorpion_cntn_read();
+			else
+				value = 0;
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_scorpion_interface = {
+	.create_files = gator_events_scorpion_create_files,
+	.stop = gator_events_scorpion_stop,
+	.online = gator_events_scorpion_online,
+	.offline = gator_events_scorpion_offline,
+	.read = gator_events_scorpion_read,
+};
+
+int gator_events_scorpion_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case SCORPION:
+		pmnc_name = "Scorpion";
+		pmnc_counters = 4;
+		break;
+	case SCORPIONMP:
+		pmnc_name = "ScorpionMP";
+		pmnc_counters = 4;
+		break;
+	default:
+		return -1;
+	}
+
+	/* CNT[n] + CCNT */
+	pmnc_counters++;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_scorpion_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_fs.c b/drivers/gator/gator_fs.c
new file mode 100644
index 000000000000..d8fb357b9eda
--- /dev/null
+++ b/drivers/gator/gator_fs.c
@@ -0,0 +1,370 @@
+/**
+ * @file gatorfs.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon
+ *
+ * A simple filesystem for configuration and
+ * access of oprofile.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+
+#define gatorfs_MAGIC 0x24051020
+#define TMPBUFSIZE 50
+DEFINE_SPINLOCK(gatorfs_lock);
+
+static struct inode *gatorfs_get_inode(struct super_block *sb, int mode)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (inode) {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 37)
+		inode->i_ino = get_next_ino();
+#endif
+		inode->i_mode = mode;
+		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	}
+	return inode;
+}
+
+static const struct super_operations s_ops = {
+	.statfs = simple_statfs,
+	.drop_inode = generic_delete_inode,
+};
+
+static ssize_t gatorfs_ulong_to_user(unsigned long val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%lu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static ssize_t gatorfs_u64_to_user(u64 val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%llu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static int gatorfs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoul(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static int gatorfs_u64_from_user(u64 *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoull(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *val = file->private_data;
+
+	return gatorfs_ulong_to_user(*val, buf, count, offset);
+}
+
+static ssize_t u64_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	u64 *val = file->private_data;
+
+	return gatorfs_u64_to_user(*val, buf, count, offset);
+}
+
+static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static ssize_t u64_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	u64 *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_u64_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static int default_open(struct inode *inode, struct file *filp)
+{
+	if (inode->i_private)
+		filp->private_data = inode->i_private;
+	return 0;
+}
+
+static const struct file_operations ulong_fops = {
+	.read = ulong_read_file,
+	.write = ulong_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_fops = {
+	.read = u64_read_file,
+	.write = u64_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations ulong_ro_fops = {
+	.read = ulong_read_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_ro_fops = {
+	.read = u64_read_file,
+	.open = default_open,
+};
+
+static struct dentry *__gatorfs_create_file(struct super_block *sb,
+					    struct dentry *root,
+					    char const *name,
+					    const struct file_operations *fops,
+					    int perm)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFREG | perm);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_fop = fops;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_u64(struct super_block *sb, struct dentry *root,
+			      char const *name, u64 *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &u64_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root,
+				 char const *name, u64 *val)
+{
+	struct dentry *d =
+	    __gatorfs_create_file(sb, root, name, &u64_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	atomic_t *val = file->private_data;
+
+	return gatorfs_ulong_to_user(atomic_read(val), buf, count, offset);
+}
+
+static const struct file_operations atomic_ro_fops = {
+	.read = atomic_read_file,
+	.open = default_open,
+};
+
+static int gatorfs_create_file(struct super_block *sb, struct dentry *root,
+			       char const *name, const struct file_operations *fops)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, 0644))
+		return -EFAULT;
+	return 0;
+}
+
+static int gatorfs_create_file_perm(struct super_block *sb, struct dentry *root,
+				    char const *name,
+				    const struct file_operations *fops, int perm)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, perm))
+		return -EFAULT;
+	return 0;
+}
+
+struct dentry *gatorfs_mkdir(struct super_block *sb,
+			     struct dentry *root, char const *name)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+static int gatorfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *root_inode;
+	struct dentry *root_dentry;
+
+	sb->s_blocksize = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_magic = gatorfs_MAGIC;
+	sb->s_op = &s_ops;
+	sb->s_time_gran = 1;
+
+	root_inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!root_inode)
+		return -ENOMEM;
+	root_inode->i_op = &simple_dir_inode_operations;
+	root_inode->i_fop = &simple_dir_operations;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	root_dentry = d_alloc_root(root_inode);
+#else
+	root_dentry = d_make_root(root_inode);
+#endif
+
+	if (!root_dentry) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+		iput(root_inode);
+#endif
+		return -ENOMEM;
+	}
+
+	sb->s_root = root_dentry;
+
+	gator_op_create_files(sb, root_dentry);
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+static int gatorfs_get_sb(struct file_system_type *fs_type,
+			  int flags, const char *dev_name, void *data,
+			  struct vfsmount *mnt)
+{
+	return get_sb_single(fs_type, flags, data, gatorfs_fill_super, mnt);
+}
+#else
+static struct dentry *gatorfs_mount(struct file_system_type *fs_type,
+				    int flags, const char *dev_name, void *data)
+{
+	return mount_nodev(fs_type, flags, data, gatorfs_fill_super);
+}
+#endif
+
+static struct file_system_type gatorfs_type = {
+	.owner = THIS_MODULE,
+	.name = "gatorfs",
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+	.get_sb = gatorfs_get_sb,
+#else
+	.mount = gatorfs_mount,
+#endif
+
+	.kill_sb = kill_litter_super,
+};
+
+static int __init gatorfs_register(void)
+{
+	return register_filesystem(&gatorfs_type);
+}
+
+static void gatorfs_unregister(void)
+{
+	unregister_filesystem(&gatorfs_type);
+}
diff --git a/drivers/gator/gator_hrtimer_gator.c b/drivers/gator/gator_hrtimer_gator.c
new file mode 100644
index 000000000000..c1525e10a8da
--- /dev/null
+++ b/drivers/gator/gator_hrtimer_gator.c
@@ -0,0 +1,80 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+void (*callback)(void);
+DEFINE_PER_CPU(struct hrtimer, percpu_hrtimer);
+DEFINE_PER_CPU(ktime_t, hrtimer_expire);
+DEFINE_PER_CPU(int, hrtimer_is_active);
+static ktime_t profiling_interval;
+static void gator_hrtimer_online(void);
+static void gator_hrtimer_offline(void);
+
+static enum hrtimer_restart gator_hrtimer_notify(struct hrtimer *hrtimer)
+{
+	int cpu = get_logical_cpu();
+
+	hrtimer_forward(hrtimer, per_cpu(hrtimer_expire, cpu), profiling_interval);
+	per_cpu(hrtimer_expire, cpu) = ktime_add(per_cpu(hrtimer_expire, cpu), profiling_interval);
+	(*callback)();
+	return HRTIMER_RESTART;
+}
+
+static void gator_hrtimer_online(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (per_cpu(hrtimer_is_active, cpu) || profiling_interval.tv64 == 0)
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 1;
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer->function = gator_hrtimer_notify;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	hrtimer->irqsafe = 1;
+#endif
+	per_cpu(hrtimer_expire, cpu) = ktime_add(hrtimer->base->get_time(), profiling_interval);
+	hrtimer_start(hrtimer, per_cpu(hrtimer_expire, cpu), HRTIMER_MODE_ABS_PINNED);
+}
+
+static void gator_hrtimer_offline(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (!per_cpu(hrtimer_is_active, cpu))
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 0;
+	hrtimer_cancel(hrtimer);
+}
+
+static int gator_hrtimer_init(int interval, void (*func)(void))
+{
+	int cpu;
+
+	(callback) = (func);
+
+	for_each_present_cpu(cpu) {
+		per_cpu(hrtimer_is_active, cpu) = 0;
+	}
+
+	/* calculate profiling interval */
+	if (interval > 0)
+		profiling_interval = ns_to_ktime(1000000000UL / interval);
+	else
+		profiling_interval.tv64 = 0;
+
+	return 0;
+}
+
+static void gator_hrtimer_shutdown(void)
+{
+	/* empty */
+}
diff --git a/drivers/gator/gator_iks.c b/drivers/gator/gator_iks.c
new file mode 100644
index 000000000000..fb78c10fd987
--- /dev/null
+++ b/drivers/gator/gator_iks.c
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if GATOR_IKS_SUPPORT
+
+#include <linux/of.h>
+#include <asm/bL_switcher.h>
+#include <asm/smp_plat.h>
+#include <trace/events/power_cpu_migrate.h>
+
+static bool map_cpuids;
+static int mpidr_cpuids[NR_CPUS];
+static const struct gator_cpu *mpidr_cpus[NR_CPUS];
+static int __lcpu_to_pcpu[NR_CPUS];
+
+static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static void calc_first_cluster_size(void)
+{
+	int len;
+	const u32 *val;
+	const char *compatible;
+	struct device_node *cn = NULL;
+	int mpidr_cpuids_count = 0;
+
+	/* Zero is a valid cpuid, so initialize the array to 0xff's */
+	memset(&mpidr_cpuids, 0xff, sizeof(mpidr_cpuids));
+	memset(&mpidr_cpus, 0, sizeof(mpidr_cpus));
+
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+		BUG_ON(mpidr_cpuids_count >= NR_CPUS);
+
+		val = of_get_property(cn, "reg", &len);
+		if (!val || len != 4) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+		compatible = of_get_property(cn, "compatible", NULL);
+		if (compatible == NULL) {
+			pr_err("%s missing compatible property\n", cn->full_name);
+			continue;
+		}
+
+		mpidr_cpuids[mpidr_cpuids_count] = be32_to_cpup(val);
+		mpidr_cpus[mpidr_cpuids_count] = gator_find_cpu_by_dt_name(compatible);
+		++mpidr_cpuids_count;
+	}
+
+	map_cpuids = (mpidr_cpuids_count == nr_cpu_ids);
+}
+
+static int linearize_mpidr(int mpidr)
+{
+	int i;
+
+	for (i = 0; i < nr_cpu_ids; ++i) {
+		if (mpidr_cpuids[i] == mpidr)
+			return i;
+	}
+
+	BUG();
+}
+
+int lcpu_to_pcpu(const int lcpu)
+{
+	int pcpu;
+
+	if (!map_cpuids)
+		return lcpu;
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	pcpu = __lcpu_to_pcpu[lcpu];
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	return pcpu;
+}
+
+int pcpu_to_lcpu(const int pcpu)
+{
+	int lcpu;
+
+	if (!map_cpuids)
+		return pcpu;
+
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	for (lcpu = 0; lcpu < nr_cpu_ids; ++lcpu) {
+		if (__lcpu_to_pcpu[lcpu] == pcpu) {
+			BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+			return lcpu;
+		}
+	}
+	BUG();
+}
+
+static void gator_update_cpu_mapping(u32 cpu_hwid)
+{
+	int lcpu = smp_processor_id();
+	int pcpu = linearize_mpidr(cpu_hwid & MPIDR_HWID_BITMASK);
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	__lcpu_to_pcpu[lcpu] = pcpu;
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_begin, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	const int cpu = get_physical_cpu();
+
+	gator_timer_offline((void *)1);
+	gator_timer_offline_dispatch(cpu, true);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_finish, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	int cpu;
+
+	gator_update_cpu_mapping(cpu_hwid);
+
+	/* get_physical_cpu must be called after gator_update_cpu_mapping */
+	cpu = get_physical_cpu();
+	gator_timer_online_dispatch(cpu, true);
+	gator_timer_online((void *)1);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_current, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	gator_update_cpu_mapping(cpu_hwid);
+}
+
+static void gator_send_iks_core_names(void)
+{
+	int cpu;
+	/* Send the cpu names */
+	preempt_disable();
+	for (cpu = 0; cpu < nr_cpu_ids; ++cpu) {
+		if (mpidr_cpus[cpu] != NULL)
+			gator_send_core_name(cpu, mpidr_cpus[cpu]->cpuid);
+	}
+	preempt_enable();
+}
+
+static int gator_migrate_start(void)
+{
+	int retval = 0;
+
+	if (!map_cpuids)
+		return retval;
+
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_begin);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_finish);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_current);
+	if (retval == 0) {
+		/* Initialize the logical to physical cpu mapping */
+		memset(&__lcpu_to_pcpu, 0xff, sizeof(__lcpu_to_pcpu));
+		bL_switcher_trace_trigger();
+	}
+	return retval;
+}
+
+static void gator_migrate_stop(void)
+{
+	if (!map_cpuids)
+		return;
+
+	GATOR_UNREGISTER_TRACE(cpu_migrate_current);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_finish);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_begin);
+}
+
+#else
+
+#define calc_first_cluster_size()
+#define gator_send_iks_core_names()
+#define gator_migrate_start() 0
+#define gator_migrate_stop()
+
+#endif
diff --git a/drivers/gator/gator_main.c b/drivers/gator/gator_main.c
new file mode 100644
index 000000000000..30bf60d95286
--- /dev/null
+++ b/drivers/gator/gator_main.c
@@ -0,0 +1,1491 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* This version must match the gator daemon version */
+#define PROTOCOL_VERSION 20
+static unsigned long gator_protocol_version = PROTOCOL_VERSION;
+
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
+
+#include "gator.h"
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#error kernels prior to 2.6.32 are not supported
+#endif
+
+#if defined(MODULE) && !defined(CONFIG_MODULES)
+#error Cannot build a module against a kernel that does not support modules. To resolve, either rebuild the kernel to support modules or build gator as part of the kernel.
+#endif
+
+#if !defined(CONFIG_GENERIC_TRACER) && !defined(CONFIG_TRACING)
+#error gator requires the kernel to have CONFIG_GENERIC_TRACER or CONFIG_TRACING defined
+#endif
+
+#ifndef CONFIG_PROFILING
+#error gator requires the kernel to have CONFIG_PROFILING defined
+#endif
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+#error gator requires the kernel to have CONFIG_HIGH_RES_TIMERS defined to support PC sampling
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 12, 0) && defined(__arm__) && defined(CONFIG_SMP) && !defined(CONFIG_LOCAL_TIMERS)
+#error gator requires the kernel to have CONFIG_LOCAL_TIMERS defined on SMP systems
+#endif
+
+#if (GATOR_PERF_SUPPORT) && (!(GATOR_PERF_PMU_SUPPORT))
+#ifndef CONFIG_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_PERF_EVENTS defined to support pmu hardware counters
+#elif !defined CONFIG_HW_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_HW_PERF_EVENTS defined to support pmu hardware counters
+#endif
+#endif
+
+/******************************************************************************
+ * DEFINES
+ ******************************************************************************/
+#define SUMMARY_BUFFER_SIZE       (1*1024)
+#define BACKTRACE_BUFFER_SIZE     (128*1024)
+#define NAME_BUFFER_SIZE          (64*1024)
+#define COUNTER_BUFFER_SIZE       (64*1024)	/* counters have the core as part of the data and the core value in the frame header may be discarded */
+#define BLOCK_COUNTER_BUFFER_SIZE (128*1024)
+#define ANNOTATE_BUFFER_SIZE      (128*1024)	/* annotate counters have the core as part of the data and the core value in the frame header may be discarded */
+#define SCHED_TRACE_BUFFER_SIZE   (128*1024)
+#define IDLE_BUFFER_SIZE          (32*1024)	/* idle counters have the core as part of the data and the core value in the frame header may be discarded */
+#define ACTIVITY_BUFFER_SIZE      (128*1024)
+
+#define NO_COOKIE      0U
+#define UNRESOLVED_COOKIE ~0U
+
+#define FRAME_SUMMARY       1
+#define FRAME_BACKTRACE     2
+#define FRAME_NAME          3
+#define FRAME_COUNTER       4
+#define FRAME_BLOCK_COUNTER 5
+#define FRAME_ANNOTATE      6
+#define FRAME_SCHED_TRACE   7
+#define FRAME_IDLE          9
+#define FRAME_ACTIVITY     13
+
+#define MESSAGE_END_BACKTRACE 1
+
+/* Name Frame Messages */
+#define MESSAGE_COOKIE      1
+#define MESSAGE_THREAD_NAME 2
+#define MESSAGE_LINK        4
+
+/* Scheduler Trace Frame Messages */
+#define MESSAGE_SCHED_SWITCH 1
+#define MESSAGE_SCHED_EXIT   2
+
+/* Idle Frame Messages */
+#define MESSAGE_IDLE_ENTER 1
+#define MESSAGE_IDLE_EXIT  2
+
+/* Summary Frame Messages */
+#define MESSAGE_SUMMARY   1
+#define MESSAGE_CORE_NAME 3
+
+/* Activity Frame Messages */
+#define MESSAGE_SWITCH 2
+#define MESSAGE_EXIT   3
+
+#define MAXSIZE_PACK32     5
+#define MAXSIZE_PACK64    10
+
+#define FRAME_HEADER_SIZE 3
+
+#if defined(__arm__)
+#define PC_REG regs->ARM_pc
+#elif defined(__aarch64__)
+#define PC_REG regs->pc
+#else
+#define PC_REG regs->ip
+#endif
+
+enum {
+	SUMMARY_BUF,
+	BACKTRACE_BUF,
+	NAME_BUF,
+	COUNTER_BUF,
+	BLOCK_COUNTER_BUF,
+	ANNOTATE_BUF,
+	SCHED_TRACE_BUF,
+	IDLE_BUF,
+	ACTIVITY_BUF,
+	NUM_GATOR_BUFS
+};
+
+/******************************************************************************
+ * Globals
+ ******************************************************************************/
+static unsigned long gator_cpu_cores;
+/* Size of the largest buffer. Effectively constant, set in gator_op_create_files */
+static unsigned long userspace_buffer_size;
+static unsigned long gator_backtrace_depth;
+/* How often to commit the buffers for live in nanoseconds */
+static u64 gator_live_rate;
+
+static unsigned long gator_started;
+static u64 gator_monotonic_started;
+static u64 gator_sync_time;
+static u64 gator_hibernate_time;
+static unsigned long gator_buffer_opened;
+static unsigned long gator_timer_count;
+static unsigned long gator_response_type;
+static DEFINE_MUTEX(start_mutex);
+static DEFINE_MUTEX(gator_buffer_mutex);
+
+bool event_based_sampling;
+
+static DECLARE_WAIT_QUEUE_HEAD(gator_buffer_wait);
+static DECLARE_WAIT_QUEUE_HEAD(gator_annotate_wait);
+static struct timer_list gator_buffer_wake_up_timer;
+static bool gator_buffer_wake_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_buffer_wake_sem);
+#else
+static DEFINE_SEMAPHORE(gator_buffer_wake_sem);
+#endif
+static struct task_struct *gator_buffer_wake_thread;
+static LIST_HEAD(gator_events);
+
+static DEFINE_PER_CPU(u64, last_timestamp);
+
+static bool printed_monotonic_warning;
+
+static u32 gator_cpuids[NR_CPUS];
+static bool sent_core_name[NR_CPUS];
+
+static DEFINE_PER_CPU(bool, in_scheduler_context);
+
+/******************************************************************************
+ * Prototypes
+ ******************************************************************************/
+static u64 gator_get_time(void);
+static void gator_emit_perf_time(u64 time);
+static void gator_op_create_files(struct super_block *sb, struct dentry *root);
+
+/* gator_buffer is protected by being per_cpu and by having IRQs
+ * disabled when writing to it. Most marshal_* calls take care of this
+ * except for marshal_cookie*, marshal_backtrace* and marshal_frame
+ * where the caller is responsible for doing so. No synchronization is
+ * needed with the backtrace buffer as it is per cpu and is only used
+ * from the hrtimer. The annotate_lock must be held when using the
+ * annotation buffer as it is not per cpu. collect_counters which is
+ * the sole writer to the block counter frame is additionally
+ * protected by the per cpu collecting flag.
+ */
+
+/* Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_size[NUM_GATOR_BUFS];
+/* gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_mask[NUM_GATOR_BUFS];
+/* Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_read);
+/* Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_write);
+/* Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_commit);
+/* If set to false, decreases the number of bytes returned by
+ * buffer_bytes_available. Set in buffer_check_space if no space is
+ * remaining. Initialized to true in gator_op_setup. This means that
+ * if we run out of space, continue to report that no space is
+ * available until bytes are read by userspace
+ */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], buffer_space_available);
+/* The buffer. Allocated in gator_op_setup */
+static DEFINE_PER_CPU(char *[NUM_GATOR_BUFS], gator_buffer);
+/* The time after which the buffer should be committed for live display */
+static DEFINE_PER_CPU(u64, gator_buffer_commit_time);
+
+/* List of all gator events - new events must be added to this list */
+#define GATOR_EVENTS_LIST \
+	GATOR_EVENT(gator_events_armv6_init) \
+	GATOR_EVENT(gator_events_armv7_init) \
+	GATOR_EVENT(gator_events_block_init) \
+	GATOR_EVENT(gator_events_ccn504_init) \
+	GATOR_EVENT(gator_events_irq_init) \
+	GATOR_EVENT(gator_events_l2c310_init) \
+	GATOR_EVENT(gator_events_mali_init) \
+	GATOR_EVENT(gator_events_mali_midgard_hw_init) \
+	GATOR_EVENT(gator_events_mali_midgard_init) \
+	GATOR_EVENT(gator_events_meminfo_init) \
+	GATOR_EVENT(gator_events_mmapped_init) \
+	GATOR_EVENT(gator_events_net_init) \
+	GATOR_EVENT(gator_events_perf_pmu_init) \
+	GATOR_EVENT(gator_events_sched_init) \
+	GATOR_EVENT(gator_events_scorpion_init) \
+
+#define GATOR_EVENT(EVENT_INIT) __weak int EVENT_INIT(void);
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+
+static int (*gator_events_list[])(void) = {
+#define GATOR_EVENT(EVENT_INIT) EVENT_INIT,
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+};
+
+/******************************************************************************
+ * Application Includes
+ ******************************************************************************/
+#include "gator_fs.c"
+#include "gator_buffer_write.c"
+#include "gator_buffer.c"
+#include "gator_marshaling.c"
+#include "gator_hrtimer_gator.c"
+#include "gator_cookies.c"
+#include "gator_annotate.c"
+#include "gator_trace_sched.c"
+#include "gator_trace_power.c"
+#include "gator_trace_gpu.c"
+#include "gator_backtrace.c"
+
+/******************************************************************************
+ * Misc
+ ******************************************************************************/
+
+static const struct gator_cpu gator_cpus[] = {
+	{
+		.cpuid = ARM1136,
+		.core_name = "ARM1136",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1136",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1156,
+		.core_name = "ARM1156",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1156",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1176,
+		.core_name = "ARM1176",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1176",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM11MPCORE,
+		.core_name = "ARM11MPCore",
+		.pmnc_name = "ARM_ARM11MPCore",
+		.dt_name = "arm,arm11mpcore",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = CORTEX_A5,
+		.core_name = "Cortex-A5",
+		.pmnc_name = "ARMv7_Cortex_A5",
+		.dt_name = "arm,cortex-a5",
+		.pmnc_counters = 2,
+	},
+	{
+		.cpuid = CORTEX_A7,
+		.core_name = "Cortex-A7",
+		.pmnc_name = "ARMv7_Cortex_A7",
+		.dt_name = "arm,cortex-a7",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A8,
+		.core_name = "Cortex-A8",
+		.pmnc_name = "ARMv7_Cortex_A8",
+		.dt_name = "arm,cortex-a8",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A9,
+		.core_name = "Cortex-A9",
+		.pmnc_name = "ARMv7_Cortex_A9",
+		.dt_name = "arm,cortex-a9",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A15,
+		.core_name = "Cortex-A15",
+		.pmnc_name = "ARMv7_Cortex_A15",
+		.dt_name = "arm,cortex-a15",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A17,
+		.core_name = "Cortex-A17",
+		.pmnc_name = "ARMv7_Cortex_A17",
+		.dt_name = "arm,cortex-a17",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = SCORPION,
+		.core_name = "Scorpion",
+		.pmnc_name = "Scorpion",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = SCORPIONMP,
+		.core_name = "ScorpionMP",
+		.pmnc_name = "ScorpionMP",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAITSIM,
+		.core_name = "KraitSIM",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT,
+		.core_name = "Krait",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT_S4_PRO,
+		.core_name = "Krait S4 Pro",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A53,
+		.core_name = "Cortex-A53",
+		.pmnc_name = "ARM_Cortex-A53",
+		.dt_name = "arm,cortex-a53",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A57,
+		.core_name = "Cortex-A57",
+		.pmnc_name = "ARM_Cortex-A57",
+		.dt_name = "arm,cortex-a57",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = AARCH64,
+		.core_name = "AArch64",
+		.pmnc_name = "ARM_AArch64",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = OTHER,
+		.core_name = "Other",
+		.pmnc_name = "Other",
+		.pmnc_counters = 6,
+	},
+	{}
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->cpuid == cpuid)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->pmnc_name != NULL &&
+		    /* Do the names match exactly? */
+		    (strcasecmp(gator_cpu->pmnc_name, name) == 0 ||
+		     /* Do these names match but have the old vs new prefix? */
+		     ((strncasecmp(name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) == 0 &&
+		       strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) == 0 &&
+		       strcasecmp(name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) == 0))))
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+u32 gator_cpuid(void)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	u32 val;
+#if !defined(__aarch64__)
+	asm volatile("mrc p15, 0, %0, c0, c0, 0" : "=r" (val));
+#else
+	asm volatile("mrs %0, midr_el1" : "=r" (val));
+#endif
+	return (val >> 4) & 0xfff;
+#else
+	return OTHER;
+#endif
+}
+
+static void gator_buffer_wake_up(unsigned long data)
+{
+	wake_up(&gator_buffer_wait);
+}
+
+static int gator_buffer_wake_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_buffer_wake_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_buffer_wake_sem))
+			;
+
+		if (!gator_buffer_wake_run)
+			break;
+
+		gator_buffer_wake_up(0);
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * Commit interface
+ ******************************************************************************/
+static bool buffer_commit_ready(int *cpu, int *buftype)
+{
+	int cpu_x, x;
+
+	for_each_present_cpu(cpu_x) {
+		for (x = 0; x < NUM_GATOR_BUFS; x++)
+			if (per_cpu(gator_buffer_commit, cpu_x)[x] != per_cpu(gator_buffer_read, cpu_x)[x]) {
+				*cpu = cpu_x;
+				*buftype = x;
+				return true;
+			}
+	}
+	*cpu = -1;
+	*buftype = -1;
+	return false;
+}
+
+/******************************************************************************
+ * hrtimer interrupt processing
+ ******************************************************************************/
+static void gator_timer_interrupt(void)
+{
+	struct pt_regs *const regs = get_irq_regs();
+
+	gator_backtrace_handler(regs);
+}
+
+void gator_backtrace_handler(struct pt_regs *const regs)
+{
+	u64 time = gator_get_time();
+	int cpu = get_physical_cpu();
+
+	/* Output backtrace */
+	gator_add_sample(cpu, regs, time);
+
+	/* Collect counters */
+	if (!per_cpu(collecting, cpu))
+		collect_counters(time, current, false);
+
+	/* No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed */
+#ifdef CONFIG_PREEMPT_RT_FULL
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+#endif
+}
+
+static int gator_running;
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_offline(void *migrate)
+{
+	struct gator_interface *gi;
+	int i, len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	gator_trace_sched_offline();
+	gator_trace_power_offline();
+
+	if (!migrate)
+		gator_hrtimer_offline();
+
+	/* Offline any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->offline) {
+				len = gi->offline(&buffer, migrate);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	/* Flush all buffers on this core */
+	for (i = 0; i < NUM_GATOR_BUFS; i++)
+		gator_commit_buffer(cpu, i, time);
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_offline_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->offline_dispatch)
+			gi->offline_dispatch(cpu, migrate);
+	}
+}
+
+static void gator_timer_stop(void)
+{
+	int cpu;
+
+	if (gator_running) {
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		gator_running = 0;
+		gator_hrtimer_shutdown();
+	}
+}
+
+static void gator_send_core_name(const int cpu, const u32 cpuid)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	if (!sent_core_name[cpu] || (cpuid != gator_cpuids[cpu])) {
+		const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(cpuid);
+		const char *core_name = NULL;
+		char core_name_buf[32];
+
+		/* Save off this cpuid */
+		gator_cpuids[cpu] = cpuid;
+		if (gator_cpu != NULL) {
+			core_name = gator_cpu->core_name;
+		} else {
+			if (cpuid == -1)
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown");
+			else
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown (0x%.3x)", cpuid);
+			core_name = core_name_buf;
+		}
+
+		marshal_core_name(cpu, cpuid, core_name);
+		sent_core_name[cpu] = true;
+	}
+#endif
+}
+
+static void gator_read_cpuid(void *arg)
+{
+	gator_cpuids[get_physical_cpu()] = gator_cpuid();
+}
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_online(void *migrate)
+{
+	struct gator_interface *gi;
+	int len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	/* Send what is currently running on this core */
+	marshal_sched_trace_switch(current->pid, 0);
+
+	gator_trace_power_online();
+
+	/* online any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->online) {
+				len = gi->online(&buffer, migrate);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	if (!migrate)
+		gator_hrtimer_online();
+
+	gator_send_core_name(cpu, gator_cpuid());
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_online_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->online_dispatch)
+			gi->online_dispatch(cpu, migrate);
+	}
+}
+
+#include "gator_iks.c"
+
+static int gator_timer_start(unsigned long sample_rate)
+{
+	int cpu;
+
+	if (gator_running) {
+		pr_notice("gator: already running\n");
+		return 0;
+	}
+
+	gator_running = 1;
+
+	/* event based sampling trumps hr timer based sampling */
+	if (event_based_sampling)
+		sample_rate = 0;
+
+	if (gator_hrtimer_init(sample_rate, gator_timer_interrupt) == -1)
+		return -1;
+
+	/* Send off the previously saved cpuids */
+	for_each_present_cpu(cpu) {
+		preempt_disable();
+		gator_send_core_name(cpu, gator_cpuids[cpu]);
+		preempt_enable();
+	}
+
+	gator_send_iks_core_names();
+	for_each_online_cpu(cpu) {
+		gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+	}
+	on_each_cpu(gator_timer_online, NULL, 1);
+
+	return 0;
+}
+
+static u64 gator_get_time(void)
+{
+	struct timespec ts;
+	u64 timestamp;
+	u64 prev_timestamp;
+	u64 delta;
+	int cpu = smp_processor_id();
+
+	/* Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace */
+	getrawmonotonic(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* getrawmonotonic is not monotonic on all systems. Detect and
+	 * attempt to correct these cases. up to 0.5ms delta has been seen
+	 * on some systems, which can skew Streamline data when viewing at
+	 * high resolution. This doesn't work well with interrupts, but that
+	 * it's OK - the real concern is to catch big jumps in time
+	 */
+	prev_timestamp = per_cpu(last_timestamp, cpu);
+	if (prev_timestamp <= timestamp) {
+		per_cpu(last_timestamp, cpu) = timestamp;
+	} else {
+		delta = prev_timestamp - timestamp;
+		/* Log the error once */
+		if (!printed_monotonic_warning && delta > 500000) {
+			pr_err("%s: getrawmonotonic is not monotonic  cpu: %i  delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __func__, cpu, delta);
+			printed_monotonic_warning = true;
+		}
+		timestamp = prev_timestamp;
+	}
+
+	return timestamp - gator_monotonic_started;
+}
+
+static void gator_emit_perf_time(u64 time)
+{
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 10, 0)
+	if (time >= gator_sync_time) {
+		int cpu = get_physical_cpu();
+
+		marshal_event_single64(0, -1, local_clock());
+		gator_sync_time += NSEC_PER_SEC;
+		gator_commit_buffer(cpu, COUNTER_BUF, time);
+	}
+#endif
+}
+
+/******************************************************************************
+ * cpu hotplug and pm notifiers
+ ******************************************************************************/
+static int __cpuinit gator_hotcpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	int cpu = lcpu_to_pcpu((long)hcpu);
+
+	switch (action) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		smp_call_function_single(cpu, gator_timer_offline, NULL, 1);
+		gator_timer_offline_dispatch(cpu, false);
+		break;
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		gator_timer_online_dispatch(cpu, false);
+		smp_call_function_single(cpu, gator_timer_online, NULL, 1);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata gator_hotcpu_notifier = {
+	.notifier_call = gator_hotcpu_notify,
+};
+
+/* n.b. calling "on_each_cpu" only runs on those that are online.
+ * Registered linux events are not disabled, so their counters will
+ * continue to collect
+ */
+static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void *dummy)
+{
+	int cpu;
+	struct timespec ts;
+
+	switch (event) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+		unregister_scheduler_tracepoints();
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		/* Record the wallclock hibernate time */
+		getnstimeofday(&ts);
+		gator_hibernate_time = timespec_to_ns(&ts) - gator_get_time();
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		/* Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it */
+		if (gator_hibernate_time > 0) {
+			getnstimeofday(&ts);
+			gator_monotonic_started += gator_hibernate_time + gator_get_time() - timespec_to_ns(&ts);
+			gator_hibernate_time = 0;
+		}
+
+		for_each_online_cpu(cpu) {
+			gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+		on_each_cpu(gator_timer_online, NULL, 1);
+		register_scheduler_tracepoints();
+		register_hotcpu_notifier(&gator_hotcpu_notifier);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gator_pm_notifier = {
+	.notifier_call = gator_pm_notify,
+};
+
+static int gator_notifier_start(void)
+{
+	int retval;
+
+	retval = register_hotcpu_notifier(&gator_hotcpu_notifier);
+	if (retval == 0)
+		retval = register_pm_notifier(&gator_pm_notifier);
+	return retval;
+}
+
+static void gator_notifier_stop(void)
+{
+	unregister_pm_notifier(&gator_pm_notifier);
+	unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+}
+
+/******************************************************************************
+ * Main
+ ******************************************************************************/
+static void gator_summary(void)
+{
+	u64 timestamp, uptime;
+	struct timespec ts;
+	char uname_buf[512];
+
+	snprintf(uname_buf, sizeof(uname_buf), "%s %s %s %s %s GNU/Linux", utsname()->sysname, utsname()->nodename, utsname()->release, utsname()->version, utsname()->machine);
+
+	getnstimeofday(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* Similar to reading /proc/uptime from fs/proc/uptime.c, calculate uptime */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 11, 0)
+	{
+		void (*m2b)(struct timespec *ts);
+
+		do_posix_clock_monotonic_gettime(&ts);
+		/* monotonic_to_bootbased is not defined for some versions of Android */
+		m2b = symbol_get(monotonic_to_bootbased);
+		if (m2b)
+			m2b(&ts);
+	}
+#else
+	get_monotonic_boottime(&ts);
+#endif
+	uptime = timespec_to_ns(&ts);
+
+	/* Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic */
+	preempt_disable();
+	/* Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started */
+	gator_monotonic_started = 0;
+	gator_monotonic_started = gator_get_time();
+
+	marshal_summary(timestamp, uptime, gator_monotonic_started, uname_buf);
+	gator_sync_time = 0;
+	gator_emit_perf_time(gator_monotonic_started);	
+	preempt_enable();
+}
+
+int gator_events_install(struct gator_interface *interface)
+{
+	list_add_tail(&interface->list, &gator_events);
+
+	return 0;
+}
+
+int gator_events_get_key(void)
+{
+	/* key 0 is reserved as a timestamp. key 1 is reserved as the marker
+	 * for thread specific counters. key 2 is reserved as the marker for
+	 * core. Odd keys are assigned by the driver, even keys by the
+	 * daemon.
+	 */
+	static int key = 3;
+	const int ret = key;
+
+	key += 2;
+	return ret;
+}
+
+static int gator_init(void)
+{
+	int i;
+
+	calc_first_cluster_size();
+
+	/* events sources */
+	for (i = 0; i < ARRAY_SIZE(gator_events_list); i++)
+		if (gator_events_list[i])
+			gator_events_list[i]();
+
+	gator_trace_sched_init();
+	gator_trace_power_init();
+
+	return 0;
+}
+
+static void gator_exit(void)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->shutdown)
+			gi->shutdown();
+}
+
+static int gator_start(void)
+{
+	unsigned long cpu, i;
+	struct gator_interface *gi;
+
+	gator_buffer_wake_run = true;
+	gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake");
+	if (IS_ERR(gator_buffer_wake_thread))
+		goto bwake_failure;
+
+	if (gator_migrate_start())
+		goto migrate_failure;
+
+	/* Initialize the buffer with the frame type and core */
+	for_each_present_cpu(cpu) {
+		for (i = 0; i < NUM_GATOR_BUFS; i++)
+			marshal_frame(cpu, i);
+		per_cpu(last_timestamp, cpu) = 0;
+	}
+	printed_monotonic_warning = false;
+
+	/* Capture the start time */
+	gator_summary();
+
+	/* start all events */
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->start && gi->start() != 0) {
+			struct list_head *ptr = gi->list.prev;
+
+			while (ptr != &gator_events) {
+				gi = list_entry(ptr, struct gator_interface, list);
+
+				if (gi->stop)
+					gi->stop();
+
+				ptr = ptr->prev;
+			}
+			goto events_failure;
+		}
+	}
+
+	/* cookies shall be initialized before trace_sched_start() and gator_timer_start() */
+	if (cookies_initialize())
+		goto cookies_failure;
+	if (gator_annotate_start())
+		goto annotate_failure;
+	if (gator_trace_sched_start())
+		goto sched_failure;
+	if (gator_trace_power_start())
+		goto power_failure;
+	if (gator_trace_gpu_start())
+		goto gpu_failure;
+	if (gator_timer_start(gator_timer_count))
+		goto timer_failure;
+	if (gator_notifier_start())
+		goto notifier_failure;
+
+	return 0;
+
+notifier_failure:
+	gator_timer_stop();
+timer_failure:
+	gator_trace_gpu_stop();
+gpu_failure:
+	gator_trace_power_stop();
+power_failure:
+	gator_trace_sched_stop();
+sched_failure:
+	gator_annotate_stop();
+annotate_failure:
+	cookies_release();
+cookies_failure:
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+events_failure:
+	gator_migrate_stop();
+migrate_failure:
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+bwake_failure:
+
+	return -1;
+}
+
+static void gator_stop(void)
+{
+	struct gator_interface *gi;
+
+	gator_annotate_stop();
+	gator_trace_sched_stop();
+	gator_trace_power_stop();
+	gator_trace_gpu_stop();
+
+	/* stop all interrupt callback reads before tearing down other interfaces */
+	gator_notifier_stop();	/* should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined */
+	gator_timer_stop();
+
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+
+	gator_migrate_stop();
+
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+}
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+/* fopen("buffer") */
+static int gator_op_setup(void)
+{
+	int err = 0;
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	gator_buffer_size[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE;
+	gator_buffer_mask[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE;
+	gator_buffer_mask[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[NAME_BUF] = NAME_BUFFER_SIZE;
+	gator_buffer_mask[NAME_BUF] = NAME_BUFFER_SIZE - 1;
+
+	gator_buffer_size[COUNTER_BUF] = COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[COUNTER_BUF] = COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE;
+	gator_buffer_mask[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE;
+	gator_buffer_mask[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[IDLE_BUF] = IDLE_BUFFER_SIZE;
+	gator_buffer_mask[IDLE_BUF] = IDLE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE;
+	gator_buffer_mask[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE - 1;
+
+	/* Initialize percpu per buffer variables */
+	for (i = 0; i < NUM_GATOR_BUFS; i++) {
+		/* Verify buffers are a power of 2 */
+		if (gator_buffer_size[i] & (gator_buffer_size[i] - 1)) {
+			err = -ENOEXEC;
+			goto setup_error;
+		}
+
+		for_each_present_cpu(cpu) {
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = gator_live_rate;
+
+			/* Annotation is a special case that only uses a single buffer */
+			if (cpu > 0 && i == ANNOTATE_BUF) {
+				per_cpu(gator_buffer, cpu)[i] = NULL;
+				continue;
+			}
+
+			per_cpu(gator_buffer, cpu)[i] = vmalloc(gator_buffer_size[i]);
+			if (!per_cpu(gator_buffer, cpu)[i]) {
+				err = -ENOMEM;
+				goto setup_error;
+			}
+		}
+	}
+
+setup_error:
+	mutex_unlock(&start_mutex);
+	return err;
+}
+
+/* Actually start profiling (echo 1>/dev/gator/enable) */
+static int gator_op_start(void)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started || gator_start())
+		err = -EINVAL;
+	else
+		gator_started = 1;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+/* echo 0>/dev/gator/enable */
+static void gator_op_stop(void)
+{
+	mutex_lock(&start_mutex);
+
+	if (gator_started) {
+		gator_stop();
+
+		mutex_lock(&gator_buffer_mutex);
+
+		gator_started = 0;
+		gator_monotonic_started = 0;
+		cookies_release();
+		wake_up(&gator_buffer_wait);
+
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void gator_shutdown(void)
+{
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	for_each_present_cpu(cpu) {
+		mutex_lock(&gator_buffer_mutex);
+		for (i = 0; i < NUM_GATOR_BUFS; i++) {
+			vfree(per_cpu(gator_buffer, cpu)[i]);
+			per_cpu(gator_buffer, cpu)[i] = NULL;
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = 0;
+		}
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	memset(&sent_core_name, 0, sizeof(sent_core_name));
+
+	mutex_unlock(&start_mutex);
+}
+
+static int gator_set_backtrace(unsigned long val)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started)
+		err = -EBUSY;
+	else
+		gator_backtrace_depth = val;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+static ssize_t enable_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_started, buf, count, offset);
+}
+
+static ssize_t enable_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val)
+		retval = gator_op_start();
+	else
+		gator_op_stop();
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations enable_fops = {
+	.read = enable_read,
+	.write = enable_write,
+};
+
+static int userspace_buffer_open(struct inode *inode, struct file *file)
+{
+	int err = -EPERM;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (test_and_set_bit_lock(0, &gator_buffer_opened))
+		return -EBUSY;
+
+	err = gator_op_setup();
+	if (err)
+		goto fail;
+
+	/* NB: the actual start happens from userspace
+	 * echo 1 >/dev/gator/enable
+	 */
+
+	return 0;
+
+fail:
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return err;
+}
+
+static int userspace_buffer_release(struct inode *inode, struct file *file)
+{
+	gator_op_stop();
+	gator_shutdown();
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return 0;
+}
+
+static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	int commit, length1, length2, read;
+	char *buffer1;
+	char *buffer2;
+	int cpu, buftype;
+	int written = 0;
+
+	/* ensure there is enough space for a whole frame */
+	if (count < userspace_buffer_size || *offset)
+		return -EINVAL;
+
+	/* sleep until the condition is true or a signal is received the
+	 * condition is checked each time gator_buffer_wait is woken up
+	 */
+	wait_event_interruptible(gator_buffer_wait, buffer_commit_ready(&cpu, &buftype) || !gator_started);
+
+	if (signal_pending(current))
+		return -EINTR;
+
+	if (buftype == -1 || cpu == -1)
+		return 0;
+
+	mutex_lock(&gator_buffer_mutex);
+
+	do {
+		read = per_cpu(gator_buffer_read, cpu)[buftype];
+		commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+
+		/* May happen if the buffer is freed during pending reads. */
+		if (!per_cpu(gator_buffer, cpu)[buftype])
+			break;
+
+		/* determine the size of two halves */
+		length1 = commit - read;
+		length2 = 0;
+		buffer1 = &(per_cpu(gator_buffer, cpu)[buftype][read]);
+		buffer2 = &(per_cpu(gator_buffer, cpu)[buftype][0]);
+		if (length1 < 0) {
+			length1 = gator_buffer_size[buftype] - read;
+			length2 = commit;
+		}
+
+		if (length1 + length2 > count - written)
+			break;
+
+		/* start, middle or end */
+		if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1))
+			break;
+
+		/* possible wrap around */
+		if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2))
+			break;
+
+		per_cpu(gator_buffer_read, cpu)[buftype] = commit;
+		written += length1 + length2;
+
+		/* Wake up annotate_write if more space is available */
+		if (buftype == ANNOTATE_BUF)
+			wake_up(&gator_annotate_wait);
+	} while (buffer_commit_ready(&cpu, &buftype));
+
+	mutex_unlock(&gator_buffer_mutex);
+
+	/* kick just in case we've lost an SMP event */
+	wake_up(&gator_buffer_wait);
+
+	return written > 0 ? written : -EFAULT;
+}
+
+static const struct file_operations gator_event_buffer_fops = {
+	.open = userspace_buffer_open,
+	.release = userspace_buffer_release,
+	.read = userspace_buffer_read,
+};
+
+static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_backtrace_depth, buf, count, offset);
+}
+
+static ssize_t depth_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	retval = gator_set_backtrace(val);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations depth_fops = {
+	.read = depth_read,
+	.write = depth_write
+};
+
+static void gator_op_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	struct gator_interface *gi;
+	int cpu;
+
+	/* reinitialize default values */
+	gator_cpu_cores = 0;
+	for_each_present_cpu(cpu) {
+		gator_cpu_cores++;
+	}
+	userspace_buffer_size = BACKTRACE_BUFFER_SIZE;
+	gator_response_type = 1;
+	gator_live_rate = 0;
+
+	gatorfs_create_file(sb, root, "enable", &enable_fops);
+	gatorfs_create_file(sb, root, "buffer", &gator_event_buffer_fops);
+	gatorfs_create_file(sb, root, "backtrace_depth", &depth_fops);
+	gatorfs_create_ro_ulong(sb, root, "cpu_cores", &gator_cpu_cores);
+	gatorfs_create_ro_ulong(sb, root, "buffer_size", &userspace_buffer_size);
+	gatorfs_create_ulong(sb, root, "tick", &gator_timer_count);
+	gatorfs_create_ulong(sb, root, "response_type", &gator_response_type);
+	gatorfs_create_ro_ulong(sb, root, "version", &gator_protocol_version);
+	gatorfs_create_ro_u64(sb, root, "started", &gator_monotonic_started);
+	gatorfs_create_u64(sb, root, "live_rate", &gator_live_rate);
+
+	/* Annotate interface */
+	gator_annotate_create_files(sb, root);
+
+	/* Linux Events */
+	dir = gatorfs_mkdir(sb, root, "events");
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->create_files)
+			gi->create_files(sb, dir);
+
+	/* Sched Events */
+	sched_trace_create_files(sb, dir);
+
+	/* Power interface */
+	gator_trace_power_create_files(sb, dir);
+}
+
+/******************************************************************************
+ * Module
+ ******************************************************************************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 15, 0)
+
+#define GATOR_TRACEPOINTS \
+	GATOR_HANDLE_TRACEPOINT(block_rq_complete); \
+	GATOR_HANDLE_TRACEPOINT(cpu_frequency); \
+	GATOR_HANDLE_TRACEPOINT(cpu_idle); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_begin); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_current); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_finish); \
+	GATOR_HANDLE_TRACEPOINT(irq_handler_exit); \
+	GATOR_HANDLE_TRACEPOINT(mali_hw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_job_slots_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_in_use); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_released); \
+	GATOR_HANDLE_TRACEPOINT(mali_page_fault_insert_pages); \
+	GATOR_HANDLE_TRACEPOINT(mali_pm_status); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counters); \
+	GATOR_HANDLE_TRACEPOINT(mali_timeline_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_total_alloc_pages_change); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_alloc); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free_batched); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_exec); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_fork); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_free); \
+	GATOR_HANDLE_TRACEPOINT(sched_switch); \
+	GATOR_HANDLE_TRACEPOINT(softirq_exit); \
+	GATOR_HANDLE_TRACEPOINT(task_rename); \
+
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	struct tracepoint *gator_tracepoint_##probe_name
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+
+static void gator_save_tracepoint(struct tracepoint *tp, void *priv)
+{
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	do { \
+		if (strcmp(tp->name, #probe_name) == 0) { \
+			gator_tracepoint_##probe_name = tp; \
+			return; \
+		} \
+	} while (0)
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+}
+
+#else
+
+#define for_each_kernel_tracepoint(fct, priv)
+
+#endif
+
+static int __init gator_module_init(void)
+{
+	for_each_kernel_tracepoint(gator_save_tracepoint, NULL);
+
+	if (gatorfs_register())
+		return -1;
+
+	if (gator_init()) {
+		gatorfs_unregister();
+		return -1;
+	}
+
+	setup_timer(&gator_buffer_wake_up_timer, gator_buffer_wake_up, 0);
+
+	/* Initialize the list of cpuids */
+	memset(gator_cpuids, -1, sizeof(gator_cpuids));
+	on_each_cpu(gator_read_cpuid, NULL, 1);
+
+	return 0;
+}
+
+static void __exit gator_module_exit(void)
+{
+	del_timer_sync(&gator_buffer_wake_up_timer);
+	tracepoint_synchronize_unregister();
+	gator_exit();
+	gatorfs_unregister();
+}
+
+module_init(gator_module_init);
+module_exit(gator_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ARM Ltd");
+MODULE_DESCRIPTION("Gator system profiler");
+#define STRIFY2(ARG) #ARG
+#define STRIFY(ARG) STRIFY2(ARG)
+MODULE_VERSION(STRIFY(PROTOCOL_VERSION));
diff --git a/drivers/gator/gator_marshaling.c b/drivers/gator/gator_marshaling.c
new file mode 100644
index 000000000000..0d1167643642
--- /dev/null
+++ b/drivers/gator/gator_marshaling.c
@@ -0,0 +1,371 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+#ifdef MALI_SUPPORT
+#include "gator_events_mali_common.h"
+#endif
+
+static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char *uname)
+{
+	unsigned long flags;
+	int cpu = 0;
+
+	local_irq_save(flags);
+	gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_SUMMARY);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, NEWLINE_CANARY);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, timestamp);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, uptime);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, monotonic_delta);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "uname");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, uname);
+#if GATOR_IKS_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "iks");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RTB
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rtb");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rt_full");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+	/* Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. */
+#ifdef MALI_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "mali_type");
+#if (MALI_SUPPORT == MALI_4xx)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "4xx");
+#elif (MALI_SUPPORT == MALI_MIDGARD)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "6xx");
+#else
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "unknown");
+#endif
+#endif
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+	/* Commit the buffer now so it can be one of the first frames read by Streamline */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+
+static bool marshal_cookie_header(const char *text)
+{
+	int cpu = get_physical_cpu();
+
+	return buffer_check_space(cpu, NAME_BUF, strlen(text) + 3 * MAXSIZE_PACK32);
+}
+
+static void marshal_cookie(int cookie, const char *text)
+{
+	int cpu = get_physical_cpu();
+	/* buffer_check_space already called by marshal_cookie_header */
+	gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_COOKIE);
+	gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+	gator_buffer_write_string(cpu, NAME_BUF, text);
+	buffer_check(cpu, NAME_BUF, gator_get_time());
+}
+
+static void marshal_thread_name(int pid, char *name)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, NAME_BUF, TASK_COMM_LEN + 3 * MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_THREAD_NAME);
+		gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+		gator_buffer_write_string(cpu, NAME_BUF, name);
+	}
+	local_irq_restore(flags);
+	buffer_check(cpu, NAME_BUF, time);
+}
+
+static void marshal_link(int cookie, int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, NAME_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_LINK);
+		gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, tgid);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, NAME_BUF, time);
+}
+
+static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	if (!buffer_check_space(cpu, BACKTRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32 + gator_backtrace_depth * 2 * MAXSIZE_PACK32)) {
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, BACKTRACE_BUF, time);
+
+		return false;
+	}
+
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, time);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, exec_cookie);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, tgid);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, pid);
+
+	return true;
+}
+
+static void marshal_backtrace(unsigned long address, int cookie, int in_kernel)
+{
+	int cpu = get_physical_cpu();
+
+	if (cookie == 0 && !in_kernel)
+		cookie = UNRESOLVED_COOKIE;
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, cookie);
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, address);
+}
+
+static void marshal_backtrace_footer(u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, MESSAGE_END_BACKTRACE);
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, BACKTRACE_BUF, time);
+}
+
+static bool marshal_event_header(u64 time)
+{
+	unsigned long flags, cpu = get_physical_cpu();
+	bool retval = false;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, BLOCK_COUNTER_BUF, MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0);	/* key of zero indicates a timestamp */
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, time);
+		retval = true;
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+static void marshal_event(int len, int *buffer)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32))
+			break;
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i]);
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void marshal_event64(int len, long long *buffer64)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64))
+			break;
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i]);
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void __maybe_unused marshal_event_single(int core, int key, int value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void __maybe_unused marshal_event_single64(int core, int key, long long value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, 2 * MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void marshal_sched_trace_switch(int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_SWITCH);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+static void marshal_sched_trace_exit(int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_EXIT);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+#if GATOR_CPU_FREQ_SUPPORT
+static void marshal_idle(int core, int state)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, IDLE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, state);
+		gator_buffer_write_packed_int64(cpu, IDLE_BUF, time);
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, core);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, IDLE_BUF, time);
+}
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+static void marshal_core_name(const int core, const int cpuid, const char *name)
+{
+	int cpu = get_physical_cpu();
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, SUMMARY_BUF, MAXSIZE_PACK32 + MAXSIZE_CORE_NAME)) {
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_CORE_NAME);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, core);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, cpuid);
+		gator_buffer_write_string(cpu, SUMMARY_BUF, name);
+	}
+	/* Commit core names now so that they can show up in live */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+#endif
+
+static void marshal_activity_switch(int core, int key, int activity, int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[ACTIVITY_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_SWITCH);
+		gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, core);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, key);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, activity);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid)
+{
+	/* state is reserved for cpu use only */
+	marshal_activity_switch(core, key, activity, pid, 0);
+}
diff --git a/drivers/gator/gator_trace_gpu.c b/drivers/gator/gator_trace_gpu.c
new file mode 100644
index 000000000000..5de9152e365a
--- /dev/null
+++ b/drivers/gator/gator_trace_gpu.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#ifdef MALI_SUPPORT
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+#endif
+
+/*
+ * Taken from MALI_PROFILING_EVENT_TYPE_* items in Mali DDK.
+ */
+#define EVENT_TYPE_SINGLE  0
+#define EVENT_TYPE_START   1
+#define EVENT_TYPE_STOP    2
+#define EVENT_TYPE_SUSPEND 3
+#define EVENT_TYPE_RESUME  4
+
+/* Note whether tracepoints have been registered */
+static int mali_timeline_trace_registered;
+static int mali_job_slots_trace_registered;
+
+enum {
+	GPU_UNIT_NONE = 0,
+	GPU_UNIT_VP,
+	GPU_UNIT_FP,
+	GPU_UNIT_CL,
+	NUMBER_OF_GPU_UNITS
+};
+
+#if defined(MALI_SUPPORT)
+
+struct mali_activity {
+	int core;
+	int key;
+	int count;
+	int last_activity;
+	int last_pid;
+};
+
+#define NUMBER_OF_GPU_CORES 16
+static struct mali_activity mali_activities[NUMBER_OF_GPU_UNITS*NUMBER_OF_GPU_CORES];
+static DEFINE_SPINLOCK(mali_activities_lock);
+
+/* Only one event should be running on a unit and core at a time (ie,
+ * a start event can only be followed by a stop and vice versa), but
+ * because the kernel only knows when a job is enqueued and not
+ * started, it is possible for a start1, start2, stop1, stop2. Change
+ * it back into start1, stop1, start2, stop2 by queueing up start2 and
+ * releasing it when stop1 is received.
+ */
+
+static int mali_activity_index(int core, int key)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mali_activities); ++i) {
+		if ((mali_activities[i].core == core) && (mali_activities[i].key == key))
+			break;
+		if ((mali_activities[i].core == 0) && (mali_activities[i].key == 0)) {
+			mali_activities[i].core = core;
+			mali_activities[i].key = key;
+			break;
+		}
+	}
+	BUG_ON(i >= ARRAY_SIZE(mali_activities));
+
+	return i;
+}
+
+static void mali_activity_enqueue(int core, int key, int activity, int pid)
+{
+	int i;
+	int count;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	count = mali_activities[i].count;
+	BUG_ON(count < 0);
+	++mali_activities[i].count;
+	if (count) {
+		mali_activities[i].last_activity = activity;
+		mali_activities[i].last_pid = pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	if (!count)
+		gator_marshal_activity_switch(core, key, activity, pid);
+}
+
+static void mali_activity_stop(int core, int key)
+{
+	int i;
+	int count;
+	int last_activity = 0;
+	int last_pid = 0;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	if (mali_activities[i].count == 0) {
+		spin_unlock(&mali_activities_lock);
+		return;
+	}
+	--mali_activities[i].count;
+	count = mali_activities[i].count;
+	if (count) {
+		last_activity = mali_activities[i].last_activity;
+		last_pid = mali_activities[i].last_pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	gator_marshal_activity_switch(core, key, 0, 0);
+	if (count)
+		gator_marshal_activity_switch(core, key, last_activity, last_pid);
+}
+
+void mali_activity_clear(struct mali_counter mali_activity[], size_t mali_activity_size)
+{
+	int activity;
+	int cores;
+	int core;
+
+	for (activity = 0; activity < mali_activity_size; ++activity) {
+		cores = mali_activity[activity].cores;
+		if (cores < 0)
+			cores = 1;
+		for (core = 0; core < cores; ++core) {
+			if (mali_activity[activity].enabled) {
+				preempt_disable();
+				gator_marshal_activity_switch(core, mali_activity[activity].key, 0, 0);
+				preempt_enable();
+			}
+		}
+	}
+}
+
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+#include "gator_events_mali_4xx.h"
+
+/*
+ * Taken from MALI_PROFILING_EVENT_CHANNEL_* in Mali DDK.
+ */
+enum {
+	EVENT_CHANNEL_SOFTWARE = 0,
+	EVENT_CHANNEL_VP0 = 1,
+	EVENT_CHANNEL_FP0 = 5,
+	EVENT_CHANNEL_FP1,
+	EVENT_CHANNEL_FP2,
+	EVENT_CHANNEL_FP3,
+	EVENT_CHANNEL_FP4,
+	EVENT_CHANNEL_FP5,
+	EVENT_CHANNEL_FP6,
+	EVENT_CHANNEL_FP7,
+	EVENT_CHANNEL_GPU = 21
+};
+
+/**
+ * These events are applicable when the type MALI_PROFILING_EVENT_TYPE_SINGLE is used from the GPU channel
+ */
+enum {
+	EVENT_REASON_SINGLE_GPU_NONE = 0,
+	EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE = 1,
+};
+
+struct mali_counter mali_activity[2];
+
+GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned int d0, unsigned int d1, unsigned int d2, unsigned int d3, unsigned int d4))
+{
+	unsigned int component, state;
+
+	/* do as much work as possible before disabling interrupts */
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (state) {
+	case EVENT_TYPE_START:
+		if (component == EVENT_CHANNEL_VP0) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[1].enabled)
+				mali_activity_enqueue(0, mali_activity[1].key, 1, d1);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[0].enabled)
+				mali_activity_enqueue(component - EVENT_CHANNEL_FP0, mali_activity[0].key, 1, d1);
+		}
+		break;
+
+	case EVENT_TYPE_STOP:
+		if (component == EVENT_CHANNEL_VP0) {
+			if (mali_activity[1].enabled)
+				mali_activity_stop(0, mali_activity[1].key);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			if (mali_activity[0].enabled)
+				mali_activity_stop(component - EVENT_CHANNEL_FP0, mali_activity[0].key);
+		}
+		break;
+
+	case EVENT_TYPE_SINGLE:
+		if (component == EVENT_CHANNEL_GPU) {
+			unsigned int reason = (event_id & 0xffff);
+
+			if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE)
+				gator_events_mali_log_dvfs_event(d0, d1);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+
+struct mali_counter mali_activity[3];
+
+#if defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid, unsigned char job_id))
+#else
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid))
+#endif
+{
+	unsigned int component, state, unit;
+#if !defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+	unsigned char job_id = 0;
+#endif
+
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (component) {
+	case 0:
+		unit = GPU_UNIT_FP;
+		break;
+	case 1:
+		unit = GPU_UNIT_VP;
+		break;
+	case 2:
+		unit = GPU_UNIT_CL;
+		break;
+	default:
+		unit = GPU_UNIT_NONE;
+	}
+
+	if (unit != GPU_UNIT_NONE) {
+		switch (state) {
+		case EVENT_TYPE_START:
+			if (mali_activity[component].enabled)
+				mali_activity_enqueue(0, mali_activity[component].key, 1, (pid != 0 ? pid : tgid));
+			break;
+		case EVENT_TYPE_STOP:
+		default: /* Some jobs can be soft-stopped, so ensure that this terminates the activity trace. */
+			if (mali_activity[component].enabled)
+				mali_activity_stop(0, mali_activity[component].key);
+			break;
+		}
+	}
+}
+#endif
+
+static int gator_trace_gpu_start(void)
+{
+	/*
+	 * Returns nonzero for installation failed
+	 * Absence of gpu trace points is not an error
+	 */
+
+#if defined(MALI_SUPPORT)
+	memset(&mali_activities, 0, sizeof(mali_activities));
+#endif
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_timeline_event))
+		mali_timeline_trace_registered = 1;
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_job_slots_event))
+		mali_job_slots_trace_registered = 1;
+#endif
+
+	return 0;
+}
+
+static void gator_trace_gpu_stop(void)
+{
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	if (mali_timeline_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_timeline_event);
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	if (mali_job_slots_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_job_slots_event);
+#endif
+
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+}
diff --git a/drivers/gator/gator_trace_power.c b/drivers/gator/gator_trace_power.c
new file mode 100644
index 000000000000..46e04b29a187
--- /dev/null
+++ b/drivers/gator/gator_trace_power.c
@@ -0,0 +1,192 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <trace/events/power.h>
+
+#if defined(__arm__)
+
+#include <asm/mach-types.h>
+
+#define implements_wfi() (!machine_is_omap3_beagle())
+
+#else
+
+#define implements_wfi() false
+
+#endif
+
+/* cpu_frequency and cpu_idle trace points were introduced in Linux
+ * kernel v2.6.38 the now deprecated power_frequency trace point was
+ * available prior to 2.6.38, but only for x86
+ */
+#if GATOR_CPU_FREQ_SUPPORT
+enum {
+	POWER_CPU_FREQ,
+	POWER_TOTAL
+};
+
+static DEFINE_PER_CPU(ulong, idle_prev_state);
+static ulong power_cpu_enabled[POWER_TOTAL];
+static ulong power_cpu_key[POWER_TOTAL];
+static ulong power_cpu_cores;
+
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int cpu;
+	bool found_nonzero_freq = false;
+
+	/* Even if CONFIG_CPU_FREQ is defined, it still may not be
+	 * used. Check for non-zero values from cpufreq_quick_get
+	 */
+	for_each_online_cpu(cpu) {
+		if (cpufreq_quick_get(cpu) > 0) {
+			found_nonzero_freq = true;
+			break;
+		}
+	}
+
+	if (found_nonzero_freq) {
+		/* cpu_frequency */
+		dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_freq");
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_FREQ]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_FREQ]);
+	}
+
+	return 0;
+}
+
+/* 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change */
+GATOR_DEFINE_PROBE(cpu_frequency, TP_PROTO(unsigned int frequency, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+	marshal_event_single64(cpu, power_cpu_key[POWER_CPU_FREQ], frequency * 1000L);
+}
+
+GATOR_DEFINE_PROBE(cpu_idle, TP_PROTO(unsigned int state, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+
+	if (state == per_cpu(idle_prev_state, cpu))
+		return;
+
+	if (implements_wfi()) {
+		if (state == PWR_EVENT_EXIT) {
+			/* transition from wfi to non-wfi */
+			marshal_idle(cpu, MESSAGE_IDLE_EXIT);
+		} else {
+			/* transition from non-wfi to wfi */
+			marshal_idle(cpu, MESSAGE_IDLE_ENTER);
+		}
+	}
+
+	per_cpu(idle_prev_state, cpu) = state;
+}
+
+static void gator_trace_power_online(void)
+{
+	int pcpu = get_physical_cpu();
+	int lcpu = get_logical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single64(pcpu, power_cpu_key[POWER_CPU_FREQ], cpufreq_quick_get(lcpu) * 1000L);
+}
+
+static void gator_trace_power_offline(void)
+{
+	/* Set frequency to zero on an offline */
+	int cpu = get_physical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single(cpu, power_cpu_key[POWER_CPU_FREQ], 0);
+}
+
+static int gator_trace_power_start(void)
+{
+	int cpu;
+
+	/* register tracepoints */
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		if (GATOR_REGISTER_TRACE(cpu_frequency))
+			goto fail_cpu_frequency_exit;
+
+	/* Always register for cpu_idle for detecting WFI */
+	if (GATOR_REGISTER_TRACE(cpu_idle))
+		goto fail_cpu_idle_exit;
+	pr_debug("gator: registered power event tracepoints\n");
+
+	for_each_present_cpu(cpu) {
+		per_cpu(idle_prev_state, cpu) = 0;
+	}
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_cpu_idle_exit:
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+fail_cpu_frequency_exit:
+	pr_err("gator: power event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_trace_power_stop(void)
+{
+	int i;
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+	GATOR_UNREGISTER_TRACE(cpu_idle);
+	pr_debug("gator: unregistered power event tracepoints\n");
+
+	for (i = 0; i < POWER_TOTAL; i++)
+		power_cpu_enabled[i] = 0;
+}
+
+static void gator_trace_power_init(void)
+{
+	int i;
+
+	power_cpu_cores = nr_cpu_ids;
+	for (i = 0; i < POWER_TOTAL; i++) {
+		power_cpu_enabled[i] = 0;
+		power_cpu_key[i] = gator_events_get_key();
+	}
+}
+#else
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	return 0;
+}
+
+static void gator_trace_power_online(void)
+{
+}
+
+static void gator_trace_power_offline(void)
+{
+}
+
+static int gator_trace_power_start(void)
+{
+	return 0;
+}
+
+static void gator_trace_power_stop(void)
+{
+}
+
+static void gator_trace_power_init(void)
+{
+}
+#endif
diff --git a/drivers/gator/gator_trace_sched.c b/drivers/gator/gator_trace_sched.c
new file mode 100644
index 000000000000..6d7cbd7348e1
--- /dev/null
+++ b/drivers/gator/gator_trace_sched.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <trace/events/sched.h>
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+#include <trace/events/task.h>
+#endif
+
+#include "gator.h"
+
+#define TASK_MAP_ENTRIES		1024	/* must be power of 2 */
+#define TASK_MAX_COLLISIONS		2
+
+enum {
+	STATE_WAIT_ON_OTHER = 0,
+	STATE_CONTENTION,
+	STATE_WAIT_ON_IO,
+	CPU_WAIT_TOTAL
+};
+
+static DEFINE_PER_CPU(uint64_t *, taskname_keys);
+static DEFINE_PER_CPU(int, collecting);
+
+/* this array is never read as the cpu wait charts are derived
+ * counters the files are needed, nonetheless, to show that these
+ * counters are available
+ */
+static ulong cpu_wait_enabled[CPU_WAIT_TOTAL];
+static ulong sched_cpu_key[CPU_WAIT_TOTAL];
+
+static int sched_trace_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* CPU Wait - Contention */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_contention");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_CONTENTION]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_CONTENTION]);
+
+	/* CPU Wait - I/O */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_io");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_WAIT_ON_IO]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_WAIT_ON_IO]);
+
+	return 0;
+}
+
+static void emit_pid_name(const char *comm, struct task_struct *task)
+{
+	bool found = false;
+	char taskcomm[TASK_COMM_LEN + 3];
+	unsigned long x, cpu = get_physical_cpu();
+	uint64_t *keys = &(per_cpu(taskname_keys, cpu)[(task->pid & 0xFF) * TASK_MAX_COLLISIONS]);
+	uint64_t value;
+
+	value = gator_chksum_crc32(comm);
+	value = (value << 32) | (uint32_t)task->pid;
+
+	/* determine if the thread name was emitted already */
+	for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+		if (keys[x] == value) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		/* shift values, new value always in front */
+		uint64_t oldv, newv = value;
+
+		for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+			oldv = keys[x];
+			keys[x] = newv;
+			newv = oldv;
+		}
+
+		/* emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions */
+		if (strlcpy(taskcomm, comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) {
+			/* append ellipses if comm has length of TASK_COMM_LEN - 1 */
+			strcat(taskcomm, "...");
+		}
+
+		marshal_thread_name(task->pid, taskcomm);
+	}
+}
+
+static void collect_counters(u64 time, struct task_struct *task, bool sched_switch)
+{
+	int *buffer, len, cpu = get_physical_cpu();
+	long long *buffer64;
+	struct gator_interface *gi;
+
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->read) {
+				len = gi->read(&buffer, sched_switch);
+				marshal_event(len, buffer);
+			} else if (gi->read64) {
+				len = gi->read64(&buffer64);
+				marshal_event64(len, buffer64);
+			}
+			if (gi->read_proc && task != NULL) {
+				len = gi->read_proc(&buffer64, task);
+				marshal_event64(len, buffer64);
+			}
+		}
+		if (cpu == 0)
+			gator_emit_perf_time(time);
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+
+		/* Commit buffers on timeout */
+		if (gator_live_rate > 0 && time >= per_cpu(gator_buffer_commit_time, cpu)) {
+			static const int buftypes[] = { NAME_BUF, COUNTER_BUF, BLOCK_COUNTER_BUF, SCHED_TRACE_BUF, ACTIVITY_BUF };
+			int i;
+
+			for (i = 0; i < ARRAY_SIZE(buftypes); ++i)
+				gator_commit_buffer(cpu, buftypes[i], time);
+
+			/* spinlocks are noops on uniprocessor machines and mutexes do
+			 * not work in sched_switch context in RT-Preempt full, so
+			 * disable proactive flushing of the annotate frame on
+			 * uniprocessor machines.
+			 */
+#ifdef CONFIG_SMP
+			/* Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full */
+			if (on_primary_core() && spin_trylock(&annotate_lock)) {
+				gator_commit_buffer(0, ANNOTATE_BUF, time);
+				spin_unlock(&annotate_lock);
+			}
+#endif
+		}
+	}
+}
+
+/* special case used during a suspend of the system */
+static void trace_sched_insert_idle(void)
+{
+	marshal_sched_trace_switch(0, 0);
+}
+
+static void gator_trace_emit_link(struct task_struct *p)
+{
+	int cookie;
+	int cpu = get_physical_cpu();
+
+	cookie = get_exec_cookie(cpu, p);
+	emit_pid_name(p->comm, p);
+
+	marshal_link(cookie, p->tgid, p->pid);
+}
+
+GATOR_DEFINE_PROBE(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child))
+{
+	gator_trace_emit_link(child);
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+GATOR_DEFINE_PROBE(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm))
+{
+	gator_trace_emit_link(p);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, char *comm))
+#else
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, const char *comm))
+#endif
+{
+	emit_pid_name(comm, task);
+}
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	int state;
+	int cpu = get_physical_cpu();
+
+	per_cpu(in_scheduler_context, cpu) = true;
+
+	/* do as much work as possible before disabling interrupts */
+	if (prev->state == TASK_RUNNING)
+		state = STATE_CONTENTION;
+	else if (prev->in_iowait)
+		state = STATE_WAIT_ON_IO;
+	else
+		state = STATE_WAIT_ON_OTHER;
+
+	per_cpu(collecting, cpu) = 1;
+	collect_counters(gator_get_time(), prev, true);
+	per_cpu(collecting, cpu) = 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	gator_trace_emit_link(next);
+#endif
+	marshal_sched_trace_switch(next->pid, state);
+
+	per_cpu(in_scheduler_context, cpu) = false;
+}
+
+GATOR_DEFINE_PROBE(sched_process_free, TP_PROTO(struct task_struct *p))
+{
+	marshal_sched_trace_exit(p->tgid, p->pid);
+}
+
+static void do_nothing(void *info)
+{
+	/* Intentionally do nothing */
+	(void)info;
+}
+
+static int register_scheduler_tracepoints(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(sched_process_fork))
+		goto fail_sched_process_fork;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	if (GATOR_REGISTER_TRACE(sched_process_exec))
+		goto fail_sched_process_exec;
+	if (GATOR_REGISTER_TRACE(task_rename))
+		goto fail_task_rename;
+#endif
+	if (GATOR_REGISTER_TRACE(sched_switch))
+		goto fail_sched_switch;
+	if (GATOR_REGISTER_TRACE(sched_process_free))
+		goto fail_sched_process_free;
+	pr_debug("gator: registered tracepoints\n");
+
+	/* Now that the scheduler tracepoint is registered, force a context
+	 * switch on all cpus to capture what is currently running.
+	 */
+	on_each_cpu(do_nothing, NULL, 0);
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_sched_process_free:
+	GATOR_UNREGISTER_TRACE(sched_switch);
+fail_sched_switch:
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(task_rename);
+fail_task_rename:
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+fail_sched_process_exec:
+#endif
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+fail_sched_process_fork:
+	pr_err("gator: tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void unregister_scheduler_tracepoints(void)
+{
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+	GATOR_UNREGISTER_TRACE(task_rename);
+#endif
+	GATOR_UNREGISTER_TRACE(sched_switch);
+	GATOR_UNREGISTER_TRACE(sched_process_free);
+	pr_debug("gator: unregistered tracepoints\n");
+}
+
+static void gator_trace_sched_stop(void)
+{
+	int cpu;
+
+	unregister_scheduler_tracepoints();
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(taskname_keys, cpu));
+	}
+}
+
+static int gator_trace_sched_start(void)
+{
+	int cpu, size;
+	int ret;
+
+	for_each_present_cpu(cpu) {
+		size = TASK_MAP_ENTRIES * TASK_MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(taskname_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(taskname_keys, cpu))
+			return -1;
+		memset(per_cpu(taskname_keys, cpu), 0, size);
+	}
+
+	ret = register_scheduler_tracepoints();
+
+	return ret;
+}
+
+static void gator_trace_sched_offline(void)
+{
+	trace_sched_insert_idle();
+}
+
+static void gator_trace_sched_init(void)
+{
+	int i;
+
+	for (i = 0; i < CPU_WAIT_TOTAL; i++) {
+		cpu_wait_enabled[i] = 0;
+		sched_cpu_key[i] = gator_events_get_key();
+	}
+}
diff --git a/drivers/gator/mali/mali_kbase_gator_api.h b/drivers/gator/mali/mali_kbase_gator_api.h
new file mode 100644
index 000000000000..5ed069797e36
--- /dev/null
+++ b/drivers/gator/mali/mali_kbase_gator_api.h
@@ -0,0 +1,219 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef _KBASE_GATOR_API_H_
+#define _KBASE_GATOR_API_H_
+
+/**
+ * @brief This file describes the API used by Gator to collect hardware counters data from a Mali device.
+ */
+
+/* This define is used by the gator kernel module compile to select which DDK
+ * API calling convention to use. If not defined (legacy DDK) gator assumes
+ * version 1. The version to DDK release mapping is:
+ *     Version 1 API: DDK versions r1px, r2px
+ *     Version 2 API: DDK versions r3px, r4px
+ *     Version 3 API: DDK version r5p0 and newer
+ *
+ * API Usage
+ * =========
+ *
+ * 1] Call kbase_gator_hwcnt_init_names() to return the list of short counter
+ * names for the GPU present in this device.
+ *
+ * 2] Create a kbase_gator_hwcnt_info structure and set the counter enables for
+ * the counters you want enabled. The enables can all be set for simplicity in
+ * most use cases, but disabling some will let you minimize bandwidth impact.
+ *
+ * 3] Call kbase_gator_hwcnt_init() using the above structure, to create a
+ * counter context. On successful return the DDK will have populated the
+ * structure with a variety of useful information.
+ *
+ * 4] Call kbase_gator_hwcnt_dump_irq() to queue a non-blocking request for a
+ * counter dump. If this returns a non-zero value the request has been queued,
+ * otherwise the driver has been unable to do so (typically because of another
+ * user of the instrumentation exists concurrently).
+ *
+ * 5] Call kbase_gator_hwcnt_dump_complete() to test whether the  previously
+ * requested dump has been succesful. If this returns non-zero the counter dump
+ * has resolved, but the value of *success must also be tested as the dump
+ * may have not been successful. If it returns zero the counter dump was
+ * abandoned due to the device being busy (typically because of another
+ * user of the instrumentation exists concurrently).
+ *
+ * 6] Process the counters stored in the buffer pointed to by ...
+ *
+ *        kbase_gator_hwcnt_info->kernel_dump_buffer
+ *
+ *    In pseudo code you can find all of the counters via this approach:
+ *
+ *
+ *        hwcnt_info # pointer to kbase_gator_hwcnt_info structure
+ *        hwcnt_name # pointer to name list
+ *
+ *        u32 * hwcnt_data = (u32*)hwcnt_info->kernel_dump_buffer
+ *
+ *        # Iterate over each 64-counter block in this GPU configuration
+ *        for( i = 0; i < hwcnt_info->nr_hwc_blocks; i++) {
+ *            hwc_type type = hwcnt_info->hwc_layout[i];
+ *
+ *            # Skip reserved type blocks - they contain no counters at all
+ *            if( type == RESERVED_BLOCK ) {
+ *                continue;
+ *            }
+ *
+ *            size_t name_offset = type * 64;
+ *            size_t data_offset = i * 64;
+ *
+ *            # Iterate over the names of the counters in this block type
+ *            for( j = 0; j < 64; j++) {
+ *                const char * name = hwcnt_name[name_offset+j];
+ *
+ *                # Skip empty name strings - there is no counter here
+ *                if( name[0] == '\0' ) {
+ *                    continue;
+ *                }
+ *
+ *                u32 data = hwcnt_data[data_offset+j];
+ *
+ *                printk( "COUNTER: %s DATA: %u\n", name, data );
+ *            }
+ *        }
+ *
+ *
+ *     Note that in most implementations you typically want to either SUM or
+ *     AVERAGE multiple instances of the same counter if, for example, you have
+ *     multiple shader cores or multiple L2 caches. The most sensible view for
+ *     analysis is to AVERAGE shader core counters, but SUM L2 cache and MMU
+ *     counters.
+ *
+ * 7] Goto 4, repeating until you want to stop collecting counters.
+ *
+ * 8] Release the dump resources by calling kbase_gator_hwcnt_term().
+ *
+ * 9] Release the name table resources by calling kbase_gator_hwcnt_term_names().
+ *    This function must only be called if init_names() returned a non-NULL value.
+ **/
+
+#define MALI_DDK_GATOR_API_VERSION 3
+
+#if !defined(MALI_TRUE)
+	#define MALI_TRUE                ((uint32_t)1)
+#endif
+
+#if !defined(MALI_FALSE)
+	#define MALI_FALSE               ((uint32_t)0)
+#endif
+
+enum hwc_type {
+	JM_BLOCK = 0,
+	TILER_BLOCK,
+	SHADER_BLOCK,
+	MMU_L2_BLOCK,
+	RESERVED_BLOCK
+};
+
+struct kbase_gator_hwcnt_info {
+
+	/* Passed from Gator to kbase */
+
+	/* the bitmask of enabled hardware counters for each counter block */
+	uint16_t bitmask[4];
+
+	/* Passed from kbase to Gator */
+
+	/* ptr to counter dump memory */
+	void *kernel_dump_buffer;
+
+	/* size of counter dump memory */
+	uint32_t size;
+
+	/* the ID of the Mali device */
+	uint32_t gpu_id;
+
+	/* the number of shader cores in the GPU */
+	uint32_t nr_cores;
+
+	/* the number of core groups */
+	uint32_t nr_core_groups;
+
+	/* the memory layout of the performance counters */
+	enum hwc_type *hwc_layout;
+
+	/* the total number of hardware couter blocks */
+	uint32_t nr_hwc_blocks;
+};
+
+/**
+ * @brief Opaque block of Mali data which Gator needs to return to the API later.
+ */
+struct kbase_gator_hwcnt_handles;
+
+/**
+ * @brief Initialize the resources Gator needs for performance profiling.
+ *
+ * @param in_out_info   A pointer to a structure containing the enabled counters passed from Gator and all the Mali
+ *                      specific information that will be returned to Gator. On entry Gator must have populated the
+ *                      'bitmask' field with the counters it wishes to enable for each class of counter block.
+ *                      Each entry in the array corresponds to a single counter class based on the "hwc_type"
+ *                      enumeration, and each bit corresponds to an enable for 4 sequential counters (LSB enables
+ *                      the first 4 counters in the block, and so on). See the GPU counter array as returned by
+ *                      kbase_gator_hwcnt_get_names() for the index values of each counter for the curernt GPU.
+ *
+ * @return              Pointer to an opaque handle block on success, NULL on error.
+ */
+extern struct kbase_gator_hwcnt_handles *kbase_gator_hwcnt_init(struct kbase_gator_hwcnt_info *in_out_info);
+
+/**
+ * @brief Free all resources once Gator has finished using performance counters.
+ *
+ * @param in_out_info       A pointer to a structure containing the enabled counters passed from Gator and all the
+ *                          Mali specific information that will be returned to Gator.
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ */
+extern void kbase_gator_hwcnt_term(struct kbase_gator_hwcnt_info *in_out_info, struct kbase_gator_hwcnt_handles *opaque_handles);
+
+/**
+ * @brief Poll whether a counter dump is successful.
+ *
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ * @param[out] success      Non-zero on success, zero on failure.
+ *
+ * @return                  Zero if the dump is still pending, non-zero if the dump has completed. Note that a
+ *                          completed dump may not have dumped succesfully, so the caller must test for both
+ *                          a completed and successful dump before processing counters.
+ */
+extern uint32_t kbase_gator_instr_hwcnt_dump_complete(struct kbase_gator_hwcnt_handles *opaque_handles, uint32_t * const success);
+
+/**
+ * @brief Request the generation of a new counter dump.
+ *
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ *
+ * @return                  Zero if the hardware device is busy and cannot handle the request, non-zero otherwise.
+ */
+extern uint32_t kbase_gator_instr_hwcnt_dump_irq(struct kbase_gator_hwcnt_handles *opaque_handles);
+
+/**
+ * @brief This function is used to fetch the names table based on the Mali device in use.
+ *
+ * @param[out] total_number_of_counters The total number of counters short names in the Mali devices' list.
+ *
+ * @return                              Pointer to an array of strings of length *total_number_of_counters.
+ */
+extern const char * const *kbase_gator_hwcnt_init_names(uint32_t *total_number_of_counters);
+
+/**
+ * @brief This function is used to terminate the use of the names table.
+ *
+ * This function must only be called if the initial call to kbase_gator_hwcnt_init_names returned a non-NULL value.
+ */
+extern void kbase_gator_hwcnt_term_names(void);
+
+#endif
diff --git a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
new file mode 100644
index 000000000000..2bc0b037eee6
--- /dev/null
+++ b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
@@ -0,0 +1,159 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+#define __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+
+/*
+ * The number of processor cores.  Update to suit your hardware implementation.
+ */
+#define MAX_NUM_FP_CORES            (4)
+#define MAX_NUM_VP_CORES            (1)
+#define MAX_NUM_L2_CACHE_CORES      (1)
+
+enum counters {
+	/* Timeline activity */
+	ACTIVITY_VP_0 = 0,
+	ACTIVITY_FP_0,
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0,
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+
+	/* EGL Software Counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES Software Counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	COUNTER_FILMSTRIP,
+	COUNTER_FREQUENCY,
+	COUNTER_VOLTAGE,
+
+	NUMBER_OF_EVENTS
+};
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_3
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_3_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+/* Signifies that the system is able to report voltage and frequency numbers. */
+#define DVFS_REPORTED_BY_DDK 1
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/*
+ * For compatibility with utgard.
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+extern void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+extern u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * List of possible actions allowing DDK to be controlled by Streamline.
+ * The following numbers are used by DDK to control the frame buffer dumping.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE      (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_MJOLLNIR_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali/mali_utgard_profiling_gator_api.h b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
new file mode 100644
index 000000000000..d6465312628e
--- /dev/null
+++ b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_UTGARD_PROFILING_GATOR_API_H__
+#define __MALI_UTGARD_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+#define MALI_PROFILING_API_VERSION 4
+
+#define MAX_NUM_L2_CACHE_CORES 3
+#define MAX_NUM_FP_CORES 8
+#define MAX_NUM_VP_CORES 1
+
+/** The list of events supported by the Mali DDK. */
+enum {
+	/* Vertex processor activity */
+	ACTIVITY_VP_0 = 0,
+
+	/* Fragment processor activity */
+	ACTIVITY_FP_0, /* 1 */
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+	ACTIVITY_FP_4,
+	ACTIVITY_FP_5,
+	ACTIVITY_FP_6,
+	ACTIVITY_FP_7,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+	COUNTER_L2_1_C0,
+	COUNTER_L2_1_C1,
+	COUNTER_L2_2_C0,
+	COUNTER_L2_2_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0, /*15*/
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+	COUNTER_FP_4_C0,
+	COUNTER_FP_4_C1,
+	COUNTER_FP_5_C0,
+	COUNTER_FP_5_C1,
+	COUNTER_FP_6_C0,
+	COUNTER_FP_6_C1,
+	COUNTER_FP_7_C0,
+	COUNTER_FP_7_C1, /* 32 */
+
+	/*
+	 * If more hardware counters are added, the _mali_osk_hw_counter_table
+	 * below should also be updated.
+	 */
+
+	/* EGL software counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES software counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	/* Framebuffer capture pseudo-counter */
+	COUNTER_FILMSTRIP,
+
+	NUMBER_OF_EVENTS
+} _mali_osk_counter_id;
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_7
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_7_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+#define FIRST_SPECIAL_COUNTER   COUNTER_FILMSTRIP
+#define LAST_SPECIAL_COUNTER    COUNTER_FILMSTRIP
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/**
+ * Structure to pass performance counter data of Mali L2 cache cores
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+/**
+ * Structure to pass data defining Mali instance in use:
+ *
+ * mali_product_id - Mali product id
+ * mali_version_major - Mali version major number
+ * mali_version_minor - Mali version minor number
+ * num_of_l2_cores - number of L2 cache cores
+ * num_of_fp_cores - number of fragment processor cores
+ * num_of_vp_cores - number of vertex processor cores
+ */
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+/*
+ * List of possible actions to be controlled by Streamline.
+ * The following numbers are used by gator to control the frame buffer dumping and s/w counter reporting.
+ * We cannot use the enums in mali_uk_types.h because they are unknown inside gator.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+void _mali_profiling_control(u32 action, u32 value);
+
+u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+int _mali_profiling_set_event(u32 counter_id, s32 event_id);
+
+u32 _mali_profiling_get_api_version(void);
+
+void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_UTGARD_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali_midgard.mk b/drivers/gator/mali_midgard.mk
new file mode 100644
index 000000000000..1b784d5c3d58
--- /dev/null
+++ b/drivers/gator/mali_midgard.mk
@@ -0,0 +1,39 @@
+# Defines for Mali-Midgard driver
+EXTRA_CFLAGS += -DMALI_USE_UMP=1 \
+                -DMALI_LICENSE_IS_GPL=1 \
+                -DMALI_BASE_TRACK_MEMLEAK=0 \
+                -DMALI_DEBUG=0 \
+                -DMALI_ERROR_INJECT_ON=0 \
+                -DMALI_CUSTOMER_RELEASE=1 \
+                -DMALI_UNIT_TEST=0 \
+                -DMALI_BACKEND_KERNEL=1 \
+                -DMALI_NO_MALI=0
+
+DDK_DIR ?= .
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/t6xx),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase/osk
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard/osk
+EXTRA_CFLAGS += -DMALI_DIR_MIDGARD=1
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_kbase_gator_api.h),)
+EXTRA_CFLAGS += -DMALI_SIMPLE_API=1
+endif
+
+UMP_DIR = $(DDK_DIR)/include/linux
+
+# Include directories in the DDK
+EXTRA_CFLAGS += -I$(KBASE_DIR)/ \
+                -I$(KBASE_DIR)/.. \
+                -I$(OSK_DIR)/.. \
+                -I$(UMP_DIR)/.. \
+                -I$(DDK_DIR)/include \
+                -I$(KBASE_DIR)/osk/src/linux/include \
+                -I$(KBASE_DIR)/platform_dummy \
+                -I$(KBASE_DIR)/src
+
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 86c17de87692..71d86143aec5 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -248,14 +248,15 @@ static void lp_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 	struct lp_gpio *lg = irq_data_get_irq_handler_data(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	u32 base, pin, mask;
-	unsigned long reg, pending;
+	unsigned long reg, ena, pending;
 	unsigned virq;
 
 	/* check from GPIO controller which pin triggered the interrupt */
 	for (base = 0; base < lg->chip.ngpio; base += 32) {
 		reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
+		ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE);
 
-		while ((pending = inl(reg))) {
+		while ((pending = (inl(reg) & inl(ena)))) {
 			pin = __ffs(pending);
 			mask = BIT(pin);
 			/* Clear before handling so we don't lose an edge */
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index a0b33a216d4a..2aa3ca215bd6 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -69,10 +69,14 @@ static int mpc8572_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 	u32 val;
 	struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
+	u32 out_mask, out_shadow;
 
-	val = in_be32(mm->regs + GPIO_DAT) & ~in_be32(mm->regs + GPIO_DIR);
+	out_mask = in_be32(mm->regs + GPIO_DIR);
 
-	return (val | mpc8xxx_gc->data) & mpc8xxx_gpio2mask(gpio);
+	val = in_be32(mm->regs + GPIO_DAT) & ~out_mask;
+	out_shadow = mpc8xxx_gc->data & out_mask;
+
+	return (val | out_shadow) & mpc8xxx_gpio2mask(gpio);
 }
 
 static int mpc8xxx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index dd2eddeb1e0c..500c4d19322b 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -248,7 +248,7 @@ static void msm_gpio_irq_mask(struct irq_data *d)
 
 	spin_lock_irqsave(&tlmm_lock, irq_flags);
 	writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio));
-	clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+	clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
 	__clear_bit(gpio, msm_gpio.enabled_irqs);
 	spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }
@@ -260,7 +260,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
 
 	spin_lock_irqsave(&tlmm_lock, irq_flags);
 	__set_bit(gpio, msm_gpio.enabled_irqs);
-	set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+	set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
 	writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio));
 	spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 3a4816adc137..5c27da6a2853 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -79,7 +79,7 @@ struct mvebu_gpio_chip {
 	spinlock_t	   lock;
 	void __iomem	  *membase;
 	void __iomem	  *percpu_membase;
-	unsigned int       irqbase;
+	int		   irqbase;
 	struct irq_domain *domain;
 	int                soc_variant;
 };
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index f8e6af20dfbf..d599fc42ae8b 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -214,7 +214,8 @@ static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base)
 	ct->regs.ack = PINCTRL_IRQSTAT(port) + MXS_CLR;
 	ct->regs.mask = PINCTRL_IRQEN(port);
 
-	irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+			       IRQ_NOREQUEST, 0);
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 4a430360af5a..54052125859a 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -63,6 +63,7 @@ struct gpio_bank {
 	struct gpio_chip chip;
 	struct clk *dbck;
 	u32 mod_usage;
+	u32 irq_usage;
 	u32 dbck_enable_mask;
 	bool dbck_enabled;
 	struct device *dev;
@@ -86,6 +87,9 @@ struct gpio_bank {
 #define GPIO_BIT(bank, gpio) (1 << GPIO_INDEX(bank, gpio))
 #define GPIO_MOD_CTRL_BIT	BIT(0)
 
+#define BANK_USED(bank) (bank->mod_usage || bank->irq_usage)
+#define LINE_USED(line, offset) (line & (1 << offset))
+
 static int irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
 {
 	return bank->chip.base + gpio_irq;
@@ -420,15 +424,69 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio,
 	return 0;
 }
 
+static void _enable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+	if (bank->regs->pinctrl) {
+		void __iomem *reg = bank->base + bank->regs->pinctrl;
+
+		/* Claim the pin for MPU */
+		__raw_writel(__raw_readl(reg) | (1 << offset), reg);
+	}
+
+	if (bank->regs->ctrl && !BANK_USED(bank)) {
+		void __iomem *reg = bank->base + bank->regs->ctrl;
+		u32 ctrl;
+
+		ctrl = __raw_readl(reg);
+		/* Module is enabled, clocks are not gated */
+		ctrl &= ~GPIO_MOD_CTRL_BIT;
+		__raw_writel(ctrl, reg);
+		bank->context.ctrl = ctrl;
+	}
+}
+
+static void _disable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+	void __iomem *base = bank->base;
+
+	if (bank->regs->wkup_en &&
+	    !LINE_USED(bank->mod_usage, offset) &&
+	    !LINE_USED(bank->irq_usage, offset)) {
+		/* Disable wake-up during idle for dynamic tick */
+		_gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
+		bank->context.wake_en =
+			__raw_readl(bank->base + bank->regs->wkup_en);
+	}
+
+	if (bank->regs->ctrl && !BANK_USED(bank)) {
+		void __iomem *reg = bank->base + bank->regs->ctrl;
+		u32 ctrl;
+
+		ctrl = __raw_readl(reg);
+		/* Module is disabled, clocks are gated */
+		ctrl |= GPIO_MOD_CTRL_BIT;
+		__raw_writel(ctrl, reg);
+		bank->context.ctrl = ctrl;
+	}
+}
+
+static int gpio_is_input(struct gpio_bank *bank, int mask)
+{
+	void __iomem *reg = bank->base + bank->regs->direction;
+
+	return __raw_readl(reg) & mask;
+}
+
 static int gpio_irq_type(struct irq_data *d, unsigned type)
 {
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned gpio = 0;
 	int retval;
 	unsigned long flags;
+	unsigned offset;
 
-	if (WARN_ON(!bank->mod_usage))
-		return -EINVAL;
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
 
 #ifdef CONFIG_ARCH_OMAP1
 	if (d->irq > IH_MPUIO_BASE)
@@ -446,7 +504,17 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 		return -EINVAL;
 
 	spin_lock_irqsave(&bank->lock, flags);
-	retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type);
+	offset = GPIO_INDEX(bank, gpio);
+	retval = _set_gpio_triggering(bank, offset, type);
+	if (!LINE_USED(bank->mod_usage, offset)) {
+		_enable_gpio_module(bank, offset);
+		_set_gpio_direction(bank, offset, 1);
+	} else if (!gpio_is_input(bank, 1 << offset)) {
+		spin_unlock_irqrestore(&bank->lock, flags);
+		return -EINVAL;
+	}
+
+	bank->irq_usage |= 1 << GPIO_INDEX(bank, gpio);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
@@ -603,35 +671,19 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 	 * If this is the first gpio_request for the bank,
 	 * enable the bank module.
 	 */
-	if (!bank->mod_usage)
+	if (!BANK_USED(bank))
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
 	/* Set trigger to none. You need to enable the desired trigger with
-	 * request_irq() or set_irq_type().
+	 * request_irq() or set_irq_type(). Only do this if the IRQ line has
+	 * not already been requested.
 	 */
-	_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-
-	if (bank->regs->pinctrl) {
-		void __iomem *reg = bank->base + bank->regs->pinctrl;
-
-		/* Claim the pin for MPU */
-		__raw_writel(__raw_readl(reg) | (1 << offset), reg);
-	}
-
-	if (bank->regs->ctrl && !bank->mod_usage) {
-		void __iomem *reg = bank->base + bank->regs->ctrl;
-		u32 ctrl;
-
-		ctrl = __raw_readl(reg);
-		/* Module is enabled, clocks are not gated */
-		ctrl &= ~GPIO_MOD_CTRL_BIT;
-		__raw_writel(ctrl, reg);
-		bank->context.ctrl = ctrl;
+	if (!LINE_USED(bank->irq_usage, offset)) {
+		_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+		_enable_gpio_module(bank, offset);
 	}
-
 	bank->mod_usage |= 1 << offset;
-
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
@@ -640,31 +692,11 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 {
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
-	void __iomem *base = bank->base;
 	unsigned long flags;
 
 	spin_lock_irqsave(&bank->lock, flags);
-
-	if (bank->regs->wkup_en) {
-		/* Disable wake-up during idle for dynamic tick */
-		_gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
-		bank->context.wake_en =
-			__raw_readl(bank->base + bank->regs->wkup_en);
-	}
-
 	bank->mod_usage &= ~(1 << offset);
-
-	if (bank->regs->ctrl && !bank->mod_usage) {
-		void __iomem *reg = bank->base + bank->regs->ctrl;
-		u32 ctrl;
-
-		ctrl = __raw_readl(reg);
-		/* Module is disabled, clocks are gated */
-		ctrl |= GPIO_MOD_CTRL_BIT;
-		__raw_writel(ctrl, reg);
-		bank->context.ctrl = ctrl;
-	}
-
+	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, bank->chip.base + offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -672,7 +704,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 	 * If this is the last gpio to be freed in the bank,
 	 * disable the bank module.
 	 */
-	if (!bank->mod_usage)
+	if (!BANK_USED(bank))
 		pm_runtime_put(bank->dev);
 }
 
@@ -762,10 +794,20 @@ static void gpio_irq_shutdown(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned int gpio = irq_to_gpio(bank, d->hwirq);
 	unsigned long flags;
+	unsigned offset = GPIO_INDEX(bank, gpio);
 
 	spin_lock_irqsave(&bank->lock, flags);
+	bank->irq_usage &= ~(1 << offset);
+	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, gpio);
 	spin_unlock_irqrestore(&bank->lock, flags);
+
+	/*
+	 * If this is the last IRQ to be freed in the bank,
+	 * disable the bank module.
+	 */
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -897,13 +939,6 @@ static int gpio_input(struct gpio_chip *chip, unsigned offset)
 	return 0;
 }
 
-static int gpio_is_input(struct gpio_bank *bank, int mask)
-{
-	void __iomem *reg = bank->base + bank->regs->direction;
-
-	return __raw_readl(reg) & mask;
-}
-
 static int gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct gpio_bank *bank;
@@ -922,13 +957,22 @@ static int gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct gpio_bank *bank;
 	unsigned long flags;
+	int retval = 0;
 
 	bank = container_of(chip, struct gpio_bank, chip);
 	spin_lock_irqsave(&bank->lock, flags);
+
+	if (LINE_USED(bank->irq_usage, offset)) {
+			retval = -EINVAL;
+			goto exit;
+	}
+
 	bank->set_dataout(bank, offset, value);
 	_set_gpio_direction(bank, offset, 0);
+
+exit:
 	spin_unlock_irqrestore(&bank->lock, flags);
-	return 0;
+	return retval;
 }
 
 static int gpio_debounce(struct gpio_chip *chip, unsigned offset,
@@ -1400,7 +1444,7 @@ void omap2_gpio_prepare_for_idle(int pwr_mode)
 	struct gpio_bank *bank;
 
 	list_for_each_entry(bank, &omap_gpio_list, node) {
-		if (!bank->mod_usage || !bank->loses_context)
+		if (!BANK_USED(bank) || !bank->loses_context)
 			continue;
 
 		bank->power_mode = pwr_mode;
@@ -1414,7 +1458,7 @@ void omap2_gpio_resume_after_idle(void)
 	struct gpio_bank *bank;
 
 	list_for_each_entry(bank, &omap_gpio_list, node) {
-		if (!bank->mod_usage || !bank->loses_context)
+		if (!BANK_USED(bank) || !bank->loses_context)
 			continue;
 
 		pm_runtime_get_sync(bank->dev);
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 6a4bd0dae0ce..4fbe12d283d5 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -286,11 +286,6 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!chip->base)
 		return -ENOMEM;
 
-	chip->domain = irq_domain_add_simple(adev->dev.of_node, PL061_GPIO_NR,
-					     irq_base, &pl061_domain_ops, chip);
-	if (!chip->domain)
-		return -ENODEV;
-
 	spin_lock_init(&chip->lock);
 
 	chip->gc.request = pl061_gpio_request;
@@ -320,6 +315,11 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id)
 	irq_set_chained_handler(irq, pl061_irq_handler);
 	irq_set_handler_data(irq, chip);
 
+	chip->domain = irq_domain_add_simple(adev->dev.of_node, PL061_GPIO_NR,
+					     irq_base, &pl061_domain_ops, chip);
+	if (!chip->domain)
+		return -ENODEV;
+
 	for (i = 0; i < PL061_GPIO_NR; i++) {
 		if (pdata) {
 			if (pdata->directions & (1 << i))
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index b4ca450947b8..f3c5d39f138e 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -329,11 +329,11 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	if (!p->irq_domain) {
 		ret = -ENXIO;
 		dev_err(&pdev->dev, "cannot initialize irq domain\n");
-		goto err1;
+		goto err0;
 	}
 
 	if (devm_request_irq(&pdev->dev, irq->start,
-			     gpio_rcar_irq_handler, 0, name, p)) {
+			     gpio_rcar_irq_handler, IRQF_SHARED, name, p)) {
 		dev_err(&pdev->dev, "failed to request IRQ\n");
 		ret = -ENOENT;
 		goto err1;
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index 4d330e36da1d..28d987661146 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -300,7 +300,7 @@ static int twl_direction_in(struct gpio_chip *chip, unsigned offset)
 	if (offset < TWL4030_GPIO_MAX)
 		ret = twl4030_set_gpio_direction(offset, 1);
 	else
-		ret = -EINVAL;
+		ret = -EINVAL;	/* LED outputs can't be set as input */
 
 	if (!ret)
 		priv->direction &= ~BIT(offset);
@@ -354,17 +354,27 @@ static void twl_set(struct gpio_chip *chip, unsigned offset, int value)
 static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip);
+	int ret = 0;
 
 	mutex_lock(&priv->mutex);
-	if (offset < TWL4030_GPIO_MAX)
-		twl4030_set_gpio_dataout(offset, value);
+	if (offset < TWL4030_GPIO_MAX) {
+		ret = twl4030_set_gpio_direction(offset, 0);
+		if (ret) {
+			mutex_unlock(&priv->mutex);
+			return ret;
+		}
+	}
+
+	/*
+	 *  LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output
+	 */
 
 	priv->direction |= BIT(offset);
 	mutex_unlock(&priv->mutex);
 
 	twl_set(chip, offset, value);
 
-	return 0;
+	return ret;
 }
 
 static int twl_to_irq(struct gpio_chip *chip, unsigned offset)
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 02e52d543e4b..b6b7d70f2832 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -177,7 +177,7 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast,
 
 static inline void ast_open_key(struct ast_private *ast)
 {
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xA1, 0xFF, 0x04);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x80, 0xA8);
 }
 
 #define AST_VIDMEM_SIZE_8M    0x00800000
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f60fd7bd1183..96f874a508e2 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -100,7 +100,7 @@ static int ast_detect_chip(struct drm_device *dev)
 			}
 			ast->vga2_clone = false;
 		} else {
-			ast->chip = 2000;
+			ast->chip = AST2000;
 			DRM_INFO("AST 2000 detected\n");
 		}
 	}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 7fc9f7272b56..e8f6418b6dec 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1012,8 +1012,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height)
 			srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0;
 			data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4);
 			data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4);
-			data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4);
-			data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4);
+			data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4);
+			data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4);
 
 			writel(data32.ul, dstxor);
 			csum += data32.ul;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 8ecb601152ef..64bfc235021a 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/console.h>
 #include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
 
 #include "cirrus_drv.h"
 
@@ -75,6 +76,41 @@ static void cirrus_pci_remove(struct pci_dev *pdev)
 	drm_put_dev(dev);
 }
 
+static int cirrus_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_kms_helper_poll_disable(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 1);
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int cirrus_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_helper_resume_force_mode(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 0);
+		console_unlock();
+	}
+
+	drm_kms_helper_poll_enable(drm_dev);
+	return 0;
+}
+
 static const struct file_operations cirrus_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -105,11 +141,17 @@ static struct drm_driver driver = {
 	.dumb_destroy = cirrus_dumb_destroy,
 };
 
+static const struct dev_pm_ops cirrus_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(cirrus_pm_suspend,
+				cirrus_pm_resume)
+};
+
 static struct pci_driver cirrus_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
 	.probe = cirrus_pci_probe,
 	.remove = cirrus_pci_remove,
+	.driver.pm = &cirrus_pm_ops,
 };
 
 static int __init cirrus_init(void)
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 60685b21cc36..b86f68d8b726 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -273,8 +273,8 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc,
 		sr07 |= 0x11;
 		break;
 	case 16:
-		sr07 |= 0xc1;
-		hdr = 0xc0;
+		sr07 |= 0x17;
+		hdr = 0xc1;
 		break;
 	case 24:
 		sr07 |= 0x15;
@@ -308,6 +308,9 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc,
 
 	WREG_HDR(hdr);
 	cirrus_crtc_do_set_base(crtc, old_fb, x, y, 0);
+
+	/* Unblank (needed on S3 resume, vgabios doesn't do it then) */
+	outb(0x20, 0x3c0);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index e7e92429d10f..8759d699bd8e 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2501,10 +2501,22 @@ int drm_mode_getfb(struct drm_device *dev,
 	r->depth = fb->depth;
 	r->bpp = fb->bits_per_pixel;
 	r->pitch = fb->pitches[0];
-	if (fb->funcs->create_handle)
-		ret = fb->funcs->create_handle(fb, file_priv, &r->handle);
-	else
+	if (fb->funcs->create_handle) {
+		if (file_priv->is_master || capable(CAP_SYS_ADMIN)) {
+			ret = fb->funcs->create_handle(fb, file_priv,
+						       &r->handle);
+		} else {
+			/* GET_FB() is an unprivileged ioctl so we must not
+			 * return a buffer-handle to non-master processes! For
+			 * backwards-compatibility reasons, we cannot make
+			 * GET_FB() privileged, so just return an invalid handle
+			 * for non-masters. */
+			r->handle = 0;
+			ret = 0;
+		}
+	} else {
 		ret = -ENODEV;
+	}
 
 	drm_framebuffer_unreference(fb);
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 9cc247f55502..2ab782cb38a2 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -406,9 +406,16 @@ long drm_ioctl(struct file *filp,
 		cmd = ioctl->cmd_drv;
 	}
 	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) {
+		u32 drv_size;
+
 		ioctl = &drm_ioctls[nr];
-		cmd = ioctl->cmd;
+
+		drv_size = _IOC_SIZE(ioctl->cmd);
 		usize = asize = _IOC_SIZE(cmd);
+		if (drv_size > asize)
+			asize = drv_size;
+
+		cmd = ioctl->cmd;
 	} else
 		goto err_i1;
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 0cb9b5d8e30a..83f0ba5859c0 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -68,6 +68,8 @@
 #define EDID_QUIRK_DETAILED_SYNC_PP		(1 << 6)
 /* Force reduced-blanking timings for detailed modes */
 #define EDID_QUIRK_FORCE_REDUCED_BLANKING	(1 << 7)
+/* Force 8bpc */
+#define EDID_QUIRK_FORCE_8BPC			(1 << 8)
 
 struct detailed_mode_closure {
 	struct drm_connector *connector;
@@ -128,6 +130,9 @@ static struct edid_quirk {
 
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
+
+	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
+	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 };
 
 /*
@@ -2955,6 +2960,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 
 	drm_add_display_info(edid, &connector->display_info);
 
+	if (quirks & EDID_QUIRK_FORCE_8BPC)
+		connector->display_info.bpc = 8;
+
 	return num_modes;
 }
 EXPORT_SYMBOL(drm_add_edid_modes);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 17d9b0b6afc5..ccfc63665e76 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -84,6 +84,14 @@ void i915_update_dri1_breadcrumb(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv;
 
+	/*
+	 * The dri breadcrumb update races against the drm master disappearing.
+	 * Instead of trying to fix this (this is by far not the only ums issue)
+	 * just don't do the update in kms mode.
+	 */
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
 	if (dev->primary->master) {
 		master_priv = dev->primary->master->driver_priv;
 		if (master_priv->sarea_priv)
@@ -1679,6 +1687,7 @@ out_gem_unload:
 
 	intel_teardown_gmbus(dev);
 	intel_teardown_mchbar(dev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 	destroy_workqueue(dev_priv->wq);
 out_mtrrfree:
 	if (dev_priv->mm.gtt_mtrr >= 0) {
@@ -1847,8 +1856,10 @@ void i915_driver_lastclose(struct drm_device * dev)
 
 void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
 {
+	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_close(dev, file_priv);
 	i915_gem_release(dev, file_priv);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 3bc8a58a8d5f..b10b1b1b4873 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -291,10 +291,8 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
-	mutex_lock(&dev->struct_mutex);
 	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
 	idr_destroy(&file_priv->context_idr);
-	mutex_unlock(&dev->struct_mutex);
 }
 
 static struct i915_hw_context *
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 117ce3813681..6416d0d07394 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -635,9 +635,9 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		 * relocations were valid.
 		 */
 		for (j = 0; j < exec[i].relocation_count; j++) {
-			if (copy_to_user(&user_relocs[j].presumed_offset,
-					 &invalid_offset,
-					 sizeof(invalid_offset))) {
+			if (__copy_to_user(&user_relocs[j].presumed_offset,
+					   &invalid_offset,
+					   sizeof(invalid_offset))) {
 				ret = -EFAULT;
 				mutex_lock(&dev->struct_mutex);
 				goto err;
@@ -1151,18 +1151,21 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 
 	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
 	if (!ret) {
+		struct drm_i915_gem_exec_object __user *user_exec_list =
+			to_user_ptr(args->buffers_ptr);
+
 		/* Copy the new buffer offsets back to the user's exec list. */
-		for (i = 0; i < args->buffer_count; i++)
-			exec_list[i].offset = exec2_list[i].offset;
-		/* ... and back out to userspace */
-		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
-				   exec_list,
-				   sizeof(*exec_list) * args->buffer_count);
-		if (ret) {
-			ret = -EFAULT;
-			DRM_DEBUG("failed to copy %d exec entries "
-				  "back to user (%d)\n",
-				  args->buffer_count, ret);
+		for (i = 0; i < args->buffer_count; i++) {
+			ret = __copy_to_user(&user_exec_list[i].offset,
+					     &exec2_list[i].offset,
+					     sizeof(user_exec_list[i].offset));
+			if (ret) {
+				ret = -EFAULT;
+				DRM_DEBUG("failed to copy %d exec entries "
+					  "back to user (%d)\n",
+					  args->buffer_count, ret);
+				break;
+			}
 		}
 	}
 
@@ -1208,14 +1211,21 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
-		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
-				   exec2_list,
-				   sizeof(*exec2_list) * args->buffer_count);
-		if (ret) {
-			ret = -EFAULT;
-			DRM_DEBUG("failed to copy %d exec entries "
-				  "back to user (%d)\n",
-				  args->buffer_count, ret);
+		struct drm_i915_gem_exec_object2 *user_exec_list =
+				   to_user_ptr(args->buffers_ptr);
+		int i;
+
+		for (i = 0; i < args->buffer_count; i++) {
+			ret = __copy_to_user(&user_exec_list[i].offset,
+					     &exec2_list[i].offset,
+					     sizeof(user_exec_list[i].offset));
+			if (ret) {
+				ret = -EFAULT;
+				DRM_DEBUG("failed to copy %d exec entries "
+					  "back to user\n",
+					  args->buffer_count);
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 130d1db27e28..fa2d15b16739 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -222,7 +222,7 @@ i915_pages_create_for_stolen(struct drm_device *dev,
 	}
 
 	sg = st->sgl;
-	sg->offset = offset;
+	sg->offset = 0;
 	sg->length = size;
 
 	sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e5e328691e3a..c8d16a622f3c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1009,6 +1009,34 @@ done:
 	return ret;
 }
 
+static void i915_error_wake_up(struct drm_i915_private *dev_priv,
+			       bool reset_completed)
+{
+	struct intel_ring_buffer *ring;
+	int i;
+
+	/*
+	 * Notify all waiters for GPU completion events that reset state has
+	 * been changed, and that they need to restart their wait after
+	 * checking for potential errors (and bail out to drop locks if there is
+	 * a gpu reset pending so that i915_error_work_func can acquire them).
+	 */
+
+	/* Wake up __wait_seqno, potentially holding dev->struct_mutex. */
+	for_each_ring(ring, dev_priv, i)
+		wake_up_all(&ring->irq_queue);
+
+	/* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */
+	wake_up_all(&dev_priv->pending_flip_queue);
+
+	/*
+	 * Signal tasks blocked in i915_gem_wait_for_error that the pending
+	 * reset state is cleared.
+	 */
+	if (reset_completed)
+		wake_up_all(&dev_priv->gpu_error.reset_queue);
+}
+
 /**
  * i915_error_work_func - do process context error handling work
  * @work: work struct
@@ -1023,11 +1051,10 @@ static void i915_error_work_func(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t,
 						    gpu_error);
 	struct drm_device *dev = dev_priv->dev;
-	struct intel_ring_buffer *ring;
 	char *error_event[] = { "ERROR=1", NULL };
 	char *reset_event[] = { "RESET=1", NULL };
 	char *reset_done_event[] = { "ERROR=0", NULL };
-	int i, ret;
+	int ret;
 
 	kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event);
 
@@ -1046,8 +1073,16 @@ static void i915_error_work_func(struct work_struct *work)
 		kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE,
 				   reset_event);
 
+		/*
+		 * All state reset _must_ be completed before we update the
+		 * reset counter, for otherwise waiters might miss the reset
+		 * pending state and not properly drop locks, resulting in
+		 * deadlocks with the reset work.
+		 */
 		ret = i915_reset(dev);
 
+		intel_display_handle_reset(dev);
+
 		if (ret == 0) {
 			/*
 			 * After all the gem state is reset, increment the reset
@@ -1068,12 +1103,11 @@ static void i915_error_work_func(struct work_struct *work)
 			atomic_set(&error->reset_counter, I915_WEDGED);
 		}
 
-		for_each_ring(ring, dev_priv, i)
-			wake_up_all(&ring->irq_queue);
-
-		intel_display_handle_reset(dev);
-
-		wake_up_all(&dev_priv->gpu_error.reset_queue);
+		/*
+		 * Note: The wake_up also serves as a memory barrier so that
+		 * waiters see the update value of the reset counter atomic_t.
+		 */
+		i915_error_wake_up(dev_priv, true);
 	}
 }
 
@@ -1709,8 +1743,6 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 void i915_handle_error(struct drm_device *dev, bool wedged)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
-	int i;
 
 	i915_capture_error_state(dev);
 	i915_report_and_clear_eir(dev);
@@ -1720,14 +1752,28 @@ void i915_handle_error(struct drm_device *dev, bool wedged)
 				&dev_priv->gpu_error.reset_counter);
 
 		/*
-		 * Wakeup waiting processes so that the reset work item
-		 * doesn't deadlock trying to grab various locks.
+		 * Wakeup waiting processes so that the reset work function
+		 * i915_error_work_func doesn't deadlock trying to grab various
+		 * locks. By bumping the reset counter first, the woken
+		 * processes will see a reset in progress and back off,
+		 * releasing their locks and then wait for the reset completion.
+		 * We must do this for _all_ gpu waiters that might hold locks
+		 * that the reset work needs to acquire.
+		 *
+		 * Note: The wake_up serves as the required memory barrier to
+		 * ensure that the waiters see the updated value of the reset
+		 * counter atomic_t.
 		 */
-		for_each_ring(ring, dev_priv, i)
-			wake_up_all(&ring->irq_queue);
+		i915_error_wake_up(dev_priv, false);
 	}
 
-	queue_work(dev_priv->wq, &dev_priv->gpu_error.work);
+	/*
+	 * Our reset work can grab modeset locks (since it needs to reset the
+	 * state of outstanding pagelips). Hence it must not be run on our own
+	 * dev-priv->wq work queue for otherwise the flush_work in the pageflip
+	 * code will deadlock.
+	 */
+	schedule_work(&dev_priv->gpu_error.work);
 }
 
 static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, int pipe)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a365780aeb1e..2d90f96c19d0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1675,10 +1675,20 @@
 #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV	(1 << 2)
 
 #define PORT_HOTPLUG_STAT	(dev_priv->info->display_mmio_offset + 0x61114)
-/* HDMI/DP bits are gen4+ */
-#define   PORTB_HOTPLUG_LIVE_STATUS               (1 << 29)
-#define   PORTC_HOTPLUG_LIVE_STATUS               (1 << 28)
-#define   PORTD_HOTPLUG_LIVE_STATUS               (1 << 27)
+/*
+ * HDMI/DP bits are gen4+
+ *
+ * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
+ * Please check the detailed lore in the commit message for for experimental
+ * evidence.
+ */
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
+/* VLV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
+#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTC_HOTPLUG_INT_STATUS		(3 << 19)
 #define   PORTB_HOTPLUG_INT_STATUS		(3 << 17)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 95070b2124c6..49acec155046 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -657,7 +657,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	DRM_DEBUG_KMS("Set default to SSC at %dMHz\n", dev_priv->lvds_ssc_freq);
 }
 
-static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
+static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
 {
 	DRM_DEBUG_KMS("Falling back to manually reading VBT from "
 		      "VBIOS ROM for %s\n",
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 58b4a53715cd..53435a9d847e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -702,7 +702,7 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = {
 	.destroy = intel_encoder_destroy,
 };
 
-static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_crt_dmi_callback(const struct dmi_system_id *id)
 {
 	DRM_INFO("Skipping CRT initialization for %s\n", id->ident);
 	return 1;
@@ -717,6 +717,14 @@ static const struct dmi_system_id intel_no_crt[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"),
 		},
 	},
+	{
+		.callback = intel_no_crt_dmi_callback,
+		.ident = "DELL XPS 8700",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 16e674af4d57..7ce38344e484 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1193,12 +1193,18 @@ void intel_ddi_setup_hw_pll_state(struct drm_device *dev)
 	enum pipe pipe;
 	struct intel_crtc *intel_crtc;
 
+	dev_priv->ddi_plls.spll_refcount = 0;
+	dev_priv->ddi_plls.wrpll1_refcount = 0;
+	dev_priv->ddi_plls.wrpll2_refcount = 0;
+
 	for_each_pipe(pipe) {
 		intel_crtc =
 			to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
-		if (!intel_crtc->active)
+		if (!intel_crtc->active) {
+			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_NONE;
 			continue;
+		}
 
 		intel_crtc->ddi_pll_sel = intel_ddi_get_crtc_pll(dev_priv,
 								 pipe);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index eea5982657a8..8814b0dbfc4f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3946,8 +3946,6 @@ static void intel_connector_check_state(struct intel_connector *connector)
  * consider. */
 void intel_connector_dpms(struct drm_connector *connector, int mode)
 {
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-
 	/* All the simple cases only support two dpms states. */
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
@@ -3958,10 +3956,8 @@ void intel_connector_dpms(struct drm_connector *connector, int mode)
 	connector->dpms = mode;
 
 	/* Only need to change hw state when actually enabled */
-	if (encoder->base.crtc)
-		intel_encoder_dpms(encoder, mode);
-	else
-		WARN_ON(encoder->connectors_active != false);
+	if (connector->encoder)
+		intel_encoder_dpms(to_intel_encoder(connector->encoder), mode);
 
 	intel_modeset_check_state(connector->dev);
 }
@@ -4564,6 +4560,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
 	pipeconf = I915_READ(PIPECONF(intel_crtc->pipe));
 
+	if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
+	    I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
+		pipeconf |= PIPECONF_ENABLE;
+
 	if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) {
 		/* Enable pixel doubling when the dot clock is > 90% of the (display)
 		 * core speed.
@@ -5225,7 +5225,7 @@ static void intel_set_pipe_csc(struct drm_crtc *crtc)
 		uint16_t postoff = 0;
 
 		if (intel_crtc->config.limited_color_range)
-			postoff = (16 * (1 << 13) / 255) & 0x1fff;
+			postoff = (16 * (1 << 12) / 255) & 0x1fff;
 
 		I915_WRITE(PIPE_CSC_POSTOFF_HI(pipe), postoff);
 		I915_WRITE(PIPE_CSC_POSTOFF_ME(pipe), postoff);
@@ -6262,7 +6262,9 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 		intel_crtc->cursor_visible = visible;
 	}
 	/* and commit changes on next vblank */
+	POSTING_READ(CURCNTR(pipe));
 	I915_WRITE(CURBASE(pipe), base);
+	POSTING_READ(CURBASE(pipe));
 }
 
 static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
@@ -6289,7 +6291,9 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 		intel_crtc->cursor_visible = visible;
 	}
 	/* and commit changes on next vblank */
+	POSTING_READ(CURCNTR_IVB(pipe));
 	I915_WRITE(CURBASE_IVB(pipe), base);
+	POSTING_READ(CURBASE_IVB(pipe));
 }
 
 /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
@@ -9119,15 +9123,6 @@ void intel_modeset_init(struct drm_device *dev)
 	intel_disable_fbc(dev);
 }
 
-static void
-intel_connector_break_all_links(struct intel_connector *connector)
-{
-	connector->base.dpms = DRM_MODE_DPMS_OFF;
-	connector->base.encoder = NULL;
-	connector->encoder->connectors_active = false;
-	connector->encoder->base.crtc = NULL;
-}
-
 static void intel_enable_pipe_a(struct drm_device *dev)
 {
 	struct intel_connector *connector;
@@ -9209,8 +9204,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 			if (connector->encoder->base.crtc != &crtc->base)
 				continue;
 
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
+		/* multiple connectors may have the same encoder:
+		 *  handle them and break crtc link separately */
+		list_for_each_entry(connector, &dev->mode_config.connector_list,
+				    base.head)
+			if (connector->encoder->base.crtc == &crtc->base) {
+				connector->encoder->base.crtc = NULL;
+				connector->encoder->connectors_active = false;
+			}
 
 		WARN_ON(crtc->active);
 		crtc->base.enabled = false;
@@ -9281,6 +9285,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				      drm_get_encoder_name(&encoder->base));
 			encoder->disable(encoder);
 		}
+		encoder->base.crtc = NULL;
+		encoder->connectors_active = false;
 
 		/* Inconsistent output/port/pipe state happens presumably due to
 		 * a bug in one of the get_hw_state functions. Or someplace else
@@ -9291,8 +9297,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				    base.head) {
 			if (connector->encoder != encoder)
 				continue;
-
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
 	}
 	/* Enabled encoders without active connectors will be fixed in
@@ -9452,7 +9458,9 @@ void intel_modeset_gem_init(struct drm_device *dev)
 
 	intel_setup_overlay(dev);
 
+	mutex_lock(&dev->mode_config.mutex);
 	intel_modeset_setup_hw_state(dev, false);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 void intel_modeset_cleanup(struct drm_device *dev)
@@ -9526,14 +9534,15 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
 	u16 gmch_ctrl;
 
-	pci_read_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, &gmch_ctrl);
+	pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl);
 	if (state)
 		gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
 	else
 		gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
-	pci_write_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, gmch_ctrl);
+	pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 70789b1b5642..cfd327c292ee 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -604,7 +604,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 			DRM_DEBUG_KMS("aux_ch native nack\n");
 			return -EREMOTEIO;
 		case AUX_NATIVE_REPLY_DEFER:
-			udelay(100);
+			/*
+			 * For now, just give more slack to branch devices. We
+			 * could check the DPCD for I2C bit rate capabilities,
+			 * and if available, adjust the interval. We could also
+			 * be more careful with DP-to-Legacy adapters where a
+			 * long legacy cable may force very low I2C bit rates.
+			 */
+			if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+			    DP_DWN_STRM_PORT_PRESENT)
+				usleep_range(500, 600);
+			else
+				usleep_range(300, 400);
 			continue;
 		default:
 			DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
@@ -2266,18 +2277,34 @@ g4x_dp_detect(struct intel_dp *intel_dp)
 		return status;
 	}
 
-	switch (intel_dig_port->port) {
-	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS;
-		break;
-	default:
-		return connector_status_unknown;
+	if (IS_VALLEYVIEW(dev)) {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		default:
+			return connector_status_unknown;
+		}
+	} else {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		default:
+			return connector_status_unknown;
+		}
 	}
 
 	if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0)
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 29412cc89c7a..f5d1dc5b5563 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -694,7 +694,7 @@ static const struct drm_encoder_funcs intel_lvds_enc_funcs = {
 	.destroy = intel_encoder_destroy,
 };
 
-static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
 {
 	DRM_INFO("Skipping LVDS initialization for %s\n", id->ident);
 	return 1;
@@ -869,6 +869,30 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Q900"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D410PT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_MATCH(DMI_BOARD_NAME, "D410PT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D425KT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D510MO",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D510MO"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
@@ -1073,6 +1097,17 @@ bool intel_lvds_init(struct drm_device *dev)
 	int pipe;
 	u8 pin;
 
+	/*
+	 * Unlock registers and just leave them unlocked. Do this before
+	 * checking quirk lists to avoid bogus WARNINGs.
+	 */
+	if (HAS_PCH_SPLIT(dev)) {
+		I915_WRITE(PCH_PP_CONTROL,
+			   I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
+	} else {
+		I915_WRITE(PP_CONTROL,
+			   I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
+	}
 	if (!intel_lvds_supported(dev))
 		return false;
 
@@ -1256,17 +1291,6 @@ out:
 	DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
 		      lvds_encoder->is_dual_link ? "dual" : "single");
 
-	/*
-	 * Unlock registers and just
-	 * leave them unlocked
-	 */
-	if (HAS_PCH_SPLIT(dev)) {
-		I915_WRITE(PCH_PP_CONTROL,
-			   I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
-	} else {
-		I915_WRITE(PP_CONTROL,
-			   I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
-	}
 	lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
 	if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
 		DRM_DEBUG_KMS("lid notifier registration failed\n");
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 48fe23e8d180..4605c3877c95 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -396,6 +396,9 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		}
 	}
 
+	/* Enforce ordering by reading HEAD register back */
+	I915_READ_HEAD(ring);
+
 	/* Initialize the ring. This must happen _after_ we've cleared the ring
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
@@ -1459,8 +1462,8 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring)
 	return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_request);
 }
 
-static int __intel_ring_begin(struct intel_ring_buffer *ring,
-			      int bytes)
+static int __intel_ring_prepare(struct intel_ring_buffer *ring,
+				int bytes)
 {
 	int ret;
 
@@ -1476,7 +1479,6 @@ static int __intel_ring_begin(struct intel_ring_buffer *ring,
 			return ret;
 	}
 
-	ring->space -= bytes;
 	return 0;
 }
 
@@ -1491,12 +1493,17 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
+	ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
+	if (ret)
+		return ret;
+
 	/* Preallocate the olr before touching the ring */
 	ret = intel_ring_alloc_seqno(ring);
 	if (ret)
 		return ret;
 
-	return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t));
+	ring->space -= num_dwords * sizeof(uint32_t);
+	return 0;
 }
 
 void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index b945bc54207a..7c4e3126df27 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -856,6 +856,10 @@ intel_enable_tv(struct intel_encoder *encoder)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
+	intel_wait_for_vblank(encoder->base.dev,
+			      to_intel_crtc(encoder->base.crtc)->pipe);
+
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
 }
 
@@ -921,6 +925,14 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;
 
+	/* TV has it's own notion of sync and other mode flags, so clear them. */
+	pipe_config->adjusted_mode.flags = 0;
+
+	/*
+	 * FIXME: We don't check whether the input mode is actually what we want
+	 * or whether userspace is doing something stupid.
+	 */
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 99e07b688ea8..f6341e8622ee 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1477,11 +1477,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (32700 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_EH &&
+	} else if (mdev->type == G200_EH &&
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (37500 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_ER &&
+	} else if (mdev->type == G200_ER &&
 		(mga_vga_calculate_mode_bandwidth(mode,
 			bpp) > (55000 * 1024))) {
 		return MODE_BANDWIDTH;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
index f02fd9f443ff..a66b27c0fcab 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
@@ -49,18 +49,23 @@ int
 nv50_dac_sense(struct nv50_disp_priv *priv, int or, u32 loadval)
 {
 	const u32 doff = (or * 0x800);
-	int load = -EINVAL;
+
 	nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80150000);
 	nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
+
 	nv_wr32(priv, 0x61a00c + doff, 0x00100000 | loadval);
 	mdelay(9);
 	udelay(500);
-	nv_wr32(priv, 0x61a00c + doff, 0x80000000);
-	load = (nv_rd32(priv, 0x61a00c + doff) & 0x38000000) >> 27;
-	nv_wr32(priv, 0x61a00c + doff, 0x00000000);
+	loadval = nv_mask(priv, 0x61a00c + doff, 0xffffffff, 0x00000000);
+
 	nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80550000);
 	nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
-	return load;
+
+	nv_debug(priv, "DAC%d sense: 0x%08x\n", or, loadval);
+	if (!(loadval & 0x80000000))
+		return -ETIMEDOUT;
+
+	return (loadval & 0x38000000) >> 27;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
index 373dbcc523b2..a19e7d79b847 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
@@ -36,6 +36,8 @@ nva3_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size)
 	if (data && data[0]) {
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x61c440 + soff, (i << 8) | data[i]);
+		for (; i < 0x60; i++)
+			nv_wr32(priv, 0x61c440 + soff, (i << 8));
 		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000003);
 	} else
 	if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
index dc57e24fc1df..717639386ced 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
@@ -41,6 +41,8 @@ nvd0_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size)
 	if (data && data[0]) {
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x10ec00 + soff, (i << 8) | data[i]);
+		for (; i < 0x60; i++)
+			nv_wr32(priv, 0x10ec00 + soff, (i << 8));
 		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000003);
 	} else
 	if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 5680d3eb11ca..4b7d4343f4ac 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -1112,7 +1112,7 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head)
 	if (conf != ~0) {
 		if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) {
 			u32 soff = (ffs(outp.or) - 1) * 0x08;
-			u32 ctrl = nv_rd32(priv, 0x610798 + soff);
+			u32 ctrl = nv_rd32(priv, 0x610794 + soff);
 			u32 datarate;
 
 			switch ((ctrl & 0x000f0000) >> 16) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index 019eacd8a68f..9ee40042fa3a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -679,7 +679,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
 	}
 
 	if (outp == 8)
-		return false;
+		return conf;
 
 	data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1);
 	if (data == 0x0000)
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
index ab1e918469a8..526b75242899 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
@@ -47,14 +47,8 @@ int
 nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 {
 	struct nv50_disp_priv *priv = (void *)object->engine;
-	struct nouveau_bios *bios = nouveau_bios(priv);
-	const u16 type = (mthd & NV50_DISP_SOR_MTHD_TYPE) >> 12;
 	const u8  head = (mthd & NV50_DISP_SOR_MTHD_HEAD) >> 3;
-	const u8  link = (mthd & NV50_DISP_SOR_MTHD_LINK) >> 2;
 	const u8    or = (mthd & NV50_DISP_SOR_MTHD_OR);
-	const u16 mask = (0x0100 << head) | (0x0040 << link) | (0x0001 << or);
-	struct dcb_output outp;
-	u8  ver, hdr;
 	u32 data;
 	int ret = -EINVAL;
 
@@ -62,8 +56,6 @@ nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 		return -EINVAL;
 	data = *(u32 *)args;
 
-	if (type && !dcb_outp_match(bios, type, mask, &ver, &hdr, &outp))
-		return -ENODEV;
 
 	switch (mthd & ~0x3f) {
 	case NV50_DISP_SOR_PWR:
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
index 2d9b9d7a7992..f3edd2841f2d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
@@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len,
 	       struct dcb_output *outp)
 {
 	u16 dcb = dcb_outp(bios, idx, ver, len);
+	memset(outp, 0x00, sizeof(*outp));
 	if (dcb) {
 		if (*ver >= 0x20) {
 			u32 conn = nv_ro32(bios, dcb + 0x00);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index c434d398d16f..c7bf974ed4a6 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -366,13 +366,13 @@ static u16
 init_script(struct nouveau_bios *bios, int index)
 {
 	struct nvbios_init init = { .bios = bios };
-	u16 data;
+	u16 bmp_ver = bmp_version(bios), data;
 
-	if (bmp_version(bios) && bmp_version(bios) < 0x0510) {
-		if (index > 1)
+	if (bmp_ver && bmp_ver < 0x0510) {
+		if (index > 1 || bmp_ver < 0x0100)
 			return 0x0000;
 
-		data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18);
+		data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18);
 		return nv_ro16(bios, data + (index * 2));
 	}
 
@@ -580,8 +580,22 @@ static void
 init_reserved(struct nvbios_init *init)
 {
 	u8 opcode = nv_ro08(init->bios, init->offset);
-	trace("RESERVED\t0x%02x\n", opcode);
-	init->offset += 1;
+	u8 length, i;
+
+	switch (opcode) {
+	case 0xaa:
+		length = 4;
+		break;
+	default:
+		length = 1;
+		break;
+	}
+
+	trace("RESERVED 0x%02x\t", opcode);
+	for (i = 1; i < length; i++)
+		cont(" 0x%02x", nv_ro08(init->bios, init->offset + i));
+	cont("\n");
+	init->offset += length;
 }
 
 /**
@@ -1281,7 +1295,11 @@ init_jump(struct nvbios_init *init)
 	u16 offset = nv_ro16(bios, init->offset + 1);
 
 	trace("JUMP\t0x%04x\n", offset);
-	init->offset = offset;
+
+	if (init_exec(init))
+		init->offset = offset;
+	else
+		init->offset += 3;
 }
 
 /**
@@ -2136,6 +2154,7 @@ static struct nvbios_init_opcode {
 	[0x99] = { init_zm_auxch },
 	[0x9a] = { init_i2c_long_if },
 	[0xa9] = { init_gpio_ne },
+	[0xaa] = { init_reserved },
 };
 
 #define init_opcode_nr (sizeof(init_opcode) / sizeof(init_opcode[0]))
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
index c728380d3d62..ea19acd20784 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
@@ -54,8 +54,10 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 
 	/* check that we're not already at the target duty cycle */
 	duty = fan->get(therm);
-	if (duty == target)
-		goto done;
+	if (duty == target) {
+		spin_unlock_irqrestore(&fan->lock, flags);
+		return 0;
+	}
 
 	/* smooth out the fanspeed increase/decrease */
 	if (!immediate && duty >= 0) {
@@ -73,8 +75,15 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 
 	nv_debug(therm, "FAN update: %d\n", duty);
 	ret = fan->set(therm, duty);
-	if (ret)
-		goto done;
+	if (ret) {
+		spin_unlock_irqrestore(&fan->lock, flags);
+		return ret;
+	}
+
+	/* fan speed updated, drop the fan lock before grabbing the
+	 * alarm-scheduling lock and risking a deadlock
+	 */
+	spin_unlock_irqrestore(&fan->lock, flags);
 
 	/* schedule next fan update, if not at target speed already */
 	if (list_empty(&fan->alarm.head) && target != duty) {
@@ -92,8 +101,6 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 		ptimer->alarm(ptimer, delay * 1000 * 1000, &fan->alarm);
 	}
 
-done:
-	spin_unlock_irqrestore(&fan->lock, flags);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index d97f20069d3e..5cec3a0c6c85 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -372,9 +372,6 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev)
 	acpi_status status;
 	acpi_handle dhandle, rom_handle;
 
-	if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
-		return false;
-
 	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 7ff10711a4d0..5a5f021d5863 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -788,25 +788,25 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 		  struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_mem *node = old_mem->mm_node;
-	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	u64 length = (new_mem->num_pages << PAGE_SHIFT);
 	u64 src_offset = node->vma[0].offset;
 	u64 dst_offset = node->vma[1].offset;
+	int src_tiled = !!node->memtype;
+	int dst_tiled = !!((struct nouveau_mem *)new_mem->mm_node)->memtype;
 	int ret;
 
 	while (length) {
 		u32 amount, stride, height;
 
+		ret = RING_SPACE(chan, 18 + 6 * (src_tiled + dst_tiled));
+		if (ret)
+			return ret;
+
 		amount  = min(length, (u64)(4 * 1024 * 1024));
 		stride  = 16 * 4;
 		height  = amount / stride;
 
-		if (old_mem->mem_type == TTM_PL_VRAM &&
-		    nouveau_bo_tile_layout(nvbo)) {
-			ret = RING_SPACE(chan, 8);
-			if (ret)
-				return ret;
-
+		if (src_tiled) {
 			BEGIN_NV04(chan, NvSubCopy, 0x0200, 7);
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
@@ -816,19 +816,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
 		} else {
-			ret = RING_SPACE(chan, 2);
-			if (ret)
-				return ret;
-
 			BEGIN_NV04(chan, NvSubCopy, 0x0200, 1);
 			OUT_RING  (chan, 1);
 		}
-		if (new_mem->mem_type == TTM_PL_VRAM &&
-		    nouveau_bo_tile_layout(nvbo)) {
-			ret = RING_SPACE(chan, 8);
-			if (ret)
-				return ret;
-
+		if (dst_tiled) {
 			BEGIN_NV04(chan, NvSubCopy, 0x021c, 7);
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
@@ -838,18 +829,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
 		} else {
-			ret = RING_SPACE(chan, 2);
-			if (ret)
-				return ret;
-
 			BEGIN_NV04(chan, NvSubCopy, 0x021c, 1);
 			OUT_RING  (chan, 1);
 		}
 
-		ret = RING_SPACE(chan, 14);
-		if (ret)
-			return ret;
-
 		BEGIN_NV04(chan, NvSubCopy, 0x0238, 2);
 		OUT_RING  (chan, upper_32_bits(src_offset));
 		OUT_RING  (chan, upper_32_bits(dst_offset));
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 383f4e6ea9d1..4598a6afea1e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -339,6 +339,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto fail_device;
 
+	dev->irq_enabled = true;
+
 	/* workaround an odd issue on nvc1 by disabling the device's
 	 * nosnoop capability.  hopefully won't cause issues until a
 	 * better fix is found - assuming there is one...
@@ -426,6 +428,7 @@ nouveau_drm_remove(struct pci_dev *pdev)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_object *device;
 
+	dev->irq_enabled = false;
 	device = drm->client.base.device;
 	drm_put_dev(dev);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index b4b4d0c1f4af..5bccf31cc974 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -287,7 +287,8 @@ validate_fini_list(struct list_head *list, struct nouveau_fence *fence)
 	list_for_each_safe(entry, tmp, list) {
 		nvbo = list_entry(entry, struct nouveau_bo, entry);
 
-		nouveau_bo_fence(nvbo, fence);
+		if (likely(fence))
+			nouveau_bo_fence(nvbo, fence);
 
 		if (unlikely(nvbo->validate_mapped)) {
 			ttm_bo_kunmap(&nvbo->kmap);
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 9b794c933c81..b5df614660a8 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -199,7 +199,7 @@ static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm)
 static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 		struct page **pages, uint32_t npages, uint32_t roll)
 {
-	dma_addr_t pat_pa = 0;
+	dma_addr_t pat_pa = 0, data_pa = 0;
 	uint32_t *data;
 	struct pat *pat;
 	struct refill_engine *engine = txn->engine_handle;
@@ -223,7 +223,9 @@ static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 			.lut_id = engine->tcm->lut_id,
 		};
 
-	data = alloc_dma(txn, 4*i, &pat->data_pa);
+	data = alloc_dma(txn, 4*i, &data_pa);
+	/* FIXME: what if data_pa is more than 32-bit ? */
+	pat->data_pa = data_pa;
 
 	while (i--) {
 		int n = i + roll;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index ebbdf4132e9c..2272c66f1842 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -806,7 +806,7 @@ int omap_gem_get_paddr(struct drm_gem_object *obj,
 			omap_obj->paddr = tiler_ssptr(block);
 			omap_obj->block = block;
 
-			DBG("got paddr: %08x", omap_obj->paddr);
+			DBG("got paddr: %pad", &omap_obj->paddr);
 		}
 
 		omap_obj->paddr_cnt++;
@@ -1004,9 +1004,9 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	if (obj->map_list.map)
 		off = (uint64_t)obj->map_list.hash.key;
 
-	seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d",
+	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
 			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
-			off, omap_obj->paddr, omap_obj->paddr_cnt,
+			off, &omap_obj->paddr, omap_obj->paddr_cnt,
 			omap_obj->vaddr, omap_obj->roll);
 
 	if (omap_obj->flags & OMAP_BO_TILED) {
@@ -1489,8 +1489,8 @@ void omap_gem_init(struct drm_device *dev)
 			entry->paddr = tiler_ssptr(block);
 			entry->block = block;
 
-			DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h,
-					entry->paddr,
+			DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h,
+					&entry->paddr,
 					usergart[i].stride_pfn << PAGE_SHIFT);
 		}
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 8d225d7ff4e3..6d01c2ad8428 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -146,8 +146,8 @@ static void omap_plane_pre_apply(struct omap_drm_apply *apply)
 	DBG("%dx%d -> %dx%d (%d)", info->width, info->height,
 			info->out_width, info->out_height,
 			info->screen_width);
-	DBG("%d,%d %08x %08x", info->pos_x, info->pos_y,
-			info->paddr, info->p_uv_addr);
+	DBG("%d,%d %pad %pad", info->pos_x, info->pos_y,
+			&info->paddr, &info->p_uv_addr);
 
 	/* TODO: */
 	ilace = false;
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index b3c51275df5c..7002de79e5da 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -91,7 +91,7 @@ static void qxl_fb_dirty_flush(struct fb_info *info)
 	u32 x1, x2, y1, y2;
 
 	/* TODO: hard coding 32 bpp */
-	int stride = qfbdev->qfb.base.pitches[0] * 4;
+	int stride = qfbdev->qfb.base.pitches[0];
 
 	x1 = qfbdev->dirty.x1;
 	x2 = qfbdev->dirty.x2;
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index 21393dc4700a..f4b6b89b98f3 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -33,6 +33,9 @@ irqreturn_t qxl_irq_handler(DRM_IRQ_ARGS)
 
 	pending = xchg(&qdev->ram_header->int_pending, 0);
 
+	if (!pending)
+		return IRQ_NONE;
+
 	atomic_inc(&qdev->irq_received);
 
 	if (pending & QXL_INTERRUPT_DISPLAY) {
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 489cb8cece4d..3401eb86786c 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -431,6 +431,7 @@ static int qxl_sync_obj_flush(void *sync_obj)
 
 static void qxl_sync_obj_unref(void **sync_obj)
 {
+	*sync_obj = NULL;
 }
 
 static void *qxl_sync_obj_ref(void *sync_obj)
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index d5df8fd10217..971dd8795b68 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -839,14 +839,16 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+					break;
+				}
 			}
 			args.v5.ucTransmitterID = encoder_id;
 			args.v5.ucEncoderMode = encoder_mode;
@@ -861,20 +863,22 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
-				break;
-			case 12:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
-				break;
-			case 16:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
+					break;
+				case 12:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
+					break;
+				case 16:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+					break;
+				}
 			}
 			args.v6.ucTransmitterID = encoder_id;
 			args.v6.ucEncoderMode = encoder_mode;
@@ -938,11 +942,14 @@ static bool atombios_crtc_prepare_pll(struct drm_crtc *crtc, struct drm_display_
 							radeon_atombios_get_ppll_ss_info(rdev,
 											 &radeon_crtc->ss,
 											 ATOM_DP_SS_ID1);
-				} else
+				} else {
 					radeon_crtc->ss_enabled =
 						radeon_atombios_get_ppll_ss_info(rdev,
 										 &radeon_crtc->ss,
 										 ATOM_DP_SS_ID1);
+				}
+				/* disable spread spectrum on DCE3 DP */
+				radeon_crtc->ss_enabled = false;
 			}
 			break;
 		case ATOM_ENCODER_MODE_LVDS:
@@ -1176,7 +1183,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	if ((rdev->family == CHIP_TAHITI) ||
 	    (rdev->family == CHIP_PITCAIRN))
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
-	else if (rdev->family == CHIP_VERDE)
+	else if ((rdev->family == CHIP_VERDE) ||
+		 (rdev->family == CHIP_OLAND) ||
+		 (rdev->family == CHIP_HAINAN)) /* for completeness.  HAINAN has no display hw */
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16);
 
 	switch (radeon_crtc->crtc_id) {
@@ -1656,6 +1665,20 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 			return ATOM_PPLL1;
 		DRM_ERROR("unable to allocate a PPLL\n");
 		return ATOM_PPLL_INVALID;
+	} else if (ASIC_IS_DCE41(rdev)) {
+		/* Don't share PLLs on DCE4.1 chips */
+		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+			if (rdev->clock.dp_extclk)
+				/* skip PPLL programming if using ext clock */
+				return ATOM_PPLL_INVALID;
+		}
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
+			return ATOM_PPLL1;
+		if (!(pll_in_use & (1 << ATOM_PPLL2)))
+			return ATOM_PPLL2;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else if (ASIC_IS_DCE4(rdev)) {
 		/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
 		 * depending on the asic:
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 32501f6ec991..4c05f2b015cf 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -50,7 +50,7 @@ static char *pre_emph_names[] = {
  * or from atom. Note that atom operates on
  * dw units.
  */
-static void radeon_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
+void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
 	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
@@ -100,7 +100,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 
 	base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
 
-	radeon_copy_swap(base, send, send_bytes, true);
+	radeon_atom_copy_swap(base, send, send_bytes, true);
 
 	args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4));
 	args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4));
@@ -137,7 +137,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 		recv_bytes = recv_size;
 
 	if (recv && recv_size)
-		radeon_copy_swap(recv, base + 16, recv_bytes, false);
+		radeon_atom_copy_swap(recv, base + 16, recv_bytes, false);
 
 	return recv_bytes;
 }
@@ -384,6 +384,19 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 
 /***** radeon specific DP functions *****/
 
+static int radeon_dp_get_max_link_rate(struct drm_connector *connector,
+				       u8 dpcd[DP_DPCD_SIZE])
+{
+	int max_link_rate;
+
+	if (radeon_connector_is_dp12_capable(connector))
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
+	else
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
+
+	return max_link_rate;
+}
+
 /* First get the min lane# when low rate is used according to pixel clock
  * (prefer low rate), second check max lane# supported by DP panel,
  * if the max lane# < low rate lane# then use max lane# instead.
@@ -393,7 +406,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 					int pix_clock)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
+	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
 	int max_lane_num = drm_dp_max_lane_count(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
@@ -431,7 +444,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
 			return 540000;
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return radeon_dp_get_max_link_rate(connector, dpcd);
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 4120d355cadd..1b564d7e4191 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -183,7 +183,6 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	struct backlight_properties props;
 	struct radeon_backlight_privdata *pdata;
 	struct radeon_encoder_atom_dig *dig;
-	u8 backlight_level;
 	char bl_name[16];
 
 	/* Mac laptops with multiple GPUs use the gmux driver for backlight
@@ -222,12 +221,17 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 
 	pdata->encoder = radeon_encoder;
 
-	backlight_level = radeon_atom_get_backlight_level_from_reg(rdev);
-
 	dig = radeon_encoder->enc_priv;
 	dig->bl_dev = bd;
 
 	bd->props.brightness = radeon_atom_backlight_get_brightness(bd);
+	/* Set a reasonable default here if the level is 0 otherwise
+	 * fbdev will attempt to turn the backlight on after console
+	 * unblanking and it will try and restore 0 which turns the backlight
+	 * off again.
+	 */
+	if (bd->props.brightness == 0)
+		bd->props.brightness = RADEON_MAX_BL_LEVEL;
 	bd->props.power = FB_BLANK_UNBLANK;
 	backlight_update_status(bd);
 
@@ -1281,7 +1285,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 			}
 			if (is_dp)
 				args.v5.ucLaneNum = dp_lane_count;
-			else if (radeon_encoder->pixel_clock > 165000)
+			else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 				args.v5.ucLaneNum = 8;
 			else
 				args.v5.ucLaneNum = 4;
@@ -1636,8 +1640,12 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			/* some early dce3.2 boards have a bug in their transmitter control table */
-			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730))
+			/* some dce3.x boards have a bug in their transmitter control table.
+			 * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE
+			 * does the same thing and more.
+			 */
+			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
+			    (rdev->family != CHIP_RS780) && (rdev->family != CHIP_RS880))
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
@@ -1873,8 +1881,11 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
 					args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT;
 				else
 					args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
-			} else
+			} else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+				args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS;
+			} else {
 				args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
+			}
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index 082338df708a..2ca389d19258 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -27,6 +27,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+extern void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
+
 #define TARGET_HW_I2C_CLOCK 50
 
 /* these are a limitation of ProcessI2cChannelTransaction not the hw */
@@ -77,7 +79,7 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	}
 
 	if (!(flags & HW_I2C_WRITE))
-		memcpy(buf, base, num);
+		radeon_atom_copy_swap(buf, base, num, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 687b421f75c3..ead08a49bec0 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -94,7 +94,7 @@ static const u32 evergreen_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002,
 	0x913c, 0x0000000f, 0x0000000a
 };
@@ -381,7 +381,7 @@ static const u32 cedar_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002
 };
 
@@ -540,7 +540,7 @@ static const u32 juniper_mgcg_init[] =
 static const u32 supersumo_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -624,7 +624,7 @@ static const u32 sumo_golden_registers[] =
 static const u32 wrestler_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -1718,7 +1718,8 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 					struct drm_display_mode *mode,
 					struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1741,18 +1742,34 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	/* second controller of the pair uses second half of the lb */
 	if (radeon_crtc->crtc_id % 2)
 		tmp += 4;
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp);
 
+	if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+		WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+		       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+		for (i = 0; i < rdev->usec_timeout; i++) {
+			if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+			    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+				break;
+			udelay(1);
+		}
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -2362,6 +2379,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
@@ -2973,7 +2991,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.sx_max_export_size = 256;
 		rdev->config.evergreen.sx_max_export_pos_size = 64;
 		rdev->config.evergreen.sx_max_export_smx_size = 192;
-		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.max_hw_contexts = 4;
 		rdev->config.evergreen.sq_num_cf_insts = 2;
 
 		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
@@ -3775,8 +3793,8 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev)
 		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
 
-	/* only one DAC on DCE6 */
-	if (!ASIC_IS_DCE6(rdev))
+	/* only one DAC on DCE5 */
+	if (!ASIC_IS_DCE5(rdev))
 		WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
 	WREG32(DACB_AUTODETECT_INT_CONTROL, 0);
 
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index eb8ac315f92f..c7cac07f139b 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -967,7 +967,10 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 	if (track->cb_dirty) {
 		tmp = track->cb_target_mask;
 		for (i = 0; i < 8; i++) {
-			if ((tmp >> (i * 4)) & 0xF) {
+			u32 format = G_028C70_FORMAT(track->cb_color_info[i]);
+
+			if (format != V_028C70_COLOR_INVALID &&
+			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
 					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index bb9ea3641312..067cc1fc48e5 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -219,8 +219,7 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
-	       HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI_ACR_SOURCE); /* select SW CTS value */
+	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 75c05631146d..150e3186bec0 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -810,6 +810,10 @@
 #       define LATENCY_LOW_WATERMARK(x)                   ((x) << 0)
 #       define LATENCY_HIGH_WATERMARK(x)                  ((x) << 16)
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define IH_RB_CNTL                                        0x3e00
 #       define IH_RB_ENABLE                               (1 << 0)
 #       define IH_IB_SIZE(x)                              ((x) << 1) /* log2 */
@@ -1100,7 +1104,7 @@
  * 6. COMMAND [29:22] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1115,7 +1119,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 3bf43a16adcc..451d7886644c 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -753,6 +753,10 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 		    (rdev->pdev->device == 0x999C)) {
 			rdev->config.cayman.max_simds_per_se = 6;
 			rdev->config.cayman.max_backends_per_se = 2;
+			rdev->config.cayman.max_hw_contexts = 8;
+			rdev->config.cayman.sx_max_export_size = 256;
+			rdev->config.cayman.sx_max_export_pos_size = 64;
+			rdev->config.cayman.sx_max_export_smx_size = 192;
 		} else if ((rdev->pdev->device == 0x9903) ||
 			   (rdev->pdev->device == 0x9904) ||
 			   (rdev->pdev->device == 0x990A) ||
@@ -763,6 +767,10 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x999D)) {
 			rdev->config.cayman.max_simds_per_se = 4;
 			rdev->config.cayman.max_backends_per_se = 2;
+			rdev->config.cayman.max_hw_contexts = 8;
+			rdev->config.cayman.sx_max_export_size = 256;
+			rdev->config.cayman.sx_max_export_pos_size = 64;
+			rdev->config.cayman.sx_max_export_smx_size = 192;
 		} else if ((rdev->pdev->device == 0x9919) ||
 			   (rdev->pdev->device == 0x9990) ||
 			   (rdev->pdev->device == 0x9991) ||
@@ -773,9 +781,17 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x99A0)) {
 			rdev->config.cayman.max_simds_per_se = 3;
 			rdev->config.cayman.max_backends_per_se = 1;
+			rdev->config.cayman.max_hw_contexts = 4;
+			rdev->config.cayman.sx_max_export_size = 128;
+			rdev->config.cayman.sx_max_export_pos_size = 32;
+			rdev->config.cayman.sx_max_export_smx_size = 96;
 		} else {
 			rdev->config.cayman.max_simds_per_se = 2;
 			rdev->config.cayman.max_backends_per_se = 1;
+			rdev->config.cayman.max_hw_contexts = 4;
+			rdev->config.cayman.sx_max_export_size = 128;
+			rdev->config.cayman.sx_max_export_pos_size = 32;
+			rdev->config.cayman.sx_max_export_smx_size = 96;
 		}
 		rdev->config.cayman.max_texture_channel_caches = 2;
 		rdev->config.cayman.max_gprs = 256;
@@ -783,10 +799,6 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 		rdev->config.cayman.max_gs_threads = 32;
 		rdev->config.cayman.max_stack_entries = 512;
 		rdev->config.cayman.sx_num_of_sets = 8;
-		rdev->config.cayman.sx_max_export_size = 256;
-		rdev->config.cayman.sx_max_export_pos_size = 64;
-		rdev->config.cayman.sx_max_export_smx_size = 192;
-		rdev->config.cayman.max_hw_contexts = 8;
 		rdev->config.cayman.sq_num_cf_insts = 2;
 
 		rdev->config.cayman.sc_prim_fifo_size = 0x40;
@@ -1166,13 +1178,12 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 10); /* poll interval */
@@ -1188,6 +1199,8 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
@@ -1212,14 +1225,11 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 			  (ib->vm ? (ib->vm->id << 24) : 0));
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 10); /* poll interval */
+	radeon_ring_write(ring, ((ib->vm ? ib->vm->id : 0) << 24) | 10); /* poll interval */
 }
 
 void cayman_uvd_semaphore_emit(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index e226faf16fea..e49f7b456038 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -573,6 +573,7 @@
 #              define PACKET3_DB_ACTION_ENA        (1 << 26)
 #              define PACKET3_SH_ACTION_ENA        (1 << 27)
 #              define PACKET3_SX_ACTION_ENA        (1 << 28)
+#              define PACKET3_ENGINE_ME            (1 << 31)
 #define	PACKET3_ME_INITIALIZE				0x44
 #define		PACKET3_ME_INITIALIZE_DEVICE_ID(x) ((x) << 16)
 #define	PACKET3_COND_WRITE				0x45
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index d0314ecbd7c1..46470dd7c710 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2935,9 +2935,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
 	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
 	seq_printf(m, "%u dwords in ring\n", count);
-	for (j = 0; j <= count; j++) {
-		i = (rdp + j) & ring->ptr_mask;
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+	if (ring->ready) {
+		for (j = 0; j <= count; j++) {
+			i = (rdp + j) & ring->ptr_mask;
+			seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index f19620b472f5..4cf21ec1abe3 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2957,14 +2957,17 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence)
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u32 cp_coher_cntl = PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
+
+	if (rdev->family >= CHIP_RV770)
+		cp_coher_cntl |= PACKET3_FULL_CACHE_ENA;
 
 	if (rdev->wb.use_event) {
 		u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */
@@ -2978,9 +2981,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	} else {
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */
@@ -4508,6 +4509,10 @@ restart_ih:
 				break;
 			}
 			break;
+		case 124: /* UVD */
+			DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+			radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+			break;
 		case 176: /* CP_INT in ring buffer */
 		case 177: /* CP_INT in IB1 */
 		case 178: /* CP_INT in IB2 */
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 01a3ec83f284..745e66eacd47 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -749,7 +749,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 		}
 
 		for (i = 0; i < 8; i++) {
-			if ((tmp >> (i * 4)) & 0xF) {
+			u32 format = G_0280A0_FORMAT(track->cb_color_info[i]);
+
+			if (format != V_0280A0_COLOR_INVALID &&
+			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
 					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index b9b1139da356..5df711659049 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -24,6 +24,7 @@
  * Authors: Christian König
  */
 #include <linux/hdmi.h>
+#include <linux/gcd.h>
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
 #include "radeon.h"
@@ -57,28 +58,57 @@ enum r600_hdmi_iec_status_bits {
 static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
     /*	     32kHz	  44.1kHz	48kHz    */
     /* Clock      N     CTS      N     CTS      N     CTS */
-    {  25174,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
+    {  25175,  4096,  25175, 28224, 125875,  6144,  25175 }, /*  25,20/1.001 MHz */
     {  25200,  4096,  25200,  6272,  28000,  6144,  25200 }, /*  25.20       MHz */
     {  27000,  4096,  27000,  6272,  30000,  6144,  27000 }, /*  27.00       MHz */
     {  27027,  4096,  27027,  6272,  30030,  6144,  27027 }, /*  27.00*1.001 MHz */
     {  54000,  4096,  54000,  6272,  60000,  6144,  54000 }, /*  54.00       MHz */
     {  54054,  4096,  54054,  6272,  60060,  6144,  54054 }, /*  54.00*1.001 MHz */
-    {  74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
+    {  74176,  4096,  74176,  5733,  75335,  6144,  74176 }, /*  74.25/1.001 MHz */
     {  74250,  4096,  74250,  6272,  82500,  6144,  74250 }, /*  74.25       MHz */
-    { 148351, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
+    { 148352,  4096, 148352,  5733, 150670,  6144, 148352 }, /* 148.50/1.001 MHz */
     { 148500,  4096, 148500,  6272, 165000,  6144, 148500 }, /* 148.50       MHz */
-    {      0,  4096,      0,  6272,      0,  6144,      0 }  /* Other */
 };
 
+
 /*
- * calculate CTS value if it's not found in the table
+ * calculate CTS and N values if they are not found in the table
  */
-static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
+static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq)
 {
-	if (*CTS == 0)
-		*CTS = clock * N / (128 * freq) * 1000;
-	DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n",
-		  N, *CTS, freq);
+	int n, cts;
+	unsigned long div, mul;
+
+	/* Safe, but overly large values */
+	n = 128 * freq;
+	cts = clock * 1000;
+
+	/* Smallest valid fraction */
+	div = gcd(n, cts);
+
+	n /= div;
+	cts /= div;
+
+	/*
+	 * The optimal N is 128*freq/1000. Calculate the closest larger
+	 * value that doesn't truncate any bits.
+	 */
+	mul = ((128*freq/1000) + (n-1))/n;
+
+	n *= mul;
+	cts *= mul;
+
+	/* Check that we are in spec (not always possible) */
+	if (n < (128*freq/1500))
+		printk(KERN_WARNING "Calculated ACR N value is too small. You may experience audio problems.\n");
+	if (n > (128*freq/300))
+		printk(KERN_WARNING "Calculated ACR N value is too large. You may experience audio problems.\n");
+
+	*N = n;
+	*CTS = cts;
+
+	DRM_DEBUG("Calculated ACR timing N=%d CTS=%d for frequency %d\n",
+		  *N, *CTS, freq);
 }
 
 struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
@@ -86,15 +116,16 @@ struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
 	struct radeon_hdmi_acr res;
 	u8 i;
 
-	for (i = 0; r600_hdmi_predefined_acr[i].clock != clock &&
-	     r600_hdmi_predefined_acr[i].clock != 0; i++)
-		;
-	res = r600_hdmi_predefined_acr[i];
+	/* Precalculated values for common clocks */
+	for (i = 0; i < ARRAY_SIZE(r600_hdmi_predefined_acr); i++) {
+		if (r600_hdmi_predefined_acr[i].clock == clock)
+			return r600_hdmi_predefined_acr[i];
+	}
 
-	/* In case some CTS are missing */
-	r600_hdmi_calc_cts(clock, &res.cts_32khz, res.n_32khz, 32000);
-	r600_hdmi_calc_cts(clock, &res.cts_44_1khz, res.n_44_1khz, 44100);
-	r600_hdmi_calc_cts(clock, &res.cts_48khz, res.n_48khz, 48000);
+	/* And odd clocks get manually calculated */
+	r600_hdmi_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000);
+	r600_hdmi_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100);
+	r600_hdmi_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000);
 
 	return res;
 }
@@ -238,9 +269,19 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	if (ASIC_IS_DCE3(rdev)) {
+	if (ASIC_IS_DCE32(rdev)) {
+		if (dig->dig_encoder == 0) {
+			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		} else {
+			WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+		}
+	} else {
 		/* according to the reg specs, this should DCE3.2 only, but in
-		 * practice it seems to cover DCE3.0 as well.
+		 * practice it seems to cover DCE2.0/3.0/3.1 as well.
 		 */
 		if (dig->dig_encoder == 0) {
 			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
@@ -251,10 +292,6 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
-	} else {
-		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
-		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
-		       AUDIO_DTO_MODULE(clock / 10));
 	}
 }
 
@@ -303,8 +340,8 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	}
 
 	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
-	       HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI0_ACR_SOURCE); /* select SW CTS value */
+	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
 	       HDMI0_NULL_SEND | /* send null packets when required */
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 79df558f8c40..eb28716e87fa 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1259,7 +1259,7 @@
  */
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
@@ -1283,6 +1283,7 @@
 #              define PACKET3_CP_DMA_CMD_DAIC      (1 << 29)
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
+#              define PACKET3_FULL_CACHE_ENA       (1 << 20) /* r7xx+ only */
 #              define PACKET3_TC_ACTION_ENA        (1 << 23)
 #              define PACKET3_VC_ACTION_ENA        (1 << 24)
 #              define PACKET3_CB_ACTION_ENA        (1 << 25)
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index dea6f63c9724..ba2ab9a9b988 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -463,6 +463,13 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 		}
 	}
 
+	/* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */
+	if ((dev->pdev->device == 0x9805) &&
+	    (dev->pdev->subsystem_vendor == 0x1734) &&
+	    (dev->pdev->subsystem_device == 0x11bd)) {
+		if (*connector_type == DRM_MODE_CONNECTOR_VGA)
+			return false;
+	}
 
 	return true;
 }
@@ -715,13 +722,16 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 								(ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT *)
 								(ctx->bios + data_offset +
 								 le16_to_cpu(router_obj->asObjects[k].usSrcDstTableOffset));
+							u8 *num_dst_objs = (u8 *)
+								((u8 *)router_src_dst_table + 1 +
+								 (router_src_dst_table->ucNumberOfSrc * 2));
+							u16 *dst_objs = (u16 *)(num_dst_objs + 1);
 							int enum_id;
 
 							router.router_id = router_obj_id;
-							for (enum_id = 0; enum_id < router_src_dst_table->ucNumberOfDst;
-							     enum_id++) {
+							for (enum_id = 0; enum_id < (*num_dst_objs); enum_id++) {
 								if (le16_to_cpu(path->usConnObjectId) ==
-								    le16_to_cpu(router_src_dst_table->usDstObjectID[enum_id]))
+								    le16_to_cpu(dst_objs[enum_id]))
 									break;
 							}
 
@@ -1651,7 +1661,9 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct
 								kfree(edid);
 						}
 					}
-					record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
+					record += fake_edid_record->ucFakeEDIDLength ?
+						fake_edid_record->ucFakeEDIDLength + 2 :
+						sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
 					break;
 				case LCD_PANEL_RESOLUTION_RECORD_TYPE:
 					panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
@@ -1903,7 +1915,7 @@ static const char *thermal_controller_names[] = {
 	"adm1032",
 	"adm1030",
 	"max6649",
-	"lm64",
+	"lm63", /* lm64 */
 	"f75375",
 	"asc7xxx",
 };
@@ -1914,7 +1926,7 @@ static const char *pp_lib_thermal_controller_names[] = {
 	"adm1032",
 	"adm1030",
 	"max6649",
-	"lm64",
+	"lm63", /* lm64 */
 	"f75375",
 	"RV6xx",
 	"RV770",
@@ -2921,6 +2933,10 @@ void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev)
 	/* tell the bios not to handle mode switching */
 	bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH;
 
+	/* clear the vbios dpms state */
+	if (ASIC_IS_DCE4(rdev))
+		bios_2_scratch &= ~ATOM_S2_DEVICE_DPMS_STATE;
+
 	if (rdev->family >= CHIP_R600) {
 		WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch);
 		WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch);
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index d96070bf8388..8c44ef57864b 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -215,7 +215,8 @@ static int radeon_atpx_verify_interface(struct radeon_atpx *atpx)
 	memcpy(&output, info->buffer.pointer, size);
 
 	/* TODO: check version? */
-	printk("ATPX version %u\n", output.version);
+	printk("ATPX version %u, functions 0x%08x\n",
+	       output.version, output.function_bits);
 
 	radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
 
@@ -522,6 +523,13 @@ static bool radeon_atpx_detect(void)
 		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
 	}
 
+	/* some newer PX laptops mark the dGPU as a non-VGA display device */
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+		vga_count++;
+
+		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
+	}
+
 	if (has_atpx && vga_count == 2) {
 		acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 061b227dae0c..b131520521e4 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -196,6 +196,20 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 		}
 	}
 
+	if (!found) {
+		while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+			dhandle = ACPI_HANDLE(&pdev->dev);
+			if (!dhandle)
+				continue;
+
+			status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+			if (!ACPI_FAILURE(status)) {
+				found = true;
+				break;
+			}
+		}
+	}
+
 	if (!found)
 		return false;
 
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2399f25ec037..fc604fc75797 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1345,7 +1345,7 @@ bool radeon_connector_is_dp12_capable(struct drm_connector *connector)
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (ASIC_IS_DCE5(rdev) &&
-	    (rdev->clock.dp_extclk >= 53900) &&
+	    (rdev->clock.default_dispclk >= 53900) &&
 	    radeon_connector_encoder_is_hbr2(connector)) {
 		return true;
 	}
@@ -1489,6 +1489,24 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = {
 	.force = radeon_dvi_force,
 };
 
+static const struct drm_connector_funcs radeon_edp_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
+static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
 void
 radeon_add_atom_connector(struct drm_device *dev,
 			  uint32_t connector_id,
@@ -1580,8 +1598,6 @@ radeon_add_atom_connector(struct drm_device *dev,
 			goto failed;
 		radeon_dig_connector->igp_lane_info = igp_lane_info;
 		radeon_connector->con_priv = radeon_dig_connector;
-		drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			/* add DP i2c bus */
 			if (connector_type == DRM_MODE_CONNECTOR_eDP)
@@ -1598,6 +1614,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_VGA:
 		case DRM_MODE_CONNECTOR_DVIA:
 		default:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			radeon_connector->dac_load_detect = true;
@@ -1610,6 +1630,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_HDMIA:
 		case DRM_MODE_CONNECTOR_HDMIB:
 		case DRM_MODE_CONNECTOR_DisplayPort:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.underscan_property,
 						      UNDERSCAN_OFF);
@@ -1634,6 +1658,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 			break;
 		case DRM_MODE_CONNECTOR_LVDS:
 		case DRM_MODE_CONNECTOR_eDP:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_lvds_bridge_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      dev->mode_config.scaling_mode_property,
 						      DRM_MODE_SCALE_FULLSCREEN);
@@ -1797,7 +1825,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
+			drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type);
 			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				/* add DP i2c bus */
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7e265a58141f..60af3cda587b 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -80,9 +80,11 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		p->relocs[i].lobj.bo = p->relocs[i].robj;
 		p->relocs[i].lobj.written = !!r->write_domain;
 
-		/* the first reloc of an UVD job is the
-		   msg and that must be in VRAM */
-		if (p->ring == R600_RING_TYPE_UVD_INDEX && i == 0) {
+		/* the first reloc of an UVD job is the msg and that must be in
+		   VRAM, also but everything into VRAM on AGP cards to avoid
+		   image corruptions */
+		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
+		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
 			/* TODO: is this still needed for NI+ ? */
 			p->relocs[i].lobj.domain =
 				RADEON_GEM_DOMAIN_VRAM;
@@ -94,6 +96,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 			uint32_t domain = r->write_domain ?
 				r->write_domain : r->read_domains;
 
+			if (domain & RADEON_GEM_DOMAIN_CPU) {
+				DRM_ERROR("RADEON_GEM_DOMAIN_CPU is not valid "
+					  "for command submission\n");
+				return -EINVAL;
+			}
+
 			p->relocs[i].lobj.domain = domain;
 			if (domain == RADEON_GEM_DOMAIN_VRAM)
 				domain |= RADEON_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b0dc0b6cb4e0..8df1525f71d2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1196,13 +1196,22 @@ int radeon_device_init(struct radeon_device *rdev,
 			return r;
 	}
 	if ((radeon_testing & 1)) {
-		radeon_test_moves(rdev);
+		if (rdev->accel_working)
+			radeon_test_moves(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
 	}
 	if ((radeon_testing & 2)) {
-		radeon_test_syncing(rdev);
+		if (rdev->accel_working)
+			radeon_test_syncing(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
 	}
 	if (radeon_benchmarking) {
-		radeon_benchmark(rdev, radeon_benchmarking);
+		if (rdev->accel_working)
+			radeon_benchmark(rdev, radeon_benchmarking);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index eb18bb7af1cc..a84de32a91f5 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -688,6 +688,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 	struct radeon_device *rdev = dev->dev_private;
 	int ret = 0;
 
+	/* don't leak the edid if we already fetched it in detect() */
+	if (radeon_connector->edid)
+		goto got_edid;
+
 	/* on hw with routers, select right port */
 	if (radeon_connector->router.ddc_valid)
 		radeon_router_select_ddc_port(radeon_connector);
@@ -727,8 +731,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 			radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev);
 	}
 	if (radeon_connector->edid) {
+got_edid:
 		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
+		drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
 	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 5ce190b8bd1f..2915a1c56934 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -1157,6 +1157,8 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 		return -ENOMEM;
 
 	r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4);
+	if (r)
+		return r;
 	ib.length_dw = 0;
 
 	r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index fc60b74ee304..e24ca6ab96de 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -1020,6 +1020,9 @@ void radeon_i2c_destroy(struct radeon_i2c_chan *i2c)
 /* Add the default buses */
 void radeon_i2c_init(struct radeon_device *rdev)
 {
+	if (radeon_hw_i2c)
+		DRM_INFO("hw_i2c forced on, you may experience display detection problems!\n");
+
 	if (rdev->is_atom_bios)
 		radeon_atombios_i2c_init(rdev);
 	else
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 4f2d4f4c1dab..2c3c4c58a765 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -414,6 +414,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		value = rdev->config.si.tile_mode_array;
 		value_size = sizeof(uint32_t)*32;
 		break;
+	case RADEON_INFO_SI_CP_DMA_COMPUTE:
+		*value = 1;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
@@ -482,6 +485,10 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 		radeon_vm_init(rdev, &fpriv->vm);
 
+		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+		if (r)
+			return r;
+
 		/* map the ib pool buffer read only into
 		 * virtual address space */
 		bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
@@ -489,6 +496,8 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
 					  RADEON_VM_PAGE_READABLE |
 					  RADEON_VM_PAGE_SNOOPED);
+
+		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		if (r) {
 			radeon_vm_fini(rdev, &fpriv->vm);
 			kfree(fpriv);
@@ -657,6 +666,8 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
 
 	/* Get associated drm_crtc: */
 	drmcrtc = &rdev->mode_info.crtcs[crtc]->base;
+	if (!drmcrtc)
+		return -EINVAL;
 
 	/* Helper routine in DRM core does all the work: */
 	return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error,
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 7cb178a34a0f..bc73021d3596 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -422,6 +422,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 	/* Pin framebuffer & get tilling informations */
 	obj = radeon_fb->obj;
 	rbo = gem_to_radeon_bo(obj);
+retry:
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		return r;
@@ -430,6 +431,33 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 				     &base);
 	if (unlikely(r != 0)) {
 		radeon_bo_unreserve(rbo);
+
+		/* On old GPU like RN50 with little vram pining can fails because
+		 * current fb is taking all space needed. So instead of unpining
+		 * the old buffer after pining the new one, first unpin old one
+		 * and then retry pining new one.
+		 *
+		 * As only master can set mode only master can pin and it is
+		 * unlikely the master client will race with itself especialy
+		 * on those old gpu with single crtc.
+		 *
+		 * We don't shutdown the display controller because new buffer
+		 * will end up in same spot.
+		 */
+		if (!atomic && fb && fb != crtc->fb) {
+			struct radeon_bo *old_rbo;
+			unsigned long nsize, osize;
+
+			old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj);
+			osize = radeon_bo_size(old_rbo);
+			nsize = radeon_bo_size(rbo);
+			if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) {
+				radeon_bo_unpin(old_rbo);
+				radeon_bo_unreserve(old_rbo);
+				fb = NULL;
+				goto retry;
+			}
+		}
 		return -EINVAL;
 	}
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 1424ccde2377..f83727915787 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -582,22 +582,30 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	radeon_bo_check_tiling(rbo, 0, 0);
 	rdev = rbo->rdev;
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		size = bo->mem.num_pages << PAGE_SHIFT;
-		offset = bo->mem.start << PAGE_SHIFT;
-		if ((offset + size) > rdev->mc.visible_vram_size) {
-			/* hurrah the memory is not visible ! */
-			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
-			rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
-			r = ttm_bo_validate(bo, &rbo->placement, false, false);
-			if (unlikely(r != 0))
-				return r;
-			offset = bo->mem.start << PAGE_SHIFT;
-			/* this should not happen */
-			if ((offset + size) > rdev->mc.visible_vram_size)
-				return -EINVAL;
-		}
+	if (bo->mem.mem_type != TTM_PL_VRAM)
+		return 0;
+
+	size = bo->mem.num_pages << PAGE_SHIFT;
+	offset = bo->mem.start << PAGE_SHIFT;
+	if ((offset + size) <= rdev->mc.visible_vram_size)
+		return 0;
+
+	/* hurrah the memory is not visible ! */
+	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
+	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+	r = ttm_bo_validate(bo, &rbo->placement, false, false);
+	if (unlikely(r == -ENOMEM)) {
+		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
+		return ttm_bo_validate(bo, &rbo->placement, false, false);
+	} else if (unlikely(r != 0)) {
+		return r;
 	}
+
+	offset = bo->mem.start << PAGE_SHIFT;
+	/* this should never happen */
+	if ((offset + size) > rdev->mc.visible_vram_size)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 788c64cb4b47..469ba710b52f 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -561,8 +561,10 @@ void radeon_pm_resume(struct radeon_device *rdev)
 	rdev->pm.current_clock_mode_index = 0;
 	rdev->pm.current_sclk = rdev->pm.default_sclk;
 	rdev->pm.current_mclk = rdev->pm.default_mclk;
-	rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
-	rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+	if (rdev->pm.power_state) {
+		rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
+		rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+	}
 	if (rdev->pm.pm_method == PM_METHOD_DYNPM
 	    && rdev->pm.dynpm_state == DYNPM_STATE_SUSPENDED) {
 		rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 83f6295a0e5e..6e0f4809bda0 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -823,9 +823,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	 * packet that is the root issue
 	 */
 	i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-	for (j = 0; j <= (count + 32); j++) {
-		seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
-		i = (i + 1) & ring->ptr_mask;
+	if (ring->ready) {
+		for (j = 0; j <= (count + 32); j++) {
+			seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+			i = (i + 1) & ring->ptr_mask;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index bbed4af8d0bc..f9ebf2bf8b57 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -37,8 +37,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	struct radeon_bo **gtt_obj = NULL;
 	struct radeon_fence *fence = NULL;
 	uint64_t gtt_addr, vram_addr;
-	unsigned i, n, size;
-	int r, ring;
+	unsigned n, size;
+	int i, r, ring;
 
 	switch (flag) {
 	case RADEON_TEST_COPY_DMA:
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index f3ccf6d4addb..5715429279fb 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -242,6 +242,8 @@ void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
 		if (handle != 0 && rdev->uvd.filp[i] == filp) {
 			struct radeon_fence *fence;
 
+			radeon_uvd_note_usage(rdev);
+
 			r = radeon_uvd_get_destroy_msg(rdev,
 				R600_RING_TYPE_UVD_INDEX, handle, &fence);
 			if (r) {
@@ -447,6 +449,10 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 	cmd = radeon_get_ib_value(p, p->idx) >> 1;
 
 	if (cmd < 0x4) {
+		if (end <= start) {
+			DRM_ERROR("invalid reloc offset %X!\n", offset);
+			return -EINVAL;
+		}
 		if ((end - start) < buf_sizes[cmd]) {
 			DRM_ERROR("buffer to small (%d / %d)!\n",
 				  (unsigned)(end - start), buf_sizes[cmd]);
@@ -458,7 +464,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	if ((start >> 28) != (end >> 28)) {
+	if ((start >> 28) != ((end - 1) >> 28)) {
 		DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n",
 			  start, end);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 233a9b9fa1f7..b8074a8ec75a 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -174,10 +174,13 @@ int rs400_gart_enable(struct radeon_device *rdev)
 	/* FIXME: according to doc we should set HIDE_MMCFG_BAR=0,
 	 * AGPMODE30=0 & AGP30ENHANCED=0 in NB_CNTL */
 	if ((rdev->family == CHIP_RS690) || (rdev->family == CHIP_RS740)) {
-		WREG32_MC(RS480_MC_MISC_CNTL,
-			  (RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN));
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	} else {
-		WREG32_MC(RS480_MC_MISC_CNTL, RS480_GART_INDEX_REG_EN);
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	}
 	/* Enable gart */
 	WREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE, (RS480_GART_EN | size_reg));
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 670b555d2ca2..ae813fef0818 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -582,8 +582,10 @@ int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
 		return -EINVAL;
 	}
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
-	addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
+	if (addr != rdev->dummy_page.addr)
+		addr |= R600_PTE_VALID | R600_PTE_READABLE |
+			R600_PTE_WRITEABLE;
+	addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
 	writeq(addr, ptr + (i * 8));
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 55880d5962c3..ea28ecbd5c79 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -162,6 +162,16 @@ static void rs690_mc_init(struct radeon_device *rdev)
 	base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
 	base = G_000100_MC_FB_START(base) << 16;
 	rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
+	/* Some boards seem to be configured for 128MB of sideport memory,
+	 * but really only have 64MB.  Just skip the sideport and use
+	 * UMA memory.
+	 */
+	if (rdev->mc.igp_sideport_enabled &&
+	    (rdev->mc.real_vram_size == (384 * 1024 * 1024))) {
+		base += 128 * 1024 * 1024;
+		rdev->mc.real_vram_size -= 128 * 1024 * 1024;
+		rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+	}
 
 	/* Use K8 direct mapping for fast fb access. */ 
 	rdev->fastfb_working = false;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1a96a16b9996..03add5d5542e 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1467,7 +1467,8 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1482,16 +1483,30 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset,
 	       DC_LB_MEMORY_CONFIG(tmp));
 
+	WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+	       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+		    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+			break;
+		udelay(1);
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -3600,8 +3615,15 @@ static int si_mc_init(struct radeon_device *rdev)
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	/* size in MB on si */
-	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
-	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	tmp = RREG32(CONFIG_MEMSIZE);
+	/* some boards may have garbage in the upper 16 bits */
+	if (tmp & 0xffff0000) {
+		DRM_INFO("Probable bad vram size: 0x%08x\n", tmp);
+		if (tmp & 0xffff)
+			tmp &= 0xffff;
+	}
+	rdev->mc.mc_vram_size = tmp * 1024ULL * 1024ULL;
+	rdev->mc.real_vram_size = rdev->mc.mc_vram_size;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	si_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
@@ -3796,13 +3818,64 @@ static int si_vm_packet3_ce_check(struct radeon_device *rdev,
 	return 0;
 }
 
+static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx)
+{
+	u32 start_reg, reg, i;
+	u32 command = ib[idx + 4];
+	u32 info = ib[idx + 1];
+	u32 idx_value = ib[idx];
+	if (command & PACKET3_CP_DMA_CMD_SAS) {
+		/* src address space is register */
+		if (((info & 0x60000000) >> 29) == 0) {
+			start_reg = idx_value << 2;
+			if (command & PACKET3_CP_DMA_CMD_SAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad SRC register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+					if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad SRC register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	if (command & PACKET3_CP_DMA_CMD_DAS) {
+		/* dst address space is register */
+		if (((info & 0x00300000) >> 20) == 0) {
+			start_reg = ib[idx + 2];
+			if (command & PACKET3_CP_DMA_CMD_DAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad DST register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+				if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad DST register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	return 0;
+}
+
 static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 				   u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, end_reg, reg, i;
-	u32 command, info;
 
 	switch (pkt->opcode) {
 	case PACKET3_NOP:
@@ -3903,50 +3976,9 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 		}
 		break;
 	case PACKET3_CP_DMA:
-		command = ib[idx + 4];
-		info = ib[idx + 1];
-		if (command & PACKET3_CP_DMA_CMD_SAS) {
-			/* src address space is register */
-			if (((info & 0x60000000) >> 29) == 0) {
-				start_reg = idx_value << 2;
-				if (command & PACKET3_CP_DMA_CMD_SAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad SRC register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad SRC register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
-		if (command & PACKET3_CP_DMA_CMD_DAS) {
-			/* dst address space is register */
-			if (((info & 0x00300000) >> 20) == 0) {
-				start_reg = ib[idx + 2];
-				if (command & PACKET3_CP_DMA_CMD_DAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad DST register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad DST register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
 		break;
 	default:
 		DRM_ERROR("Invalid GFX packet3: 0x%x\n", pkt->opcode);
@@ -3958,6 +3990,7 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				       u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, reg, i;
@@ -4030,6 +4063,11 @@ static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				return -EINVAL;
 		}
 		break;
+	case PACKET3_CP_DMA:
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
+		break;
 	default:
 		DRM_ERROR("Invalid Compute packet3: 0x%x\n", pkt->opcode);
 		return -EINVAL;
@@ -4481,7 +4519,7 @@ static void si_disable_interrupt_state(struct radeon_device *rdev)
 	}
 
 	if (!ASIC_IS_NODCE(rdev)) {
-		WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
+		WREG32(DAC_AUTODETECT_INT_CONTROL, 0);
 
 		tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY;
 		WREG32(DC_HPD1_INT_CONTROL, tmp);
@@ -5121,6 +5159,10 @@ restart_ih:
 				break;
 			}
 			break;
+		case 124: /* UVD */
+			DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+			radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+			break;
 		case 146:
 		case 147:
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 8f2d7d4f9b28..9652ed9ec639 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -97,6 +97,10 @@
 
 #define DMIF_ADDR_CALC  				0xC00
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define	SRBM_STATUS				        0xE50
 #define		GRBM_RQ_PENDING 			(1 << 5)
 #define		VMC_BUSY 				(1 << 8)
@@ -243,7 +247,7 @@
 #define		NOOFGROUPS_SHIFT				12
 #define		NOOFGROUPS_MASK					0x00001000
 
-#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x2808
+#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x28e8
 #define		TRAIN_DONE_D0      			(1 << 30)
 #define		TRAIN_DONE_D1      			(1 << 31)
 
@@ -390,7 +394,7 @@
 #       define GRPH_PFLIP_INT_MASK                      (1 << 0)
 #       define GRPH_PFLIP_INT_TYPE                      (1 << 8)
 
-#define	DACA_AUTODETECT_INT_CONTROL			0x66c8
+#define	DAC_AUTODETECT_INT_CONTROL			0x67c8
 
 #define DC_HPD1_INT_STATUS                              0x601c
 #define DC_HPD2_INT_STATUS                              0x6028
@@ -924,7 +928,7 @@
  * 6. COMMAND [30:21] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -939,7 +943,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 2b5461bcd9fb..f5ddd3550796 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -78,6 +78,7 @@ static int modeset_init(struct drm_device *dev)
 	if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) {
 		/* oh nos! */
 		dev_err(dev->dev, "no encoders/connectors found\n");
+		drm_mode_config_cleanup(dev);
 		return -ENXIO;
 	}
 
@@ -116,6 +117,7 @@ static int tilcdc_unload(struct drm_device *dev)
 	struct tilcdc_drm_private *priv = dev->dev_private;
 	struct tilcdc_module *mod, *cur;
 
+	drm_fbdev_cma_fini(priv->fbdev);
 	drm_kms_helper_poll_fini(dev);
 	drm_mode_config_cleanup(dev);
 	drm_vblank_cleanup(dev);
@@ -169,33 +171,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = priv;
 
 	priv->wq = alloc_ordered_workqueue("tilcdc", 0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto fail_free_priv;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(dev->dev, "failed to get memory resource\n");
 		ret = -EINVAL;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->mmio = ioremap_nocache(res->start, resource_size(res));
 	if (!priv->mmio) {
 		dev_err(dev->dev, "failed to ioremap\n");
 		ret = -ENOMEM;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->clk = clk_get(dev->dev, "fck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get functional clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_iounmap;
 	}
 
 	priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get display clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_put_clk;
 	}
 
 #ifdef CONFIG_CPU_FREQ
@@ -205,7 +211,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 			CPUFREQ_TRANSITION_NOTIFIER);
 	if (ret) {
 		dev_err(dev->dev, "failed to register cpufreq notifier\n");
-		goto fail;
+		goto fail_put_disp_clk;
 	}
 #endif
 
@@ -237,13 +243,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	ret = modeset_init(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize mode setting\n");
-		goto fail;
+		goto fail_cpufreq_unregister;
 	}
 
 	ret = drm_vblank_init(dev, 1);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
-		goto fail;
+		goto fail_mode_config_cleanup;
 	}
 
 	pm_runtime_get_sync(dev->dev);
@@ -251,7 +257,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
-		goto fail;
+		goto fail_vblank_cleanup;
 	}
 
 	platform_set_drvdata(pdev, dev);
@@ -259,13 +265,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	priv->fbdev = drm_fbdev_cma_init(dev, 16,
 			dev->mode_config.num_crtc,
 			dev->mode_config.num_connector);
+	if (IS_ERR(priv->fbdev)) {
+		ret = PTR_ERR(priv->fbdev);
+		goto fail_irq_uninstall;
+	}
 
 	drm_kms_helper_poll_init(dev);
 
 	return 0;
 
-fail:
-	tilcdc_unload(dev);
+fail_irq_uninstall:
+	pm_runtime_get_sync(dev->dev);
+	drm_irq_uninstall(dev);
+	pm_runtime_put_sync(dev->dev);
+
+fail_vblank_cleanup:
+	drm_vblank_cleanup(dev);
+
+fail_mode_config_cleanup:
+	drm_mode_config_cleanup(dev);
+
+fail_cpufreq_unregister:
+	pm_runtime_disable(dev->dev);
+#ifdef CONFIG_CPU_FREQ
+	cpufreq_unregister_notifier(&priv->freq_transition,
+			CPUFREQ_TRANSITION_NOTIFIER);
+fail_put_disp_clk:
+	clk_put(priv->disp_clk);
+#endif
+
+fail_put_clk:
+	clk_put(priv->clk);
+
+fail_iounmap:
+	iounmap(priv->mmio);
+
+fail_free_wq:
+	flush_workqueue(priv->wq);
+	destroy_workqueue(priv->wq);
+
+fail_free_priv:
+	dev->dev_private = NULL;
+	kfree(priv);
 	return ret;
 }
 
@@ -596,10 +637,10 @@ static int __init tilcdc_drm_init(void)
 static void __exit tilcdc_drm_fini(void)
 {
 	DBG("fini");
-	tilcdc_tfp410_fini();
-	tilcdc_slave_fini();
-	tilcdc_panel_fini();
 	platform_driver_unregister(&tilcdc_platform_driver);
+	tilcdc_panel_fini();
+	tilcdc_slave_fini();
+	tilcdc_tfp410_fini();
 }
 
 late_initcall(tilcdc_drm_init);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 09176654fddb..779d508616d3 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -151,6 +151,7 @@ struct panel_connector {
 static void panel_connector_destroy(struct drm_connector *connector)
 {
 	struct panel_connector *panel_connector = to_panel_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(panel_connector);
 }
@@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod)
 {
 	struct panel_module *panel_mod = to_panel_module(mod);
 
-	if (panel_mod->timings) {
+	if (panel_mod->timings)
 		display_timings_release(panel_mod->timings);
-		kfree(panel_mod->timings);
-	}
 
 	tilcdc_module_cleanup(mod);
 	kfree(panel_mod->info);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
index db1d2fc9dfb5..5d6c597a5d69 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
@@ -142,6 +142,7 @@ struct slave_connector {
 static void slave_connector_destroy(struct drm_connector *connector)
 {
 	struct slave_connector *slave_connector = to_slave_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(slave_connector);
 }
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index a36788fbcd98..986131dd9f47 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -168,6 +168,7 @@ struct tfp410_connector {
 static void tfp410_connector_destroy(struct drm_connector *connector)
 {
 	struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(tfp410_connector);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 9b07b7d44a58..0ac0a88860a4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -498,9 +498,11 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 moved:
 	if (bo->evicted) {
-		ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
-		if (ret)
-			pr_err("Can not flush read caches\n");
+		if (bdev->driver->invalidate_caches) {
+			ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
+			if (ret)
+				pr_err("Can not flush read caches\n");
+		}
 		bo->evicted = false;
 	}
 
@@ -1153,24 +1155,32 @@ out_unlock:
 	return ret;
 }
 
-static int ttm_bo_mem_compat(struct ttm_placement *placement,
-			     struct ttm_mem_reg *mem)
+static bool ttm_bo_mem_compat(struct ttm_placement *placement,
+			      struct ttm_mem_reg *mem,
+			      uint32_t *new_flags)
 {
 	int i;
 
 	if (mem->mm_node && placement->lpfn != 0 &&
 	    (mem->start < placement->fpfn ||
 	     mem->start + mem->num_pages > placement->lpfn))
-		return -1;
+		return false;
 
 	for (i = 0; i < placement->num_placement; i++) {
-		if ((placement->placement[i] & mem->placement &
-			TTM_PL_MASK_CACHING) &&
-			(placement->placement[i] & mem->placement &
-			TTM_PL_MASK_MEM))
-			return i;
+		*new_flags = placement->placement[i];
+		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
+		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
+			return true;
 	}
-	return -1;
+
+	for (i = 0; i < placement->num_busy_placement; i++) {
+		*new_flags = placement->busy_placement[i];
+		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
+		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
+			return true;
+	}
+
+	return false;
 }
 
 int ttm_bo_validate(struct ttm_buffer_object *bo,
@@ -1179,6 +1189,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 			bool no_wait_gpu)
 {
 	int ret;
+	uint32_t new_flags;
 
 	BUG_ON(!ttm_bo_is_reserved(bo));
 	/* Check that range is valid */
@@ -1189,8 +1200,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * Check whether we need to move buffer.
 	 */
-	ret = ttm_bo_mem_compat(placement, &bo->mem);
-	if (ret < 0) {
+	if (!ttm_bo_mem_compat(placement, &bo->mem, &new_flags)) {
 		ret = ttm_bo_move_buffer(bo, placement, interruptible,
 					 no_wait_gpu);
 		if (ret)
@@ -1200,7 +1210,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 		 * Use the access and other non-mapping-related flag bits from
 		 * the compatible memory placement flags to the active flags
 		 */
-		ttm_flag_masked(&bo->mem.placement, placement->placement[ret],
+		ttm_flag_masked(&bo->mem.placement, new_flags,
 				~TTM_PL_MASK_MEMTYPE);
 	}
 	/*
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index af894584dd90..b7f757158df7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -342,19 +342,25 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	if (ret)
 		goto out;
 
+	/*
+	 * Single TTM move. NOP.
+	 */
 	if (old_iomap == NULL && new_iomap == NULL)
 		goto out2;
+
+	/*
+	 * Move nonexistent data. NOP.
+	 */
 	if (old_iomap == NULL && ttm == NULL)
 		goto out2;
 
-	if (ttm->state == tt_unpopulated) {
+	/*
+	 * TTM might be null for moves within the same region.
+	 */
+	if (ttm && ttm->state == tt_unpopulated) {
 		ret = ttm->bdev->driver->ttm_tt_populate(ttm);
-		if (ret) {
-			/* if we fail here don't nuke the mm node
-			 * as the bo still owns it */
-			old_copy.mm_node = NULL;
+		if (ret)
 			goto out1;
-		}
 	}
 
 	add = 0;
@@ -380,11 +386,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 						   prot);
 		} else
 			ret = ttm_copy_io_page(new_iomap, old_iomap, page);
-		if (ret) {
-			/* failing here, means keep old copy as-is */
-			old_copy.mm_node = NULL;
+		if (ret)
 			goto out1;
-		}
 	}
 	mb();
 out2:
@@ -402,7 +405,12 @@ out1:
 	ttm_mem_reg_iounmap(bdev, old_mem, new_iomap);
 out:
 	ttm_mem_reg_iounmap(bdev, &old_copy, old_iomap);
-	ttm_bo_mem_put(bo, &old_copy);
+
+	/*
+	 * On error, keep the mm node!
+	 */
+	if (!ret)
+		ttm_bo_mem_put(bo, &old_copy);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_move_memcpy);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b8b394319b45..de1a753b1d56 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -1006,9 +1006,9 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
 static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
 				  struct shrink_control *sc)
 {
-	static atomic_t start_pool = ATOMIC_INIT(0);
+	static unsigned start_pool;
 	unsigned idx = 0;
-	unsigned pool_offset = atomic_add_return(1, &start_pool);
+	unsigned pool_offset;
 	unsigned shrink_pages = sc->nr_to_scan;
 	struct device_pools *p;
 
@@ -1016,7 +1016,9 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
 		return 0;
 
 	mutex_lock(&_manager->lock);
-	pool_offset = pool_offset % _manager->npools;
+	if (!_manager->npools)
+		goto out;
+	pool_offset = ++start_pool % _manager->npools;
 	list_for_each_entry(p, &_manager->pools, pools) {
 		unsigned nr_free;
 
@@ -1033,6 +1035,7 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
 			 p->pool->dev_name, p->pool->name, current->pid,
 			 nr_free, shrink_pages);
 	}
+out:
 	mutex_unlock(&_manager->lock);
 	/* return estimated number of unused pages in pool */
 	return ttm_dma_pool_get_num_unused_pages();
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5e93a52d4f2c..210d50365162 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -170,7 +170,7 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 		ttm_tt_unbind(ttm);
 	}
 
-	if (likely(ttm->pages != NULL)) {
+	if (ttm->state == tt_unbound) {
 		ttm->bdev->driver->ttm_tt_unpopulate(ttm);
 	}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 07dfd823cc30..6c44c69a5ba4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -740,9 +740,17 @@ static void vmw_postclose(struct drm_device *dev,
 	struct vmw_fpriv *vmw_fp;
 
 	vmw_fp = vmw_fpriv(file_priv);
-	ttm_object_file_release(&vmw_fp->tfile);
-	if (vmw_fp->locked_master)
+
+	if (vmw_fp->locked_master) {
+		struct vmw_master *vmaster =
+			vmw_master(vmw_fp->locked_master);
+
+		ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+		ttm_vt_unlock(&vmaster->lock);
 		drm_master_put(&vmw_fp->locked_master);
+	}
+
+	ttm_object_file_release(&vmw_fp->tfile);
 	kfree(vmw_fp);
 }
 
@@ -942,14 +950,13 @@ static void vmw_master_drop(struct drm_device *dev,
 
 	vmw_fp->locked_master = drm_master_get(file_priv->master);
 	ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile);
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
 	if (unlikely((ret != 0))) {
 		DRM_ERROR("Unable to lock TTM at VT switch.\n");
 		drm_master_put(&vmw_fp->locked_master);
 	}
 
-	ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+	ttm_lock_set_kill(&vmaster->lock, false, SIGTERM);
+	vmw_execbuf_release_pinned_bo(dev_priv);
 
 	if (!dev_priv->enable_fb) {
 		ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 394e6476105b..da068bd13f92 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -834,14 +834,36 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		SVGA3dCmdSurfaceDMA dma;
 	} *cmd;
 	int ret;
+	SVGA3dCmdSurfaceDMASuffix *suffix;
+	uint32_t bo_size;
 
 	cmd = container_of(header, struct vmw_dma_cmd, header);
+	suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma +
+					       header->size - sizeof(*suffix));
+
+	/* Make sure device and verifier stays in sync. */
+	if (unlikely(suffix->suffixSize != sizeof(*suffix))) {
+		DRM_ERROR("Invalid DMA suffix size.\n");
+		return -EINVAL;
+	}
+
 	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
 				      &cmd->dma.guest.ptr,
 				      &vmw_bo);
 	if (unlikely(ret != 0))
 		return ret;
 
+	/* Make sure DMA doesn't cross BO boundaries. */
+	bo_size = vmw_bo->base.num_pages * PAGE_SIZE;
+	if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) {
+		DRM_ERROR("Invalid DMA offset.\n");
+		return -EINVAL;
+	}
+
+	bo_size -= cmd->dma.guest.ptr.offset;
+	if (unlikely(suffix->maximumOffset > bo_size))
+		suffix->maximumOffset = bo_size;
+
 	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				user_surface_converter, &cmd->dma.host.sid,
 				NULL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index ed5ce2a41bbf..1b0f34bd3a03 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -147,7 +147,7 @@ static int vmw_fb_check_var(struct fb_var_screeninfo *var,
 	}
 
 	if (!vmw_kms_validate_mode_vram(vmw_priv,
-					info->fix.line_length,
+					var->xres * var->bits_per_pixel/8,
 					var->yoffset + var->yres)) {
 		DRM_ERROR("Requested geom can not fit in framebuffer\n");
 		return -EINVAL;
@@ -162,6 +162,8 @@ static int vmw_fb_set_par(struct fb_info *info)
 	struct vmw_private *vmw_priv = par->vmw_priv;
 	int ret;
 
+	info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8;
+
 	ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres,
 				 info->fix.line_length,
 				 par->bpp, par->depth);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 3eb148667d63..89664933861f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -163,8 +163,9 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 
 	mutex_lock(&dev_priv->hw_mutex);
 
+	vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
 	while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0)
-		vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
+		;
 
 	dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index bc784254e78e..407d7f9fe8a8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -970,7 +970,7 @@ void vmw_resource_unreserve(struct vmw_resource *res,
 	if (new_backup)
 		res->backup_offset = new_backup_offset;
 
-	if (!res->func->may_evict)
+	if (!res->func->may_evict || res->id == -1)
 		return;
 
 	write_lock(&dev_priv->resource_lock);
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index b592eef1efcb..b083509325e4 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -48,7 +48,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 	unsigned long reg;
 	int i, id;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); i++) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
 		for_each_set_bit(id, &reg, BITS_PER_LONG) {
@@ -65,7 +65,7 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
 	u32 i;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); ++i) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
 		host1x_sync_writel(host, 0xffffffffu,
 			HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
 		host1x_sync_writel(host, 0xffffffffu,
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index fb52f3f6de80..bee88ee8066e 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -352,12 +352,14 @@ config LOGITECH_FF
 	  force feedback.
 
 config LOGIRUMBLEPAD2_FF
-	bool "Logitech RumblePad/Rumblepad 2 force feedback support"
+	bool "Logitech force feedback support (variant 2)"
 	depends on HID_LOGITECH
 	select INPUT_FF_MEMLESS
 	help
-	  Say Y here if you want to enable force feedback support for Logitech
-	  RumblePad and Rumblepad 2 devices.
+	  Say Y here if you want to enable force feedback support for:
+	  - Logitech RumblePad
+	  - Logitech Rumblepad 2
+	  - Logitech Formula Vibration Feedback Wheel
 
 config LOGIG940_FF
 	bool "Logitech Flight System G940 force feedback support"
@@ -436,9 +438,11 @@ config HID_MULTITOUCH
 	  - Pixcir dual touch panels
 	  - Quanta panels
 	  - eGalax dual-touch panels, including the Joojoo and Wetab tablets
+	  - SiS multitouch panels
 	  - Stantum multitouch panels
 	  - Touch International Panels
 	  - Unitec Panels
+	  - Wistron optical touch panels
 	  - XAT optical touch panels
 	  - Xiroku optical touch panels
 	  - Zytronic touch panels
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index c7710b5c69af..d54e1d0a4b14 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -46,6 +46,12 @@ module_param(iso_layout, uint, 0644);
 MODULE_PARM_DESC(iso_layout, "Enable/Disable hardcoded ISO-layout of the keyboard. "
 		"(0 = disabled, [1] = enabled)");
 
+static unsigned int swap_opt_cmd = 0;
+module_param(swap_opt_cmd, uint, 0644);
+MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option (\"Alt\") and Command (\"Flag\") keys. "
+		"(For people who want to keep Windows PC keyboard muscle memory. "
+		"[0] = as-is, Mac layout. 1 = swapped, Windows layout.)");
+
 struct apple_sc {
 	unsigned long quirks;
 	unsigned int fn_on;
@@ -150,6 +156,14 @@ static const struct apple_key_translation apple_iso_keyboard[] = {
 	{ }
 };
 
+static const struct apple_key_translation swapped_option_cmd_keys[] = {
+	{ KEY_LEFTALT,	KEY_LEFTMETA },
+	{ KEY_LEFTMETA,	KEY_LEFTALT },
+	{ KEY_RIGHTALT,	KEY_RIGHTMETA },
+	{ KEY_RIGHTMETA,KEY_RIGHTALT },
+	{ }
+};
+
 static const struct apple_key_translation *apple_find_translation(
 		const struct apple_key_translation *table, u16 from)
 {
@@ -242,6 +256,14 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 		}
 	}
 
+	if (swap_opt_cmd) {
+		trans = apple_find_translation(swapped_option_cmd_keys, usage->code);
+		if (trans) {
+			input_event(input, usage->type, trans->to, value);
+			return 1;
+		}
+	}
+
 	return 0;
 }
 
diff --git a/drivers/hid/hid-axff.c b/drivers/hid/hid-axff.c
index 64ab94a55aa7..a594e478a1e2 100644
--- a/drivers/hid/hid-axff.c
+++ b/drivers/hid/hid-axff.c
@@ -95,7 +95,7 @@ static int axff_init(struct hid_device *hid)
 		}
 	}
 
-	if (field_count < 4) {
+	if (field_count < 4 && hid->product != 0xf705) {
 		hid_err(hid, "not enough fields in the report: %d\n",
 			field_count);
 		return -ENODEV;
@@ -180,6 +180,7 @@ static void ax_remove(struct hid_device *hdev)
 
 static const struct hid_device_id ax_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0x0802), },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0xf705), },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, ax_devices);
diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index 1bdcccc54a1d..f745d2c1325e 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -28,7 +28,7 @@
 static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
+	if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
 		hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n");
 		rdesc[11] = rdesc[16] = 0xff;
 		rdesc[12] = rdesc[17] = 0x03;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index ed626e01514b..2bd798a7d9aa 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -94,7 +94,6 @@ EXPORT_SYMBOL_GPL(hid_register_report);
 static struct hid_field *hid_register_field(struct hid_report *report, unsigned usages, unsigned values)
 {
 	struct hid_field *field;
-	int i;
 
 	if (report->maxfield == HID_MAX_FIELDS) {
 		hid_err(report->device, "too many fields in report\n");
@@ -113,9 +112,6 @@ static struct hid_field *hid_register_field(struct hid_report *report, unsigned
 	field->value = (s32 *)(field->usage + usages);
 	field->report = report;
 
-	for (i = 0; i < usages; i++)
-		field->usage[i].usage_index = i;
-
 	return field;
 }
 
@@ -226,9 +222,9 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 {
 	struct hid_report *report;
 	struct hid_field *field;
-	int usages;
+	unsigned usages;
 	unsigned offset;
-	int i;
+	unsigned i;
 
 	report = hid_register_report(parser->device, report_type, parser->global.report_id);
 	if (!report) {
@@ -255,7 +251,8 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 	if (!parser->local.usage_index) /* Ignore padding fields */
 		return 0;
 
-	usages = max_t(int, parser->local.usage_index, parser->global.report_count);
+	usages = max_t(unsigned, parser->local.usage_index,
+				 parser->global.report_count);
 
 	field = hid_register_field(report, usages, parser->global.report_count);
 	if (!field)
@@ -266,13 +263,14 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 	field->application = hid_lookup_collection(parser, HID_COLLECTION_APPLICATION);
 
 	for (i = 0; i < usages; i++) {
-		int j = i;
+		unsigned j = i;
 		/* Duplicate the last usage we parsed if we have excess values */
 		if (i >= parser->local.usage_index)
 			j = parser->local.usage_index - 1;
 		field->usage[i].hid = parser->local.usage[j];
 		field->usage[i].collection_index =
 			parser->local.collection_index[j];
+		field->usage[i].usage_index = i;
 	}
 
 	field->maxusage = usages;
@@ -759,6 +757,74 @@ int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size)
 }
 EXPORT_SYMBOL_GPL(hid_parse_report);
 
+static const char * const hid_report_names[] = {
+	"HID_INPUT_REPORT",
+	"HID_OUTPUT_REPORT",
+	"HID_FEATURE_REPORT",
+};
+/**
+ * hid_validate_values - validate existing device report's value indexes
+ *
+ * @device: hid device
+ * @type: which report type to examine
+ * @id: which report ID to examine (0 for first)
+ * @field_index: which report field to examine
+ * @report_counts: expected number of values
+ *
+ * Validate the number of values in a given field of a given report, after
+ * parsing.
+ */
+struct hid_report *hid_validate_values(struct hid_device *hid,
+				       unsigned int type, unsigned int id,
+				       unsigned int field_index,
+				       unsigned int report_counts)
+{
+	struct hid_report *report;
+
+	if (type > HID_FEATURE_REPORT) {
+		hid_err(hid, "invalid HID report type %u\n", type);
+		return NULL;
+	}
+
+	if (id >= HID_MAX_IDS) {
+		hid_err(hid, "invalid HID report id %u\n", id);
+		return NULL;
+	}
+
+	/*
+	 * Explicitly not using hid_get_report() here since it depends on
+	 * ->numbered being checked, which may not always be the case when
+	 * drivers go to access report values.
+	 */
+	if (id == 0) {
+		/*
+		 * Validating on id 0 means we should examine the first
+		 * report in the list.
+		 */
+		report = list_entry(
+				hid->report_enum[type].report_list.next,
+				struct hid_report, list);
+	} else {
+		report = hid->report_enum[type].report_id_hash[id];
+	}
+	if (!report) {
+		hid_err(hid, "missing %s %u\n", hid_report_names[type], id);
+		return NULL;
+	}
+	if (report->maxfield <= field_index) {
+		hid_err(hid, "not enough fields in %s %u\n",
+			hid_report_names[type], id);
+		return NULL;
+	}
+	if (report->field[field_index]->report_count < report_counts) {
+		hid_err(hid, "not enough values in %s %u field %u\n",
+			hid_report_names[type], id, field_index);
+		return NULL;
+	}
+	return report;
+}
+EXPORT_SYMBOL_GPL(hid_validate_values);
+
 /**
  * hid_open_report - open a driver-specific device report
  *
@@ -1132,7 +1198,8 @@ static void hid_output_field(const struct hid_device *hid,
 }
 
 /*
- * Create a report.
+ * Create a report. 'data' has to be allocated using
+ * hid_alloc_report_buf() so that it has proper size.
  */
 
 void hid_output_report(struct hid_report *report, __u8 *data)
@@ -1149,6 +1216,22 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 EXPORT_SYMBOL_GPL(hid_output_report);
 
 /*
+ * Allocator for buffer that is going to be passed to hid_output_report()
+ */
+u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
+{
+	/*
+	 * 7 extra bytes are necessary to achieve proper functionality
+	 * of implement() working on 8 byte chunks
+	 */
+
+	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+
+	return kmalloc(len, flags);
+}
+EXPORT_SYMBOL_GPL(hid_alloc_report_buf);
+
+/*
  * Set a field value. The report this field belongs to has to be
  * created and transferred to the device, to set this value in the
  * device.
@@ -1237,7 +1320,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
 			goto out;
 	}
 
-	if (hid->claimed != HID_CLAIMED_HIDRAW) {
+	if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) {
 		for (a = 0; a < report->maxfield; a++)
 			hid_input_field(hid, report->field[a], cdata, interrupt);
 		hdrv = hid->driver;
@@ -1489,6 +1572,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_RP_649) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0x0802) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0xf705) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MIGHTYMOUSE) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICMOUSE) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICTRACKPAD) },
@@ -1603,6 +1687,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
@@ -1630,6 +1715,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_FLIGHT_SYSTEM_G940) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFP_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFGT_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G25_WHEEL) },
@@ -1677,11 +1763,14 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_KEYBOARD) },
 #if IS_ENABLED(CONFIG_HID_ROCCAT)
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ARVO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKUFX) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPLUS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEXTD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KOVAPLUS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_LUA) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_PYRA_WIRED) },
@@ -1691,6 +1780,8 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_PS1000) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS9200_TOUCH) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS817_TOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SKYCABLE, USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
@@ -2243,15 +2334,6 @@ bool hid_ignore(struct hid_device *hdev)
 				hdev->type == HID_TYPE_USBNONE)
 			return true;
 		break;
-	case USB_VENDOR_ID_DWAV:
-		/* These are handled by usbtouchscreen. hdev->type is probably
-		 * HID_TYPE_USBNONE, but we say !HID_TYPE_USBMOUSE to match
-		 * usbtouchscreen. */
-		if ((hdev->product == USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER ||
-		     hdev->product == USB_DEVICE_ID_DWAV_TOUCHCONTROLLER) &&
-		    hdev->type != HID_TYPE_USBMOUSE)
-			return true;
-		break;
 	case USB_VENDOR_ID_VELLEMAN:
 		/* These are not HID devices.  They are handled by comedi. */
 		if ((hdev->product >= USB_DEVICE_ID_VELLEMAN_K8055_FIRST &&
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index ca0219f98c65..45c593dbf5cd 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -330,6 +330,11 @@
 #define USB_VENDOR_ID_GENERAL_TOUCH	0x0dfc
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0003
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PWT_TENFINGERS 0x0100
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0101 0x0101
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0102 0x0102
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0106 0x0106
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
 #define USB_VENDOR_ID_GLAB		0x06c2
 #define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
@@ -473,6 +478,7 @@
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 #define USB_DEVICE_ID_KYE_EASYPEN_I405X	0x5010
 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X	0x5011
+#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2	0x501a
 #define USB_DEVICE_ID_KYE_EASYPEN_M610X	0x5013
 
 #define USB_VENDOR_ID_LABTEC		0x1020
@@ -557,6 +563,7 @@
 #define USB_DEVICE_ID_DINOVO_EDGE	0xc714
 #define USB_DEVICE_ID_DINOVO_MINI	0xc71f
 #define USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2	0xca03
+#define USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL	0xca04
 
 #define USB_VENDOR_ID_LUMIO		0x202e
 #define USB_DEVICE_ID_CRYSTALTOUCH	0x0006
@@ -705,6 +712,7 @@
 #define USB_DEVICE_ID_ROCCAT_KONE	0x2ced
 #define USB_DEVICE_ID_ROCCAT_KONEPLUS	0x2d51
 #define USB_DEVICE_ID_ROCCAT_KONEPURE	0x2dbe
+#define USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL	0x2db4
 #define USB_DEVICE_ID_ROCCAT_KONEXTD	0x2e22
 #define USB_DEVICE_ID_ROCCAT_KOVAPLUS	0x2d50
 #define USB_DEVICE_ID_ROCCAT_LUA	0x2c2e
@@ -729,6 +737,10 @@
 #define USB_VENDOR_ID_SIGMATEL		0x066F
 #define USB_DEVICE_ID_SIGMATEL_STMP3780	0x3780
 
+#define USB_VENDOR_ID_SIS2_TOUCH	0x0457
+#define USB_DEVICE_ID_SIS9200_TOUCH	0x9200
+#define USB_DEVICE_ID_SIS817_TOUCH	0x0817
+
 #define USB_VENDOR_ID_SKYCABLE			0x1223
 #define	USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER	0x3F07
 
@@ -775,6 +787,8 @@
 #define USB_DEVICE_ID_SYNAPTICS_COMP_TP	0x0009
 #define USB_DEVICE_ID_SYNAPTICS_WTP	0x0010
 #define USB_DEVICE_ID_SYNAPTICS_DPAD	0x0013
+#define USB_DEVICE_ID_SYNAPTICS_LTS1	0x0af8
+#define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 
 #define USB_VENDOR_ID_THINGM		0x27b8
 #define USB_DEVICE_ID_BLINK1		0x01ed
@@ -868,6 +882,9 @@
 #define USB_DEVICE_ID_SUPER_DUAL_BOX_PRO 0x8802
 #define USB_DEVICE_ID_SUPER_JOY_BOX_5_PRO 0x8804
 
+#define USB_VENDOR_ID_WISTRON		0x0fb8
+#define USB_DEVICE_ID_WISTRON_OPTICAL_TOUCH		0x1109
+
 #define USB_VENDOR_ID_X_TENSIONS               0x1ae7
 #define USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE    0x9001
 
@@ -899,4 +916,7 @@
 #define USB_VENDOR_ID_PRIMAX	0x0461
 #define USB_DEVICE_ID_PRIMAX_KEYBOARD	0x4e05
 
+#define USB_VENDOR_ID_SIS	0x0457
+#define USB_DEVICE_ID_SIS_TS	0x1013
+
 #endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index ac5e93528dfa..03a6acffed5d 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -317,6 +317,9 @@ static const struct hid_device_id hid_battery_quirks[] = {
 			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{}
@@ -485,6 +488,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 	if (field->flags & HID_MAIN_ITEM_CONSTANT)
 		goto ignore;
 
+	/* Ignore if report count is out of bounds. */
+	if (field->report_count < 1)
+		goto ignore;
+
 	/* only LED usages are supported in output fields */
 	if (field->report_type == HID_OUTPUT_REPORT &&
 			(usage->hid & HID_USAGE_PAGE) != HID_UP_LED) {
@@ -1163,7 +1170,11 @@ static void report_features(struct hid_device *hid)
 
 	rep_enum = &hid->report_enum[HID_FEATURE_REPORT];
 	list_for_each_entry(rep, &rep_enum->report_list, list)
-		for (i = 0; i < rep->maxfield; i++)
+		for (i = 0; i < rep->maxfield; i++) {
+			/* Ignore if report count is out of bounds. */
+			if (rep->field[i]->report_count < 1)
+				continue;
+
 			for (j = 0; j < rep->field[i]->maxusage; j++) {
 				/* Verify if Battery Strength feature is available */
 				hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i]);
@@ -1172,6 +1183,7 @@ static void report_features(struct hid_device *hid)
 					drv->feature_mapping(hid, rep->field[i],
 							     rep->field[i]->usage + j);
 			}
+		}
 }
 
 static struct hid_input *hidinput_allocate(struct hid_device *hid)
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index 6af90dbdc3d4..973eed788cc6 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -280,7 +280,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 *   - change the button usage range to 4-7 for the extra
 		 *     buttons
 		 */
-		if (*rsize >= 74 &&
+		if (*rsize >= 75 &&
 			rdesc[61] == 0x05 && rdesc[62] == 0x08 &&
 			rdesc[63] == 0x19 && rdesc[64] == 0x08 &&
 			rdesc[65] == 0x29 && rdesc[66] == 0x0f &&
@@ -303,6 +303,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 		if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) {
 			rdesc = mousepen_i608x_rdesc_fixed;
 			*rsize = sizeof(mousepen_i608x_rdesc_fixed);
@@ -383,6 +384,7 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	switch (id->product) {
 	case USB_DEVICE_ID_KYE_EASYPEN_I405X:
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 	case USB_DEVICE_ID_KYE_EASYPEN_M610X:
 		ret = kye_tablet_enable(hdev);
 		if (ret) {
@@ -406,6 +408,8 @@ static const struct hid_device_id kye_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ }
 };
diff --git a/drivers/hid/hid-lenovo-tpkbd.c b/drivers/hid/hid-lenovo-tpkbd.c
index 07837f5a4eb8..31cf29a6ba17 100644
--- a/drivers/hid/hid-lenovo-tpkbd.c
+++ b/drivers/hid/hid-lenovo-tpkbd.c
@@ -339,7 +339,15 @@ static int tpkbd_probe_tp(struct hid_device *hdev)
 	struct tpkbd_data_pointer *data_pointer;
 	size_t name_sz = strlen(dev_name(dev)) + 16;
 	char *name_mute, *name_micmute;
-	int ret;
+	int i, ret;
+
+	/* Validate required reports. */
+	for (i = 0; i < 4; i++) {
+		if (!hid_validate_values(hdev, HID_FEATURE_REPORT, 4, i, 1))
+			return -ENODEV;
+	}
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 3, 0, 2))
+		return -ENODEV;
 
 	if (sysfs_create_group(&hdev->dev.kobj,
 				&tpkbd_attr_group_pointer)) {
@@ -406,22 +414,27 @@ static int tpkbd_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "hid_parse failed\n");
-		goto err_free;
+		goto err;
 	}
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hid_hw_start failed\n");
-		goto err_free;
+		goto err;
 	}
 
 	uhdev = (struct usbhid_device *) hdev->driver_data;
 
-	if (uhdev->ifnum == 1)
-		return tpkbd_probe_tp(hdev);
+	if (uhdev->ifnum == 1) {
+		ret = tpkbd_probe_tp(hdev);
+		if (ret)
+			goto err_hid;
+	}
 
 	return 0;
-err_free:
+err_hid:
+	hid_hw_stop(hdev);
+err:
 	return ret;
 }
 
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 6f12ecd36c88..12fc48c968e6 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -45,7 +45,9 @@
 /* Size of the original descriptors of the Driving Force (and Pro) wheels */
 #define DF_RDESC_ORIG_SIZE	130
 #define DFP_RDESC_ORIG_SIZE	97
+#define FV_RDESC_ORIG_SIZE	130
 #define MOMO_RDESC_ORIG_SIZE	87
+#define MOMO2_RDESC_ORIG_SIZE	87
 
 /* Fixed report descriptors for Logitech Driving Force (and Pro)
  * wheel controllers
@@ -170,6 +172,73 @@ static __u8 dfp_rdesc_fixed[] = {
 0xC0                /*  End Collection                          */
 };
 
+static __u8 fv_rdesc_fixed[] = {
+0x05, 0x01,         /*  Usage Page (Desktop),                   */
+0x09, 0x04,         /*  Usage (Joystik),                        */
+0xA1, 0x01,         /*  Collection (Application),               */
+0xA1, 0x02,         /*      Collection (Logical),               */
+0x95, 0x01,         /*          Report Count (1),               */
+0x75, 0x0A,         /*          Report Size (10),               */
+0x15, 0x00,         /*          Logical Minimum (0),            */
+0x26, 0xFF, 0x03,   /*          Logical Maximum (1023),         */
+0x35, 0x00,         /*          Physical Minimum (0),           */
+0x46, 0xFF, 0x03,   /*          Physical Maximum (1023),        */
+0x09, 0x30,         /*          Usage (X),                      */
+0x81, 0x02,         /*          Input (Variable),               */
+0x95, 0x0C,         /*          Report Count (12),              */
+0x75, 0x01,         /*          Report Size (1),                */
+0x25, 0x01,         /*          Logical Maximum (1),            */
+0x45, 0x01,         /*          Physical Maximum (1),           */
+0x05, 0x09,         /*          Usage Page (Button),            */
+0x19, 0x01,         /*          Usage Minimum (01h),            */
+0x29, 0x0C,         /*          Usage Maximum (0Ch),            */
+0x81, 0x02,         /*          Input (Variable),               */
+0x95, 0x02,         /*          Report Count (2),               */
+0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),             */
+0x09, 0x01,         /*          Usage (01h),                    */
+0x81, 0x02,         /*          Input (Variable),               */
+0x09, 0x02,         /*          Usage (02h),                    */
+0x26, 0xFF, 0x00,   /*          Logical Maximum (255),          */
+0x46, 0xFF, 0x00,   /*          Physical Maximum (255),         */
+0x95, 0x01,         /*          Report Count (1),               */
+0x75, 0x08,         /*          Report Size (8),                */
+0x81, 0x02,         /*          Input (Variable),               */
+0x05, 0x01,         /*          Usage Page (Desktop),           */
+0x25, 0x07,         /*          Logical Maximum (7),            */
+0x46, 0x3B, 0x01,   /*          Physical Maximum (315),         */
+0x75, 0x04,         /*          Report Size (4),                */
+0x65, 0x14,         /*          Unit (Degrees),                 */
+0x09, 0x39,         /*          Usage (Hat Switch),             */
+0x81, 0x42,         /*          Input (Variable, Null State),   */
+0x75, 0x01,         /*          Report Size (1),                */
+0x95, 0x04,         /*          Report Count (4),               */
+0x65, 0x00,         /*          Unit,                           */
+0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),             */
+0x09, 0x01,         /*          Usage (01h),                    */
+0x25, 0x01,         /*          Logical Maximum (1),            */
+0x45, 0x01,         /*          Physical Maximum (1),           */
+0x81, 0x02,         /*          Input (Variable),               */
+0x05, 0x01,         /*          Usage Page (Desktop),           */
+0x95, 0x01,         /*          Report Count (1),               */
+0x75, 0x08,         /*          Report Size (8),                */
+0x26, 0xFF, 0x00,   /*          Logical Maximum (255),          */
+0x46, 0xFF, 0x00,   /*          Physical Maximum (255),         */
+0x09, 0x31,         /*          Usage (Y),                      */
+0x81, 0x02,         /*          Input (Variable),               */
+0x09, 0x32,         /*          Usage (Z),                      */
+0x81, 0x02,         /*          Input (Variable),               */
+0xC0,               /*      End Collection,                     */
+0xA1, 0x02,         /*      Collection (Logical),               */
+0x26, 0xFF, 0x00,   /*          Logical Maximum (255),          */
+0x46, 0xFF, 0x00,   /*          Physical Maximum (255),         */
+0x95, 0x07,         /*          Report Count (7),               */
+0x75, 0x08,         /*          Report Size (8),                */
+0x09, 0x03,         /*          Usage (03h),                    */
+0x91, 0x02,         /*          Output (Variable),              */
+0xC0,               /*      End Collection,                     */
+0xC0                /*  End Collection                          */
+};
+
 static __u8 momo_rdesc_fixed[] = {
 0x05, 0x01,         /*  Usage Page (Desktop),               */
 0x09, 0x04,         /*  Usage (Joystik),                    */
@@ -216,6 +285,54 @@ static __u8 momo_rdesc_fixed[] = {
 0xC0                /*  End Collection                      */
 };
 
+static __u8 momo2_rdesc_fixed[] = {
+0x05, 0x01,         /*  Usage Page (Desktop),               */
+0x09, 0x04,         /*  Usage (Joystik),                    */
+0xA1, 0x01,         /*  Collection (Application),           */
+0xA1, 0x02,         /*      Collection (Logical),           */
+0x95, 0x01,         /*          Report Count (1),           */
+0x75, 0x0A,         /*          Report Size (10),           */
+0x15, 0x00,         /*          Logical Minimum (0),        */
+0x26, 0xFF, 0x03,   /*          Logical Maximum (1023),     */
+0x35, 0x00,         /*          Physical Minimum (0),       */
+0x46, 0xFF, 0x03,   /*          Physical Maximum (1023),    */
+0x09, 0x30,         /*          Usage (X),                  */
+0x81, 0x02,         /*          Input (Variable),           */
+0x95, 0x0A,         /*          Report Count (10),          */
+0x75, 0x01,         /*          Report Size (1),            */
+0x25, 0x01,         /*          Logical Maximum (1),        */
+0x45, 0x01,         /*          Physical Maximum (1),       */
+0x05, 0x09,         /*          Usage Page (Button),        */
+0x19, 0x01,         /*          Usage Minimum (01h),        */
+0x29, 0x0A,         /*          Usage Maximum (0Ah),        */
+0x81, 0x02,         /*          Input (Variable),           */
+0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+0x09, 0x00,         /*          Usage (00h),                */
+0x95, 0x04,         /*          Report Count (4),           */
+0x81, 0x02,         /*          Input (Variable),           */
+0x95, 0x01,         /*          Report Count (1),           */
+0x75, 0x08,         /*          Report Size (8),            */
+0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+0x46, 0xFF, 0x00,   /*          Physical Maximum (255),     */
+0x09, 0x01,         /*          Usage (01h),                */
+0x81, 0x02,         /*          Input (Variable),           */
+0x05, 0x01,         /*          Usage Page (Desktop),       */
+0x09, 0x31,         /*          Usage (Y),                  */
+0x81, 0x02,         /*          Input (Variable),           */
+0x09, 0x32,         /*          Usage (Z),                  */
+0x81, 0x02,         /*          Input (Variable),           */
+0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+0x09, 0x00,         /*          Usage (00h),                */
+0x81, 0x02,         /*          Input (Variable),           */
+0xC0,               /*      End Collection,                 */
+0xA1, 0x02,         /*      Collection (Logical),           */
+0x09, 0x02,         /*          Usage (02h),                */
+0x95, 0x07,         /*          Report Count (7),           */
+0x91, 0x02,         /*          Output (Variable),          */
+0xC0,               /*      End Collection,                 */
+0xC0                /*  End Collection                      */
+};
+
 /*
  * Certain Logitech keyboards send in report #3 keys which are far
  * above the logical maximum described in descriptor. This extends
@@ -228,14 +345,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	struct usb_device_descriptor *udesc;
 	__u16 bcdDevice, rev_maj, rev_min;
 
-	if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 &&
+	if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 &&
 			rdesc[84] == 0x8c && rdesc[85] == 0x02) {
 		hid_info(hdev,
 			 "fixing up Logitech keyboard report descriptor\n");
 		rdesc[84] = rdesc[89] = 0x4d;
 		rdesc[85] = rdesc[90] = 0x10;
 	}
-	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 &&
+	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 &&
 			rdesc[32] == 0x81 && rdesc[33] == 0x06 &&
 			rdesc[49] == 0x81 && rdesc[50] == 0x06) {
 		hid_info(hdev,
@@ -275,6 +392,24 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 
+	case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
+		if (*rsize == MOMO2_RDESC_ORIG_SIZE) {
+			hid_info(hdev,
+				"fixing up Logitech Momo Racing Force (Black) report descriptor\n");
+			rdesc = momo2_rdesc_fixed;
+			*rsize = sizeof(momo2_rdesc_fixed);
+		}
+		break;
+
+	case USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL:
+		if (*rsize == FV_RDESC_ORIG_SIZE) {
+			hid_info(hdev,
+				"fixing up Logitech Formula Vibration report descriptor\n");
+			rdesc = fv_rdesc_fixed;
+			*rsize = sizeof(fv_rdesc_fixed);
+		}
+		break;
+
 	case USB_DEVICE_ID_LOGITECH_DFP_WHEEL:
 		if (*rsize == DFP_RDESC_ORIG_SIZE) {
 			hid_info(hdev,
@@ -492,6 +627,7 @@ static int lg_input_mapped(struct hid_device *hdev, struct hid_input *hi,
 		case USB_DEVICE_ID_LOGITECH_G27_WHEEL:
 		case USB_DEVICE_ID_LOGITECH_WII_WHEEL:
 		case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
+		case USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL:
 			field->application = HID_GD_MULTIAXIS;
 			break;
 		default:
@@ -639,6 +775,8 @@ static const struct hid_device_id lg_devices[] = {
 		.driver_data = LG_NOGET | LG_FF4 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2),
 		.driver_data = LG_FF4 },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL),
+		.driver_data = LG_FF2 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G25_WHEEL),
 		.driver_data = LG_FF4 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFGT_WHEEL),
diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c
index b3cd1507dda2..0e3fb1a7e421 100644
--- a/drivers/hid/hid-lg2ff.c
+++ b/drivers/hid/hid-lg2ff.c
@@ -64,26 +64,13 @@ int lg2ff_init(struct hid_device *hid)
 	struct hid_report *report;
 	struct hid_input *hidinput = list_entry(hid->inputs.next,
 						struct hid_input, list);
-	struct list_head *report_list =
-			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
 	int error;
 
-	if (list_empty(report_list)) {
-		hid_err(hid, "no output report found\n");
+	/* Check that the report looks ok */
+	report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7);
+	if (!report)
 		return -ENODEV;
-	}
-
-	report = list_entry(report_list->next, struct hid_report, list);
-
-	if (report->maxfield < 1) {
-		hid_err(hid, "output report is empty\n");
-		return -ENODEV;
-	}
-	if (report->field[0]->report_count < 7) {
-		hid_err(hid, "not enough values in the field\n");
-		return -ENODEV;
-	}
 
 	lg2ff = kmalloc(sizeof(struct lg2ff_device), GFP_KERNEL);
 	if (!lg2ff)
@@ -108,7 +95,7 @@ int lg2ff_init(struct hid_device *hid)
 
 	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
 
-	hid_info(hid, "Force feedback for Logitech RumblePad/Rumblepad 2 by Anssi Hannula <anssi.hannula@gmail.com>\n");
+	hid_info(hid, "Force feedback for Logitech variant 2 rumble devices by Anssi Hannula <anssi.hannula@gmail.com>\n");
 
 	return 0;
 }
diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c
index e52f181f6aa1..8c2da183d3bc 100644
--- a/drivers/hid/hid-lg3ff.c
+++ b/drivers/hid/hid-lg3ff.c
@@ -66,10 +66,11 @@ static int hid_lg3ff_play(struct input_dev *dev, void *data,
 	int x, y;
 
 /*
- * Maxusage should always be 63 (maximum fields)
- * likely a better way to ensure this data is clean
+ * Available values in the field should always be 63, but we only use up to
+ * 35. Instead, clear the entire area, however big it is.
  */
-	memset(report->field[0]->value, 0, sizeof(__s32)*report->field[0]->maxusage);
+	memset(report->field[0]->value, 0,
+	       sizeof(__s32) * report->field[0]->report_count);
 
 	switch (effect->type) {
 	case FF_CONSTANT:
@@ -129,32 +130,14 @@ static const signed short ff3_joystick_ac[] = {
 int lg3ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	const signed short *ff_bits = ff3_joystick_ac;
 	int error;
 	int i;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	if (!report) {
-		hid_err(hid, "NULL output report\n");
-		return -1;
-	}
-
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
-		return -1;
-	}
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35))
+		return -ENODEV;
 
 	/* Assume single fixed device G940 */
 	for (i = 0; ff_bits[i] >= 0; i++)
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 0ddae2a00d59..351805362290 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -218,12 +218,46 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
 	__s32 *value = report->field[0]->value;
+	__u32 expand_a, expand_b;
+
+	/* De-activate Auto-Center */
+	if (magnitude == 0) {
+		value[0] = 0xf5;
+		value[1] = 0x00;
+		value[2] = 0x00;
+		value[3] = 0x00;
+		value[4] = 0x00;
+		value[5] = 0x00;
+		value[6] = 0x00;
+
+		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		return;
+	}
+
+	if (magnitude <= 0xaaaa) {
+		expand_a = 0x0c * magnitude;
+		expand_b = 0x80 * magnitude;
+	} else {
+		expand_a = (0x0c * 0xaaaa) + 0x06 * (magnitude - 0xaaaa);
+		expand_b = (0x80 * 0xaaaa) + 0xff * (magnitude - 0xaaaa);
+	}
 
 	value[0] = 0xfe;
 	value[1] = 0x0d;
-	value[2] = magnitude >> 13;
-	value[3] = magnitude >> 13;
-	value[4] = magnitude >> 8;
+	value[2] = expand_a / 0xaaaa;
+	value[3] = expand_a / 0xaaaa;
+	value[4] = expand_b / 0xaaaa;
+	value[5] = 0x00;
+	value[6] = 0x00;
+
+	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+
+	/* Activate Auto-Center */
+	value[0] = 0x14;
+	value[1] = 0x00;
+	value[2] = 0x00;
+	value[3] = 0x00;
+	value[4] = 0x00;
 	value[5] = 0x00;
 	value[6] = 0x00;
 
@@ -484,34 +518,16 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 int lg4ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
 	struct usb_device_descriptor *udesc;
 	int error, i, j;
 	__u16 bcdDevice, rev_maj, rev_min;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	if (!report) {
-		hid_err(hid, "NULL output report\n");
-		return -1;
-	}
-
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
-	}
 
 	/* Check what wheel has been connected */
 	for (i = 0; i < ARRAY_SIZE(lg4ff_devices); i++) {
@@ -558,17 +574,6 @@ int lg4ff_init(struct hid_device *hid)
 	if (error)
 		return error;
 
-	/* Check if autocentering is available and
-	 * set the centering force to zero by default */
-	if (test_bit(FF_AUTOCENTER, dev->ffbit)) {
-		if (rev_maj == FFEX_REV_MAJ && rev_min == FFEX_REV_MIN)	/* Formula Force EX expects different autocentering command */
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
-		else
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
-
-		dev->ff->set_autocenter(dev, 0);
-	}
-
 	/* Get private driver data */
 	drv_data = hid_get_drvdata(hid);
 	if (!drv_data) {
@@ -589,6 +594,17 @@ int lg4ff_init(struct hid_device *hid)
 	entry->max_range = lg4ff_devices[i].max_range;
 	entry->set_range = lg4ff_devices[i].set_range;
 
+	/* Check if autocentering is available and
+	 * set the centering force to zero by default */
+	if (test_bit(FF_AUTOCENTER, dev->ffbit)) {
+		if (rev_maj == FFEX_REV_MAJ && rev_min == FFEX_REV_MIN)	/* Formula Force EX expects different autocentering command */
+			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
+		else
+			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
+
+		dev->ff->set_autocenter(dev, 0);
+	}
+
 	/* Create sysfs interface */
 	error = device_create_file(&hid->dev, &dev_attr_range);
 	if (error)
diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c
index d7ea8c845b40..e1394af0ae7b 100644
--- a/drivers/hid/hid-lgff.c
+++ b/drivers/hid/hid-lgff.c
@@ -128,27 +128,14 @@ static void hid_lgff_set_autocenter(struct input_dev *dev, u16 magnitude)
 int lgff_init(struct hid_device* hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	const signed short *ff_bits = ff_joystick;
 	int error;
 	int i;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
-		return -1;
-	}
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
+		return -ENODEV;
 
 	for (i = 0; i < ARRAY_SIZE(devices); i++) {
 		if (dev->id.vendor == devices[i].idVendor &&
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 5207591a598c..d4c6d9f85ca5 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -192,6 +192,7 @@ static struct hid_ll_driver logi_dj_ll_driver;
 static int logi_dj_output_hidraw_report(struct hid_device *hid, u8 * buf,
 					size_t count,
 					unsigned char report_type);
+static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev);
 
 static void logi_dj_recv_destroy_djhid_device(struct dj_receiver_dev *djrcv_dev,
 						struct dj_report *dj_report)
@@ -232,13 +233,13 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 	if (dj_report->report_params[DEVICE_PAIRED_PARAM_SPFUNCTION] &
 	    SPFUNCTION_DEVICE_LIST_EMPTY) {
 		dbg_hid("%s: device list is empty\n", __func__);
+		djrcv_dev->querying_devices = false;
 		return;
 	}
 
-	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
-	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
-		dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n",
-			__func__, dj_report->device_index);
+	if (djrcv_dev->paired_dj_devices[dj_report->device_index]) {
+		/* The device is already known. No need to reallocate it. */
+		dbg_hid("%s: device is already known\n", __func__);
 		return;
 	}
 
@@ -305,6 +306,7 @@ static void delayedwork_callback(struct work_struct *work)
 	struct dj_report dj_report;
 	unsigned long flags;
 	int count;
+	int retval;
 
 	dbg_hid("%s\n", __func__);
 
@@ -337,6 +339,25 @@ static void delayedwork_callback(struct work_struct *work)
 		logi_dj_recv_destroy_djhid_device(djrcv_dev, &dj_report);
 		break;
 	default:
+	/* A normal report (i. e. not belonging to a pair/unpair notification)
+	 * arriving here, means that the report arrived but we did not have a
+	 * paired dj_device associated to the report's device_index, this
+	 * means that the original "device paired" notification corresponding
+	 * to this dj_device never arrived to this driver. The reason is that
+	 * hid-core discards all packets coming from a device while probe() is
+	 * executing. */
+	if (!djrcv_dev->paired_dj_devices[dj_report.device_index]) {
+		/* ok, we don't know the device, just re-ask the
+		 * receiver for the list of connected devices. */
+		retval = logi_dj_recv_query_paired_devices(djrcv_dev);
+		if (!retval) {
+			/* everything went fine, so just leave */
+			break;
+		}
+		dev_err(&djrcv_dev->hdev->dev,
+			"%s:logi_dj_recv_query_paired_devices "
+			"error:%d\n", __func__, retval);
+		}
 		dbg_hid("%s: unexpected report type\n", __func__);
 	}
 }
@@ -367,6 +388,12 @@ static void logi_dj_recv_forward_null_report(struct dj_receiver_dev *djrcv_dev,
 	if (!djdev) {
 		dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
 			" is NULL, index %d\n", dj_report->device_index);
+		kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+		if (schedule_work(&djrcv_dev->work) == 0) {
+			dbg_hid("%s: did not schedule the work item, was already "
+			"queued\n", __func__);
+		}
 		return;
 	}
 
@@ -397,6 +424,12 @@ static void logi_dj_recv_forward_report(struct dj_receiver_dev *djrcv_dev,
 	if (dj_device == NULL) {
 		dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
 			" is NULL, index %d\n", dj_report->device_index);
+		kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+		if (schedule_work(&djrcv_dev->work) == 0) {
+			dbg_hid("%s: did not schedule the work item, was already "
+			"queued\n", __func__);
+		}
 		return;
 	}
 
@@ -421,7 +454,7 @@ static int logi_dj_recv_send_report(struct dj_receiver_dev *djrcv_dev,
 	struct hid_report *report;
 	struct hid_report_enum *output_report_enum;
 	u8 *data = (u8 *)(&dj_report->device_index);
-	int i;
+	unsigned int i;
 
 	output_report_enum = &hdev->report_enum[HID_OUTPUT_REPORT];
 	report = output_report_enum->report_id_hash[REPORT_ID_DJ_SHORT];
@@ -431,7 +464,7 @@ static int logi_dj_recv_send_report(struct dj_receiver_dev *djrcv_dev,
 		return -ENODEV;
 	}
 
-	for (i = 0; i < report->field[0]->report_count; i++)
+	for (i = 0; i < DJREPORT_SHORT_LENGTH - 1; i++)
 		report->field[0]->value[i] = data[i];
 
 	hid_hw_request(hdev, report, HID_REQ_SET_REPORT);
@@ -444,6 +477,10 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
 	struct dj_report *dj_report;
 	int retval;
 
+	/* no need to protect djrcv_dev->querying_devices */
+	if (djrcv_dev->querying_devices)
+		return 0;
+
 	dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL);
 	if (!dj_report)
 		return -ENOMEM;
@@ -455,6 +492,7 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
 	return retval;
 }
 
+
 static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev,
 					  unsigned timeout)
 {
@@ -574,7 +612,7 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 
 	struct hid_field *field;
 	struct hid_report *report;
-	unsigned char data[8];
+	unsigned char *data;
 	int offset;
 
 	dbg_hid("%s: %s, type:%d | code:%d | value:%d\n",
@@ -590,6 +628,13 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 		return -1;
 	}
 	hid_set_field(field, offset, value);
+
+	data = hid_alloc_report_buf(field->report, GFP_KERNEL);
+	if (!data) {
+		dev_warn(&dev->dev, "failed to allocate report buf memory\n");
+		return -1;
+	}
+
 	hid_output_report(field->report, &data[0]);
 
 	output_report_enum = &dj_rcv_hiddev->report_enum[HID_OUTPUT_REPORT];
@@ -600,8 +645,9 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 
 	hid_hw_request(dj_rcv_hiddev, report, HID_REQ_SET_REPORT);
 
-	return 0;
+	kfree(data);
 
+	return 0;
 }
 
 static int logi_dj_ll_start(struct hid_device *hid)
@@ -633,7 +679,6 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 	struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev);
 	struct dj_report *dj_report = (struct dj_report *) data;
 	unsigned long flags;
-	bool report_processed = false;
 
 	dbg_hid("%s, size:%d\n", __func__, size);
 
@@ -661,27 +706,41 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 	 * anything else with it.
 	 */
 
+	/* case 1) */
+	if (data[0] != REPORT_ID_DJ_SHORT)
+		return false;
+
+	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
+	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
+		/*
+		 * Device index is wrong, bail out.
+		 * This driver can ignore safely the receiver notifications,
+		 * so ignore those reports too.
+		 */
+		if (dj_report->device_index != DJ_RECEIVER_INDEX)
+			dev_err(&hdev->dev, "%s: invalid device index:%d\n",
+				__func__, dj_report->device_index);
+		return false;
+	}
+
 	spin_lock_irqsave(&djrcv_dev->lock, flags);
-	if (dj_report->report_id == REPORT_ID_DJ_SHORT) {
-		switch (dj_report->report_type) {
-		case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
-		case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
-			logi_dj_recv_queue_notification(djrcv_dev, dj_report);
-			break;
-		case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
-			if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
-			    STATUS_LINKLOSS) {
-				logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
-			}
-			break;
-		default:
-			logi_dj_recv_forward_report(djrcv_dev, dj_report);
+	switch (dj_report->report_type) {
+	case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
+	case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
+		logi_dj_recv_queue_notification(djrcv_dev, dj_report);
+		break;
+	case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
+		if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
+		    STATUS_LINKLOSS) {
+			logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
 		}
-		report_processed = true;
+		break;
+	default:
+		logi_dj_recv_forward_report(djrcv_dev, dj_report);
 	}
 	spin_unlock_irqrestore(&djrcv_dev->lock, flags);
 
-	return report_processed;
+	return true;
 }
 
 static int logi_dj_probe(struct hid_device *hdev,
@@ -738,6 +797,12 @@ static int logi_dj_probe(struct hid_device *hdev,
 		goto hid_parse_fail;
 	}
 
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, REPORT_ID_DJ_SHORT,
+				 0, DJREPORT_SHORT_LENGTH - 1)) {
+		retval = -ENODEV;
+		goto hid_parse_fail;
+	}
+
 	/* Starts the usb device and connects to upper interfaces hiddev and
 	 * hidraw */
 	retval = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index fd28a5e0ca3b..daeb0aa4bee9 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -27,6 +27,7 @@
 
 #define DJ_MAX_PAIRED_DEVICES			6
 #define DJ_MAX_NUMBER_NOTIFICATIONS		8
+#define DJ_RECEIVER_INDEX			0
 #define DJ_DEVICE_INDEX_MIN 			1
 #define DJ_DEVICE_INDEX_MAX 			6
 
@@ -101,6 +102,7 @@ struct dj_receiver_dev {
 	struct work_struct work;
 	struct kfifo notif_fifo;
 	spinlock_t lock;
+	bool querying_devices;
 };
 
 struct dj_device {
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 5bc37343eb22..c24f3dfd9367 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -290,6 +290,11 @@ static int magicmouse_raw_event(struct hid_device *hdev,
 		if (size < 4 || ((size - 4) % 9) != 0)
 			return 0;
 		npoints = (size - 4) / 9;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 9 + 4);
@@ -307,6 +312,11 @@ static int magicmouse_raw_event(struct hid_device *hdev,
 		if (size < 6 || ((size - 6) % 8) != 0)
 			return 0;
 		npoints = (size - 6) / 8;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 8 + 6);
diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c
index 9e14c00eb1b6..25daf28b26bd 100644
--- a/drivers/hid/hid-monterey.c
+++ b/drivers/hid/hid-monterey.c
@@ -24,7 +24,7 @@
 static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
+	if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
 		hid_info(hdev, "fixing up button/consumer in HID report descriptor\n");
 		rdesc[30] = 0x0c;
 	}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index d39a5cede0b0..3d8e58ac7499 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -101,9 +101,9 @@ struct mt_device {
 	unsigned last_slot_field;	/* the last field of a slot */
 	unsigned mt_report_id;	/* the report ID of the multitouch device */
 	unsigned pen_report_id;	/* the report ID of the pen device */
-	__s8 inputmode;		/* InputMode HID feature, -1 if non-existent */
-	__s8 inputmode_index;	/* InputMode HID feature index in the report */
-	__s8 maxcontact_report_id;	/* Maximum Contact Number HID feature,
+	__s16 inputmode;	/* InputMode HID feature, -1 if non-existent */
+	__s16 inputmode_index;	/* InputMode HID feature index in the report */
+	__s16 maxcontact_report_id;	/* Maximum Contact Number HID feature,
 				   -1 if non-existent */
 	__u8 num_received;	/* how many contacts we received */
 	__u8 num_expected;	/* expected last contact index */
@@ -244,12 +244,12 @@ static struct mt_class mt_classes[] = {
 	{ .name	= MT_CLS_GENERALTOUCH_TWOFINGERS,
 		.quirks	= MT_QUIRK_NOT_SEEN_MEANS_UP |
 			MT_QUIRK_VALID_IS_INRANGE |
-			MT_QUIRK_SLOT_IS_CONTACTNUMBER,
+			MT_QUIRK_SLOT_IS_CONTACTID,
 		.maxcontacts = 2
 	},
 	{ .name	= MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
 		.quirks	= MT_QUIRK_NOT_SEEN_MEANS_UP |
-			MT_QUIRK_SLOT_IS_CONTACTNUMBER
+			MT_QUIRK_SLOT_IS_CONTACTID
 	},
 
 	{ .name = MT_CLS_FLATFROG,
@@ -317,20 +317,18 @@ static void mt_feature_mapping(struct hid_device *hdev,
 		struct hid_field *field, struct hid_usage *usage)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
-	int i;
 
 	switch (usage->hid) {
 	case HID_DG_INPUTMODE:
-		td->inputmode = field->report->id;
-		td->inputmode_index = 0; /* has to be updated below */
-
-		for (i=0; i < field->maxusage; i++) {
-			if (field->usage[i].hid == usage->hid) {
-				td->inputmode_index = i;
-				break;
-			}
+		/* Ignore if value index is out of bounds. */
+		if (usage->usage_index >= field->report_count) {
+			dev_err(&hdev->dev, "HID_DG_INPUTMODE out of range\n");
+			break;
 		}
 
+		td->inputmode = field->report->id;
+		td->inputmode_index = usage->usage_index;
+
 		break;
 	case HID_DG_CONTACTMAX:
 		td->maxcontact_report_id = field->report->id;
@@ -536,6 +534,10 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			mt_store_field(usage, td, hi);
 			return 1;
 		case HID_DG_CONTACTCOUNT:
+			/* Ignore if indexes are out of bounds. */
+			if (field->index >= field->report->maxfield ||
+			    usage->usage_index >= field->report_count)
+				return 1;
 			td->cc_index = field->index;
 			td->cc_value_index = usage->usage_index;
 			return 1;
@@ -1189,6 +1191,21 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
 		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
 			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PWT_TENFINGERS) },
+	{ .driver_data = MT_CLS_GENERALTOUCH_TWOFINGERS,
+		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0101) },
+	{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0102) },
+	{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0106) },
+	{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A) },
+	{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+			USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100) },
 
 	/* Gametel game controller */
 	{ .driver_data = MT_CLS_NSMU,
@@ -1300,6 +1317,14 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_QUANTA,
 			USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008) },
 
+	/* SiS panels */
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH,
+		USB_DEVICE_ID_SIS9200_TOUCH) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH,
+		USB_DEVICE_ID_SIS817_TOUCH) },
+
 	/* Stantum panels */
 	{ .driver_data = MT_CLS_CONFIDENCE,
 		MT_USB_DEVICE(USB_VENDOR_ID_STANTUM,
@@ -1328,6 +1353,12 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_NSMU,
 		MT_USB_DEVICE(USB_VENDOR_ID_UNITEC,
 			USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) },
+
+	/* Wistron panels */
+	{ .driver_data = MT_CLS_NSMU,
+		MT_USB_DEVICE(USB_VENDOR_ID_WISTRON,
+			USB_DEVICE_ID_WISTRON_OPTICAL_TOUCH) },
+
 	/* XAT */
 	{ .driver_data = MT_CLS_NSMU,
 		MT_USB_DEVICE(USB_VENDOR_ID_XAT,
diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c
index 736b2502df4f..6aca4f2554bf 100644
--- a/drivers/hid/hid-petalynx.c
+++ b/drivers/hid/hid-petalynx.c
@@ -25,7 +25,7 @@
 static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
+	if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
 			rdesc[41] == 0x00 && rdesc[59] == 0x26 &&
 			rdesc[60] == 0xf9 && rdesc[61] == 0x00) {
 		hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n");
diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
index acbb021065ec..020df3c2e8b4 100644
--- a/drivers/hid/hid-picolcd_core.c
+++ b/drivers/hid/hid-picolcd_core.c
@@ -350,6 +350,12 @@ static int picolcd_raw_event(struct hid_device *hdev,
 	if (!data)
 		return 1;
 
+	if (size > 64) {
+		hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n",
+				size);
+		return 0;
+	}
+
 	if (report->id == REPORT_KEY_STATE) {
 		if (data->input_keys)
 			ret = picolcd_raw_keypad(data, report, raw_data+1, size-1);
diff --git a/drivers/hid/hid-picolcd_debugfs.c b/drivers/hid/hid-picolcd_debugfs.c
index 59ab8e157e6b..024cdf3c2297 100644
--- a/drivers/hid/hid-picolcd_debugfs.c
+++ b/drivers/hid/hid-picolcd_debugfs.c
@@ -394,7 +394,7 @@ static void dump_buff_as_hex(char *dst, size_t dst_sz, const u8 *data,
 void picolcd_debug_out_report(struct picolcd_data *data,
 		struct hid_device *hdev, struct hid_report *report)
 {
-	u8 raw_data[70];
+	u8 *raw_data;
 	int raw_size = (report->size >> 3) + 1;
 	char *buff;
 #define BUFF_SZ 256
@@ -407,20 +407,20 @@ void picolcd_debug_out_report(struct picolcd_data *data,
 	if (!buff)
 		return;
 
-	snprintf(buff, BUFF_SZ, "\nout report %d (size %d) =  ",
-			report->id, raw_size);
-	hid_debug_event(hdev, buff);
-	if (raw_size + 5 > sizeof(raw_data)) {
+	raw_data = hid_alloc_report_buf(report, GFP_ATOMIC);
+	if (!raw_data) {
 		kfree(buff);
-		hid_debug_event(hdev, " TOO BIG\n");
 		return;
-	} else {
-		raw_data[0] = report->id;
-		hid_output_report(report, raw_data);
-		dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
-		hid_debug_event(hdev, buff);
 	}
 
+	snprintf(buff, BUFF_SZ, "\nout report %d (size %d) =  ",
+			report->id, raw_size);
+	hid_debug_event(hdev, buff);
+	raw_data[0] = report->id;
+	hid_output_report(report, raw_data);
+	dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
+	hid_debug_event(hdev, buff);
+
 	switch (report->id) {
 	case REPORT_LED_STATE:
 		/* 1 data byte with GPO state */
@@ -644,6 +644,7 @@ void picolcd_debug_out_report(struct picolcd_data *data,
 		break;
 	}
 	wake_up_interruptible(&hdev->debug_wait);
+	kfree(raw_data);
 	kfree(buff);
 }
 
diff --git a/drivers/hid/hid-roccat-common.c b/drivers/hid/hid-roccat-common.c
index 74f704032627..e84089998900 100644
--- a/drivers/hid/hid-roccat-common.c
+++ b/drivers/hid/hid-roccat-common.c
@@ -65,10 +65,11 @@ int roccat_common2_send(struct usb_device *usb_dev, uint report_id,
 EXPORT_SYMBOL_GPL(roccat_common2_send);
 
 enum roccat_common2_control_states {
-	ROCCAT_COMMON_CONTROL_STATUS_OVERLOAD = 0,
+	ROCCAT_COMMON_CONTROL_STATUS_CRITICAL = 0,
 	ROCCAT_COMMON_CONTROL_STATUS_OK = 1,
 	ROCCAT_COMMON_CONTROL_STATUS_INVALID = 2,
-	ROCCAT_COMMON_CONTROL_STATUS_WAIT = 3,
+	ROCCAT_COMMON_CONTROL_STATUS_BUSY = 3,
+	ROCCAT_COMMON_CONTROL_STATUS_CRITICAL_NEW = 4,
 };
 
 static int roccat_common2_receive_control_status(struct usb_device *usb_dev)
@@ -88,13 +89,12 @@ static int roccat_common2_receive_control_status(struct usb_device *usb_dev)
 		switch (control.value) {
 		case ROCCAT_COMMON_CONTROL_STATUS_OK:
 			return 0;
-		case ROCCAT_COMMON_CONTROL_STATUS_WAIT:
+		case ROCCAT_COMMON_CONTROL_STATUS_BUSY:
 			msleep(500);
 			continue;
 		case ROCCAT_COMMON_CONTROL_STATUS_INVALID:
-
-		case ROCCAT_COMMON_CONTROL_STATUS_OVERLOAD:
-			/* seems to be critical - replug necessary */
+		case ROCCAT_COMMON_CONTROL_STATUS_CRITICAL:
+		case ROCCAT_COMMON_CONTROL_STATUS_CRITICAL_NEW:
 			return -EINVAL;
 		default:
 			dev_err(&usb_dev->dev,
diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c
index c79d0b06c143..5850959d48f5 100644
--- a/drivers/hid/hid-roccat-konepure.c
+++ b/drivers/hid/hid-roccat-konepure.c
@@ -262,6 +262,7 @@ static int konepure_raw_event(struct hid_device *hdev,
 
 static const struct hid_device_id konepure_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
 	{ }
 };
 
@@ -300,5 +301,5 @@ module_init(konepure_init);
 module_exit(konepure_exit);
 
 MODULE_AUTHOR("Stefan Achatz");
-MODULE_DESCRIPTION("USB Roccat KonePure driver");
+MODULE_DESCRIPTION("USB Roccat KonePure/Optical driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c
index b8b37789b864..2c571dadf062 100644
--- a/drivers/hid/hid-roccat-kovaplus.c
+++ b/drivers/hid/hid-roccat-kovaplus.c
@@ -577,9 +577,13 @@ static void kovaplus_keep_values_up_to_date(struct kovaplus_device *kovaplus,
 		break;
 	case KOVAPLUS_MOUSE_REPORT_BUTTON_TYPE_CPI:
 		kovaplus->actual_cpi = kovaplus_convert_event_cpi(button_report->data1);
+		break;
 	case KOVAPLUS_MOUSE_REPORT_BUTTON_TYPE_SENSITIVITY:
 		kovaplus->actual_x_sensitivity = button_report->data1;
 		kovaplus->actual_y_sensitivity = button_report->data2;
+		break;
+	default:
+		break;
 	}
 }
 
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index d4f1e3bee590..264ddc4a0118 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -35,6 +35,8 @@ static struct class *pyra_class;
 static void profile_activated(struct pyra_device *pyra,
 		unsigned int new_profile)
 {
+	if (new_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return;
 	pyra->actual_profile = new_profile;
 	pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi;
 }
@@ -236,9 +238,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp,
 	if (off != 0 || count != PYRA_SIZE_SETTINGS)
 		return -EINVAL;
 
-	mutex_lock(&pyra->pyra_lock);
-
 	settings = (struct pyra_settings const *)buf;
+	if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return -EINVAL;
+
+	mutex_lock(&pyra->pyra_lock);
 
 	retval = pyra_set_settings(usb_dev, settings);
 	if (retval) {
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index aa34755ca205..b189feb69789 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -327,7 +327,8 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 				field->logical == attr_usage_id) {
 				sensor_hub_fill_attr_info(info, i, report->id,
 					field->unit, field->unit_exponent,
-					field->report_size);
+					field->report_size *
+							field->report_count);
 				ret = 0;
 			} else {
 				for (j = 0; j < field->maxusage; ++j) {
@@ -339,7 +340,8 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 							i, report->id,
 							field->unit,
 							field->unit_exponent,
-							field->report_size);
+							field->report_size *
+							field->report_count);
 						ret = 0;
 						break;
 					}
@@ -426,9 +428,10 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 		hid_dbg(hdev, "%d collection_index:%x hid:%x sz:%x\n",
 				i, report->field[i]->usage->collection_index,
 				report->field[i]->usage->hid,
-				report->field[i]->report_size/8);
-
-		sz = report->field[i]->report_size/8;
+				(report->field[i]->report_size *
+					report->field[i]->report_count)/8);
+		sz = (report->field[i]->report_size *
+					report->field[i]->report_count)/8;
 		if (pdata->pending.status && pdata->pending.attr_usage_id ==
 				report->field[i]->usage->hid) {
 			hid_dbg(hdev, "data was pending ...\n");
diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c
index d16491192112..29f328f411fb 100644
--- a/drivers/hid/hid-steelseries.c
+++ b/drivers/hid/hid-steelseries.c
@@ -249,6 +249,11 @@ static int steelseries_srws1_probe(struct hid_device *hdev,
 		goto err_free;
 	}
 
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 16)) {
+		ret = -ENODEV;
+		goto err_free;
+	}
+
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c
index 87fc91e1c8de..91072fa54663 100644
--- a/drivers/hid/hid-sunplus.c
+++ b/drivers/hid/hid-sunplus.c
@@ -24,7 +24,7 @@
 static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
+	if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
 			rdesc[106] == 0x03) {
 		hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n");
 		rdesc[105] = rdesc[110] = 0x03;
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index 6ec28a37c146..a29756c6ca02 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -68,21 +68,13 @@ static int zpff_init(struct hid_device *hid)
 	struct hid_report *report;
 	struct hid_input *hidinput = list_entry(hid->inputs.next,
 						struct hid_input, list);
-	struct list_head *report_list =
-			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	int error;
+	int i, error;
 
-	if (list_empty(report_list)) {
-		hid_err(hid, "no output report found\n");
-		return -ENODEV;
-	}
-
-	report = list_entry(report_list->next, struct hid_report, list);
-
-	if (report->maxfield < 4) {
-		hid_err(hid, "not enough fields in report\n");
-		return -ENODEV;
+	for (i = 0; i < 4; i++) {
+		report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1);
+		if (!report)
+			return -ENODEV;
 	}
 
 	zpff = kzalloc(sizeof(struct zpff_device), GFP_KERNEL);
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 2b1799a3b212..469daa04dadb 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -134,6 +134,7 @@ struct i2c_hid {
 						   * descriptor. */
 	unsigned int		bufsize;	/* i2c buffer size */
 	char			*inbuf;		/* Input buffer */
+	char			*rawbuf;	/* Raw Input buffer */
 	char			*cmdbuf;	/* Command buffer */
 	char			*argsbuf;	/* Command arguments buffer */
 
@@ -340,7 +341,7 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 static void i2c_hid_get_input(struct i2c_hid *ihid)
 {
 	int ret, ret_size;
-	int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
+	int size = ihid->bufsize;
 
 	ret = i2c_master_recv(ihid->client, ihid->inbuf, size);
 	if (ret != size) {
@@ -471,9 +472,11 @@ static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type,
 static void i2c_hid_free_buffers(struct i2c_hid *ihid)
 {
 	kfree(ihid->inbuf);
+	kfree(ihid->rawbuf);
 	kfree(ihid->argsbuf);
 	kfree(ihid->cmdbuf);
 	ihid->inbuf = NULL;
+	ihid->rawbuf = NULL;
 	ihid->cmdbuf = NULL;
 	ihid->argsbuf = NULL;
 	ihid->bufsize = 0;
@@ -489,10 +492,11 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size)
 		       report_size; /* report */
 
 	ihid->inbuf = kzalloc(report_size, GFP_KERNEL);
+	ihid->rawbuf = kzalloc(report_size, GFP_KERNEL);
 	ihid->argsbuf = kzalloc(args_len, GFP_KERNEL);
 	ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL);
 
-	if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) {
+	if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) {
 		i2c_hid_free_buffers(ihid);
 		return -ENOMEM;
 	}
@@ -519,12 +523,12 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	ret = i2c_hid_get_report(client,
 			report_type == HID_FEATURE_REPORT ? 0x03 : 0x01,
-			report_number, ihid->inbuf, ask_count);
+			report_number, ihid->rawbuf, ask_count);
 
 	if (ret < 0)
 		return ret;
 
-	ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8);
+	ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8);
 
 	if (ret_count <= 2)
 		return 0;
@@ -533,7 +537,7 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	/* The query buffer contains the size, dropping it in the reply */
 	count = min(count, ret_count - 2);
-	memcpy(buf, ihid->inbuf + 2, count);
+	memcpy(buf, ihid->rawbuf + 2, count);
 
 	return count;
 }
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index fc307e0422af..0bb3bb889b71 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -312,7 +312,7 @@ static int uhid_event_from_user(const char __user *buffer, size_t len,
 			 */
 			struct uhid_create_req_compat *compat;
 
-			compat = kmalloc(sizeof(*compat), GFP_KERNEL);
+			compat = kzalloc(sizeof(*compat), GFP_KERNEL);
 			if (!compat)
 				return -ENOMEM;
 
@@ -640,7 +640,7 @@ static const struct file_operations uhid_fops = {
 
 static struct miscdevice uhid_misc = {
 	.fops		= &uhid_fops,
-	.minor		= MISC_DYNAMIC_MINOR,
+	.minor		= UHID_MINOR,
 	.name		= UHID_NAME,
 };
 
@@ -659,3 +659,5 @@ module_exit(uhid_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("David Herrmann <dh.herrmann@gmail.com>");
 MODULE_DESCRIPTION("User-space I/O driver support for HID subsystem");
+MODULE_ALIAS_MISCDEV(UHID_MINOR);
+MODULE_ALIAS("devname:" UHID_NAME);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 99418285222c..ada164e1b3a1 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -535,7 +535,6 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 {
 	int head;
 	struct usbhid_device *usbhid = hid->driver_data;
-	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
 
 	if ((hid->quirks & HID_QUIRK_NOGET) && dir == USB_DIR_IN)
 		return;
@@ -546,7 +545,7 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 			return;
 		}
 
-		usbhid->out[usbhid->outhead].raw_report = kmalloc(len, GFP_ATOMIC);
+		usbhid->out[usbhid->outhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
 		if (!usbhid->out[usbhid->outhead].raw_report) {
 			hid_warn(hid, "output queueing failed\n");
 			return;
@@ -595,7 +594,7 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 	}
 
 	if (dir == USB_DIR_OUT) {
-		usbhid->ctrl[usbhid->ctrlhead].raw_report = kmalloc(len, GFP_ATOMIC);
+		usbhid->ctrl[usbhid->ctrlhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
 		if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) {
 			hid_warn(hid, "control queueing failed\n");
 			return;
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 07345521f421..5b46a79dcb1f 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -84,6 +84,8 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_REALTEK, USB_DEVICE_ID_REALTEK_READER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_SIGMATEL, USB_DEVICE_ID_SIGMATEL_STMP3780, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS9200_TOUCH, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS817_TOUCH, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_SUN, USB_DEVICE_ID_RARITAN_KVM_DONGLE, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_1, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_2, HID_QUIRK_NOGET },
@@ -108,8 +110,12 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SIS, USB_DEVICE_ID_SIS_TS, HID_QUIRK_NO_INIT_REPORTS },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 0b122f8c7005..92f34de7aee9 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -199,8 +199,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	ret = vmbus_post_msg(open_msg,
 			       sizeof(struct vmbus_channel_open_channel));
 
-	if (ret != 0)
+	if (ret != 0) {
+		err = ret;
 		goto error1;
+	}
 
 	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
 	if (t == 0) {
@@ -392,7 +394,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	u32 next_gpadl_handle;
 	unsigned long flags;
 	int ret = 0;
-	int t;
 
 	next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle);
 	atomic_inc(&vmbus_connection.next_gpadl_handle);
@@ -439,9 +440,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 
 		}
 	}
-	t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	BUG_ON(t == 0);
-
+	wait_for_completion(&msginfo->waitevent);
 
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
@@ -464,7 +463,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
 	unsigned long flags;
-	int ret, t;
+	int ret;
 
 	info = kmalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
@@ -486,11 +485,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	ret = vmbus_post_msg(msg,
 			       sizeof(struct vmbus_channel_gpadl_teardown));
 
-	BUG_ON(ret != 0);
-	t = wait_for_completion_timeout(&info->waitevent, 5*HZ);
-	BUG_ON(t == 0);
+	if (ret)
+		goto post_msg_err;
+
+	wait_for_completion(&info->waitevent);
 
-	/* Received a torndown response */
+post_msg_err:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 253a74ba245c..a3b555808768 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -55,6 +55,9 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	case (VERSION_WIN8):
 		return VERSION_WIN7;
 
+	case (VERSION_WIN8_1):
+		return VERSION_WIN8;
+
 	case (VERSION_WS2008):
 	default:
 		return VERSION_INVAL;
@@ -67,7 +70,6 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	int ret = 0;
 	struct vmbus_channel_initiate_contact *msg;
 	unsigned long flags;
-	int t;
 
 	init_completion(&msginfo->waitevent);
 
@@ -81,6 +83,9 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 			(void *)((unsigned long)vmbus_connection.monitor_pages +
 				 PAGE_SIZE));
 
+	if (version == VERSION_WIN8_1)
+		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
+
 	/*
 	 * Add to list before we send the request since we may
 	 * receive the response before returning from this routine
@@ -102,15 +107,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	}
 
 	/* Wait for the connection response */
-	t =  wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	if (t == 0) {
-		spin_lock_irqsave(&vmbus_connection.channelmsg_lock,
-				flags);
-		list_del(&msginfo->msglistentry);
-		spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
-					flags);
-		return -ETIMEDOUT;
-	}
+	wait_for_completion(&msginfo->waitevent);
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&msginfo->msglistentry);
@@ -307,9 +304,13 @@ static void process_chn_event(u32 relid)
 		 */
 
 		do {
-			hv_begin_read(&channel->inbound);
+			if (read_state)
+				hv_begin_read(&channel->inbound);
 			channel->onchannel_callback(arg);
-			bytes_to_read = hv_end_read(&channel->inbound);
+			if (read_state)
+				bytes_to_read = hv_end_read(&channel->inbound);
+			else
+				bytes_to_read = 0;
 		} while (read_state && (bytes_to_read != 0));
 	} else {
 		pr_err("no channel callback for relid - %u\n", relid);
@@ -392,10 +393,21 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	 * insufficient resources. Retry the operation a couple of
 	 * times before giving up.
 	 */
-	while (retries < 3) {
-		ret =  hv_post_message(conn_id, 1, buffer, buflen);
-		if (ret != HV_STATUS_INSUFFICIENT_BUFFERS)
+	while (retries < 10) {
+		ret = hv_post_message(conn_id, 1, buffer, buflen);
+
+		switch (ret) {
+		case HV_STATUS_INSUFFICIENT_BUFFERS:
+			ret = -ENOMEM;
+		case -ENOMEM:
+			break;
+		case HV_STATUS_SUCCESS:
 			return ret;
+		default:
+			pr_err("hv_post_msg() failed; error code:%d\n", ret);
+			return -EINVAL;
+		}
+
 		retries++;
 		msleep(100);
 	}
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index deb5c25305af..694173f662d1 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/jiffies.h>
 #include <linux/mman.h>
 #include <linux/delay.h>
 #include <linux/init.h>
@@ -459,6 +460,11 @@ static bool do_hot_add;
  */
 static uint pressure_report_delay = 45;
 
+/*
+ * The last time we posted a pressure report to host.
+ */
+static unsigned long last_post_time;
+
 module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
 
@@ -542,6 +548,7 @@ struct hv_dynmem_device {
 
 static struct hv_dynmem_device dm_device;
 
+static void post_status(struct hv_dynmem_device *dm);
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
@@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 		 * have not been "onlined" within the allowed time.
 		 */
 		wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
-
+		post_status(&dm_device);
 	}
 
 	return;
@@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm)
 {
 	struct dm_status status;
 	struct sysinfo val;
+	unsigned long now = jiffies;
+	unsigned long last_post = last_post_time;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
 		return;
 	}
+
+	if (!time_after(now, (last_post_time + HZ)))
+		return;
+
 	si_meminfo(&val);
 	memset(&status, 0, sizeof(struct dm_status));
 	status.hdr.type = DM_STATUS_REPORT;
@@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm)
 	if (status.hdr.trans_id != atomic_read(&trans_id))
 		return;
 
+	/*
+	 * If the last post time that we sampled has changed,
+	 * we have raced, don't post the status.
+	 */
+	if (last_post != last_post_time)
+		return;
+
+	last_post_time = jiffies;
 	vmbus_sendpacket(dm->dev->channel, &status,
 				sizeof(struct dm_status),
 				(unsigned long)NULL,
@@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy)
 
 			if (ret == -EAGAIN)
 				msleep(20);
-
+			post_status(&dm_device);
 		} while (ret == -EAGAIN);
 
 		if (ret) {
@@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm,
 	struct dm_unballoon_response resp;
 	int i;
 
-	for (i = 0; i < range_count; i++)
+	for (i = 0; i < range_count; i++) {
 		free_balloon_pages(dm, &range_array[i]);
+		post_status(&dm_device);
+	}
 
 	if (req->more_pages == 1)
 		return;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ed50e9e83c61..0e8c1ea4dd53 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -111,6 +111,15 @@ kvp_work_func(struct work_struct *dummy)
 	kvp_respond_to_host(NULL, HV_E_FAIL);
 }
 
+static void poll_channel(struct vmbus_channel *channel)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&channel->inbound_lock, flags);
+	hv_kvp_onchannelcallback(channel);
+	spin_unlock_irqrestore(&channel->inbound_lock, flags);
+}
+
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 {
 	int ret = 1;
@@ -139,7 +148,7 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 		kvp_register(dm_reg_value);
 		kvp_transaction.active = false;
 		if (kvp_transaction.kvp_context)
-			hv_kvp_onchannelcallback(kvp_transaction.kvp_context);
+			poll_channel(kvp_transaction.kvp_context);
 	}
 	return ret;
 }
@@ -552,6 +561,7 @@ response_done:
 
 	vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
 				VM_PKT_DATA_INBAND, 0);
+	poll_channel(channel);
 
 }
 
@@ -585,7 +595,7 @@ void hv_kvp_onchannelcallback(void *context)
 		return;
 	}
 
-	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
+	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
 			 &requestid);
 
 	if (recvlen > 0) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 2f561c5dfe24..64c778f7756f 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -279,7 +279,7 @@ static int util_probe(struct hv_device *dev,
 		(struct hv_util_service *)dev_id->driver_data;
 	int ret;
 
-	srv->recv_buffer = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
+	srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
 	if (!srv->recv_buffer)
 		return -ENOMEM;
 	if (srv->util_init) {
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index df064e8cd9dc..f25f29835b3e 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -944,7 +944,7 @@ config SENSORS_NCT6775
 
 config SENSORS_NTC_THERMISTOR
 	tristate "NTC thermistor support"
-	depends on (!OF && !IIO) || (OF && IIO)
+	depends on !OF || IIO=n || IIO
 	help
 	  This driver supports NTC thermistors sensor reading and its
 	  interpretation. The driver can also monitor the temperature and
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index f920619cd6da..27ad7fb06572 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -185,7 +185,7 @@ static ssize_t set_temp_max(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adm1021_data *data = i2c_get_clientdata(client);
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -193,10 +193,11 @@ static ssize_t set_temp_max(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_max[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_max[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_TOS_W(index),
-					  data->temp_max[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
@@ -210,7 +211,7 @@ static ssize_t set_temp_min(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adm1021_data *data = i2c_get_clientdata(client);
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -218,10 +219,11 @@ static ssize_t set_temp_min(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_min[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_min[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_THYST_W(index),
-					  data->temp_min[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index 9ee5e066423b..39441e5d922c 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -232,6 +232,9 @@ static ssize_t set_fan_div(struct device *dev,
 	/* Update the value */
 	reg = (reg & 0x3F) | (val << 6);
 
+	/* Update the cache */
+	data->fan_div[attr->index] = reg;
+
 	/* Write value */
 	i2c_smbus_write_byte_data(client,
 				  ADM1029_REG_FAN_DIV[attr->index], reg);
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index 253ea396106d..bdceca0d7e22 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -365,6 +365,7 @@ set_auto_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->auto_temp[nr] = AUTO_TEMP_MIN_TO_REG(val, data->auto_temp[nr]);
 	adm1031_write_value(client, ADM1031_REG_AUTO_TEMP(nr),
@@ -394,6 +395,7 @@ set_auto_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = AUTO_TEMP_MAX_TO_REG(val, data->auto_temp[nr],
 						  data->pwm[nr]);
@@ -696,7 +698,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_min[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MIN(nr),
@@ -717,7 +719,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MAX(nr),
@@ -738,7 +740,7 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_crit[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_CRIT(nr),
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 2798246ad814..3930a7e7a56d 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -184,7 +184,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 		}
 
 		channel = be32_to_cpup(property);
-		if (channel > ADS1015_CHANNELS) {
+		if (channel >= ADS1015_CHANNELS) {
 			dev_err(&client->dev,
 				"invalid channel index %d on %s\n",
 				channel, node->full_name);
@@ -198,6 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid gain on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
@@ -208,6 +209,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid data_rate on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index 58637355c1f6..79610bdf1d35 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -515,7 +515,7 @@ static ssize_t set_temp_min(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_min[attr->index] = temp;
@@ -549,7 +549,7 @@ static ssize_t set_temp_max(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_max[attr->index] = temp;
@@ -826,7 +826,7 @@ static ssize_t set_pwm_tmin(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->pwm_tmin[attr->index] = temp;
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 4fe49d2bfe1d..09d2d78d482b 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -707,7 +707,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_MAX);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_CRIT);
-static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO,
 	get_temp, NULL, IDX_TEMP2_INPUT);
 static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp,
 	set_temp, IDX_TEMP2_MIN);
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 62c2e32e25ef..3288f13d2d87 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -230,6 +230,7 @@ static int send_argument(const char *key)
 
 static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 {
+	u8 status, data = 0;
 	int i;
 
 	if (send_command(cmd) || send_argument(key)) {
@@ -237,6 +238,7 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 		return -EIO;
 	}
 
+	/* This has no effect on newer (2012) SMCs */
 	if (send_byte(len, APPLESMC_DATA_PORT)) {
 		pr_warn("%.4s: read len fail\n", key);
 		return -EIO;
@@ -250,6 +252,17 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 		buffer[i] = inb(APPLESMC_DATA_PORT);
 	}
 
+	/* Read the data port until bit0 is cleared */
+	for (i = 0; i < 16; i++) {
+		udelay(APPLESMC_MIN_WAIT);
+		status = inb(APPLESMC_CMD_PORT);
+		if (!(status & 0x01))
+			break;
+		data = inb(APPLESMC_DATA_PORT);
+	}
+	if (i)
+		pr_warn("flushed %d bytes, last value is: %d\n", i, data);
+
 	return 0;
 }
 
@@ -525,16 +538,25 @@ static int applesmc_init_smcreg_try(void)
 {
 	struct applesmc_registers *s = &smcreg;
 	bool left_light_sensor, right_light_sensor;
+	unsigned int count;
 	u8 tmp[1];
 	int ret;
 
 	if (s->init_complete)
 		return 0;
 
-	ret = read_register_count(&s->key_count);
+	ret = read_register_count(&count);
 	if (ret)
 		return ret;
 
+	if (s->cache && s->key_count != count) {
+		pr_warn("key count changed from %d to %d\n",
+			s->key_count, count);
+		kfree(s->cache);
+		s->cache = NULL;
+	}
+	s->key_count = count;
+
 	if (!s->cache)
 		s->cache = kcalloc(s->key_count, sizeof(*s->cache), GFP_KERNEL);
 	if (!s->cache)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 658ce3a8717f..0cf25101b3c3 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
 #define NUM_REAL_CORES		32	/* Number of Real cores per cpu */
-#define CORETEMP_NAME_LENGTH	17	/* String Length of attrs */
+#define CORETEMP_NAME_LENGTH	19	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 960fac3fb166..48044b044b7a 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -194,7 +194,7 @@ static ssize_t da9052_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9052-hwmon\n");
+	return sprintf(buf, "da9052\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 029ecabc4380..1b275a2881d6 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -204,7 +204,7 @@ static ssize_t da9055_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9055-hwmon\n");
+	return sprintf(buf, "da9055\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 4ae3fff13f44..bea0a344fab5 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -247,8 +247,8 @@ struct dme1737_data {
 	u8  pwm_acz[3];
 	u8  pwm_freq[6];
 	u8  pwm_rr[2];
-	u8  zone_low[3];
-	u8  zone_abs[3];
+	s8  zone_low[3];
+	s8  zone_abs[3];
 	u8  zone_hyst[2];
 	u32 alarms;
 };
@@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res)
 	return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2));
 }
 
-static inline int IN_TO_REG(int val, int nominal)
+static inline int IN_TO_REG(long val, int nominal)
 {
 	return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
 }
@@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res)
 	return (reg * 1000) >> (res - 8);
 }
 
-static inline int TEMP_TO_REG(int val)
+static inline int TEMP_TO_REG(long val)
 {
 	return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
 }
@@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg)
 	return TEMP_RANGE[(reg >> 4) & 0x0f];
 }
 
-static int TEMP_RANGE_TO_REG(int val, int reg)
+static int TEMP_RANGE_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix)
 	return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
 }
 
-static inline int TEMP_HYST_TO_REG(int val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
 {
 	int hyst = clamp_val((val + 500) / 1000, 0, 15);
 
@@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc)
 		return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg;
 }
 
-static inline int FAN_TO_REG(int val, int tpc)
+static inline int FAN_TO_REG(long val, int tpc)
 {
 	if (tpc) {
 		return clamp_val(val / tpc, 0, 0xffff);
@@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg)
 	return (edge > 0) ? 1 << (edge - 1) : 0;
 }
 
-static inline int FAN_TYPE_TO_REG(int val, int reg)
+static inline int FAN_TYPE_TO_REG(long val, int reg)
 {
 	int edge = (val == 4) ? 3 : val;
 
@@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg)
 	return 1000 + i * 500;
 }
 
-static int FAN_MAX_TO_REG(int val)
+static int FAN_MAX_TO_REG(long val)
 {
 	int i;
 
@@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg)
 	return acz[(reg >> 5) & 0x07];
 }
 
-static inline int PWM_ACZ_TO_REG(int val, int reg)
+static inline int PWM_ACZ_TO_REG(long val, int reg)
 {
 	int acz = (val == 4) ? 2 : val - 1;
 
@@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg)
 	return PWM_FREQ[reg & 0x0f];
 }
 
-static int PWM_FREQ_TO_REG(int val, int reg)
+static int PWM_FREQ_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix)
 	return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0;
 }
 
-static int PWM_RR_TO_REG(int val, int ix, int reg)
+static int PWM_RR_TO_REG(long val, int ix, int reg)
 {
 	int i;
 
@@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix)
 	return PWM_RR_FROM_REG(reg, ix) ? 1 : 0;
 }
 
-static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg)
+static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg)
 {
 	int en = (ix == 1) ? 0x80 : 0x08;
 
@@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 		       const char *buf, size_t count)
 {
 	struct dme1737_data *data = dev_get_drvdata(dev);
-	long val;
+	unsigned long val;
 	int err;
 
-	err = kstrtol(buf, 10, &val);
+	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 142e1cb8dea7..361f50b221bd 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -162,7 +162,7 @@ static ssize_t store_hyst(struct device *dev,
 	if (retval < 0)
 		goto fail;
 
-	hyst = val - retval * 1000;
+	hyst = retval * 1000 - val;
 	hyst = DIV_ROUND_CLOSEST(hyst, 1000);
 	if (hyst < 0 || hyst > 255) {
 		retval = -ERANGE;
@@ -295,7 +295,7 @@ static int emc1403_detect(struct i2c_client *client,
 	}
 
 	id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
-	if (id != 0x01)
+	if (id < 0x01 || id > 0x04)
 		return -ENODEV;
 
 	return 0;
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 3104149795c5..ce1d82762ba6 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -172,7 +172,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data)
 	return -EINVAL;
 }
 
-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm)
+static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
 {
 	struct gpio_fan_speed *speed = fan_data->speed;
 	int i;
diff --git a/drivers/hwmon/hih6130.c b/drivers/hwmon/hih6130.c
index 2dc37c7c6947..7d68a08baaa8 100644
--- a/drivers/hwmon/hih6130.c
+++ b/drivers/hwmon/hih6130.c
@@ -43,6 +43,7 @@
  * @last_update: time of last update (jiffies)
  * @temperature: cached temperature measurement value
  * @humidity: cached humidity measurement value
+ * @write_length: length for I2C measurement request
  */
 struct hih6130 {
 	struct device *hwmon_dev;
@@ -51,6 +52,7 @@ struct hih6130 {
 	unsigned long last_update;
 	int temperature;
 	int humidity;
+	size_t write_length;
 };
 
 /**
@@ -121,8 +123,15 @@ static int hih6130_update_measurements(struct i2c_client *client)
 	 */
 	if (time_after(jiffies, hih6130->last_update + HZ) || !hih6130->valid) {
 
-		/* write to slave address, no data, to request a measurement */
-		ret = i2c_master_send(client, tmp, 0);
+		/*
+		 * Write to slave address to request a measurement.
+		 * According with the datasheet it should be with no data, but
+		 * for systems with I2C bus drivers that do not allow zero
+		 * length packets we write one dummy byte to allow sensor
+		 * measurements on them.
+		 */
+		tmp[0] = 0;
+		ret = i2c_master_send(client, tmp, hih6130->write_length);
 		if (ret < 0)
 			goto out;
 
@@ -252,6 +261,9 @@ static int hih6130_probe(struct i2c_client *client,
 		goto fail_remove_sysfs;
 	}
 
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_QUICK))
+		hih6130->write_length = 1;
+
 	return 0;
 
 fail_remove_sysfs:
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 4958b2f89dce..371c1ee233b7 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -147,7 +147,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 
 	switch (reg) {
 	case INA2XX_SHUNT_VOLTAGE:
-		val = DIV_ROUND_CLOSEST(data->regs[reg],
+		/* signed register */
+		val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
 					data->config->shunt_div);
 		break;
 	case INA2XX_BUS_VOLTAGE:
@@ -159,8 +160,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 		val = data->regs[reg] * data->config->power_lsb;
 		break;
 	case INA2XX_CURRENT:
-		/* LSB=1mA (selected). Is in mA */
-		val = data->regs[reg];
+		/* signed register, LSB=1mA (selected), in mA */
+		val = (s16)data->regs[reg];
 		break;
 	default:
 		/* programmer goofed */
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index e633856370cf..9bcf175c4921 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -211,6 +211,7 @@ static DEFINE_PCI_DEVICE_TABLE(k10temp_id_table) = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{}
 };
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index c03b490bba81..1d3600aa4ca5 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -27,6 +27,8 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/thermal.h>
 #include "lm75.h"
 
 
@@ -70,6 +72,7 @@ static const u8 LM75_REG_TEMP[3] = {
 /* Each client has this additional data */
 struct lm75_data {
 	struct device		*hwmon_dev;
+	struct thermal_zone_device	*tz;
 	struct mutex		update_lock;
 	u8			orig_conf;
 	u8			resolution;	/* In bits, between 9 and 12 */
@@ -90,22 +93,36 @@ static struct lm75_data *lm75_update_device(struct device *dev);
 
 /*-----------------------------------------------------------------------*/
 
+static inline long lm75_reg_to_mc(s16 temp, u8 resolution)
+{
+	return ((temp >> (16 - resolution)) * 1000) >> (resolution - 8);
+}
+
 /* sysfs attributes for hwmon */
 
+static int lm75_read_temp(void *dev, long *temp)
+{
+	struct lm75_data *data = lm75_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	*temp = lm75_reg_to_mc(data->temp[0], data->resolution);
+
+	return 0;
+}
+
 static ssize_t show_temp(struct device *dev, struct device_attribute *da,
 			 char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct lm75_data *data = lm75_update_device(dev);
-	long temp;
 
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
-	temp = ((data->temp[attr->index] >> (16 - data->resolution)) * 1000)
-	       >> (data->resolution - 8);
-
-	return sprintf(buf, "%ld\n", temp);
+	return sprintf(buf, "%ld\n", lm75_reg_to_mc(data->temp[attr->index],
+						    data->resolution));
 }
 
 static ssize_t set_temp(struct device *dev, struct device_attribute *da,
@@ -271,6 +288,13 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		goto exit_remove;
 	}
 
+	data->tz = thermal_zone_of_sensor_register(&client->dev,
+						   0,
+						   &client->dev,
+						   lm75_read_temp, NULL);
+	if (IS_ERR(data->tz))
+		data->tz = NULL;
+
 	dev_info(&client->dev, "%s: sensor '%s'\n",
 		 dev_name(data->hwmon_dev), client->name);
 
@@ -285,6 +309,7 @@ static int lm75_remove(struct i2c_client *client)
 {
 	struct lm75_data *data = i2c_get_clientdata(client);
 
+	thermal_zone_of_sensor_unregister(&client->dev, data->tz);
 	hwmon_device_unregister(data->hwmon_dev);
 	sysfs_remove_group(&client->dev.kobj, &lm75_group);
 	lm75_write_value(client, LM75_REG_CONF, data->orig_conf);
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 6cf6bff79003..b879427e9a46 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -94,6 +94,8 @@ static inline u8 FAN_TO_REG(long rpm, int div)
 {
 	if (rpm <= 0)
 		return 255;
+	if (rpm > 1350000)
+		return 1;
 	return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254);
 }
 
@@ -106,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div)
  * TEMP: mC (-128C to +127C)
  * REG: 1C/bit, two's complement
  */
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -128000, 127000) ;
 	return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000;
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 3894c408fda3..b9d6e7d0ba37 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -158,7 +158,7 @@ static inline u16 FAN_TO_REG(unsigned long val)
 
 /* Temperature is reported in .001 degC increments */
 #define TEMP_TO_REG(val)	\
-		clamp_val(SCALE(val, 1000, 1), -127, 127)
+		DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000)
 #define TEMPEXT_FROM_REG(val, ext)	\
 		SCALE(((val) << 4) + (ext), 16, 1000)
 #define TEMP_FROM_REG(val)	((val) * 1000)
@@ -192,7 +192,7 @@ static const int lm85_range_map[] = {
 	13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000
 };
 
-static int RANGE_TO_REG(int range)
+static int RANGE_TO_REG(long range)
 {
 	int i;
 
@@ -214,7 +214,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */
 	11, 15, 22, 29, 35, 44, 59, 88
 };
 
-static int FREQ_TO_REG(const int *map, int freq)
+static int FREQ_TO_REG(const int *map, unsigned long freq)
 {
 	int i;
 
@@ -463,6 +463,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 8eeb141c85ac..74813130d211 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -278,7 +278,7 @@ static const struct lm90_params lm90_params[] = {
 	[max6696] = {
 		.flags = LM90_HAVE_EMERGENCY
 		  | LM90_HAVE_EMERGENCY_ALARM | LM90_HAVE_TEMP3,
-		.alert_alarms = 0x187c,
+		.alert_alarms = 0x1c7c,
 		.max_convrate = 6,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
@@ -1500,19 +1500,22 @@ static void lm90_alert(struct i2c_client *client, unsigned int flag)
 	if ((alarms & 0x7f) == 0 && (alarms2 & 0xfe) == 0) {
 		dev_info(&client->dev, "Everything OK\n");
 	} else {
-		if (alarms & 0x61)
+		if ((alarms & 0x61) || (alarms2 & 0x80))
 			dev_warn(&client->dev,
 				 "temp%d out of range, please check!\n", 1);
-		if (alarms & 0x1a)
+		if ((alarms & 0x1a) || (alarms2 & 0x20))
 			dev_warn(&client->dev,
 				 "temp%d out of range, please check!\n", 2);
 		if (alarms & 0x04)
 			dev_warn(&client->dev,
 				 "temp%d diode open, please check!\n", 2);
 
-		if (alarms2 & 0x18)
+		if (alarms2 & 0x5a)
 			dev_warn(&client->dev,
 				 "temp%d out of range, please check!\n", 3);
+		if (alarms2 & 0x04)
+			dev_warn(&client->dev,
+				 "temp%d diode open, please check!\n", 3);
 
 		/*
 		 * Disable ALERT# output, because these chips don't implement
diff --git a/drivers/hwmon/max1668.c b/drivers/hwmon/max1668.c
index a7626358c95d..029b65e6c589 100644
--- a/drivers/hwmon/max1668.c
+++ b/drivers/hwmon/max1668.c
@@ -243,7 +243,7 @@ static ssize_t set_temp_min(struct device *dev,
 	data->temp_min[index] = clamp_val(temp/1000, -128, 127);
 	if (i2c_smbus_write_byte_data(client,
 					MAX1668_REG_LIML_WR(index),
-					data->temp_max[index]))
+					data->temp_min[index]))
 		count = -EIO;
 	mutex_unlock(&data->update_lock);
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index d6d640a733d5..c64d3d497c50 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -44,6 +44,7 @@ struct ntc_compensation {
 	unsigned int	ohm;
 };
 
+/* Order matters, ntc_match references the entries by index */
 static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp15wb473", TYPE_NCPXXWB473 },
 	{ "ncp18wb473", TYPE_NCPXXWB473 },
@@ -141,11 +142,11 @@ struct ntc_data {
 	char name[PLATFORM_NAME_SIZE];
 };
 
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
-	unsigned int result;
+	s64 result;
 	int val, ret;
 
 	ret = iio_read_channel_raw(channel, &val);
@@ -155,23 +156,23 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 	}
 
 	/* unit: mV */
-	result = pdata->pullup_uv * val;
+	result = pdata->pullup_uv * (s64) val;
 	result >>= 12;
 
-	return result;
+	return (int)result;
 }
 
 static const struct of_device_id ntc_match[] = {
 	{ .compatible = "ntc,ncp15wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[0] },
 	{ .compatible = "ntc,ncp18wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[1] },
 	{ .compatible = "ntc,ncp21wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[2] },
 	{ .compatible = "ntc,ncp03wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[3] },
 	{ .compatible = "ntc,ncp15wl333",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWL333] },
+		.data = &ntc_thermistor_id[4] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ntc_match);
@@ -223,6 +224,8 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
 	return NULL;
 }
 
+#define ntc_match	NULL
+
 static void ntc_iio_channel_release(struct ntc_thermistor_platform_data *pdata)
 { }
 #endif
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 1404e6319deb..9ec7d2e2542c 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -141,6 +141,8 @@ static inline u8 FAN_TO_REG(long rpm, int div)
 {
 	if (rpm <= 0)
 		return 255;
+	if (rpm > 1350000)
+		return 1;
 	return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254);
 }
 
@@ -157,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val)
 {
 	return val * 830 + 52120;
 }
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -54120, 157530) ;
 	return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830;
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index efee4c59239f..34b9a601ad07 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -86,7 +86,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n)
  */
 static inline s8 TEMP_TO_REG(int val)
 {
-	return clamp_val(SCALE(val, 1, 1000), -128000, 127000);
+	return SCALE(clamp_val(val, -128000, 127000), 1, 1000);
 }
 
 static inline int TEMP_FROM_REG(s8 val)
@@ -384,6 +384,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
+	if (val > 255)
+		return -EINVAL;
 
 	data->vrm = val;
 	return count;
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index d7b47abf37fe..6748b4583e7b 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -27,6 +27,8 @@
 #include <linux/mutex.h>
 #include <linux/device.h>
 #include <linux/jiffies.h>
+#include <linux/thermal.h>
+#include <linux/of.h>
 
 #define	DRIVER_NAME "tmp102"
 
@@ -50,6 +52,7 @@
 
 struct tmp102 {
 	struct device *hwmon_dev;
+	struct thermal_zone_device *tz;
 	struct mutex lock;
 	u16 config_orig;
 	unsigned long last_update;
@@ -93,6 +96,15 @@ static struct tmp102 *tmp102_update_device(struct i2c_client *client)
 	return tmp102;
 }
 
+static int tmp102_read_temp(void *dev, long *temp)
+{
+	struct tmp102 *tmp102 = tmp102_update_device(to_i2c_client(dev));
+
+	*temp = tmp102->temp[0];
+
+	return 0;
+}
+
 static ssize_t tmp102_show_temp(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
@@ -204,6 +216,12 @@ static int tmp102_probe(struct i2c_client *client,
 		goto fail_remove_sysfs;
 	}
 
+	tmp102->tz = thermal_zone_of_sensor_register(&client->dev, 0,
+						     &client->dev,
+						     tmp102_read_temp, NULL);
+	if (IS_ERR(tmp102->tz))
+		tmp102->tz = NULL;
+
 	dev_info(&client->dev, "initialized\n");
 
 	return 0;
@@ -220,6 +238,7 @@ static int tmp102_remove(struct i2c_client *client)
 {
 	struct tmp102 *tmp102 = i2c_get_clientdata(client);
 
+	thermal_zone_of_sensor_unregister(&client->dev, tmp102->tz);
 	hwmon_device_unregister(tmp102->hwmon_dev);
 	sysfs_remove_group(&client->dev.kobj, &tmp102_attr_group);
 
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index 0e7017841f7d..aee14e2192f8 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -145,7 +145,7 @@ static const u8 regtempmin[] = { 0x3a, 0x3e, 0x2c, 0x2e, 0x30, 0x32 };
  */
 static inline u8 FAN_TO_REG(long rpm, int div)
 {
-	if (rpm == 0)
+	if (rpm <= 0 || rpm > 1310720)
 		return 0;
 	return clamp_val(1310720 / (rpm * div), 1, 255);
 }
diff --git a/drivers/hwmon/w83l786ng.c b/drivers/hwmon/w83l786ng.c
index edb06cda5a68..6ed76ceb9270 100644
--- a/drivers/hwmon/w83l786ng.c
+++ b/drivers/hwmon/w83l786ng.c
@@ -481,9 +481,11 @@ store_pwm(struct device *dev, struct device_attribute *attr,
 	if (err)
 		return err;
 	val = clamp_val(val, 0, 255);
+	val = DIV_ROUND_CLOSEST(val, 0x11);
 
 	mutex_lock(&data->update_lock);
-	data->pwm[nr] = val;
+	data->pwm[nr] = val * 0x11;
+	val |= w83l786ng_read_value(client, W83L786NG_REG_PWM[nr]) & 0xf0;
 	w83l786ng_write_value(client, W83L786NG_REG_PWM[nr], val);
 	mutex_unlock(&data->update_lock);
 	return count;
@@ -510,7 +512,7 @@ store_pwm_enable(struct device *dev, struct device_attribute *attr,
 	mutex_lock(&data->update_lock);
 	reg = w83l786ng_read_value(client, W83L786NG_REG_FAN_CFG);
 	data->pwm_enable[nr] = val;
-	reg &= ~(0x02 << W83L786NG_PWM_ENABLE_SHIFT[nr]);
+	reg &= ~(0x03 << W83L786NG_PWM_ENABLE_SHIFT[nr]);
 	reg |= (val - 1) << W83L786NG_PWM_ENABLE_SHIFT[nr];
 	w83l786ng_write_value(client, W83L786NG_REG_FAN_CFG, reg);
 	mutex_unlock(&data->update_lock);
@@ -776,9 +778,10 @@ static struct w83l786ng_data *w83l786ng_update_device(struct device *dev)
 			    ((pwmcfg >> W83L786NG_PWM_MODE_SHIFT[i]) & 1)
 			    ? 0 : 1;
 			data->pwm_enable[i] =
-			    ((pwmcfg >> W83L786NG_PWM_ENABLE_SHIFT[i]) & 2) + 1;
-			data->pwm[i] = w83l786ng_read_value(client,
-			    W83L786NG_REG_PWM[i]);
+			    ((pwmcfg >> W83L786NG_PWM_ENABLE_SHIFT[i]) & 3) + 1;
+			data->pwm[i] =
+			    (w83l786ng_read_value(client, W83L786NG_REG_PWM[i])
+			     & 0x0f) * 0x11;
 		}
 
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 4faf02b3657d..d4fe13ee543e 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -108,6 +108,9 @@ config I2C_I801
 	    Lynx Point-LP (PCH)
 	    Avoton (SOC)
 	    Wellsburg (PCH)
+	    Coleto Creek (PCH)
+	    Wildcat Point-LP (PCH)
+	    BayTrail (SOC)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 6bb839b688be..09324d0178d5 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -102,6 +102,7 @@ struct at91_twi_dev {
 	unsigned twi_cwgr_reg;
 	struct at91_twi_pdata *pdata;
 	bool use_dma;
+	bool recv_len_abort;
 	struct at91_twi_dma dma;
 };
 
@@ -211,7 +212,7 @@ static void at91_twi_write_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_MEM_TO_DEV);
+			 dev->buf_len, DMA_TO_DEVICE);
 
 	at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
 }
@@ -268,12 +269,24 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev)
 	*dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff;
 	--dev->buf_len;
 
+	/* return if aborting, we only needed to read RHR to clear RXRDY*/
+	if (dev->recv_len_abort)
+		return;
+
 	/* handle I2C_SMBUS_BLOCK_DATA */
 	if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) {
-		dev->msg->flags &= ~I2C_M_RECV_LEN;
-		dev->buf_len += *dev->buf;
-		dev->msg->len = dev->buf_len + 1;
-		dev_dbg(dev->dev, "received block length %d\n", dev->buf_len);
+		/* ensure length byte is a valid value */
+		if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) {
+			dev->msg->flags &= ~I2C_M_RECV_LEN;
+			dev->buf_len += *dev->buf;
+			dev->msg->len = dev->buf_len + 1;
+			dev_dbg(dev->dev, "received block length %d\n",
+					 dev->buf_len);
+		} else {
+			/* abort and send the stop by reading one more byte */
+			dev->recv_len_abort = true;
+			dev->buf_len = 1;
+		}
 	}
 
 	/* send stop if second but last byte has been read */
@@ -290,7 +303,7 @@ static void at91_twi_read_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_DEV_TO_MEM);
+			 dev->buf_len, DMA_FROM_DEVICE);
 
 	/* The last two bytes have to be read without using dma */
 	dev->buf += dev->buf_len - 2;
@@ -422,8 +435,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 		}
 	}
 
-	ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete,
-							dev->adapter.timeout);
+	ret = wait_for_completion_timeout(&dev->cmd_complete,
+					     dev->adapter.timeout);
 	if (ret == 0) {
 		dev_err(dev->dev, "controller timed out\n");
 		at91_init_twi_bus(dev);
@@ -445,6 +458,12 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 		ret = -EIO;
 		goto error;
 	}
+	if (dev->recv_len_abort) {
+		dev_err(dev->dev, "invalid smbus block length recvd\n");
+		ret = -EPROTO;
+		goto error;
+	}
+
 	dev_dbg(dev->dev, "transfer complete\n");
 
 	return 0;
@@ -501,6 +520,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num)
 	dev->buf_len = m_start->len;
 	dev->buf = m_start->buf;
 	dev->msg = m_start;
+	dev->recv_len_abort = false;
 
 	ret = at91_do_twi_transfer(dev);
 
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index cf20e06a88e1..09f29e92095a 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -414,11 +414,9 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 	if (dev->cmd_err & DAVINCI_I2C_STR_NACK) {
 		if (msg->flags & I2C_M_IGNORE_NAK)
 			return msg->len;
-		if (stop) {
-			w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
-			w |= DAVINCI_I2C_MDR_STP;
-			davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
-		}
+		w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
+		w |= DAVINCI_I2C_MDR_STP;
+		davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
 		return -EREMOTEIO;
 	}
 	return -EIO;
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index c41ca6354fc5..f24a7385260a 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -380,6 +380,9 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 		ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
 	dw_writel(dev, ic_con, DW_IC_CON);
 
+	/* enforce disabled interrupts (due to HW issues) */
+	i2c_dw_disable_int(dev);
+
 	/* Enable the adapter */
 	__i2c_dw_enable(dev, true);
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 3a6903f63913..783fa75e13ae 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -58,6 +58,9 @@
   Wellsburg (PCH) MS    0x8d7d     32     hard     yes     yes     yes
   Wellsburg (PCH) MS    0x8d7e     32     hard     yes     yes     yes
   Wellsburg (PCH) MS    0x8d7f     32     hard     yes     yes     yes
+  Coleto Creek (PCH)    0x23b0     32     hard     yes     yes     yes
+  Wildcat Point-LP (PCH)   0x9ca2     32     hard     yes     yes     yes
+  BayTrail (SOC)        0x0f12     32     hard     yes     yes     yes
 
   Features supported by this driver:
   Software PEC                     no
@@ -160,6 +163,7 @@
 				 STATUS_ERROR_FLAGS)
 
 /* Older devices have their ID defined in <linux/pci_ids.h> */
+#define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS	0x0f12
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS	0x1c22
 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS	0x1d22
 /* Patsburg also has three 'Integrated Device Function' SMBus controllers */
@@ -169,6 +173,7 @@
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_SMBUS	0x1e22
 #define PCI_DEVICE_ID_INTEL_AVOTON_SMBUS	0x1f3c
 #define PCI_DEVICE_ID_INTEL_DH89XXCC_SMBUS	0x2330
+#define PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS	0x23b0
 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_SMBUS	0x3b30
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_SMBUS	0x8c22
 #define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS	0x8d22
@@ -176,6 +181,7 @@
 #define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS1	0x8d7e
 #define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2	0x8d7f
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_SMBUS	0x9c22
+#define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS	0x9ca2
 
 struct i801_mux_config {
 	char *gpio_chip;
@@ -817,6 +823,9 @@ static DEFINE_PCI_DEVICE_TABLE(i801_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS0) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS1) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS) },
 	{ 0, }
 };
 
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index cd82eb44e4c4..7c9f053556f2 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -393,6 +393,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr,
 
 	desc = &priv->hw[priv->head];
 
+	/* Initialize the DMA buffer */
+	memset(priv->dma_buffer, 0, sizeof(priv->dma_buffer));
+
 	/* Initialize the descriptor */
 	memset(desc, 0, sizeof(struct ismt_desc));
 	desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write);
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index e02f9e36a7b2..7645924f9f8b 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -928,19 +928,20 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
 		if (stat & OMAP_I2C_STAT_NACK) {
 			err |= OMAP_I2C_STAT_NACK;
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK);
-			break;
 		}
 
 		if (stat & OMAP_I2C_STAT_AL) {
 			dev_err(dev->dev, "Arbitration lost\n");
 			err |= OMAP_I2C_STAT_AL;
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL);
-			break;
 		}
 
 		/*
 		 * ProDB0017052: Clear ARDY bit twice
 		 */
+		if (stat & OMAP_I2C_STAT_ARDY)
+			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_ARDY);
+
 		if (stat & (OMAP_I2C_STAT_ARDY | OMAP_I2C_STAT_NACK |
 					OMAP_I2C_STAT_AL)) {
 			omap_i2c_ack_stat(dev, (OMAP_I2C_STAT_RRDY |
@@ -957,11 +958,13 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
 			if (dev->fifo_size)
 				num_bytes = dev->buf_len;
 
-			omap_i2c_receive_data(dev, num_bytes, true);
-
-			if (dev->errata & I2C_OMAP_ERRATA_I207)
+			if (dev->errata & I2C_OMAP_ERRATA_I207) {
 				i2c_omap_errata_i207(dev, stat);
+				num_bytes = (omap_i2c_read_reg(dev,
+					OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F;
+			}
 
+			omap_i2c_receive_data(dev, num_bytes, true);
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR);
 			continue;
 		}
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 4ba4a95b6b26..8a806f5c40cf 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -541,6 +541,12 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 	ret = -EINVAL;
 	for (i = 0; i < num; i++) {
+		/* This HW can't send STOP after address phase */
+		if (msgs[i].len == 0) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
 		/*-------------- spin lock -----------------*/
 		spin_lock_irqsave(&priv->lock, flags);
 
@@ -605,7 +611,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 static u32 rcar_i2c_func(struct i2c_adapter *adap)
 {
-	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+	/* This HW can't do SMBUS_QUICK and NOSTART */
+	return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
 }
 
 static const struct i2c_algorithm rcar_i2c_algo = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index cab1c91b75a3..a72aad9561b0 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1204,10 +1204,10 @@ static int s3c24xx_i2c_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
-	i2c->suspended = 0;
 	clk_prepare_enable(i2c->clk);
 	s3c24xx_i2c_init(i2c);
 	clk_disable_unprepare(i2c->clk);
+	i2c->suspended = 0;
 
 	return 0;
 }
diff --git a/drivers/i2c/muxes/i2c-mux-gpio.c b/drivers/i2c/muxes/i2c-mux-gpio.c
index 5a0ce0081dce..bb4f69f75f3c 100644
--- a/drivers/i2c/muxes/i2c-mux-gpio.c
+++ b/drivers/i2c/muxes/i2c-mux-gpio.c
@@ -31,15 +31,15 @@ static void i2c_mux_gpio_set(const struct gpiomux *mux, unsigned val)
 	int i;
 
 	for (i = 0; i < mux->data.n_gpios; i++)
-		gpio_set_value(mux->gpio_base + mux->data.gpios[i],
-			       val & (1 << i));
+		gpio_set_value_cansleep(mux->gpio_base + mux->data.gpios[i],
+					val & (1 << i));
 }
 
 static int i2c_mux_gpio_select(struct i2c_adapter *adap, void *data, u32 chan)
 {
 	struct gpiomux *mux = data;
 
-	i2c_mux_gpio_set(mux, mux->data.values[chan]);
+	i2c_mux_gpio_set(mux, chan);
 
 	return 0;
 }
@@ -223,7 +223,7 @@ static int i2c_mux_gpio_probe(struct platform_device *pdev)
 		unsigned int class = mux->data.classes ? mux->data.classes[i] : 0;
 
 		mux->adap[i] = i2c_add_mux_adapter(parent, &pdev->dev, mux, nr,
-						   i, class,
+						   mux->data.values[i], class,
 						   i2c_mux_gpio_select, deselect);
 		if (!mux->adap[i]) {
 			ret = -ENODEV;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index fa6964d8681a..d47bb0f267f7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -359,7 +359,10 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!need_resched()) {
+	if (!current_set_polling_and_test()) {
+
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 7229645bf1d7..7c9a1d97dc68 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -112,9 +112,10 @@ static int kxsd9_read(struct iio_dev *indio_dev, u8 address)
 	mutex_lock(&st->buf_lock);
 	st->tx[0] = KXSD9_READ(address);
 	ret = spi_sync_transfer(st->us, xfers, ARRAY_SIZE(xfers));
-	if (ret)
-		return ret;
-	return (((u16)(st->rx[0])) << 8) | (st->rx[1] & 0xF0);
+	if (!ret)
+		ret = (((u16)(st->rx[0])) << 8) | (st->rx[1] & 0xF0);
+	mutex_unlock(&st->buf_lock);
+	return ret;
 }
 
 static IIO_CONST_ATTR(accel_scale_available,
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index dd15a5b0f701..3394ebd410c7 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -211,7 +211,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
 			.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 			.address = 1,
 			.scan_index = 1,
-			.scan_type = IIO_ST('u', 12, 16, 0),
+			.scan_type = {
+				.sign = 'u',
+				.realbits = 12,
+				.storagebits = 16,
+				.shift = 0,
+				.endianness = IIO_BE,
+			},
 		},
 		.channel[1] = {
 			.type = IIO_VOLTAGE,
@@ -221,7 +227,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
 			.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 			.address = 0,
 			.scan_index = 0,
-			.scan_type = IIO_ST('u', 12, 16, 0),
+			.scan_type = {
+				.sign = 'u',
+				.realbits = 12,
+				.storagebits = 16,
+				.shift = 0,
+				.endianness = IIO_BE,
+			},
 		},
 		.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
 		.int_vref_mv = 2500,
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index f0d6335ae087..05d2733ef48c 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -477,7 +477,7 @@ static int ad_sd_probe_trigger(struct iio_dev *indio_dev)
 		goto error_free_irq;
 
 	/* select default trigger */
-	indio_dev->trig = sigma_delta->trig;
+	indio_dev->trig = iio_trigger_get(sigma_delta->trig);
 
 	return 0;
 
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index e5b88d5d3b59..14fdaf0f9d23 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -161,12 +161,11 @@ static int at91_adc_channel_init(struct iio_dev *idev)
 	return idev->num_channels;
 }
 
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 					     struct at91_adc_trigger *triggers,
 					     const char *trigger_name)
 {
 	struct at91_adc_state *st = iio_priv(idev);
-	u8 value = 0;
 	int i;
 
 	for (i = 0; i < st->trigger_number; i++) {
@@ -179,15 +178,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 			return -ENOMEM;
 
 		if (strcmp(trigger_name, name) == 0) {
-			value = triggers[i].value;
 			kfree(name);
-			break;
+			if (triggers[i].value == 0)
+				return -EINVAL;
+			return triggers[i].value;
 		}
 
 		kfree(name);
 	}
 
-	return value;
+	return -EINVAL;
 }
 
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -197,14 +197,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	struct iio_buffer *buffer = idev->buffer;
 	struct at91_adc_reg_desc *reg = st->registers;
 	u32 status = at91_adc_readl(st, reg->trigger_register);
-	u8 value;
+	int value;
 	u8 bit;
 
 	value = at91_adc_get_trigger_value_by_name(idev,
 						   st->trigger_list,
 						   idev->trig->name);
-	if (value == 0)
-		return -EINVAL;
+	if (value < 0)
+		return value;
 
 	if (state) {
 		st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index 9e6da72ad823..b2b5dcbf7122 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1214,8 +1214,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11605] = {
 		.bits = 8,
@@ -1224,8 +1224,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11606] = {
 		.bits = 10,
@@ -1274,8 +1274,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11611] = {
 		.bits = 10,
@@ -1284,8 +1284,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11612] = {
 		.bits = 12,
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index 8fc3a97eb266..8d8ca6f1e16a 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -49,7 +49,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 		dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
 		goto iio_trigger_register_error;
 	}
-	indio_dev->trig = sdata->trig;
+	indio_dev->trig = iio_trigger_get(sdata->trig);
 
 	return 0;
 
diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig
index 6be4628faffe..107cafcb89da 100644
--- a/drivers/iio/gyro/Kconfig
+++ b/drivers/iio/gyro/Kconfig
@@ -50,7 +50,7 @@ config IIO_ST_GYRO_3AXIS
 	select IIO_ST_GYRO_BUFFER if (IIO_TRIGGERED_BUFFER)
 	help
 	  Say yes here to build support for STMicroelectronics gyroscopes:
-	  L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330.
+	  L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330.
 
 	  This driver can also be built as a module. If so, will be created
 	  these modules:
diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c
index 6c43af9bb0a4..14917fae2d9d 100644
--- a/drivers/iio/gyro/itg3200_buffer.c
+++ b/drivers/iio/gyro/itg3200_buffer.c
@@ -135,7 +135,7 @@ int itg3200_probe_trigger(struct iio_dev *indio_dev)
 		goto error_free_irq;
 
 	/* select default trigger */
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 
 	return 0;
 
diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h
index 3ad9907bb154..25ee236b1bb2 100644
--- a/drivers/iio/gyro/st_gyro.h
+++ b/drivers/iio/gyro/st_gyro.h
@@ -19,7 +19,6 @@
 #define LSM330DL_GYRO_DEV_NAME		"lsm330dl_gyro"
 #define LSM330DLC_GYRO_DEV_NAME		"lsm330dlc_gyro"
 #define L3GD20_GYRO_DEV_NAME		"l3gd20"
-#define L3GD20H_GYRO_DEV_NAME		"l3gd20h"
 #define L3G4IS_GYRO_DEV_NAME		"l3g4is_ui"
 #define LSM330_GYRO_DEV_NAME		"lsm330_gyro"
 
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index fa9b24219987..1fabc3ffe7ee 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -162,11 +162,10 @@ static const struct st_sensors st_gyro_sensors[] = {
 		.wai = ST_GYRO_2_WAI_EXP,
 		.sensors_supported = {
 			[0] = L3GD20_GYRO_DEV_NAME,
-			[1] = L3GD20H_GYRO_DEV_NAME,
-			[2] = LSM330D_GYRO_DEV_NAME,
-			[3] = LSM330DLC_GYRO_DEV_NAME,
-			[4] = L3G4IS_GYRO_DEV_NAME,
-			[5] = LSM330_GYRO_DEV_NAME,
+			[1] = LSM330D_GYRO_DEV_NAME,
+			[2] = LSM330DLC_GYRO_DEV_NAME,
+			[3] = L3G4IS_GYRO_DEV_NAME,
+			[4] = LSM330_GYRO_DEV_NAME,
 		},
 		.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
 		.odr = {
diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c
index 8a310500573d..c1755ce2da30 100644
--- a/drivers/iio/gyro/st_gyro_i2c.c
+++ b/drivers/iio/gyro/st_gyro_i2c.c
@@ -61,7 +61,6 @@ static const struct i2c_device_id st_gyro_id_table[] = {
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c
index f3540390eb22..b37fc9e07706 100644
--- a/drivers/iio/gyro/st_gyro_spi.c
+++ b/drivers/iio/gyro/st_gyro_spi.c
@@ -60,7 +60,6 @@ static const struct spi_device_id st_gyro_id_table[] = {
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 2f8f9d632386..0916bf6b6c31 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -189,6 +189,7 @@ enum {
 	ADIS16300_SCAN_INCLI_X,
 	ADIS16300_SCAN_INCLI_Y,
 	ADIS16400_SCAN_ADC,
+	ADIS16400_SCAN_TIMESTAMP,
 };
 
 #ifdef CONFIG_IIO_BUFFER
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index f60591f0b925..d6ece2d17dec 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -632,7 +632,7 @@ static const struct iio_chan_spec adis16400_channels[] = {
 	ADIS16400_MAGN_CHAN(Z, ADIS16400_ZMAGN_OUT, 14),
 	ADIS16400_TEMP_CHAN(ADIS16400_TEMP_OUT, 12),
 	ADIS16400_AUX_ADC_CHAN(ADIS16400_AUX_ADC, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(12)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16448_channels[] = {
@@ -651,10 +651,15 @@ static const struct iio_chan_spec adis16448_channels[] = {
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = ADIS16448_BARO_OUT,
 		.scan_index = ADIS16400_SCAN_BARO,
-		.scan_type = IIO_ST('s', 16, 16, 0),
+		.scan_type = {
+			.sign = 's',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_BE,
+		},
 	},
 	ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(11)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16350_channels[] = {
@@ -672,7 +677,7 @@ static const struct iio_chan_spec adis16350_channels[] = {
 	ADIS16400_MOD_TEMP_CHAN(X, ADIS16350_XTEMP_OUT, 12),
 	ADIS16400_MOD_TEMP_CHAN(Y, ADIS16350_YTEMP_OUT, 12),
 	ADIS16400_MOD_TEMP_CHAN(Z, ADIS16350_ZTEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(11)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16300_channels[] = {
@@ -685,7 +690,7 @@ static const struct iio_chan_spec adis16300_channels[] = {
 	ADIS16400_AUX_ADC_CHAN(ADIS16300_AUX_ADC, 12),
 	ADIS16400_INCLI_CHAN(X, ADIS16300_PITCH_OUT, 13),
 	ADIS16400_INCLI_CHAN(Y, ADIS16300_ROLL_OUT, 13),
-	IIO_CHAN_SOFT_TIMESTAMP(14)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16334_channels[] = {
@@ -696,7 +701,7 @@ static const struct iio_chan_spec adis16334_channels[] = {
 	ADIS16400_ACCEL_CHAN(Y, ADIS16400_YACCL_OUT, 14),
 	ADIS16400_ACCEL_CHAN(Z, ADIS16400_ZACCL_OUT, 14),
 	ADIS16400_TEMP_CHAN(ADIS16350_XTEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(8)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static struct attribute *adis16400_attributes[] = {
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index fe4c61e219f3..111ac381b40b 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -660,6 +660,7 @@ static int inv_mpu_probe(struct i2c_client *client,
 {
 	struct inv_mpu6050_state *st;
 	struct iio_dev *indio_dev;
+	struct inv_mpu6050_platform_data *pdata;
 	int result;
 
 	if (!i2c_check_functionality(client->adapter,
@@ -675,8 +676,10 @@ static int inv_mpu_probe(struct i2c_client *client,
 	}
 	st = iio_priv(indio_dev);
 	st->client = client;
-	st->plat_data = *(struct inv_mpu6050_platform_data
-				*)dev_get_platdata(&client->dev);
+	pdata = (struct inv_mpu6050_platform_data
+			*)dev_get_platdata(&client->dev);
+	if (pdata)
+		st->plat_data = *pdata;
 	/* power is turned on inside check chip type*/
 	result = inv_check_and_setup_chip(st, id);
 	if (result)
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 03b9372c1212..926fccea8de0 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -135,7 +135,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev)
 	ret = iio_trigger_register(st->trig);
 	if (ret)
 		goto error_free_irq;
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 
 	return 0;
 
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index aaadd32f9f0d..e13c5f4b12cb 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -119,7 +119,8 @@ static ssize_t iio_scan_el_show(struct device *dev,
 	int ret;
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 
-	ret = test_bit(to_iio_dev_attr(attr)->address,
+	/* Ensure ret is 0 or 1. */
+	ret = !!test_bit(to_iio_dev_attr(attr)->address,
 		       indio_dev->buffer->scan_mask);
 
 	return sprintf(buf, "%d\n", ret);
@@ -762,7 +763,8 @@ int iio_scan_mask_query(struct iio_dev *indio_dev,
 	if (!buffer->scan_mask)
 		return 0;
 
-	return test_bit(bit, buffer->scan_mask);
+	/* Ensure return value is 0 or 1. */
+	return !!test_bit(bit, buffer->scan_mask);
 };
 EXPORT_SYMBOL_GPL(iio_scan_mask_query);
 
@@ -847,7 +849,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev,
 
 	/* Now we have the two masks, work from least sig and build up sizes */
 	for_each_set_bit(out_ind,
-			 indio_dev->active_scan_mask,
+			 buffer->scan_mask,
 			 indio_dev->masklength) {
 		in_ind = find_next_bit(indio_dev->active_scan_mask,
 				       indio_dev->masklength,
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index 0cf5f8e06cfc..4fc88e617acf 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -178,12 +178,12 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 			index = of_property_match_string(np, "io-channel-names",
 							 name);
 		chan = of_iio_channel_get(np, index);
-		if (!IS_ERR(chan))
+		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
 			break;
 		else if (name && index >= 0) {
 			pr_err("ERROR: could not get IIO channel %s:%s(%i)\n",
 				np->full_name, name ? name : "", index);
-			return chan;
+			return NULL;
 		}
 
 		/*
@@ -193,8 +193,9 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 		 */
 		np = np->parent;
 		if (np && !of_get_property(np, "io-channel-ranges", NULL))
-			break;
+			return NULL;
 	}
+
 	return chan;
 }
 
@@ -317,6 +318,7 @@ struct iio_channel *iio_channel_get(struct device *dev,
 		if (channel != NULL)
 			return channel;
 	}
+
 	return iio_channel_get_sys(name, channel_name);
 }
 EXPORT_SYMBOL_GPL(iio_channel_get);
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index af6c320a534e..53f829004a03 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -276,8 +276,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 {
 	struct ak8975_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	u16 meas_reg;
-	s16 raw;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -322,16 +320,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 		dev_err(&client->dev, "Read axis data fails\n");
 		goto exit;
 	}
-	meas_reg = ret;
 
 	mutex_unlock(&data->lock);
 
-	/* Endian conversion of the measured values. */
-	raw = (s16) (le16_to_cpu(meas_reg));
-
 	/* Clamp to valid range. */
-	raw = clamp_t(s16, raw, -4096, 4095);
-	*val = raw;
+	*val = clamp_t(s16, ret, -4096, 4095);
 	return IIO_VAL_INT;
 
 exit:
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 16f0d6df239f..3ce3769c0823 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -40,7 +40,8 @@
 #define ST_MAGN_FS_AVL_5600MG			5600
 #define ST_MAGN_FS_AVL_8000MG			8000
 #define ST_MAGN_FS_AVL_8100MG			8100
-#define ST_MAGN_FS_AVL_10000MG			10000
+#define ST_MAGN_FS_AVL_12000MG			12000
+#define ST_MAGN_FS_AVL_16000MG			16000
 
 /* CUSTOM VALUES FOR SENSOR 1 */
 #define ST_MAGN_1_WAI_EXP			0x3c
@@ -67,20 +68,20 @@
 #define ST_MAGN_1_FS_AVL_4700_VAL		0x05
 #define ST_MAGN_1_FS_AVL_5600_VAL		0x06
 #define ST_MAGN_1_FS_AVL_8100_VAL		0x07
-#define ST_MAGN_1_FS_AVL_1300_GAIN_XY		1100
-#define ST_MAGN_1_FS_AVL_1900_GAIN_XY		855
-#define ST_MAGN_1_FS_AVL_2500_GAIN_XY		670
-#define ST_MAGN_1_FS_AVL_4000_GAIN_XY		450
-#define ST_MAGN_1_FS_AVL_4700_GAIN_XY		400
-#define ST_MAGN_1_FS_AVL_5600_GAIN_XY		330
-#define ST_MAGN_1_FS_AVL_8100_GAIN_XY		230
-#define ST_MAGN_1_FS_AVL_1300_GAIN_Z		980
-#define ST_MAGN_1_FS_AVL_1900_GAIN_Z		760
-#define ST_MAGN_1_FS_AVL_2500_GAIN_Z		600
-#define ST_MAGN_1_FS_AVL_4000_GAIN_Z		400
-#define ST_MAGN_1_FS_AVL_4700_GAIN_Z		355
-#define ST_MAGN_1_FS_AVL_5600_GAIN_Z		295
-#define ST_MAGN_1_FS_AVL_8100_GAIN_Z		205
+#define ST_MAGN_1_FS_AVL_1300_GAIN_XY		909
+#define ST_MAGN_1_FS_AVL_1900_GAIN_XY		1169
+#define ST_MAGN_1_FS_AVL_2500_GAIN_XY		1492
+#define ST_MAGN_1_FS_AVL_4000_GAIN_XY		2222
+#define ST_MAGN_1_FS_AVL_4700_GAIN_XY		2500
+#define ST_MAGN_1_FS_AVL_5600_GAIN_XY		3030
+#define ST_MAGN_1_FS_AVL_8100_GAIN_XY		4347
+#define ST_MAGN_1_FS_AVL_1300_GAIN_Z		1020
+#define ST_MAGN_1_FS_AVL_1900_GAIN_Z		1315
+#define ST_MAGN_1_FS_AVL_2500_GAIN_Z		1666
+#define ST_MAGN_1_FS_AVL_4000_GAIN_Z		2500
+#define ST_MAGN_1_FS_AVL_4700_GAIN_Z		2816
+#define ST_MAGN_1_FS_AVL_5600_GAIN_Z		3389
+#define ST_MAGN_1_FS_AVL_8100_GAIN_Z		4878
 #define ST_MAGN_1_MULTIREAD_BIT			false
 
 /* CUSTOM VALUES FOR SENSOR 2 */
@@ -103,10 +104,12 @@
 #define ST_MAGN_2_FS_MASK			0x60
 #define ST_MAGN_2_FS_AVL_4000_VAL		0x00
 #define ST_MAGN_2_FS_AVL_8000_VAL		0x01
-#define ST_MAGN_2_FS_AVL_10000_VAL		0x02
-#define ST_MAGN_2_FS_AVL_4000_GAIN		430
-#define ST_MAGN_2_FS_AVL_8000_GAIN		230
-#define ST_MAGN_2_FS_AVL_10000_GAIN		230
+#define ST_MAGN_2_FS_AVL_12000_VAL		0x02
+#define ST_MAGN_2_FS_AVL_16000_VAL		0x03
+#define ST_MAGN_2_FS_AVL_4000_GAIN		146
+#define ST_MAGN_2_FS_AVL_8000_GAIN		292
+#define ST_MAGN_2_FS_AVL_12000_GAIN		438
+#define ST_MAGN_2_FS_AVL_16000_GAIN		584
 #define ST_MAGN_2_MULTIREAD_BIT			false
 #define ST_MAGN_2_OUT_X_L_ADDR			0x28
 #define ST_MAGN_2_OUT_Y_L_ADDR			0x2a
@@ -252,9 +255,14 @@ static const struct st_sensors st_magn_sensors[] = {
 					.gain = ST_MAGN_2_FS_AVL_8000_GAIN,
 				},
 				[2] = {
-					.num = ST_MAGN_FS_AVL_10000MG,
-					.value = ST_MAGN_2_FS_AVL_10000_VAL,
-					.gain = ST_MAGN_2_FS_AVL_10000_GAIN,
+					.num = ST_MAGN_FS_AVL_12000MG,
+					.value = ST_MAGN_2_FS_AVL_12000_VAL,
+					.gain = ST_MAGN_2_FS_AVL_12000_GAIN,
+				},
+				[3] = {
+					.num = ST_MAGN_FS_AVL_16000MG,
+					.value = ST_MAGN_2_FS_AVL_16000_VAL,
+					.gain = ST_MAGN_2_FS_AVL_16000_GAIN,
 				},
 			},
 		},
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index c47c2034ca71..4293e89bbbdd 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -46,6 +46,7 @@
 #include <linux/completion.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 
 #include <rdma/iw_cm.h>
 #include <rdma/ib_addr.h>
@@ -65,6 +66,20 @@ struct iwcm_work {
 	struct list_head free_list;
 };
 
+static unsigned int default_backlog = 256;
+
+static struct ctl_table_header *iwcm_ctl_table_hdr;
+static struct ctl_table iwcm_ctl_table[] = {
+	{
+		.procname	= "default_backlog",
+		.data		= &default_backlog,
+		.maxlen		= sizeof(default_backlog),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
 /*
  * The following services provide a mechanism for pre-allocating iwcm_work
  * elements.  The design pre-allocates them  based on the cm_id type:
@@ -419,6 +434,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog)
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
 
+	if (!backlog)
+		backlog = default_backlog;
+
 	ret = alloc_work_entries(cm_id_priv, backlog);
 	if (ret)
 		return ret;
@@ -1024,11 +1042,20 @@ static int __init iw_cm_init(void)
 	if (!iwcm_wq)
 		return -ENOMEM;
 
+	iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm",
+						 iwcm_ctl_table);
+	if (!iwcm_ctl_table_hdr) {
+		pr_err("iw_cm: couldn't register sysctl paths\n");
+		destroy_workqueue(iwcm_wq);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 static void __exit iw_cm_cleanup(void)
 {
+	unregister_net_sysctl_table(iwcm_ctl_table_hdr);
 	destroy_workqueue(iwcm_wq);
 }
 
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index f0d588f8859e..1acb99100556 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -98,7 +98,7 @@ struct ib_umad_port {
 
 struct ib_umad_device {
 	int                  start_port, end_port;
-	struct kref          ref;
+	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
 
@@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS);
 static void ib_umad_add_one(struct ib_device *device);
 static void ib_umad_remove_one(struct ib_device *device);
 
-static void ib_umad_release_dev(struct kref *ref)
+static void ib_umad_release_dev(struct kobject *kobj)
 {
 	struct ib_umad_device *dev =
-		container_of(ref, struct ib_umad_device, ref);
+		container_of(kobj, struct ib_umad_device, kobj);
 
 	kfree(dev);
 }
 
+static struct kobj_type ib_umad_dev_ktype = {
+	.release = ib_umad_release_dev,
+};
+
 static int hdr_size(struct ib_umad_file *file)
 {
 	return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
@@ -780,27 +784,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 {
 	struct ib_umad_port *port;
 	struct ib_umad_file *file;
-	int ret;
+	int ret = -ENXIO;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	mutex_lock(&port->file_mutex);
 
-	if (!port->ib_dev) {
-		ret = -ENXIO;
+	if (!port->ib_dev)
 		goto out;
-	}
 
+	ret = -ENOMEM;
 	file = kzalloc(sizeof *file, GFP_KERNEL);
-	if (!file) {
-		kref_put(&port->umad_dev->ref, ib_umad_release_dev);
-		ret = -ENOMEM;
+	if (!file)
 		goto out;
-	}
 
 	mutex_init(&file->mutex);
 	spin_lock_init(&file->send_lock);
@@ -814,6 +810,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 	list_add_tail(&file->port_list, &port->file_list);
 
 	ret = nonseekable_open(inode, filp);
+	if (ret) {
+		list_del(&file->port_list);
+		kfree(file);
+		goto out;
+	}
+
+	kobject_get(&port->umad_dev->kobj);
 
 out:
 	mutex_unlock(&port->file_mutex);
@@ -852,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp)
 	mutex_unlock(&file->port->file_mutex);
 
 	kfree(file);
-	kref_put(&dev->ref, ib_umad_release_dev);
+	kobject_put(&dev->kobj);
 
 	return 0;
 }
@@ -880,10 +883,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	int ret;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	if (filp->f_flags & O_NONBLOCK) {
 		if (down_trylock(&port->sm_sem)) {
@@ -898,17 +897,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	}
 
 	ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
-	if (ret) {
-		up(&port->sm_sem);
-		goto fail;
-	}
+	if (ret)
+		goto err_up_sem;
 
 	filp->private_data = port;
 
-	return nonseekable_open(inode, filp);
+	ret = nonseekable_open(inode, filp);
+	if (ret)
+		goto err_clr_sm_cap;
+
+	kobject_get(&port->umad_dev->kobj);
+
+	return 0;
+
+err_clr_sm_cap:
+	swap(props.set_port_cap_mask, props.clr_port_cap_mask);
+	ib_modify_port(port->ib_dev, port->port_num, 0, &props);
+
+err_up_sem:
+	up(&port->sm_sem);
 
 fail:
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
 	return ret;
 }
 
@@ -927,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp)
 
 	up(&port->sm_sem);
 
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&port->umad_dev->kobj);
 
 	return ret;
 }
@@ -995,6 +1004,7 @@ static int find_overflow_devnum(void)
 }
 
 static int ib_umad_init_port(struct ib_device *device, int port_num,
+			     struct ib_umad_device *umad_dev,
 			     struct ib_umad_port *port)
 {
 	int devnum;
@@ -1027,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 
 	cdev_init(&port->cdev, &umad_fops);
 	port->cdev.owner = THIS_MODULE;
+	port->cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num);
 	if (cdev_add(&port->cdev, base, 1))
 		goto err_cdev;
@@ -1045,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	base += IB_UMAD_MAX_PORTS;
 	cdev_init(&port->sm_cdev, &umad_sm_fops);
 	port->sm_cdev.owner = THIS_MODULE;
+	port->sm_cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num);
 	if (cdev_add(&port->sm_cdev, base, 1))
 		goto err_sm_cdev;
@@ -1138,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	kref_init(&umad_dev->ref);
+	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
 	umad_dev->start_port = s;
 	umad_dev->end_port   = e;
@@ -1146,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device)
 	for (i = s; i <= e; ++i) {
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
-		if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
+		if (ib_umad_init_port(device, i, umad_dev,
+				      &umad_dev->port[i - s]))
 			goto err;
 	}
 
@@ -1158,7 +1171,7 @@ err:
 	while (--i >= s)
 		ib_umad_kill_port(&umad_dev->port[i - s]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static void ib_umad_remove_one(struct ib_device *device)
@@ -1172,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device)
 	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
 		ib_umad_kill_port(&umad_dev->port[i]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static char *umad_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c
index 212150c25ea0..8cc837537768 100644
--- a/drivers/infiniband/hw/ehca/ehca_cq.c
+++ b/drivers/infiniband/hw/ehca/ehca_cq.c
@@ -283,6 +283,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 			(my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1));
 		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
 			ehca_err(device, "Copy to udata failed.");
+			cq = ERR_PTR(-EFAULT);
 			goto create_cq_exit4;
 		}
 	}
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index 714293b78518..45802e97332e 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -326,7 +326,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 				   size_t count, loff_t *off)
 {
 	u32 __iomem *piobuf;
-	u32 plen, clen, pbufn;
+	u32 plen, pbufn, maxlen_reserve;
 	struct ipath_diag_pkt odp;
 	struct ipath_diag_xpkt dp;
 	u32 *tmpbuf = NULL;
@@ -335,42 +335,24 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 	u64 val;
 	u32 l_state, lt_state; /* LinkState, LinkTrainingState */
 
-	if (count < sizeof(odp)) {
-		ret = -EINVAL;
-		goto bail;
-	}
 
 	if (count == sizeof(dp)) {
 		if (copy_from_user(&dp, data, sizeof(dp))) {
 			ret = -EFAULT;
 			goto bail;
 		}
-	} else if (copy_from_user(&odp, data, sizeof(odp))) {
-		ret = -EFAULT;
-		goto bail;
-	}
-
-	/*
-	 * Due to padding/alignment issues (lessened with new struct)
-	 * the old and new structs are the same length. We need to
-	 * disambiguate them, which we can do because odp.len has never
-	 * been less than the total of LRH+BTH+DETH so far, while
-	 * dp.unit (same offset) unit is unlikely to get that high.
-	 * Similarly, dp.data, the pointer to user at the same offset
-	 * as odp.unit, is almost certainly at least one (512byte)page
-	 * "above" NULL. The if-block below can be omitted if compatibility
-	 * between a new driver and older diagnostic code is unimportant.
-	 * compatibility the other direction (new diags, old driver) is
-	 * handled in the diagnostic code, with a warning.
-	 */
-	if (dp.unit >= 20 && dp.data < 512) {
-		/* very probable version mismatch. Fix it up */
-		memcpy(&odp, &dp, sizeof(odp));
-		/* We got a legacy dp, copy elements to dp */
+	} else if (count == sizeof(odp)) {
+		if (copy_from_user(&odp, data, sizeof(odp))) {
+			ret = -EFAULT;
+			goto bail;
+		}
+		dp.len = odp.len;
 		dp.unit = odp.unit;
 		dp.data = odp.data;
-		dp.len = odp.len;
-		dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */
+		dp.pbc_wd = 0;
+	} else {
+		ret = -EINVAL;
+		goto bail;
 	}
 
 	/* send count must be an exact number of dwords */
@@ -379,7 +361,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 		goto bail;
 	}
 
-	clen = dp.len >> 2;
+	plen = dp.len >> 2;
 
 	dd = ipath_lookup(dp.unit);
 	if (!dd || !(dd->ipath_flags & IPATH_PRESENT) ||
@@ -422,16 +404,22 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 		goto bail;
 	}
 
-	/* need total length before first word written */
-	/* +1 word is for the qword padding */
-	plen = sizeof(u32) + dp.len;
-
-	if ((plen + 4) > dd->ipath_ibmaxlen) {
+	/*
+	 * need total length before first word written, plus 2 Dwords. One Dword
+	 * is for padding so we get the full user data when not aligned on
+	 * a word boundary. The other Dword is to make sure we have room for the
+	 * ICRC which gets tacked on later.
+	 */
+	maxlen_reserve = 2 * sizeof(u32);
+	if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) {
 		ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n",
-			  plen - 4, dd->ipath_ibmaxlen);
+			  dp.len, dd->ipath_ibmaxlen);
 		ret = -EINVAL;
-		goto bail;	/* before writing pbc */
+		goto bail;
 	}
+
+	plen = sizeof(u32) + dp.len;
+
 	tmpbuf = vmalloc(plen);
 	if (!tmpbuf) {
 		dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, "
@@ -473,11 +461,11 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 	 */
 	if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) {
 		ipath_flush_wc();
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen - 1);
 		ipath_flush_wc();
-		__raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+		__raw_writel(tmpbuf[plen - 1], piobuf + plen + 1);
 	} else
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen);
 
 	ipath_flush_wc();
 
diff --git a/drivers/infiniband/hw/ipath/ipath_user_sdma.c b/drivers/infiniband/hw/ipath/ipath_user_sdma.c
index f5cb13b21445..cc04b7ba3488 100644
--- a/drivers/infiniband/hw/ipath/ipath_user_sdma.c
+++ b/drivers/infiniband/hw/ipath/ipath_user_sdma.c
@@ -280,9 +280,7 @@ static int ipath_user_sdma_pin_pages(const struct ipath_devdata *dd,
 	int j;
 	int ret;
 
-	ret = get_user_pages(current, current->mm, addr,
-			     npages, 0, 1, pages, NULL);
-
+	ret = get_user_pages_fast(addr, npages, 0, pages);
 	if (ret != npages) {
 		int i;
 
@@ -811,10 +809,7 @@ int ipath_user_sdma_writev(struct ipath_devdata *dd,
 	while (dim) {
 		const int mxp = 8;
 
-		down_write(&current->mm->mmap_sem);
 		ret = ipath_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
-		up_write(&current->mm->mmap_sem);
-
 		if (ret <= 0)
 			goto done_unlock;
 		else {
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 5b71d43bd89c..42dde06fdb91 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
 
 	if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) {
 		mthca_free_cq(to_mdev(ibdev), cq);
+		err = -EFAULT;
 		goto err_free;
 	}
 
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 8f67fe2e91e6..7510a3c80757 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1186,7 +1186,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd,
 					nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num);
 					kfree(nesqp->allocated_buffer);
 					nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n");
-					return NULL;
+					return ERR_PTR(-EFAULT);
 				}
 				if (req.user_wqe_buffers) {
 					virt_wqs = 1;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 3f6b21e9dc11..14103ffb4839 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2287,6 +2287,11 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd)
 	qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a);
 	qib_write_kreg(dd, kr_scratch, 0ULL);
 
+	/* ensure previous Tx parameters are not still forced */
+	qib_write_kreg_port(ppd, krp_tx_deemph_override,
+		SYM_MASK(IBSD_TX_DEEMPHASIS_OVERRIDE_0,
+		reset_tx_deemphasis_override));
+
 	if (qib_compat_ddr_negotiate) {
 		ppd->cpspec->ibdeltainprog = 1;
 		ppd->cpspec->ibsymsnap = read_7322_creg32_port(ppd,
@@ -5853,21 +5858,20 @@ static int setup_txselect(const char *str, struct kernel_param *kp)
 {
 	struct qib_devdata *dd;
 	unsigned long val;
-	int ret;
-
+	char *n;
 	if (strlen(str) >= MAX_ATTEN_LEN) {
 		pr_info("txselect_values string too long\n");
 		return -ENOSPC;
 	}
-	ret = kstrtoul(str, 0, &val);
-	if (ret || val >= (TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ +
+	val = simple_strtoul(str, &n, 0);
+	if (n == str || val >= (TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ +
 				TXDDS_MFG_SZ)) {
 		pr_info("txselect_values must start with a number < %d\n",
 			TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ + TXDDS_MFG_SZ);
-		return ret ? ret : -EINVAL;
+		return -EINVAL;
 	}
-
 	strcpy(txselect_list, str);
+
 	list_for_each_entry(dd, &qib_dev_list, list)
 		if (dd->deviceid == PCI_DEVICE_ID_QLOGIC_IB_7322)
 			set_no_qsfp_atten(dd, 1);
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index ccb119143d20..1dd9fcbb7c9a 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys)
 
 		event.event = IB_EVENT_PKEY_CHANGE;
 		event.device = &dd->verbs_dev.ibdev;
-		event.element.port_num = 1;
+		event.element.port_num = port;
 		ib_dispatch_event(&event);
 	}
 	return 0;
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index d6c7fe7f88d5..3ad651c3356c 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -57,13 +57,20 @@ static void qib_ud_loopback(struct qib_qp *sqp, struct qib_swqe *swqe)
 	struct qib_sge *sge;
 	struct ib_wc wc;
 	u32 length;
+	enum ib_qp_type sqptype, dqptype;
 
 	qp = qib_lookup_qpn(ibp, swqe->wr.wr.ud.remote_qpn);
 	if (!qp) {
 		ibp->n_pkt_drops++;
 		return;
 	}
-	if (qp->ibqp.qp_type != sqp->ibqp.qp_type ||
+
+	sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : sqp->ibqp.qp_type;
+	dqptype = qp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : qp->ibqp.qp_type;
+
+	if (dqptype != sqptype ||
 	    !(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) {
 		ibp->n_pkt_drops++;
 		goto drop;
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 82442085cbe6..573b4601d5b9 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -284,8 +284,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	int j;
 	int ret;
 
-	ret = get_user_pages(current, current->mm, addr,
-			     npages, 0, 1, pages, NULL);
+	ret = get_user_pages_fast(addr, npages, 0, pages);
 
 	if (ret != npages) {
 		int i;
@@ -830,10 +829,7 @@ int qib_user_sdma_writev(struct qib_ctxtdata *rcd,
 	while (dim) {
 		const int mxp = 8;
 
-		down_write(&current->mm->mmap_sem);
 		ret = qib_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
-		up_write(&current->mm->mmap_sem);
-
 		if (ret <= 0)
 			goto done_unlock;
 		else {
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 5849dc0726b9..5d4a4583d2df 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -27,6 +27,7 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/iscsi/iscsi_transport.h>
+#include <linux/semaphore.h>
 
 #include "isert_proto.h"
 #include "ib_isert.h"
@@ -242,21 +243,29 @@ isert_create_device_ib_res(struct isert_device *device)
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
 						ISER_MAX_RX_CQ_LEN, i);
-		if (IS_ERR(device->dev_rx_cq[i]))
+		if (IS_ERR(device->dev_rx_cq[i])) {
+			ret = PTR_ERR(device->dev_rx_cq[i]);
+			device->dev_rx_cq[i] = NULL;
 			goto out_cq;
+		}
 
 		device->dev_tx_cq[i] = ib_create_cq(device->ib_device,
 						isert_cq_tx_callback,
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
 						ISER_MAX_TX_CQ_LEN, i);
-		if (IS_ERR(device->dev_tx_cq[i]))
+		if (IS_ERR(device->dev_tx_cq[i])) {
+			ret = PTR_ERR(device->dev_tx_cq[i]);
+			device->dev_tx_cq[i] = NULL;
 			goto out_cq;
+		}
 
-		if (ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP))
+		ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP);
+		if (ret)
 			goto out_cq;
 
-		if (ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP))
+		ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP);
+		if (ret)
 			goto out_cq;
 	}
 
@@ -373,6 +382,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	struct ib_device *ib_dev = cma_id->device;
 	int ret = 0;
 
+	spin_lock_bh(&np->np_thread_lock);
+	if (!np->enabled) {
+		spin_unlock_bh(&np->np_thread_lock);
+		pr_debug("iscsi_np is not enabled, reject connect request\n");
+		return rdma_reject(cma_id, NULL, 0);
+	}
+	spin_unlock_bh(&np->np_thread_lock);
+
 	pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n",
 		 cma_id, cma_id->context);
 
@@ -384,10 +401,9 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	isert_conn->state = ISER_CONN_INIT;
 	INIT_LIST_HEAD(&isert_conn->conn_accept_node);
 	init_completion(&isert_conn->conn_login_comp);
-	init_waitqueue_head(&isert_conn->conn_wait);
-	init_waitqueue_head(&isert_conn->conn_wait_comp_err);
+	init_completion(&isert_conn->conn_wait);
+	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
-	kref_get(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
 
 	cma_id->context = isert_conn;
@@ -451,11 +467,11 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		goto out_conn_dev;
 
 	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node);
+	list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list);
 	mutex_unlock(&isert_np->np_accept_mutex);
 
-	pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np);
-	wake_up(&isert_np->np_accept_wq);
+	pr_debug("isert_connect_request() up np_sem np: %p\n", np);
+	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -513,7 +529,9 @@ isert_connect_release(struct isert_conn *isert_conn)
 static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
-	return;
+	struct isert_conn *isert_conn = cma_id->context;
+
+	kref_get(&isert_conn->conn_kref);
 }
 
 static void
@@ -542,11 +560,11 @@ isert_disconnect_work(struct work_struct *work)
 
 	pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
 	mutex_lock(&isert_conn->conn_mutex);
-	isert_conn->state = ISER_CONN_DOWN;
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 
 	if (isert_conn->post_recv_buf_count == 0 &&
 	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("Calling wake_up(&isert_conn->conn_wait);\n");
 		mutex_unlock(&isert_conn->conn_mutex);
 		goto wake_up;
 	}
@@ -555,66 +573,71 @@ isert_disconnect_work(struct work_struct *work)
 		isert_put_conn(isert_conn);
 		return;
 	}
-	if (!isert_conn->logout_posted) {
-		pr_debug("Calling rdma_disconnect for !logout_posted from"
-			 " isert_disconnect_work\n");
+
+	if (isert_conn->disconnect) {
+		/* Send DREQ/DREP towards our initiator */
 		rdma_disconnect(isert_conn->conn_cm_id);
-		mutex_unlock(&isert_conn->conn_mutex);
-		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
-		goto wake_up;
 	}
+
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
-	wake_up(&isert_conn->conn_wait);
-	isert_put_conn(isert_conn);
+	complete(&isert_conn->conn_wait);
 }
 
-static void
-isert_disconnected_handler(struct rdma_cm_id *cma_id)
+static int
+isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
 {
-	struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context;
+	struct isert_conn *isert_conn;
+
+	if (!cma_id->qp) {
+		struct isert_np *isert_np = cma_id->context;
+
+		isert_np->np_cm_id = NULL;
+		return -1;
+	}
+
+	isert_conn = (struct isert_conn *)cma_id->context;
 
+	isert_conn->disconnect = disconnect;
 	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
 	schedule_work(&isert_conn->conn_logout_work);
+
+	return 0;
 }
 
 static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
+	bool disconnect = false;
 
 	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
 		 event->event, event->status, cma_id->context, cma_id);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
-		pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n");
 		ret = isert_connect_request(cma_id, event);
+		if (ret)
+			pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
+				event->event, ret);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
-		pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n");
 		isert_connected_handler(cma_id);
 		break;
-	case RDMA_CM_EVENT_DISCONNECTED:
-		pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n");
-		isert_disconnected_handler(cma_id);
-		break;
-	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
+	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
+	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
+		disconnect = true;
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
+		ret = isert_disconnected_handler(cma_id, disconnect);
 		break;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	default:
-		pr_err("Unknown RDMA CMA event: %d\n", event->event);
+		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
 	}
 
-	if (ret != 0) {
-		pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
-		       event->event, ret);
-		dump_stack();
-	}
-
 	return ret;
 }
 
@@ -956,6 +979,8 @@ sequence_cmd:
 
 	if (!rc && dump_payload == false && unsol_data)
 		iscsit_set_unsoliticed_dataout(cmd);
+	else if (dump_payload && imm_data)
+		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
 
 	return 0;
 }
@@ -1193,7 +1218,7 @@ isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
 }
 
 static void
-isert_put_cmd(struct isert_cmd *isert_cmd)
+isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err)
 {
 	struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
 	struct isert_conn *isert_conn = isert_cmd->conn;
@@ -1205,11 +1230,24 @@ isert_put_cmd(struct isert_cmd *isert_cmd)
 	case ISCSI_OP_SCSI_CMD:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
-		if (cmd->data_direction == DMA_TO_DEVICE)
+		if (cmd->data_direction == DMA_TO_DEVICE) {
 			iscsit_stop_dataout_timer(cmd);
+			/*
+			 * Check for special case during comp_err where
+			 * WRITE_PENDING has been handed off from core,
+			 * but requires an extra target_put_sess_cmd()
+			 * before transport_generic_free_cmd() below.
+			 */
+			if (comp_err &&
+			    cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) {
+				struct se_cmd *se_cmd = &cmd->se_cmd;
+
+				target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+			}
+		}
 
 		isert_unmap_cmd(isert_cmd, isert_conn);
 		transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1217,7 +1255,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd)
 	case ISCSI_OP_SCSI_TMFUNC:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1226,7 +1264,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd)
 	case ISCSI_OP_NOOP_OUT:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		/*
@@ -1263,7 +1301,7 @@ isert_unmap_tx_desc(struct iser_tx_desc *tx_desc, struct ib_device *ib_dev)
 
 static void
 isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd,
-		     struct ib_device *ib_dev)
+		     struct ib_device *ib_dev, bool comp_err)
 {
 	if (isert_cmd->sense_buf_dma != 0) {
 		pr_debug("Calling ib_dma_unmap_single for isert_cmd->sense_buf_dma\n");
@@ -1273,7 +1311,7 @@ isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd,
 	}
 
 	isert_unmap_tx_desc(tx_desc, ib_dev);
-	isert_put_cmd(isert_cmd);
+	isert_put_cmd(isert_cmd, comp_err);
 }
 
 static void
@@ -1300,6 +1338,7 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc,
 	}
 
 	cmd->write_data_done = se_cmd->data_length;
+	wr->send_wr_num = 0;
 
 	pr_debug("isert_do_rdma_read_comp, calling target_execute_cmd\n");
 	spin_lock_bh(&cmd->istate_lock);
@@ -1327,22 +1366,19 @@ isert_do_control_comp(struct work_struct *work)
 		iscsit_tmr_post_handler(cmd, cmd->conn);
 
 		cmd->i_state = ISTATE_SENT_STATUS;
-		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
 		break;
 	case ISTATE_SEND_REJECT:
 		pr_debug("Got isert_do_control_comp ISTATE_SEND_REJECT: >>>\n");
 		atomic_dec(&isert_conn->post_send_buf_count);
 
 		cmd->i_state = ISTATE_SENT_STATUS;
-		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
 		break;
 	case ISTATE_SEND_LOGOUTRSP:
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
-		/*
-		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_free_conn()
-		 */
-		isert_conn->logout_posted = true;
+
+		atomic_dec(&isert_conn->post_send_buf_count);
 		iscsit_logout_post_handler(cmd, cmd->conn);
 		break;
 	default:
@@ -1359,6 +1395,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc,
 			  struct ib_device *ib_dev)
 {
 	struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+	struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
 
 	if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
 	    cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
@@ -1369,10 +1406,10 @@ isert_response_completion(struct iser_tx_desc *tx_desc,
 		queue_work(isert_comp_wq, &isert_cmd->comp_work);
 		return;
 	}
-	atomic_dec(&isert_conn->post_send_buf_count);
+	atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	cmd->i_state = ISTATE_SENT_STATUS;
-	isert_completion_put(tx_desc, isert_cmd, ib_dev);
+	isert_completion_put(tx_desc, isert_cmd, ib_dev, false);
 }
 
 static void
@@ -1407,7 +1444,7 @@ isert_send_completion(struct iser_tx_desc *tx_desc,
 	case ISER_IB_RDMA_READ:
 		pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n");
 
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 		isert_completion_rdma_read(tx_desc, isert_cmd);
 		break;
 	default:
@@ -1418,31 +1455,40 @@ isert_send_completion(struct iser_tx_desc *tx_desc,
 }
 
 static void
-isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
+isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
 {
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
 
-	if (tx_desc) {
-		struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+	if (!isert_cmd)
+		isert_unmap_tx_desc(tx_desc, ib_dev);
+	else
+		isert_completion_put(tx_desc, isert_cmd, ib_dev, true);
+}
 
-		if (!isert_cmd)
-			isert_unmap_tx_desc(tx_desc, ib_dev);
-		else
-			isert_completion_put(tx_desc, isert_cmd, ib_dev);
+static void
+isert_cq_rx_comp_err(struct isert_conn *isert_conn)
+{
+	struct iscsi_conn *conn = isert_conn->conn;
+
+	if (isert_conn->post_recv_buf_count)
+		return;
+
+	if (conn->sess) {
+		target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+		target_wait_for_sess_cmds(conn->sess->se_sess);
 	}
 
-	if (isert_conn->post_recv_buf_count == 0 &&
-	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
-		pr_debug("Calling wake_up from isert_cq_comp_err\n");
+	while (atomic_read(&isert_conn->post_send_buf_count))
+		msleep(3000);
 
-		mutex_lock(&isert_conn->conn_mutex);
-		if (isert_conn->state != ISER_CONN_DOWN)
-			isert_conn->state = ISER_CONN_TERMINATING;
-		mutex_unlock(&isert_conn->conn_mutex);
+	mutex_lock(&isert_conn->conn_mutex);
+	isert_conn->state = ISER_CONN_DOWN;
+	mutex_unlock(&isert_conn->conn_mutex);
 
-		wake_up(&isert_conn->conn_wait_comp_err);
-	}
+	iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+
+	complete(&isert_conn->conn_wait_comp_err);
 }
 
 static void
@@ -1467,7 +1513,7 @@ isert_cq_tx_work(struct work_struct *work)
 			pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n");
 			pr_debug("TX wc.status: 0x%08x\n", wc.status);
 			atomic_dec(&isert_conn->post_send_buf_count);
-			isert_cq_comp_err(tx_desc, isert_conn);
+			isert_cq_tx_comp_err(tx_desc, isert_conn);
 		}
 	}
 
@@ -1509,7 +1555,7 @@ isert_cq_rx_work(struct work_struct *work)
 				pr_debug("RX wc.status: 0x%08x\n", wc.status);
 
 			isert_conn->post_recv_buf_count--;
-			isert_cq_comp_err(NULL, isert_conn);
+			isert_cq_rx_comp_err(isert_conn);
 		}
 	}
 
@@ -1819,12 +1865,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 	isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
 	isert_init_send_wr(isert_cmd, &isert_cmd->tx_desc.send_wr);
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Posted RDMA_WRITE + Response for iSER Data READ\n");
 	return 1;
@@ -1927,12 +1973,12 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 		data_left -= data_len;
 	}
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Posted RDMA_READ memory for ISER Data WRITE\n");
 	return 0;
@@ -2012,7 +2058,7 @@ isert_setup_np(struct iscsi_np *np,
 		pr_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	init_waitqueue_head(&isert_np->np_accept_wq);
+	sema_init(&isert_np->np_sem, 0);
 	mutex_init(&isert_np->np_accept_mutex);
 	INIT_LIST_HEAD(&isert_np->np_accept_list);
 	init_completion(&isert_np->np_login_comp);
@@ -2061,18 +2107,6 @@ out:
 }
 
 static int
-isert_check_accept_queue(struct isert_np *isert_np)
-{
-	int empty;
-
-	mutex_lock(&isert_np->np_accept_mutex);
-	empty = list_empty(&isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
-
-	return empty;
-}
-
-static int
 isert_rdma_accept(struct isert_conn *isert_conn)
 {
 	struct rdma_cm_id *cm_id = isert_conn->conn_cm_id;
@@ -2156,16 +2190,19 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int max_accept = 0, ret;
 
 accept_wait:
-	ret = wait_event_interruptible(isert_np->np_accept_wq,
-			!isert_check_accept_queue(isert_np) ||
-			np->np_thread_state == ISCSI_NP_THREAD_RESET);
+	ret = down_interruptible(&isert_np->np_sem);
 	if (max_accept > 5)
 		return -ENODEV;
 
 	spin_lock_bh(&np->np_thread_lock);
-	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+	if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+		pr_debug("np_thread_state %d for isert_accept_np\n",
+			 np->np_thread_state);
+		/**
+		 * No point in stalling here when np_thread
+		 * is in state RESET/SHUTDOWN/EXIT - bail
+		 **/
 		return -ENODEV;
 	}
 	spin_unlock_bh(&np->np_thread_lock);
@@ -2204,69 +2241,45 @@ isert_free_np(struct iscsi_np *np)
 {
 	struct isert_np *isert_np = (struct isert_np *)np->np_context;
 
-	rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->np_cm_id)
+		rdma_destroy_id(isert_np->np_cm_id);
 
 	np->np_context = NULL;
 	kfree(isert_np);
 }
 
-static int isert_check_state(struct isert_conn *isert_conn, int state)
-{
-	int ret;
-
-	mutex_lock(&isert_conn->conn_mutex);
-	ret = (isert_conn->state == state);
-	mutex_unlock(&isert_conn->conn_mutex);
-
-	return ret;
-}
-
-static void isert_free_conn(struct iscsi_conn *conn)
+static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
 
-	pr_debug("isert_free_conn: Starting \n");
-	/*
-	 * Decrement post_send_buf_count for special case when called
-	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
-	 */
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->logout_posted)
-		atomic_dec(&isert_conn->post_send_buf_count);
+	pr_debug("isert_wait_conn: Starting \n");
 
-	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
-		pr_debug("Calling rdma_disconnect from isert_free_conn\n");
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->conn_cm_id) {
+		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
 	/*
 	 * Only wait for conn_wait_comp_err if the isert_conn made it
 	 * into full feature phase..
 	 */
-	if (isert_conn->state == ISER_CONN_UP) {
-		pr_debug("isert_free_conn: Before wait_event comp_err %d\n",
-			 isert_conn->state);
-		mutex_unlock(&isert_conn->conn_mutex);
-
-		wait_event(isert_conn->conn_wait_comp_err,
-			  (isert_check_state(isert_conn, ISER_CONN_TERMINATING)));
-
-		wait_event(isert_conn->conn_wait,
-			  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
-
-		isert_put_conn(isert_conn);
-		return;
-	}
 	if (isert_conn->state == ISER_CONN_INIT) {
 		mutex_unlock(&isert_conn->conn_mutex);
-		isert_put_conn(isert_conn);
 		return;
 	}
-	pr_debug("isert_free_conn: wait_event conn_wait %d\n",
-		 isert_conn->state);
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 	mutex_unlock(&isert_conn->conn_mutex);
 
-	wait_event(isert_conn->conn_wait,
-		  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
+	wait_for_completion(&isert_conn->conn_wait_comp_err);
+
+	wait_for_completion(&isert_conn->conn_wait);
+	isert_put_conn(isert_conn);
+}
+
+static void isert_free_conn(struct iscsi_conn *conn)
+{
+	struct isert_conn *isert_conn = conn->context;
 
 	isert_put_conn(isert_conn);
 }
@@ -2278,6 +2291,7 @@ static struct iscsit_transport iser_target_transport = {
 	.iscsit_setup_np	= isert_setup_np,
 	.iscsit_accept_np	= isert_accept_np,
 	.iscsit_free_np		= isert_free_np,
+	.iscsit_wait_conn	= isert_wait_conn,
 	.iscsit_free_conn	= isert_free_conn,
 	.iscsit_alloc_cmd	= isert_alloc_cmd,
 	.iscsit_get_login_rx	= isert_get_login_rx,
@@ -2328,6 +2342,7 @@ destroy_rx_wq:
 
 static void __exit isert_exit(void)
 {
+	flush_scheduled_work();
 	kmem_cache_destroy(isert_cmd_cache);
 	destroy_workqueue(isert_comp_wq);
 	destroy_workqueue(isert_rx_wq);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 5795c82a2306..032f65abee36 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -78,7 +78,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	bool			logout_posted;
 	int			post_recv_buf_count;
 	atomic_t		post_send_buf_count;
 	u32			responder_resources;
@@ -103,9 +102,10 @@ struct isert_conn {
 	struct isert_device	*conn_device;
 	struct work_struct	conn_logout_work;
 	struct mutex		conn_mutex;
-	wait_queue_head_t	conn_wait;
-	wait_queue_head_t	conn_wait_comp_err;
+	struct completion	conn_wait;
+	struct completion	conn_wait_comp_err;
 	struct kref		conn_kref;
+	bool			disconnect;
 };
 
 #define ISERT_MAX_CQ 64
@@ -131,7 +131,7 @@ struct isert_device {
 };
 
 struct isert_np {
-	wait_queue_head_t	np_accept_wq;
+	struct semaphore	np_sem;
 	struct rdma_cm_id	*np_cm_id;
 	struct mutex		np_accept_mutex;
 	struct list_head	np_accept_list;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 7ccf3284dda3..35dd5ff662f1 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -93,6 +93,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr);
 static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event);
 
 static struct scsi_transport_template *ib_srp_transport_template;
+static struct workqueue_struct *srp_remove_wq;
 
 static struct ib_client srp_client = {
 	.name   = "srp",
@@ -456,7 +457,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
 	spin_unlock_irq(&target->lock);
 
 	if (changed)
-		queue_work(system_long_wq, &target->remove_work);
+		queue_work(srp_remove_wq, &target->remove_work);
 
 	return changed;
 }
@@ -1300,14 +1301,13 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
 			     PFX "Recv failed with error code %d\n", res);
 }
 
-static void srp_handle_qp_err(enum ib_wc_status wc_status,
-			      enum ib_wc_opcode wc_opcode,
+static void srp_handle_qp_err(enum ib_wc_status wc_status, bool send_err,
 			      struct srp_target_port *target)
 {
 	if (target->connected && !target->qp_in_error) {
 		shost_printk(KERN_ERR, target->scsi_host,
 			     PFX "failed %s status %d\n",
-			     wc_opcode & IB_WC_RECV ? "receive" : "send",
+			     send_err ? "send" : "receive",
 			     wc_status);
 	}
 	target->qp_in_error = true;
@@ -1323,7 +1323,7 @@ static void srp_recv_completion(struct ib_cq *cq, void *target_ptr)
 		if (likely(wc.status == IB_WC_SUCCESS)) {
 			srp_handle_recv(target, &wc);
 		} else {
-			srp_handle_qp_err(wc.status, wc.opcode, target);
+			srp_handle_qp_err(wc.status, false, target);
 		}
 	}
 }
@@ -1339,7 +1339,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
 			iu = (struct srp_iu *) (uintptr_t) wc.wr_id;
 			list_add(&iu->list, &target->free_tx);
 		} else {
-			srp_handle_qp_err(wc.status, wc.opcode, target);
+			srp_handle_qp_err(wc.status, true, target);
 		}
 	}
 }
@@ -1410,6 +1410,12 @@ err_unmap:
 err_iu:
 	srp_put_tx_iu(target, iu, SRP_IU_CMD);
 
+	/*
+	 * Avoid that the loops that iterate over the request ring can
+	 * encounter a dangling SCSI command pointer.
+	 */
+	req->scmnd = NULL;
+
 	spin_lock_irqsave(&target->lock, flags);
 	list_add(&req->list, &target->free_reqs);
 
@@ -2525,9 +2531,10 @@ static void srp_remove_one(struct ib_device *device)
 		spin_unlock(&host->target_lock);
 
 		/*
-		 * Wait for target port removal tasks.
+		 * Wait for tl_err and target port removal tasks.
 		 */
 		flush_workqueue(system_long_wq);
+		flush_workqueue(srp_remove_wq);
 
 		kfree(host);
 	}
@@ -2572,16 +2579,22 @@ static int __init srp_init_module(void)
 		indirect_sg_entries = cmd_sg_entries;
 	}
 
+	srp_remove_wq = create_workqueue("srp_remove");
+	if (IS_ERR(srp_remove_wq)) {
+		ret = PTR_ERR(srp_remove_wq);
+		goto out;
+	}
+
+	ret = -ENOMEM;
 	ib_srp_transport_template =
 		srp_attach_transport(&ib_srp_transport_functions);
 	if (!ib_srp_transport_template)
-		return -ENOMEM;
+		goto destroy_wq;
 
 	ret = class_register(&srp_class);
 	if (ret) {
 		pr_err("couldn't register class infiniband_srp\n");
-		srp_release_transport(ib_srp_transport_template);
-		return ret;
+		goto release_tr;
 	}
 
 	ib_sa_register_client(&srp_sa_client);
@@ -2589,13 +2602,22 @@ static int __init srp_init_module(void)
 	ret = ib_register_client(&srp_client);
 	if (ret) {
 		pr_err("couldn't register IB client\n");
-		srp_release_transport(ib_srp_transport_template);
-		ib_sa_unregister_client(&srp_sa_client);
-		class_unregister(&srp_class);
-		return ret;
+		goto unreg_sa;
 	}
 
-	return 0;
+out:
+	return ret;
+
+unreg_sa:
+	ib_sa_unregister_client(&srp_sa_client);
+	class_unregister(&srp_class);
+
+release_tr:
+	srp_release_transport(ib_srp_transport_template);
+
+destroy_wq:
+	destroy_workqueue(srp_remove_wq);
+	goto out;
 }
 
 static void __exit srp_cleanup_module(void)
@@ -2604,6 +2626,7 @@ static void __exit srp_cleanup_module(void)
 	ib_sa_unregister_client(&srp_sa_client);
 	class_unregister(&srp_class);
 	srp_release_transport(ib_srp_transport_template);
+	destroy_workqueue(srp_remove_wq);
 }
 
 module_init(srp_init_module);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 3f3f0416fbdd..fcf9f87bcfd9 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1078,6 +1078,7 @@ static void srpt_unmap_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 				 struct srpt_send_ioctx *ioctx)
 {
+	struct ib_device *dev = ch->sport->sdev->device;
 	struct se_cmd *cmd;
 	struct scatterlist *sg, *sg_orig;
 	int sg_cnt;
@@ -1124,7 +1125,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 
 	db = ioctx->rbufs;
 	tsize = cmd->data_length;
-	dma_len = sg_dma_len(&sg[0]);
+	dma_len = ib_sg_dma_len(dev, &sg[0]);
 	riu = ioctx->rdma_ius;
 
 	/*
@@ -1155,7 +1156,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 					++j;
 					if (j < count) {
 						sg = sg_next(sg);
-						dma_len = sg_dma_len(sg);
+						dma_len = ib_sg_dma_len(
+								dev, sg);
 					}
 				}
 			} else {
@@ -1192,8 +1194,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 	tsize = cmd->data_length;
 	riu = ioctx->rdma_ius;
 	sg = sg_orig;
-	dma_len = sg_dma_len(&sg[0]);
-	dma_addr = sg_dma_address(&sg[0]);
+	dma_len = ib_sg_dma_len(dev, &sg[0]);
+	dma_addr = ib_sg_dma_address(dev, &sg[0]);
 
 	/* this second loop is really mapped sg_addres to rdma_iu->ib_sge */
 	for (i = 0, j = 0;
@@ -1216,8 +1218,10 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 					++j;
 					if (j < count) {
 						sg = sg_next(sg);
-						dma_len = sg_dma_len(sg);
-						dma_addr = sg_dma_address(sg);
+						dma_len = ib_sg_dma_len(
+								dev, sg);
+						dma_addr = ib_sg_dma_address(
+								dev, sg);
 					}
 				}
 			} else {
@@ -1588,7 +1592,7 @@ static int srpt_build_tskmgmt_rsp(struct srpt_rdma_ch *ch,
 	int resp_data_len;
 	int resp_len;
 
-	resp_data_len = (rsp_code == SRP_TSK_MGMT_SUCCESS) ? 0 : 4;
+	resp_data_len = 4;
 	resp_len = sizeof(*srp_rsp) + resp_data_len;
 
 	srp_rsp = ioctx->ioctx.buf;
@@ -1600,11 +1604,9 @@ static int srpt_build_tskmgmt_rsp(struct srpt_rdma_ch *ch,
 				    + atomic_xchg(&ch->req_lim_delta, 0));
 	srp_rsp->tag = tag;
 
-	if (rsp_code != SRP_TSK_MGMT_SUCCESS) {
-		srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID;
-		srp_rsp->resp_data_len = cpu_to_be32(resp_data_len);
-		srp_rsp->data[3] = rsp_code;
-	}
+	srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID;
+	srp_rsp->resp_data_len = cpu_to_be32(resp_data_len);
+	srp_rsp->data[3] = rsp_code;
 
 	return resp_len;
 }
@@ -2099,6 +2101,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	if (!qp_init)
 		goto out;
 
+retry:
 	ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
 			      ch->rq_size + srp_sq_size, 0);
 	if (IS_ERR(ch->cq)) {
@@ -2122,6 +2125,13 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	ch->qp = ib_create_qp(sdev->pd, qp_init);
 	if (IS_ERR(ch->qp)) {
 		ret = PTR_ERR(ch->qp);
+		if (ret == -ENOMEM) {
+			srp_sq_size /= 2;
+			if (srp_sq_size >= MIN_SRPT_SQ_SIZE) {
+				ib_destroy_cq(ch->cq);
+				goto retry;
+			}
+		}
 		printk(KERN_ERR "failed to create_qp ret= %d\n", ret);
 		goto err_destroy_cq;
 	}
@@ -2358,6 +2368,8 @@ static void srpt_release_channel_work(struct work_struct *w)
 	transport_deregister_session(se_sess);
 	ch->sess = NULL;
 
+	ib_destroy_cm_id(ch->cm_id);
+
 	srpt_destroy_ch_ib(ch);
 
 	srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring,
@@ -2368,8 +2380,6 @@ static void srpt_release_channel_work(struct work_struct *w)
 	list_del(&ch->list);
 	spin_unlock_irq(&sdev->spinlock);
 
-	ib_destroy_cm_id(ch->cm_id);
-
 	if (ch->release_done)
 		complete(ch->release_done);
 
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 38b523a1ece0..a11ff74a5127 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -80,7 +80,7 @@ config INPUT_MATRIXKMAP
 comment "Userland interfaces"
 
 config INPUT_MOUSEDEV
-	tristate "Mouse interface" if EXPERT
+	tristate "Mouse interface"
 	default y
 	help
 	  Say Y here if you want your mouse to be accessible as char devices
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index f0f8928b3c8a..c122dd2adc22 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -18,6 +18,8 @@
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/input/mt.h>
@@ -289,7 +291,11 @@ static int evdev_release(struct inode *inode, struct file *file)
 	mutex_unlock(&evdev->mutex);
 
 	evdev_detach_client(evdev, client);
-	kfree(client);
+
+	if (is_vmalloc_addr(client))
+		vfree(client);
+	else
+		kfree(client);
 
 	evdev_close_device(evdev);
 
@@ -309,12 +315,14 @@ static int evdev_open(struct inode *inode, struct file *file)
 {
 	struct evdev *evdev = container_of(inode->i_cdev, struct evdev, cdev);
 	unsigned int bufsize = evdev_compute_buffer_size(evdev->handle.dev);
+	unsigned int size = sizeof(struct evdev_client) +
+					bufsize * sizeof(struct input_event);
 	struct evdev_client *client;
 	int error;
 
-	client = kzalloc(sizeof(struct evdev_client) +
-				bufsize * sizeof(struct input_event),
-			 GFP_KERNEL);
+	client = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!client)
+		client = vzalloc(size);
 	if (!client)
 		return -ENOMEM;
 
diff --git a/drivers/input/input.c b/drivers/input/input.c
index c04469928925..a161021c4526 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -257,9 +257,10 @@ static int input_handle_abs_event(struct input_dev *dev,
 }
 
 static int input_get_disposition(struct input_dev *dev,
-			  unsigned int type, unsigned int code, int value)
+			  unsigned int type, unsigned int code, int *pval)
 {
 	int disposition = INPUT_IGNORE_EVENT;
+	int value = *pval;
 
 	switch (type) {
 
@@ -357,6 +358,7 @@ static int input_get_disposition(struct input_dev *dev,
 		break;
 	}
 
+	*pval = value;
 	return disposition;
 }
 
@@ -365,7 +367,7 @@ static void input_handle_event(struct input_dev *dev,
 {
 	int disposition;
 
-	disposition = input_get_disposition(dev, type, code, value);
+	disposition = input_get_disposition(dev, type, code, &value);
 
 	if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event)
 		dev->event(dev, type, code, value);
@@ -1866,6 +1868,10 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int
 		break;
 
 	case EV_ABS:
+		input_alloc_absinfo(dev);
+		if (!dev->absinfo)
+			return;
+
 		__set_bit(code, dev->absbit);
 		break;
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index fa061d46527f..856c1b03e22d 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -167,6 +167,7 @@ static const struct xpad_device {
 	{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
 	{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
+	{ 0x1689, 0xfd01, "Razer Onza Classic Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1bad, 0xf016, "Mad Catz Xbox 360 Controller", 0, XTYPE_XBOX360 },
@@ -1001,9 +1002,19 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 		}
 
 		ep_irq_in = &intf->cur_altsetting->endpoint[1].desc;
-		usb_fill_bulk_urb(xpad->bulk_out, udev,
-				usb_sndbulkpipe(udev, ep_irq_in->bEndpointAddress),
-				xpad->bdata, XPAD_PKT_LEN, xpad_bulk_out, xpad);
+		if (usb_endpoint_is_bulk_out(ep_irq_in)) {
+			usb_fill_bulk_urb(xpad->bulk_out, udev,
+					  usb_sndbulkpipe(udev,
+							  ep_irq_in->bEndpointAddress),
+					  xpad->bdata, XPAD_PKT_LEN,
+					  xpad_bulk_out, xpad);
+		} else {
+			usb_fill_int_urb(xpad->bulk_out, udev,
+					 usb_sndintpipe(udev,
+							ep_irq_in->bEndpointAddress),
+					 xpad->bdata, XPAD_PKT_LEN,
+					 xpad_bulk_out, xpad, 0);
+		}
 
 		/*
 		 * Submit the int URB immediately rather than waiting for open
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 7ac9c9818d55..292f3240e67b 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -2,7 +2,7 @@
 # Input core configuration
 #
 menuconfig INPUT_KEYBOARD
-	bool "Keyboards" if EXPERT || !X86
+	bool "Keyboards"
 	default y
 	help
 	  Say Y here, and a list of supported keyboards will be displayed.
@@ -67,7 +67,7 @@ config KEYBOARD_ATARI
 	  module will be called atakbd.
 
 config KEYBOARD_ATKBD
-	tristate "AT keyboard" if EXPERT || !X86
+	tristate "AT keyboard"
 	default y
 	select SERIO
 	select SERIO_LIBPS2
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 2626773ff29b..6f5d79569136 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -243,6 +243,12 @@ static void (*atkbd_platform_fixup)(struct atkbd *, const void *data);
 static void *atkbd_platform_fixup_data;
 static unsigned int (*atkbd_platform_scancode_fixup)(struct atkbd *, unsigned int);
 
+/*
+ * Certain keyboards to not like ATKBD_CMD_RESET_DIS and stop responding
+ * to many commands until full reset (ATKBD_CMD_RESET_BAT) is performed.
+ */
+static bool atkbd_skip_deactivate;
+
 static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf,
 				ssize_t (*handler)(struct atkbd *, char *));
 static ssize_t atkbd_attr_set_helper(struct device *dev, const char *buf, size_t count,
@@ -768,7 +774,8 @@ static int atkbd_probe(struct atkbd *atkbd)
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
  */
-	atkbd_deactivate(atkbd);
+	if (!atkbd_skip_deactivate)
+		atkbd_deactivate(atkbd);
 
 	return 0;
 }
@@ -1638,6 +1645,12 @@ static int __init atkbd_setup_scancode_fixup(const struct dmi_system_id *id)
 	return 1;
 }
 
+static int __init atkbd_deactivate_fixup(const struct dmi_system_id *id)
+{
+	atkbd_skip_deactivate = true;
+	return 1;
+}
+
 static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 	{
 		.matches = {
@@ -1775,6 +1788,12 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 		.callback = atkbd_setup_scancode_fixup,
 		.driver_data = atkbd_oqo_01plus_scancode_fixup,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+		},
+		.callback = atkbd_deactivate_fixup,
+	},
 	{ }
 };
 
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
index 7a04f54ef961..e7e12a5f5c2d 100644
--- a/drivers/input/misc/arizona-haptics.c
+++ b/drivers/input/misc/arizona-haptics.c
@@ -77,16 +77,14 @@ static void arizona_haptics_work(struct work_struct *work)
 			return;
 		}
 
+		mutex_unlock(dapm_mutex);
+
 		ret = snd_soc_dapm_sync(arizona->dapm);
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
-
-		mutex_unlock(dapm_mutex);
-
 	} else {
 		/* This disable sequence will be a noop if already enabled */
 		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
@@ -99,16 +97,15 @@ static void arizona_haptics_work(struct work_struct *work)
 			return;
 		}
 
+		mutex_unlock(dapm_mutex);
+
 		ret = snd_soc_dapm_sync(arizona->dapm);
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
-		mutex_unlock(dapm_mutex);
-
 		ret = regmap_update_bits(arizona->regmap,
 					 ARIZONA_HAPTICS_CONTROL_1,
 					 ARIZONA_HAP_CTRL_MASK,
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 7c5d72a6a26a..19e070f16e6b 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -873,7 +873,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse)
 {
 	struct alps_data *priv = psmouse->private;
 
-	if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */
+	/*
+	 * Check if we are dealing with a bare PS/2 packet, presumably from
+	 * a device connected to the external PS/2 port. Because bare PS/2
+	 * protocol does not have enough constant bits to self-synchronize
+	 * properly we only do this if the device is fully synchronized.
+	 */
+	if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) {
 		if (psmouse->pktcnt == 3) {
 			alps_report_bare_ps2_packet(psmouse, psmouse->packet,
 						    true);
@@ -1816,6 +1822,9 @@ int alps_init(struct psmouse *psmouse)
 	/* We are having trouble resyncing ALPS touchpads so disable it for now */
 	psmouse->resync_time = 0;
 
+	/* Allow 2 invalid packets without resetting device */
+	psmouse->resetafter = psmouse->pktsize * 2;
+
 	return 0;
 
 init_fail:
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index f51765fff054..0aaea7ad6cee 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -410,7 +410,6 @@ static int cypress_set_input_params(struct input_dev *input,
 	__clear_bit(REL_X, input->relbit);
 	__clear_bit(REL_Y, input->relbit);
 
-	__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
 	__set_bit(EV_KEY, input->evbit);
 	__set_bit(BTN_LEFT, input->keybit);
 	__set_bit(BTN_RIGHT, input->keybit);
@@ -439,7 +438,7 @@ static int cypress_get_finger_count(unsigned char header_byte)
 			case 2: return 5;
 			default:
 				/* Invalid contact (e.g. palm). Ignore it. */
-				return -1;
+				return 0;
 		}
 	}
 
@@ -452,17 +451,10 @@ static int cypress_parse_packet(struct psmouse *psmouse,
 {
 	unsigned char *packet = psmouse->packet;
 	unsigned char header_byte = packet[0];
-	int contact_cnt;
 
 	memset(report_data, 0, sizeof(struct cytp_report_data));
 
-	contact_cnt = cypress_get_finger_count(header_byte);
-
-	if (contact_cnt < 0) /* e.g. palm detect */
-		return -EINVAL;
-
-	report_data->contact_cnt = contact_cnt;
-
+	report_data->contact_cnt = cypress_get_finger_count(header_byte);
 	report_data->tap = (header_byte & ABS_MULTIFINGER_TAP) ? 1 : 0;
 
 	if (report_data->contact_cnt == 1) {
@@ -535,11 +527,9 @@ static void cypress_process_packet(struct psmouse *psmouse, bool zero_pkt)
 	int slots[CYTP_MAX_MT_SLOTS];
 	int n;
 
-	if (cypress_parse_packet(psmouse, cytp, &report_data))
-		return;
+	cypress_parse_packet(psmouse, cytp, &report_data);
 
 	n = report_data.contact_cnt;
-
 	if (n > CYTP_MAX_MT_SLOTS)
 		n = CYTP_MAX_MT_SLOTS;
 
@@ -605,10 +595,6 @@ static psmouse_ret_t cypress_validate_byte(struct psmouse *psmouse)
 		return PSMOUSE_BAD_DATA;
 
 	contact_cnt = cypress_get_finger_count(packet[0]);
-
-	if (contact_cnt < 0)
-		return PSMOUSE_BAD_DATA;
-
 	if (cytp->mode & CYTP_BIT_ABS_NO_PRESSURE)
 		cypress_set_packet_size(psmouse, contact_cnt == 2 ? 7 : 4);
 	else
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 1e8e42fb03a4..85e75239c814 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/input.h>
@@ -472,8 +473,15 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 	input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
 	input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2);
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_report_abs(dev, ABS_PRESSURE, pres);
 	input_report_abs(dev, ABS_TOOL_WIDTH, width);
 
@@ -483,9 +491,17 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 static void elantech_input_sync_v4(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
+	struct elantech_data *etd = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_mt_report_pointer_emulation(dev, true);
 	input_sync(dev);
 }
@@ -800,7 +816,11 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		break;
 
 	case 3:
-		etd->reg_10 = 0x0b;
+		if (etd->set_hw_resolution)
+			etd->reg_10 = 0x0b;
+		else
+			etd->reg_10 = 0x01;
+
 		if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
 			rc = -1;
 
@@ -954,6 +974,44 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
 }
 
 /*
+ * Advertise INPUT_PROP_BUTTONPAD for clickpads. The testing of bit 12 in
+ * fw_version for this is based on the following fw_version & caps table:
+ *
+ * Laptop-model:           fw_version:     caps:           buttons:
+ * Acer S3                 0x461f00        10, 13, 0e      clickpad
+ * Acer S7-392             0x581f01        50, 17, 0d      clickpad
+ * Acer V5-131             0x461f02        01, 16, 0c      clickpad
+ * Acer V5-551             0x461f00        ?               clickpad
+ * Asus K53SV              0x450f01        78, 15, 0c      2 hw buttons
+ * Asus G46VW              0x460f02        00, 18, 0c      2 hw buttons
+ * Asus G750JX             0x360f00        00, 16, 0c      2 hw buttons
+ * Asus UX31               0x361f00        20, 15, 0e      clickpad
+ * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
+ * Avatar AVIU-145A2       0x361f00        ?               clickpad
+ * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
+ * Lenovo L430             0x350f02        b9, 15, 0c      2 hw buttons (*)
+ * Samsung NF210           0x150b00        78, 14, 0a      2 hw buttons
+ * Samsung NP770Z5E        0x575f01        10, 15, 0f      clickpad
+ * Samsung NP700Z5B        0x361f06        21, 15, 0f      clickpad
+ * Samsung NP900X3E-A02    0x575f03        ?               clickpad
+ * Samsung NP-QX410        0x851b00        19, 14, 0c      clickpad
+ * Samsung RC512           0x450f00        08, 15, 0c      2 hw buttons
+ * Samsung RF710           0x450f00        ?               2 hw buttons
+ * System76 Pangolin       0x250f01        ?               2 hw buttons
+ * (*) + 3 trackpoint buttons
+ */
+static void elantech_set_buttonpad_prop(struct psmouse *psmouse)
+{
+	struct input_dev *dev = psmouse->dev;
+	struct elantech_data *etd = psmouse->private;
+
+	if (etd->fw_version & 0x001000) {
+		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
+		__clear_bit(BTN_RIGHT, dev->keybit);
+	}
+}
+
+/*
  * Set the appropriate event bits for the input subsystem
  */
 static int elantech_set_input_params(struct psmouse *psmouse)
@@ -996,6 +1054,8 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 		__set_bit(INPUT_PROP_SEMI_MT, dev->propbit);
 		/* fall through */
 	case 3:
+		if (etd->hw_version == 3)
+			elantech_set_buttonpad_prop(psmouse);
 		input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
 		input_set_abs_params(dev, ABS_Y, y_min, y_max, 0, 0);
 		if (etd->reports_pressure) {
@@ -1017,9 +1077,7 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 			 */
 			psmouse_warn(psmouse, "couldn't query resolution data.\n");
 		}
-		/* v4 is clickpad, with only one button. */
-		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
-		__clear_bit(BTN_RIGHT, dev->keybit);
+		elantech_set_buttonpad_prop(psmouse);
 		__set_bit(BTN_TOOL_QUADTAP, dev->keybit);
 		/* For X to recognize me as touchpad. */
 		input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
@@ -1165,6 +1223,13 @@ static bool elantech_is_signature_valid(const unsigned char *param)
 	if (param[1] == 0)
 		return true;
 
+	/*
+	 * Some models have a revision higher then 20. Meaning param[2] may
+	 * be 10 or 20, skip the rates check for these.
+	 */
+	if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+		return true;
+
 	for (i = 0; i < ARRAY_SIZE(rates); i++)
 		if (param[2] == rates[i])
 			return false;
@@ -1262,6 +1327,23 @@ static int elantech_reconnect(struct psmouse *psmouse)
 }
 
 /*
+ * Some hw_version 3 models go into error state when we try to set
+ * bit 3 and/or bit 1 of r10.
+ */
+static const struct dmi_system_id no_hw_res_dmi_table[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		/* Gigabyte U2442 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "U2442"),
+		},
+	},
+#endif
+	{ }
+};
+
+/*
  * determine hardware version and set some properties according to it.
  */
 static int elantech_set_properties(struct elantech_data *etd)
@@ -1312,6 +1394,9 @@ static int elantech_set_properties(struct elantech_data *etd)
 			etd->reports_pressure = true;
 	}
 
+	/* Enable real hardware resolution on hw_version 3 ? */
+	etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
+
 	return 0;
 }
 
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index 46db3be45ac9..c1c15ab6872d 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -129,6 +129,7 @@ struct elantech_data {
 	bool paritycheck;
 	bool jumpy_cursor;
 	bool reports_pressure;
+	bool set_hw_resolution;
 	unsigned char hw_version;
 	unsigned int fw_version;
 	unsigned int single_finger_reports;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index b2420ae19e14..d1c47d135c07 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -265,11 +265,22 @@ static int synaptics_identify(struct psmouse *psmouse)
  * Read touchpad resolution and maximum reported coordinates
  * Resolution is left zero if touchpad does not support the query
  */
+
+static const int *quirk_min_max;
+
 static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
 
+	if (quirk_min_max) {
+		priv->x_min = quirk_min_max[0];
+		priv->x_max = quirk_min_max[1];
+		priv->y_min = quirk_min_max[2];
+		priv->y_max = quirk_min_max[3];
+		return 0;
+	}
+
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
 
@@ -538,10 +549,61 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 			 ((buf[0] & 0x04) >> 1) |
 			 ((buf[3] & 0x04) >> 2));
 
+		if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
+			SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
+		    hw->w == 2) {
+			synaptics_parse_agm(buf, priv, hw);
+			return 1;
+		}
+
+		hw->x = (((buf[3] & 0x10) << 8) |
+			 ((buf[1] & 0x0f) << 8) |
+			 buf[4]);
+		hw->y = (((buf[3] & 0x20) << 7) |
+			 ((buf[1] & 0xf0) << 4) |
+			 buf[5]);
+		hw->z = buf[2];
+
 		hw->left  = (buf[0] & 0x01) ? 1 : 0;
 		hw->right = (buf[0] & 0x02) ? 1 : 0;
 
-		if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
+		if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) {
+			/*
+			 * ForcePads, like Clickpads, use middle button
+			 * bits to report primary button clicks.
+			 * Unfortunately they report primary button not
+			 * only when user presses on the pad above certain
+			 * threshold, but also when there are more than one
+			 * finger on the touchpad, which interferes with
+			 * out multi-finger gestures.
+			 */
+			if (hw->z == 0) {
+				/* No contacts */
+				priv->press = priv->report_press = false;
+			} else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) {
+				/*
+				 * Single-finger touch with pressure above
+				 * the threshold. If pressure stays long
+				 * enough, we'll start reporting primary
+				 * button. We rely on the device continuing
+				 * sending data even if finger does not
+				 * move.
+				 */
+				if  (!priv->press) {
+					priv->press_start = jiffies;
+					priv->press = true;
+				} else if (time_after(jiffies,
+						priv->press_start +
+							msecs_to_jiffies(50))) {
+					priv->report_press = true;
+				}
+			} else {
+				priv->press = false;
+			}
+
+			hw->left = priv->report_press;
+
+		} else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
 			/*
 			 * Clickpad's button is transmitted as middle button,
 			 * however, since it is primary button, we will report
@@ -560,21 +622,6 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 			hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0;
 		}
 
-		if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
-			SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
-		    hw->w == 2) {
-			synaptics_parse_agm(buf, priv, hw);
-			return 1;
-		}
-
-		hw->x = (((buf[3] & 0x10) << 8) |
-			 ((buf[1] & 0x0f) << 8) |
-			 buf[4]);
-		hw->y = (((buf[3] & 0x20) << 7) |
-			 ((buf[1] & 0xf0) << 4) |
-			 buf[5]);
-		hw->z = buf[2];
-
 		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) &&
 		    ((buf[0] ^ buf[3]) & 0x02)) {
 			switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) {
@@ -1485,10 +1532,112 @@ static const struct dmi_system_id __initconst olpc_dmi_table[] = {
 	{ }
 };
 
+static const struct dmi_system_id min_max_dmi_table[] __initconst = {
+#if defined(CONFIG_DMI)
+	{
+		/* Lenovo ThinkPad Helix */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+		},
+		.driver_data = (int []){1024, 5052, 2258, 4832},
+	},
+	{
+		/* Lenovo ThinkPad X240 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
+		},
+		.driver_data = (int []){1232, 5710, 1156, 4696},
+	},
+	{
+		/* Lenovo ThinkPad Edge E431 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Edge E431"),
+		},
+		.driver_data = (int []){1024, 5022, 2508, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T431s */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T431"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T440s */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad L440 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L440"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T540p */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad L540 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L540"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad W540 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W540"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo Yoga S1 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"ThinkPad S1 Yoga"),
+		},
+		.driver_data = (int []){1232, 5710, 1156, 4696},
+	},
+	{
+		/* Lenovo ThinkPad X1 Carbon Haswell (3rd generation) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION,
+					"ThinkPad X1 Carbon 2nd"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+#endif
+	{ }
+};
+
 void __init synaptics_module_init(void)
 {
+	const struct dmi_system_id *min_max_dmi;
+
 	impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
 	broken_olpc_ec = dmi_check_system(olpc_dmi_table);
+
+	min_max_dmi = dmi_first_match(min_max_dmi_table);
+	if (min_max_dmi)
+		quirk_min_max = min_max_dmi->driver_data;
 }
 
 static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index e594af0b264b..fb2e076738ae 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -78,6 +78,11 @@
  * 2	0x08	image sensor		image sensor tracks 5 fingers, but only
  *					reports 2.
  * 2	0x20	report min		query 0x0f gives min coord reported
+ * 2	0x80	forcepad		forcepad is a variant of clickpad that
+ *					does not have physical buttons but rather
+ *					uses pressure above certain threshold to
+ *					report primary clicks. Forcepads also have
+ *					clickpad bit set.
  */
 #define SYN_CAP_CLICKPAD(ex0c)		((ex0c) & 0x100000) /* 1-button ClickPad */
 #define SYN_CAP_CLICKPAD2BTN(ex0c)	((ex0c) & 0x000100) /* 2-button ClickPad */
@@ -86,6 +91,7 @@
 #define SYN_CAP_ADV_GESTURE(ex0c)	((ex0c) & 0x080000)
 #define SYN_CAP_REDUCED_FILTERING(ex0c)	((ex0c) & 0x000400)
 #define SYN_CAP_IMAGE_SENSOR(ex0c)	((ex0c) & 0x000800)
+#define SYN_CAP_FORCEPAD(ex0c)		((ex0c) & 0x008000)
 
 /* synaptics modes query bits */
 #define SYN_MODE_ABSOLUTE(m)		((m) & (1 << 7))
@@ -177,6 +183,11 @@ struct synaptics_data {
 	 */
 	struct synaptics_hw_state agm;
 	bool agm_pending;			/* new AGM packet received */
+
+	/* ForcePad handling */
+	unsigned long				press_start;
+	bool					press;
+	bool					report_press;
 };
 
 void synaptics_module_init(void);
diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c
index 4c842c320c2e..b604564dec5c 100644
--- a/drivers/input/mousedev.c
+++ b/drivers/input/mousedev.c
@@ -67,7 +67,6 @@ struct mousedev {
 	struct device dev;
 	struct cdev cdev;
 	bool exist;
-	bool is_mixdev;
 
 	struct list_head mixdev_node;
 	bool opened_by_mixdev;
@@ -77,6 +76,9 @@ struct mousedev {
 	int old_x[4], old_y[4];
 	int frac_dx, frac_dy;
 	unsigned long touch;
+
+	int (*open_device)(struct mousedev *mousedev);
+	void (*close_device)(struct mousedev *mousedev);
 };
 
 enum mousedev_emul {
@@ -116,9 +118,6 @@ static unsigned char mousedev_imex_seq[] = { 0xf3, 200, 0xf3, 200, 0xf3, 80 };
 static struct mousedev *mousedev_mix;
 static LIST_HEAD(mousedev_mix_list);
 
-static void mixdev_open_devices(void);
-static void mixdev_close_devices(void);
-
 #define fx(i)  (mousedev->old_x[(mousedev->pkt_count - (i)) & 03])
 #define fy(i)  (mousedev->old_y[(mousedev->pkt_count - (i)) & 03])
 
@@ -428,9 +427,7 @@ static int mousedev_open_device(struct mousedev *mousedev)
 	if (retval)
 		return retval;
 
-	if (mousedev->is_mixdev)
-		mixdev_open_devices();
-	else if (!mousedev->exist)
+	if (!mousedev->exist)
 		retval = -ENODEV;
 	else if (!mousedev->open++) {
 		retval = input_open_device(&mousedev->handle);
@@ -446,9 +443,7 @@ static void mousedev_close_device(struct mousedev *mousedev)
 {
 	mutex_lock(&mousedev->mutex);
 
-	if (mousedev->is_mixdev)
-		mixdev_close_devices();
-	else if (mousedev->exist && !--mousedev->open)
+	if (mousedev->exist && !--mousedev->open)
 		input_close_device(&mousedev->handle);
 
 	mutex_unlock(&mousedev->mutex);
@@ -459,21 +454,29 @@ static void mousedev_close_device(struct mousedev *mousedev)
  * stream. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_open_devices(void)
+static int mixdev_open_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	int error;
+
+	error = mutex_lock_interruptible(&mixdev->mutex);
+	if (error)
+		return error;
 
-	if (mousedev_mix->open++)
-		return;
+	if (!mixdev->open++) {
+		struct mousedev *mousedev;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (!mousedev->opened_by_mixdev) {
-			if (mousedev_open_device(mousedev))
-				continue;
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (!mousedev->opened_by_mixdev) {
+				if (mousedev_open_device(mousedev))
+					continue;
 
-			mousedev->opened_by_mixdev = true;
+				mousedev->opened_by_mixdev = true;
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
+	return 0;
 }
 
 /*
@@ -481,19 +484,22 @@ static void mixdev_open_devices(void)
  * device. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_close_devices(void)
+static void mixdev_close_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	mutex_lock(&mixdev->mutex);
 
-	if (--mousedev_mix->open)
-		return;
+	if (!--mixdev->open) {
+		struct mousedev *mousedev;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (mousedev->opened_by_mixdev) {
-			mousedev->opened_by_mixdev = false;
-			mousedev_close_device(mousedev);
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (mousedev->opened_by_mixdev) {
+				mousedev->opened_by_mixdev = false;
+				mousedev_close_device(mousedev);
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
 }
 
 
@@ -522,7 +528,7 @@ static int mousedev_release(struct inode *inode, struct file *file)
 	mousedev_detach_client(mousedev, client);
 	kfree(client);
 
-	mousedev_close_device(mousedev);
+	mousedev->close_device(mousedev);
 
 	return 0;
 }
@@ -550,7 +556,7 @@ static int mousedev_open(struct inode *inode, struct file *file)
 	client->mousedev = mousedev;
 	mousedev_attach_client(mousedev, client);
 
-	error = mousedev_open_device(mousedev);
+	error = mousedev->open_device(mousedev);
 	if (error)
 		goto err_free_client;
 
@@ -861,16 +867,21 @@ static struct mousedev *mousedev_create(struct input_dev *dev,
 
 	if (mixdev) {
 		dev_set_name(&mousedev->dev, "mice");
+
+		mousedev->open_device = mixdev_open_devices;
+		mousedev->close_device = mixdev_close_devices;
 	} else {
 		int dev_no = minor;
 		/* Normalize device number if it falls into legacy range */
 		if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS)
 			dev_no -= MOUSEDEV_MINOR_BASE;
 		dev_set_name(&mousedev->dev, "mouse%d", dev_no);
+
+		mousedev->open_device = mousedev_open_device;
+		mousedev->close_device = mousedev_close_device;
 	}
 
 	mousedev->exist = true;
-	mousedev->is_mixdev = mixdev;
 	mousedev->handle.dev = input_get_device(dev);
 	mousedev->handle.name = dev_name(&mousedev->dev);
 	mousedev->handle.handler = handler;
@@ -919,7 +930,7 @@ static void mousedev_destroy(struct mousedev *mousedev)
 	device_del(&mousedev->dev);
 	mousedev_cleanup(mousedev);
 	input_free_minor(MINOR(mousedev->dev.devt));
-	if (!mousedev->is_mixdev)
+	if (mousedev != mousedev_mix)
 		input_unregister_handle(&mousedev->handle);
 	put_device(&mousedev->dev);
 }
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 1bda828f4b55..0455a2735fb0 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -2,7 +2,7 @@
 # Input core configuration
 #
 config SERIO
-	tristate "Serial I/O support" if EXPERT || !X86
+	tristate "Serial I/O support"
 	default y
 	help
 	  Say Yes here if you have any input device that uses serial I/O to
@@ -19,7 +19,7 @@ config SERIO
 if SERIO
 
 config SERIO_I8042
-	tristate "i8042 PC Keyboard controller" if EXPERT || !X86
+	tristate "i8042 PC Keyboard controller"
 	default y
 	depends on !PARISC && (!ARM || ARCH_SHARK || FOOTBRIDGE_HOST) && \
 		   (!SUPERH || SH_CAYMAN) && !M68K && !BLACKFIN && !S390
@@ -169,7 +169,7 @@ config SERIO_MACEPS2
 	  module will be called maceps2.
 
 config SERIO_LIBPS2
-	tristate "PS/2 driver library" if EXPERT
+	tristate "PS/2 driver library"
 	depends on SERIO_I8042 || SERIO_I8042=n
 	help
 	  Say Y here if you are using a driver for device connected
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 5f306f79da0c..ce715b1bee46 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -101,6 +101,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 	},
 	{
 		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"),
+		},
+	},
+	{
+		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
 			DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"),
 			DMI_MATCH(DMI_PRODUCT_VERSION, "8500"),
@@ -458,6 +464,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
 		},
 	},
+	{
+		/* Avatar AVIU-145A6 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
+		},
+	},
 	{ }
 };
 
@@ -601,6 +614,30 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
 		},
 	},
+	{
+		/* Fujitsu A544 laptop */
+		/* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"),
+		},
+	},
+	{
+		/* Fujitsu AH544 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"),
+		},
+	},
+	{
+		/* Fujitsu U574 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
+		},
+	},
 	{ }
 };
 
@@ -765,6 +802,7 @@ static struct pnp_device_id pnp_kbd_devids[] = {
 	{ .id = "CPQA0D7", .driver_data = 0 },
 	{ .id = "", },
 };
+MODULE_DEVICE_TABLE(pnp, pnp_kbd_devids);
 
 static struct pnp_driver i8042_pnp_kbd_driver = {
 	.name           = "i8042 kbd",
@@ -786,6 +824,7 @@ static struct pnp_device_id pnp_aux_devids[] = {
 	{ .id = "SYN0801", .driver_data = 0 },
 	{ .id = "", },
 };
+MODULE_DEVICE_TABLE(pnp, pnp_aux_devids);
 
 static struct pnp_driver i8042_pnp_aux_driver = {
 	.name           = "i8042 aux",
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index 8755f5f3ad37..e4ecf3b64794 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/serio.h>
 #include <linux/tty.h>
+#include <linux/compat.h>
 
 MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
 MODULE_DESCRIPTION("Input device TTY line discipline");
@@ -196,28 +197,55 @@ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u
 	return 0;
 }
 
+static void serport_set_type(struct tty_struct *tty, unsigned long type)
+{
+	struct serport *serport = tty->disc_data;
+
+	serport->id.proto = type & 0x000000ff;
+	serport->id.id    = (type & 0x0000ff00) >> 8;
+	serport->id.extra = (type & 0x00ff0000) >> 16;
+}
+
 /*
  * serport_ldisc_ioctl() allows to set the port protocol, and device ID
  */
 
-static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg)
+static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file,
+			       unsigned int cmd, unsigned long arg)
 {
-	struct serport *serport = (struct serport*) tty->disc_data;
-	unsigned long type;
-
 	if (cmd == SPIOCSTYPE) {
+		unsigned long type;
+
 		if (get_user(type, (unsigned long __user *) arg))
 			return -EFAULT;
 
-		serport->id.proto = type & 0x000000ff;
-		serport->id.id	  = (type & 0x0000ff00) >> 8;
-		serport->id.extra = (type & 0x00ff0000) >> 16;
+		serport_set_type(tty, type);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+#define COMPAT_SPIOCSTYPE	_IOW('q', 0x01, compat_ulong_t)
+static long serport_ldisc_compat_ioctl(struct tty_struct *tty,
+				       struct file *file,
+				       unsigned int cmd, unsigned long arg)
+{
+	if (cmd == COMPAT_SPIOCSTYPE) {
+		void __user *uarg = compat_ptr(arg);
+		compat_ulong_t compat_type;
+
+		if (get_user(compat_type, (compat_ulong_t __user *)uarg))
+			return -EFAULT;
 
+		serport_set_type(tty, compat_type);
 		return 0;
 	}
 
 	return -EINVAL;
 }
+#endif
 
 static void serport_ldisc_write_wakeup(struct tty_struct * tty)
 {
@@ -241,6 +269,9 @@ static struct tty_ldisc_ops serport_ldisc = {
 	.close =	serport_ldisc_close,
 	.read =		serport_ldisc_read,
 	.ioctl =	serport_ldisc_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	serport_ldisc_compat_ioctl,
+#endif
 	.receive_buf =	serport_ldisc_receive,
 	.write_wakeup =	serport_ldisc_write_wakeup
 };
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index aaf23aeae2ea..3d838c0b495d 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -339,7 +339,7 @@ static int wacom_parse_hid(struct usb_interface *intf,
 	struct usb_device *dev = interface_to_usbdev(intf);
 	char limit = 0;
 	/* result has to be defined as int for some devices */
-	int result = 0;
+	int result = 0, touch_max = 0;
 	int i = 0, usage = WCM_UNDEFINED, finger = 0, pen = 0;
 	unsigned char *report;
 
@@ -386,7 +386,8 @@ static int wacom_parse_hid(struct usb_interface *intf,
 				if (usage == WCM_DESKTOP) {
 					if (finger) {
 						features->device_type = BTN_TOOL_FINGER;
-
+						/* touch device at least supports one touch point */
+						touch_max = 1;
 						switch (features->type) {
 						case TABLETPC2FG:
 							features->pktlen = WACOM_PKGLEN_TPC2FG;
@@ -539,6 +540,8 @@ static int wacom_parse_hid(struct usb_interface *intf,
 	}
 
  out:
+	if (!features->touch_max && touch_max)
+		features->touch_max = touch_max;
 	result = 0;
 	kfree(report);
 	return result;
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 721fdb3597ca..5f87bed05467 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -106,6 +106,7 @@ struct usbtouch_device_info {
 struct usbtouch_usb {
 	unsigned char *data;
 	dma_addr_t data_dma;
+	int data_size;
 	unsigned char *buffer;
 	int buf_len;
 	struct urb *irq;
@@ -146,12 +147,10 @@ enum {
 
 #define USB_DEVICE_HID_CLASS(vend, prod) \
 	.match_flags = USB_DEVICE_ID_MATCH_INT_CLASS \
-		| USB_DEVICE_ID_MATCH_INT_PROTOCOL \
 		| USB_DEVICE_ID_MATCH_DEVICE, \
 	.idVendor = (vend), \
 	.idProduct = (prod), \
-	.bInterfaceClass = USB_INTERFACE_CLASS_HID, \
-	.bInterfaceProtocol = USB_INTERFACE_PROTOCOL_MOUSE
+	.bInterfaceClass = USB_INTERFACE_CLASS_HID
 
 static const struct usb_device_id usbtouch_devices[] = {
 #ifdef CONFIG_TOUCHSCREEN_USB_EGALAX
@@ -1523,7 +1522,7 @@ static int usbtouch_reset_resume(struct usb_interface *intf)
 static void usbtouch_free_buffers(struct usb_device *udev,
 				  struct usbtouch_usb *usbtouch)
 {
-	usb_free_coherent(udev, usbtouch->type->rept_size,
+	usb_free_coherent(udev, usbtouch->data_size,
 			  usbtouch->data, usbtouch->data_dma);
 	kfree(usbtouch->buffer);
 }
@@ -1568,7 +1567,20 @@ static int usbtouch_probe(struct usb_interface *intf,
 	if (!type->process_pkt)
 		type->process_pkt = usbtouch_process_pkt;
 
-	usbtouch->data = usb_alloc_coherent(udev, type->rept_size,
+	usbtouch->data_size = type->rept_size;
+	if (type->get_pkt_len) {
+		/*
+		 * When dealing with variable-length packets we should
+		 * not request more than wMaxPacketSize bytes at once
+		 * as we do not know if there is more data coming or
+		 * we filled exactly wMaxPacketSize bytes and there is
+		 * nothing else.
+		 */
+		usbtouch->data_size = min(usbtouch->data_size,
+					  usb_endpoint_maxp(endpoint));
+	}
+
+	usbtouch->data = usb_alloc_coherent(udev, usbtouch->data_size,
 					    GFP_KERNEL, &usbtouch->data_dma);
 	if (!usbtouch->data)
 		goto out_free;
@@ -1628,12 +1640,12 @@ static int usbtouch_probe(struct usb_interface *intf,
 	if (usb_endpoint_type(endpoint) == USB_ENDPOINT_XFER_INT)
 		usb_fill_int_urb(usbtouch->irq, udev,
 			 usb_rcvintpipe(udev, endpoint->bEndpointAddress),
-			 usbtouch->data, type->rept_size,
+			 usbtouch->data, usbtouch->data_size,
 			 usbtouch_irq, usbtouch, endpoint->bInterval);
 	else
 		usb_fill_bulk_urb(usbtouch->irq, udev,
 			 usb_rcvbulkpipe(udev, endpoint->bEndpointAddress),
-			 usbtouch->data, type->rept_size,
+			 usbtouch->data, usbtouch->data_size,
 			 usbtouch_irq, usbtouch);
 
 	usbtouch->irq->dev = udev;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a3c338942f10..dfb401cba733 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3187,14 +3187,16 @@ free_domains:
 
 static void cleanup_domain(struct protection_domain *domain)
 {
-	struct iommu_dev_data *dev_data, *next;
+	struct iommu_dev_data *entry;
 	unsigned long flags;
 
 	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
 
-	list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
-		__detach_device(dev_data);
-		atomic_set(&dev_data->bind, 0);
+	while (!list_empty(&domain->dev_list)) {
+		entry = list_first_entry(&domain->dev_list,
+					 struct iommu_dev_data, list);
+		__detach_device(entry);
+		atomic_set(&entry->bind, 0);
 	}
 
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -3959,7 +3961,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	iommu_flush_dte(iommu, devid);
 	if (devid != alias) {
 		irq_lookup_table[alias] = table;
-		set_dte_irq_entry(devid, table);
+		set_dte_irq_entry(alias, table);
 		iommu_flush_dte(iommu, alias);
 	}
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index fa004b112a89..db4e10d4c7f5 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -782,7 +782,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 	int offset;
 
 	BUG_ON(!domain->pgd);
-	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
+
+	if (addr_width < BITS_PER_LONG && pfn >> addr_width)
+		/* Address beyond IOMMU's addressing capabilities. */
+		return NULL;
+
 	parent = domain->pgd;
 
 	while (level > 0) {
@@ -913,7 +917,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 
 		/* If range covers entire pagetable, free it */
 		if (!(start_pfn > level_pfn ||
-		      last_pfn < level_pfn + level_size(level))) {
+		      last_pfn < level_pfn + level_size(level) - 1)) {
 			dma_clear_pte(pte);
 			domain_flush_cache(domain, pte, sizeof(*pte));
 			free_pgtable_page(level_pte);
@@ -1792,7 +1796,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	struct dma_pte *first_pte = NULL, *pte = NULL;
 	phys_addr_t uninitialized_var(pteval);
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
-	unsigned long sg_res;
+	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
 
@@ -1803,10 +1807,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 
 	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
 
-	if (sg)
-		sg_res = 0;
-	else {
-		sg_res = nr_pages + 1;
+	if (!sg) {
+		sg_res = nr_pages;
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5b19b2d6ec2d..45011f63ad16 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -525,12 +525,13 @@ static int __init intel_irq_remapping_supported(void)
 	if (disable_irq_remap)
 		return 0;
 	if (irq_remap_broken) {
-		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
-			   "This system BIOS has enabled interrupt remapping\n"
-			   "on a chipset that contains an erratum making that\n"
-			   "feature unstable.  To maintain system stability\n"
-			   "interrupt remapping is being disabled.  Please\n"
-			   "contact your BIOS vendor for an update\n");
+		printk(KERN_WARNING
+			"This system BIOS has enabled interrupt remapping\n"
+			"on a chipset that contains an erratum making that\n"
+			"feature unstable.  To maintain system stability\n"
+			"interrupt remapping is being disabled.  Please\n"
+			"contact your BIOS vendor for an update\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		disable_irq_remap = 1;
 		return 0;
 	}
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 4a33351c25dc..7709b1dbf6cc 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -10,6 +10,11 @@ config ARM_GIC
 config GIC_NON_BANKED
 	bool
 
+config ARM_GIC_V3
+	bool
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index cda4cb5f7327..bf4667b34306 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -9,7 +9,8 @@ obj-$(CONFIG_METAG)			+= irq-metag-ext.o
 obj-$(CONFIG_METAG_PERFCOUNTER_IRQS)	+= irq-metag.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
-obj-$(CONFIG_ARM_GIC)			+= irq-gic.o
+obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_SIRF_IRQ)			+= irq-sirfsoc.o
 obj-$(CONFIG_RENESAS_INTC_IRQPIN)	+= irq-renesas-intc-irqpin.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index bb328a366122..a51ee009ed83 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -229,7 +229,7 @@ armada_370_xp_handle_irq(struct pt_regs *regs)
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& IPI_DOORBELL_MASK;
 
-			writel(~IPI_DOORBELL_MASK, per_cpu_int_base +
+			writel(~ipimask, per_cpu_int_base +
 				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
 			/* Handle all pending doorbells */
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
new file mode 100644
index 000000000000..60ac704d2090
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include "irq-gic-common.h"
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+		       void __iomem *base, void (*sync_access)(void))
+{
+	u32 enablemask = 1 << (irq % 32);
+	u32 enableoff = (irq / 32) * 4;
+	u32 confmask = 0x2 << ((irq % 16) * 2);
+	u32 confoff = (irq / 16) * 4;
+	bool enabled = false;
+	u32 val;
+
+	/*
+	 * Read current configuration register, and insert the config
+	 * for "irq", depending on "type".
+	 */
+	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
+	if (type == IRQ_TYPE_LEVEL_HIGH)
+		val &= ~confmask;
+	else if (type == IRQ_TYPE_EDGE_RISING)
+		val |= confmask;
+
+	/*
+	 * As recommended by the spec, disable the interrupt before changing
+	 * the configuration
+	 */
+	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+		if (sync_access)
+			sync_access();
+		enabled = true;
+	}
+
+	/*
+	 * Write back the new configuration, and possibly re-enable
+	 * the interrupt.
+	 */
+	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
+
+	if (enabled)
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+
+	if (sync_access)
+		sync_access();
+}
+
+void __init gic_dist_config(void __iomem *base, int gic_irqs,
+			    void (*sync_access)(void))
+{
+	unsigned int i;
+
+	/*
+	 * Set all global interrupts to be level triggered, active low.
+	 */
+	for (i = 32; i < gic_irqs; i += 16)
+		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+
+	/*
+	 * Set priority on all global interrupts.
+	 */
+	for (i = 32; i < gic_irqs; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+
+	/*
+	 * Disable all interrupts.  Leave the PPI and SGIs alone
+	 * as they are enabled by redistributor registers.
+	 */
+	for (i = 32; i < gic_irqs; i += 32)
+		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+
+	if (sync_access)
+		sync_access();
+}
+
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
+{
+	int i;
+
+	/*
+	 * Deal with the banked PPI and SGI interrupts - disable all
+	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 */
+	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+
+	/*
+	 * Set priority on PPI and SGI interrupts
+	 */
+	for (i = 0; i < 32; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+
+	if (sync_access)
+		sync_access();
+}
diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h
new file mode 100644
index 000000000000..b41f02481c3a
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _IRQ_GIC_COMMON_H
+#define _IRQ_GIC_COMMON_H
+
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+                       void __iomem *base, void (*sync_access)(void));
+void gic_dist_config(void __iomem *base, int gic_irqs,
+		     void (*sync_access)(void));
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
+
+#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
new file mode 100644
index 000000000000..57eaa5a0b1e3
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -0,0 +1,692 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+struct gic_chip_data {
+	void __iomem		*dist_base;
+	void __iomem		**redist_base;
+	void __percpu __iomem	**rdist;
+	struct irq_domain	*domain;
+	u64			redist_stride;
+	u32			redist_regions;
+	unsigned int		irq_nr;
+};
+
+static struct gic_chip_data gic_data __read_mostly;
+
+#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdist))
+#define gic_data_rdist_rd_base()	(*gic_data_rdist())
+#define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
+
+/* Our default, arbitrary priority value. Linux only uses one anyway. */
+#define DEFAULT_PMR_VALUE	0xf0
+
+static inline unsigned int gic_irq(struct irq_data *d)
+{
+	return d->hwirq;
+}
+
+static inline int gic_irq_in_rdist(struct irq_data *d)
+{
+	return gic_irq(d) < 32;
+}
+
+static inline void __iomem *gic_dist_base(struct irq_data *d)
+{
+	if (gic_irq_in_rdist(d))	/* SGI+PPI -> SGI_base for this CPU */
+		return gic_data_rdist_sgi_base();
+
+	if (d->hwirq <= 1023)		/* SPI -> dist_base */
+		return gic_data.dist_base;
+
+	if (d->hwirq >= 8192)
+		BUG();		/* LPI Detected!!! */
+
+	return NULL;
+}
+
+static void gic_do_wait_for_rwp(void __iomem *base)
+{
+	u32 count = 1000000;	/* 1s! */
+
+	while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("RWP timeout, gone fishing\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/* Wait for completion of a distributor change */
+static void gic_dist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data.dist_base);
+}
+
+/* Wait for completion of a redistributor change */
+static void gic_redist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+}
+
+/* Low level accessors */
+static u64 gic_read_iar(void)
+{
+	u64 irqstat;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static void gic_write_pmr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_write_ctlr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_grpen1(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_sgi1r(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_enable_sre(void)
+{
+	u64 val;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	val |= ICC_SRE_EL1_SRE;
+	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
+	isb();
+
+	/*
+	 * Need to check that the SRE bit has actually been set. If
+	 * not, it means that SRE is disabled at EL2. We're going to
+	 * die painfully, and there is nothing we can do about it.
+	 *
+	 * Kindly inform the luser.
+	 */
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	if (!(val & ICC_SRE_EL1_SRE))
+		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_enable_redist(void)
+{
+	void __iomem *rbase;
+	u32 count = 1000000;	/* 1s! */
+	u32 val;
+
+	rbase = gic_data_rdist_rd_base();
+
+	/* Wake up this CPU redistributor */
+	val = readl_relaxed(rbase + GICR_WAKER);
+	val &= ~GICR_WAKER_ProcessorSleep;
+	writel_relaxed(val, rbase + GICR_WAKER);
+
+	while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("redist didn't wake up...\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/*
+ * Routines to disable, enable, EOI and route interrupts
+ */
+static void gic_poke_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	writel_relaxed(mask, base + offset + (gic_irq(d) / 32) * 4);
+	rwp_wait();
+}
+
+static int gic_peek_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d))
+		base = gic_data_rdist_sgi_base();
+	else
+		base = gic_data.dist_base;
+
+	return !!(readl_relaxed(base + offset + (gic_irq(d) / 32) * 4) & mask);
+}
+
+static void gic_mask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ICENABLER);
+}
+
+static void gic_unmask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ISENABLER);
+}
+
+static void gic_eoi_irq(struct irq_data *d)
+{
+	gic_write_eoir(gic_irq(d));
+}
+
+static int gic_set_type(struct irq_data *d, unsigned int type)
+{
+	unsigned int irq = gic_irq(d);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	/* Interrupt configuration for SGIs can't be changed */
+	if (irq < 16)
+		return -EINVAL;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	gic_configure_irq(irq, type, base, rwp_wait);
+
+	return 0;
+}
+
+static u64 gic_mpidr_to_affinity(u64 mpidr)
+{
+	u64 aff;
+
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8  |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	return aff;
+}
+
+static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+	u64 irqnr;
+
+	do {
+		irqnr = gic_read_iar();
+
+		if (likely(irqnr > 15 && irqnr < 1020)) {
+			u64 irq = irq_find_mapping(gic_data.domain, irqnr);
+			if (likely(irq)) {
+				handle_IRQ(irq, regs);
+				continue;
+			}
+
+			WARN_ONCE(true, "Unexpected SPI received!\n");
+			gic_write_eoir(irqnr);
+		}
+		if (irqnr < 16) {
+			gic_write_eoir(irqnr);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#else
+			WARN_ONCE(true, "Unexpected SGI received!\n");
+#endif
+			continue;
+		}
+	} while (irqnr != ICC_IAR1_EL1_SPURIOUS);
+}
+
+static void __init gic_dist_init(void)
+{
+	unsigned int i;
+	u64 affinity;
+	void __iomem *base = gic_data.dist_base;
+
+	/* Disable the distributor */
+	writel_relaxed(0, base + GICD_CTLR);
+	gic_dist_wait_for_rwp();
+
+	gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
+
+	/* Enable distributor with ARE, Group1 */
+	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
+		       base + GICD_CTLR);
+
+	/*
+	 * Set all global interrupts to the boot CPU only. ARE must be
+	 * enabled.
+	 */
+	affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
+	for (i = 32; i < gic_data.irq_nr; i++)
+		writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+}
+
+static int gic_populate_rdist(void)
+{
+	u64 mpidr = cpu_logical_map(smp_processor_id());
+	u64 typer;
+	u32 aff;
+	int i;
+
+	/*
+	 * Convert affinity to a 32bit value that can be matched to
+	 * GICR_TYPER bits [63:32].
+	 */
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	for (i = 0; i < gic_data.redist_regions; i++) {
+		void __iomem *ptr = gic_data.redist_base[i];
+		u32 reg;
+
+		reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
+		if (reg != GIC_PIDR2_ARCH_GICv3 &&
+		    reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
+			pr_warn("No redistributor present @%p\n", ptr);
+			break;
+		}
+
+		do {
+			typer = readq_relaxed(ptr + GICR_TYPER);
+			if ((typer >> 32) == aff) {
+				gic_data_rdist_rd_base() = ptr;
+				pr_info("CPU%d: found redistributor %llx @%p\n",
+					smp_processor_id(),
+					(unsigned long long)mpidr, ptr);
+				return 0;
+			}
+
+			if (gic_data.redist_stride) {
+				ptr += gic_data.redist_stride;
+			} else {
+				ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
+				if (typer & GICR_TYPER_VLPIS)
+					ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
+			}
+		} while (!(typer & GICR_TYPER_LAST));
+	}
+
+	/* We couldn't even deal with ourselves... */
+	WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
+	     smp_processor_id(), (unsigned long long)mpidr);
+	return -ENODEV;
+}
+
+static void gic_cpu_init(void)
+{
+	void __iomem *rbase;
+
+	/* Register ourselves with the rest of the world */
+	if (gic_populate_rdist())
+		return;
+
+	gic_enable_redist();
+
+	rbase = gic_data_rdist_sgi_base();
+
+	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
+
+	/* Enable system registers */
+	gic_enable_sre();
+
+	/* Set priority mask register */
+	gic_write_pmr(DEFAULT_PMR_VALUE);
+
+	/* EOI deactivates interrupt too (mode 0) */
+	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+	/* ... and let's hit the road... */
+	gic_write_grpen1(1);
+}
+
+#ifdef CONFIG_SMP
+static int gic_secondary_init(struct notifier_block *nfb,
+			      unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		gic_cpu_init();
+	return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the GIC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block gic_cpu_notifier = {
+	.notifier_call = gic_secondary_init,
+	.priority = 100,
+};
+
+static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
+				   u64 cluster_id)
+{
+	int cpu = *base_cpu;
+	u64 mpidr = cpu_logical_map(cpu);
+	u16 tlist = 0;
+
+	while (cpu < nr_cpu_ids) {
+		/*
+		 * If we ever get a cluster of more than 16 CPUs, just
+		 * scream and skip that CPU.
+		 */
+		if (WARN_ON((mpidr & 0xff) >= 16))
+			goto out;
+
+		tlist |= 1 << (mpidr & 0xf);
+
+		cpu = cpumask_next(cpu, mask);
+		if (cpu == nr_cpu_ids)
+			goto out;
+
+		mpidr = cpu_logical_map(cpu);
+
+		if (cluster_id != (mpidr & ~0xffUL)) {
+			cpu--;
+			goto out;
+		}
+	}
+out:
+	*base_cpu = cpu;
+	return tlist;
+}
+
+static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
+{
+	u64 val;
+
+	val = (MPIDR_AFFINITY_LEVEL(cluster_id, 3) << 48	|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 2) << 32	|
+	       irq << 24			    		|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 1) << 16	|
+	       tlist);
+
+	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+	gic_write_sgi1r(val);
+}
+
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+
+	if (WARN_ON(irq >= 16))
+		return;
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	smp_wmb();
+
+	for_each_cpu_mask(cpu, *mask) {
+		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		u16 tlist;
+
+		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
+		gic_send_sgi(cluster_id, tlist, irq);
+	}
+
+	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
+	isb();
+}
+
+static void gic_smp_init(void)
+{
+	set_smp_cross_call(gic_raise_softirq);
+	register_cpu_notifier(&gic_cpu_notifier);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	void __iomem *reg;
+	int enabled;
+	u64 val;
+
+	if (gic_irq_in_rdist(d))
+		return -EINVAL;
+
+	/* If interrupt was enabled, disable it first */
+	enabled = gic_peek_irq(d, GICD_ISENABLER);
+	if (enabled)
+		gic_mask_irq(d);
+
+	reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
+	val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
+
+	writeq_relaxed(val, reg);
+
+	/*
+	 * If the interrupt was enabled, enabled it again. Otherwise,
+	 * just wait for the distributor to have digested our changes.
+	 */
+	if (enabled)
+		gic_unmask_irq(d);
+	else
+		gic_dist_wait_for_rwp();
+
+	return IRQ_SET_MASK_OK;
+}
+#else
+#define gic_set_affinity	NULL
+#define gic_smp_init()		do { } while(0)
+#endif
+
+static struct irq_chip gic_chip = {
+	.name			= "GICv3",
+	.irq_mask		= gic_mask_irq,
+	.irq_unmask		= gic_unmask_irq,
+	.irq_eoi		= gic_eoi_irq,
+	.irq_set_type		= gic_set_type,
+	.irq_set_affinity	= gic_set_affinity,
+};
+
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	/* SGIs are private to the core kernel */
+	if (hw < 16)
+		return -EPERM;
+	/* PPIs */
+	if (hw < 32) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_percpu_devid_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+	}
+	/* SPIs */
+	if (hw >= 32 && hw < gic_data.irq_nr) {
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_fasteoi_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	}
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static int gic_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	switch(intspec[0]) {
+	case 0:			/* SPI */
+		*out_hwirq = intspec[1] + 32;
+		break;
+	case 1:			/* PPI */
+		*out_hwirq = intspec[1] + 16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.map = gic_irq_domain_map,
+	.xlate = gic_irq_domain_xlate,
+};
+
+static int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *dist_base;
+	void __iomem **redist_base;
+	u64 redist_stride;
+	u32 redist_regions;
+	u32 reg;
+	int gic_irqs;
+	int err;
+	int i;
+
+	dist_base = of_iomap(node, 0);
+	if (!dist_base) {
+		pr_err("%s: unable to map gic dist registers\n",
+			node->full_name);
+		return -ENXIO;
+	}
+
+	reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+		pr_err("%s: no distributor detected, giving up\n",
+			node->full_name);
+		err = -ENODEV;
+		goto out_unmap_dist;
+	}
+
+	if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
+		redist_regions = 1;
+
+	redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
+	if (!redist_base) {
+		err = -ENOMEM;
+		goto out_unmap_dist;
+	}
+
+	for (i = 0; i < redist_regions; i++) {
+		redist_base[i] = of_iomap(node, 1 + i);
+		if (!redist_base[i]) {
+			pr_err("%s: couldn't map region %d\n",
+			       node->full_name, i);
+			err = -ENODEV;
+			goto out_unmap_rdist;
+		}
+	}
+
+	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
+		redist_stride = 0;
+
+	gic_data.dist_base = dist_base;
+	gic_data.redist_base = redist_base;
+	gic_data.redist_regions = redist_regions;
+	gic_data.redist_stride = redist_stride;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 */
+	gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic_data.irq_nr = gic_irqs;
+
+	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
+					      &gic_data);
+	gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	set_handle_irq(gic_handle_irq);
+
+	gic_smp_init();
+	gic_dist_init();
+	gic_cpu_init();
+
+	return 0;
+
+out_free:
+	if (gic_data.domain)
+		irq_domain_remove(gic_data.domain);
+	free_percpu(gic_data.rdist);
+out_unmap_rdist:
+	for (i = 0; i < redist_regions; i++)
+		if (redist_base[i])
+			iounmap(redist_base[i]);
+	kfree(redist_base);
+out_unmap_dist:
+	iounmap(dist_base);
+	return err;
+}
+
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 19ceaa60e0f4..4cb670e61707 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/arm/common/gic.c
- *
  *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -41,16 +39,19 @@
 #include <linux/slab.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/arm-gic.h>
+#include <trace/events/arm-ipi.h>
 
+#include <asm/cputype.h>
 #include <asm/irq.h>
 #include <asm/exception.h>
 #include <asm/smp_plat.h>
 
+#include "irq-gic-common.h"
 #include "irqchip.h"
 
 union gic_base {
 	void __iomem *common_base;
-	void __percpu __iomem **percpu_base;
+	void __percpu * __iomem *percpu_base;
 };
 
 struct gic_chip_data {
@@ -188,12 +189,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
-	u32 enablemask = 1 << (gicirq % 32);
-	u32 enableoff = (gicirq / 32) * 4;
-	u32 confmask = 0x2 << ((gicirq % 16) * 2);
-	u32 confoff = (gicirq / 16) * 4;
-	bool enabled = false;
-	u32 val;
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
@@ -207,25 +202,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
-	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
-	if (type == IRQ_TYPE_LEVEL_HIGH)
-		val &= ~confmask;
-	else if (type == IRQ_TYPE_EDGE_RISING)
-		val |= confmask;
-
-	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		enabled = true;
-	}
-
-	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
-
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+	gic_configure_irq(gicirq, type, base, NULL);
 
 	raw_spin_unlock(&irq_controller_lock);
 
@@ -253,10 +230,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
+	raw_spin_lock(&irq_controller_lock);
 	mask = 0xff << shift;
 	bit = gic_cpu_map[cpu] << shift;
-
-	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	raw_spin_unlock(&irq_controller_lock);
@@ -280,7 +256,7 @@ static int gic_set_wake(struct irq_data *d, unsigned int on)
 #define gic_set_wake	NULL
 #endif
 
-static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqstat, irqnr;
 	struct gic_chip_data *gic = &gic_data[0];
@@ -288,7 +264,7 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 
 	do {
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
-		irqnr = irqstat & ~0x1c00;
+		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
 		if (likely(irqnr > 15 && irqnr < 1021)) {
 			irqnr = irq_find_mapping(gic->domain, irqnr);
@@ -384,12 +360,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
-	 * Set all global interrupts to be level triggered, active low.
-	 */
-	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
-
-	/*
 	 * Set all global interrupts to this CPU only.
 	 */
 	cpumask = gic_get_cpumask(gic);
@@ -398,18 +368,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
-	/*
-	 * Set priority on all global interrupts.
-	 */
-	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
-
-	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as these enables are banked registers.
-	 */
-	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+	gic_dist_config(base, gic_irqs, NULL);
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
 }
@@ -436,23 +395,18 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 		if (i != cpu)
 			gic_cpu_map[i] &= ~cpu_mask;
 
-	/*
-	 * Deal with the banked PPI and SGI interrupts - disable all
-	 * PPI interrupts, ensure all SGI interrupts are enabled.
-	 */
-	writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
-
-	/*
-	 * Set priority on PPI and SGI interrupts
-	 */
-	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
+void gic_cpu_if_down(void)
+{
+	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
+	writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+}
+
 #ifdef CONFIG_CPU_PM
 /*
  * Saves the GIC distributor registers during suspend or idle.  Must be called
@@ -643,26 +597,172 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
-void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
-	unsigned long map = 0;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 
 	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
+	for_each_cpu(cpu, mask) {
+		trace_arm_ipi_send(irq, cpu);
 		map |= gic_cpu_map[cpu];
+	}
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
+	 * other CPUs before they observe us issuing the IPI.
 	 */
-	dsb();
+	dmb(ishst);
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 #endif
 
+#ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_send_sgi - send a SGI directly to given CPU interface number
+ *
+ * cpu_id: the ID for the destination CPU interface
+ * irq: the IPI number to send a SGI for
+ */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
+{
+	BUG_ON(cpu_id >= NR_GIC_CPU_IF);
+	cpu_id = 1 << cpu_id;
+	/* this always happens on GIC0 */
+	writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+}
+
+/*
+ * gic_get_cpu_id - get the CPU interface ID for the specified CPU
+ *
+ * @cpu: the logical CPU number to get the GIC ID for.
+ *
+ * Return the CPU interface ID for the given logical CPU number,
+ * or -1 if the CPU number is too large or the interface ID is
+ * unknown (more than one bit set).
+ */
+int gic_get_cpu_id(unsigned int cpu)
+{
+	unsigned int cpu_bit;
+
+	if (cpu >= NR_GIC_CPU_IF)
+		return -1;
+	cpu_bit = gic_cpu_map[cpu];
+	if (cpu_bit & (cpu_bit - 1))
+		return -1;
+	return __ffs(cpu_bit);
+}
+
+/*
+ * gic_migrate_target - migrate IRQs to another CPU interface
+ *
+ * @new_cpu_id: the CPU target ID to migrate IRQs to
+ *
+ * Migrate all peripheral interrupts with a target matching the current CPU
+ * to the interface corresponding to @new_cpu_id.  The CPU interface mapping
+ * is also updated.  Targets to other CPU interfaces are unchanged.
+ * This must be called with IRQs locally disabled.
+ */
+void gic_migrate_target(unsigned int new_cpu_id)
+{
+	unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
+	void __iomem *dist_base;
+	int i, ror_val, cpu = smp_processor_id();
+	u32 val, cur_target_mask, active_mask;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	if (!dist_base)
+		return;
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+
+	cur_cpu_id = __ffs(gic_cpu_map[cpu]);
+	cur_target_mask = 0x01010101 << cur_cpu_id;
+	ror_val = (cur_cpu_id - new_cpu_id) & 31;
+
+	raw_spin_lock(&irq_controller_lock);
+
+	/* Update the target interface for this logical CPU */
+	gic_cpu_map[cpu] = 1 << new_cpu_id;
+
+	/*
+	 * Find all the peripheral interrupts targetting the current
+	 * CPU interface and migrate them to the new CPU interface.
+	 * We skip DIST_TARGET 0 to 7 as they are read-only.
+	 */
+	for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
+		val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+		active_mask = val & cur_target_mask;
+		if (active_mask) {
+			val &= ~active_mask;
+			val |= ror32(active_mask, ror_val);
+			writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
+		}
+	}
+
+	raw_spin_unlock(&irq_controller_lock);
+
+	/*
+	 * Now let's migrate and clear any potential SGIs that might be
+	 * pending for us (cur_cpu_id).  Since GIC_DIST_SGI_PENDING_SET
+	 * is a banked register, we can only forward the SGI using
+	 * GIC_DIST_SOFTINT.  The original SGI source is lost but Linux
+	 * doesn't use that information anyway.
+	 *
+	 * For the same reason we do not adjust SGI source information
+	 * for previously sent SGIs by us to other CPUs either.
+	 */
+	for (i = 0; i < 16; i += 4) {
+		int j;
+		val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
+		if (!val)
+			continue;
+		writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
+		for (j = i; j < i + 4; j++) {
+			if (val & 0xff)
+				writel_relaxed((1 << (new_cpu_id + 16)) | j,
+						dist_base + GIC_DIST_SOFTINT);
+			val >>= 8;
+		}
+	}
+}
+
+/*
+ * gic_get_sgir_physaddr - get the physical address for the SGI register
+ *
+ * REturn the physical address of the SGI register to be used
+ * by some early assembly code when the kernel is not yet available.
+ */
+static unsigned long gic_dist_physaddr;
+
+unsigned long gic_get_sgir_physaddr(void)
+{
+	if (!gic_dist_physaddr)
+		return 0;
+	return gic_dist_physaddr + GIC_DIST_SOFTINT;
+}
+
+void __init gic_init_physaddr(struct device_node *node)
+{
+	struct resource res;
+	if (of_address_to_resource(node, 0, &res) == 0) {
+		gic_dist_physaddr = res.start;
+		pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
+	}
+}
+
+#else
+#define gic_init_physaddr(node)  do { } while (0)
+#endif
+
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
@@ -675,16 +775,25 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		irq_set_chip_and_handler(irq, &gic_chip,
 					 handle_fasteoi_irq);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+
+		gic_routable_irq_domain_ops->map(d, irq, hw);
 	}
 	irq_set_chip_data(irq, d->host_data);
 	return 0;
 }
 
+static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	gic_routable_irq_domain_ops->unmap(d, irq);
+}
+
 static int gic_irq_domain_xlate(struct irq_domain *d,
 				struct device_node *controller,
 				const u32 *intspec, unsigned int intsize,
 				unsigned long *out_hwirq, unsigned int *out_type)
 {
+	unsigned long ret = 0;
+
 	if (d->of_node != controller)
 		return -EINVAL;
 	if (intsize < 3)
@@ -694,11 +803,20 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 	*out_hwirq = intspec[1] + 16;
 
 	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
-	if (!intspec[0])
-		*out_hwirq += 16;
+	if (!intspec[0]) {
+		ret = gic_routable_irq_domain_ops->xlate(d, controller,
+							 intspec,
+							 intsize,
+							 out_hwirq,
+							 out_type);
+
+		if (IS_ERR_VALUE(ret))
+			return ret;
+	}
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
-	return 0;
+
+	return ret;
 }
 
 #ifdef CONFIG_SMP
@@ -720,11 +838,43 @@ static struct notifier_block __cpuinitdata gic_cpu_notifier = {
 };
 #endif
 
-const struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
+	.unmap = gic_irq_domain_unmap,
 	.xlate = gic_irq_domain_xlate,
 };
 
+/* Default functions for routable irq domain */
+static int gic_routable_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	return 0;
+}
+
+static void gic_routable_irq_domain_unmap(struct irq_domain *d,
+					  unsigned int irq)
+{
+}
+
+static int gic_routable_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq,
+				unsigned int *out_type)
+{
+	*out_hwirq += 16;
+	return 0;
+}
+
+const struct irq_domain_ops gic_default_routable_irq_domain_ops = {
+	.map = gic_routable_irq_domain_map,
+	.unmap = gic_routable_irq_domain_unmap,
+	.xlate = gic_routable_irq_domain_xlate,
+};
+
+const struct irq_domain_ops *gic_routable_irq_domain_ops =
+					&gic_default_routable_irq_domain_ops;
+
 void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 			   void __iomem *dist_base, void __iomem *cpu_base,
 			   u32 percpu_offset, struct device_node *node)
@@ -732,6 +882,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	irq_hw_number_t hwirq_base;
 	struct gic_chip_data *gic;
 	int gic_irqs, irq_base, i;
+	int nr_routable_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -750,7 +901,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 		}
 
 		for_each_possible_cpu(cpu) {
-			unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+			u32 mpidr = cpu_logical_map(cpu);
+			u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			unsigned long offset = percpu_offset * core_id;
 			*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
 			*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
 		}
@@ -797,23 +950,35 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	gic->gic_irqs = gic_irqs;
 
 	gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-	irq_base = irq_alloc_descs(irq_start, 16, gic_irqs, numa_node_id());
-	if (IS_ERR_VALUE(irq_base)) {
-		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
-		     irq_start);
-		irq_base = irq_start;
+
+	if (of_property_read_u32(node, "arm,routable-irqs",
+				 &nr_routable_irqs)) {
+		irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+					   numa_node_id());
+		if (IS_ERR_VALUE(irq_base)) {
+			WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+			     irq_start);
+			irq_base = irq_start;
+		}
+
+		gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
+					hwirq_base, &gic_irq_domain_ops, gic);
+	} else {
+		gic->domain = irq_domain_add_linear(node, nr_routable_irqs,
+						    &gic_irq_domain_ops,
+						    gic);
 	}
-	gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
-				    hwirq_base, &gic_irq_domain_ops, gic);
+
 	if (WARN_ON(!gic->domain))
 		return;
 
+	if (gic_nr == 0) {
 #ifdef CONFIG_SMP
-	set_smp_cross_call(gic_raise_softirq);
-	register_cpu_notifier(&gic_cpu_notifier);
+		set_smp_cross_call(gic_raise_softirq);
+		register_cpu_notifier(&gic_cpu_notifier);
 #endif
-
-	set_handle_irq(gic_handle_irq);
+		set_handle_irq(gic_handle_irq);
+	}
 
 	gic_chip.flags |= gic_arch_extn.flags;
 	gic_dist_init(gic);
@@ -824,7 +989,8 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 #ifdef CONFIG_OF
 static int gic_cnt __initdata;
 
-int __init gic_of_init(struct device_node *node, struct device_node *parent)
+static int __init
+gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
 	void __iomem *dist_base;
@@ -844,6 +1010,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 		percpu_offset = 0;
 
 	gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
+	if (!gic_cnt)
+		gic_init_physaddr(node);
 
 	if (parent) {
 		irq = irq_of_parse_and_map(node, 0);
@@ -852,8 +1020,10 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 	gic_cnt++;
 	return 0;
 }
+IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
 IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
 IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
+IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 92c41ab4dbfd..2cb474ad8809 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -515,7 +515,7 @@ static int meta_intc_set_affinity(struct irq_data *data,
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr);
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 8e94d7a3b20d..c16c186d97d3 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -201,7 +201,7 @@ static int metag_internal_irq_set_affinity(struct irq_data *data,
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)),
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index 927bff373aac..2f404ba61c6c 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -248,8 +248,8 @@ static int irqc_probe(struct platform_device *pdev)
 
 	return 0;
 err3:
-	for (; k >= 0; k--)
-		free_irq(p->irq[k - 1].requested_irq, &p->irq[k - 1]);
+	while (--k >= 0)
+		free_irq(p->irq[k].requested_irq, &p->irq[k]);
 
 	irq_domain_remove(p->irq_domain);
 err2:
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 8527743b5cef..391b9cea73ed 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -125,7 +125,7 @@ static struct spear_shirq spear320_shirq_ras2 = {
 };
 
 static struct spear_shirq spear320_shirq_ras3 = {
-	.irq_nr = 3,
+	.irq_nr = 7,
 	.irq_bit_off = 0,
 	.invalid_irq = 1,
 	.regs = {
diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index baf2686aa8eb..5a4da94aefb0 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card *card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }
@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
 	case 7:
 		/* 0x;EAZ */
 		p += 3;
+		if (strlen(p) >= sizeof(card->eazlist[0]))
+			break;
 		strcpy(card->eazlist[ch - 1], p);
 		break;
 	case 8:
@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 	case ISDN_PTYPE_EURO:
@@ -1083,8 +1091,10 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 			spin_unlock_irqrestore(&card->isdnloop_lock, flags);
 			return -ENOMEM;
 		}
-		for (i = 0; i < 3; i++)
-			strcpy(card->s0num[i], sdef.num[i]);
+		for (i = 0; i < 3; i++) {
+			strlcpy(card->s0num[i], sdef.num[i],
+				sizeof(card->s0num[0]));
+		}
 		break;
 	case ISDN_PTYPE_1TR6:
 		if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95",
@@ -1097,7 +1107,7 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 			spin_unlock_irqrestore(&card->isdnloop_lock, flags);
 			return -ENOMEM;
 		}
-		strcpy(card->s0num[0], sdef.num[0]);
+		strlcpy(card->s0num[0], sdef.num[0], sizeof(card->s0num[0]));
 		card->s0num[1][0] = '\0';
 		card->s0num[2][0] = '\0';
 		break;
@@ -1125,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;
 
@@ -1190,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			break;
 		if ((c->arg & 255) < ISDNLOOP_BCH) {
 			char *p;
-			char dial[50];
 			char dcode[4];
 
 			a = c->arg;
@@ -1202,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			} else
 				/* Normal Dial */
 				strcpy(dcode, "CAL");
-			strcpy(dial, p);
-			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-				dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+			snprintf(cbuf, sizeof(cbuf),
+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+				 dcode, p, c->parm.setup.si1,
+				 c->parm.setup.si2, c->parm.setup.eazmsn);
 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 		}
 		break;
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index e47dcb9d1e91..5cefb479c707 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -117,7 +117,6 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sk_buff		*skb;
 	struct sock		*sk = sock->sk;
-	struct sockaddr_mISDN	*maddr;
 
 	int		copied, err;
 
@@ -135,9 +134,9 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return err;
 
-	if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) {
-		msg->msg_namelen = sizeof(struct sockaddr_mISDN);
-		maddr = (struct sockaddr_mISDN *)msg->msg_name;
+	if (msg->msg_name) {
+		struct sockaddr_mISDN *maddr = msg->msg_name;
+
 		maddr->family = AF_ISDN;
 		maddr->dev = _pms(sk)->dev->id;
 		if ((sk->sk_protocol == ISDN_P_LAPD_TE) ||
@@ -150,11 +149,7 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 			maddr->sapi = _pms(sk)->ch.addr & 0xFF;
 			maddr->tei =  (_pms(sk)->ch.addr >> 8) & 0xFF;
 		}
-	} else {
-		if (msg->msg_namelen)
-			printk(KERN_WARNING "%s: too small namelen %d\n",
-			       __func__, msg->msg_namelen);
-		msg->msg_namelen = 0;
+		msg->msg_namelen = sizeof(*maddr);
 	}
 
 	copied = skb->len + MISDN_HEADER_LEN;
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index faf52c005e8c..5d64b2431415 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -82,6 +82,15 @@ static inline size_t sizeof_pwm_leds_priv(int num_leds)
 		      (sizeof(struct led_pwm_data) * num_leds);
 }
 
+static void led_pwm_cleanup(struct led_pwm_priv *priv)
+{
+	while (priv->num_leds--) {
+		led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+		if (priv->leds[priv->num_leds].can_sleep)
+			cancel_work_sync(&priv->leds[priv->num_leds].work);
+	}
+}
+
 static struct led_pwm_priv *led_pwm_create_of(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
@@ -139,8 +148,7 @@ static struct led_pwm_priv *led_pwm_create_of(struct platform_device *pdev)
 
 	return priv;
 err:
-	while (priv->num_leds--)
-		led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+	led_pwm_cleanup(priv);
 
 	return NULL;
 }
@@ -200,8 +208,8 @@ static int led_pwm_probe(struct platform_device *pdev)
 	return 0;
 
 err:
-	while (i--)
-		led_classdev_unregister(&priv->leds[i].cdev);
+	priv->num_leds = i;
+	led_pwm_cleanup(priv);
 
 	return ret;
 }
@@ -209,13 +217,8 @@ err:
 static int led_pwm_remove(struct platform_device *pdev)
 {
 	struct led_pwm_priv *priv = platform_get_drvdata(pdev);
-	int i;
 
-	for (i = 0; i < priv->num_leds; i++) {
-		led_classdev_unregister(&priv->leds[i].cdev);
-		if (priv->leds[i].can_sleep)
-			cancel_work_sync(&priv->leds[i].work);
-	}
+	led_pwm_cleanup(priv);
 
 	return 0;
 }
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index f0a3347b6441..516923926335 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -700,7 +700,7 @@ void lguest_arch_setup_regs(struct lg_cpu *cpu, unsigned long start)
 	 * interrupts are enabled.  We always leave interrupts enabled while
 	 * running the Guest.
 	 */
-	regs->eflags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+	regs->eflags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 
 	/*
 	 * The "Extended Instruction Pointer" register says where the Guest is
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 543ad6a79505..fefef7ebcbec 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -1 +1,5 @@
+# Generic MAILBOX API
+
+obj-$(CONFIG_MAILBOX)		+= mailbox.o
+
 obj-$(CONFIG_PL320_MBOX)	+= pl320-ipc.o
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
new file mode 100644
index 000000000000..afcb430508ec
--- /dev/null
+++ b/drivers/mailbox/mailbox.c
@@ -0,0 +1,465 @@
+/*
+ * Mailbox: Common code for Mailbox controllers and users
+ *
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/bitops.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox_controller.h>
+
+#define TXDONE_BY_IRQ	BIT(0) /* controller has remote RTR irq */
+#define TXDONE_BY_POLL	BIT(1) /* controller can read status of last TX */
+#define TXDONE_BY_ACK	BIT(2) /* S/W ACK recevied by Client ticks the TX */
+
+static LIST_HEAD(mbox_cons);
+static DEFINE_MUTEX(con_mutex);
+
+static int add_to_rbuf(struct mbox_chan *chan, void *mssg)
+{
+	int idx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	/* See if there is any space left */
+	if (chan->msg_count == MBOX_TX_QUEUE_LEN) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -ENOBUFS;
+	}
+
+	idx = chan->msg_free;
+	chan->msg_data[idx] = mssg;
+	chan->msg_count++;
+
+	if (idx == MBOX_TX_QUEUE_LEN - 1)
+		chan->msg_free = 0;
+	else
+		chan->msg_free++;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return idx;
+}
+
+static void msg_submit(struct mbox_chan *chan)
+{
+	unsigned count, idx;
+	unsigned long flags;
+	void *data;
+	int err;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	if (!chan->msg_count || chan->active_req)
+		goto exit;
+
+	count = chan->msg_count;
+	idx = chan->msg_free;
+	if (idx >= count)
+		idx -= count;
+	else
+		idx += MBOX_TX_QUEUE_LEN - count;
+
+	data = chan->msg_data[idx];
+
+	/* Try to submit a message to the MBOX controller */
+	err = chan->mbox->ops->send_data(chan, data);
+	if (!err) {
+		chan->active_req = data;
+		chan->msg_count--;
+	}
+exit:
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+static void tx_tick(struct mbox_chan *chan, int r)
+{
+	unsigned long flags;
+	void *mssg;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	mssg = chan->active_req;
+	chan->active_req = NULL;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	/* Submit next message */
+	msg_submit(chan);
+
+	/* Notify the client */
+	if (mssg && chan->cl->tx_done)
+		chan->cl->tx_done(chan->cl, mssg, r);
+
+	if (chan->cl->tx_block)
+		complete(&chan->tx_complete);
+}
+
+static void poll_txdone(unsigned long data)
+{
+	struct mbox_controller *mbox = (struct mbox_controller *)data;
+	bool txdone, resched = false;
+	int i;
+
+	for (i = 0; i < mbox->num_chans; i++) {
+		struct mbox_chan *chan = &mbox->chans[i];
+
+		if (chan->active_req && chan->cl) {
+			resched = true;
+			txdone = chan->mbox->ops->last_tx_done(chan);
+			if (txdone)
+				tx_tick(chan, 0);
+		}
+	}
+
+	if (resched)
+		mod_timer(&mbox->poll, jiffies +
+				msecs_to_jiffies(mbox->txpoll_period));
+}
+
+/**
+ * mbox_chan_received_data - A way for controller driver to push data
+ *				received from remote to the upper layer.
+ * @chan: Pointer to the mailbox channel on which RX happened.
+ * @mssg: Client specific message typecasted as void *
+ *
+ * After startup and before shutdown any data received on the chan
+ * is passed on to the API via atomic mbox_chan_received_data().
+ * The controller should ACK the RX only after this call returns.
+ */
+void mbox_chan_received_data(struct mbox_chan *chan, void *mssg)
+{
+	/* No buffering the received data */
+	if (chan->cl->rx_callback)
+		chan->cl->rx_callback(chan->cl, mssg);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_received_data);
+
+/**
+ * mbox_chan_txdone - A way for controller driver to notify the
+ *			framework that the last TX has completed.
+ * @chan: Pointer to the mailbox chan on which TX happened.
+ * @r: Status of last TX - OK or ERROR
+ *
+ * The controller that has IRQ for TX ACK calls this atomic API
+ * to tick the TX state machine. It works only if txdone_irq
+ * is set by the controller.
+ */
+void mbox_chan_txdone(struct mbox_chan *chan, int r)
+{
+	if (unlikely(!(chan->txdone_method & TXDONE_BY_IRQ))) {
+		dev_err(chan->mbox->dev,
+		       "Controller can't run the TX ticker\n");
+		return;
+	}
+
+	tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_txdone);
+
+/**
+ * mbox_client_txdone - The way for a client to run the TX state machine.
+ * @chan: Mailbox channel assigned to this client.
+ * @r: Success status of last transmission.
+ *
+ * The client/protocol had received some 'ACK' packet and it notifies
+ * the API that the last packet was sent successfully. This only works
+ * if the controller can't sense TX-Done.
+ */
+void mbox_client_txdone(struct mbox_chan *chan, int r)
+{
+	if (unlikely(!(chan->txdone_method & TXDONE_BY_ACK))) {
+		dev_err(chan->mbox->dev, "Client can't run the TX ticker\n");
+		return;
+	}
+
+	tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_client_txdone);
+
+/**
+ * mbox_client_peek_data - A way for client driver to pull data
+ *			received from remote by the controller.
+ * @chan: Mailbox channel assigned to this client.
+ *
+ * A poke to controller driver for any received data.
+ * The data is actually passed onto client via the
+ * mbox_chan_received_data()
+ * The call can be made from atomic context, so the controller's
+ * implementation of peek_data() must not sleep.
+ *
+ * Return: True, if controller has, and is going to push after this,
+ *          some data.
+ *         False, if controller doesn't have any data to be read.
+ */
+bool mbox_client_peek_data(struct mbox_chan *chan)
+{
+	if (chan->mbox->ops->peek_data)
+		return chan->mbox->ops->peek_data(chan);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(mbox_client_peek_data);
+
+/**
+ * mbox_send_message -	For client to submit a message to be
+ *				sent to the remote.
+ * @chan: Mailbox channel assigned to this client.
+ * @mssg: Client specific message typecasted.
+ *
+ * For client to submit data to the controller destined for a remote
+ * processor. If the client had set 'tx_block', the call will return
+ * either when the remote receives the data or when 'tx_tout' millisecs
+ * run out.
+ *  In non-blocking mode, the requests are buffered by the API and a
+ * non-negative token is returned for each queued request. If the request
+ * is not queued, a negative token is returned. Upon failure or successful
+ * TX, the API calls 'tx_done' from atomic context, from which the client
+ * could submit yet another request.
+ * The pointer to message should be preserved until it is sent
+ * over the chan, i.e, tx_done() is made.
+ * This function could be called from atomic context as it simply
+ * queues the data and returns a token against the request.
+ *
+ * Return: Non-negative integer for successful submission (non-blocking mode)
+ *	or transmission over chan (blocking mode).
+ *	Negative value denotes failure.
+ */
+int mbox_send_message(struct mbox_chan *chan, void *mssg)
+{
+	int t;
+
+	if (!chan || !chan->cl)
+		return -EINVAL;
+
+	t = add_to_rbuf(chan, mssg);
+	if (t < 0) {
+		dev_err(chan->mbox->dev, "Try increasing MBOX_TX_QUEUE_LEN\n");
+		return t;
+	}
+
+	msg_submit(chan);
+
+	if (chan->txdone_method	== TXDONE_BY_POLL)
+		poll_txdone((unsigned long)chan->mbox);
+
+	if (chan->cl->tx_block && chan->active_req) {
+		unsigned long wait;
+		int ret;
+
+		if (!chan->cl->tx_tout) /* wait forever */
+			wait = msecs_to_jiffies(3600000);
+		else
+			wait = msecs_to_jiffies(chan->cl->tx_tout);
+
+		ret = wait_for_completion_timeout(&chan->tx_complete, wait);
+		if (ret == 0) {
+			t = -EIO;
+			tx_tick(chan, -EIO);
+		}
+	}
+
+	return t;
+}
+EXPORT_SYMBOL_GPL(mbox_send_message);
+
+/**
+ * mbox_request_channel - Request a mailbox channel.
+ * @cl: Identity of the client requesting the channel.
+ * @index: Index of mailbox specifier in 'mboxes' property.
+ *
+ * The Client specifies its requirements and capabilities while asking for
+ * a mailbox channel. It can't be called from atomic context.
+ * The channel is exclusively allocated and can't be used by another
+ * client before the owner calls mbox_free_channel.
+ * After assignment, any packet received on this channel will be
+ * handed over to the client via the 'rx_callback'.
+ * The framework holds reference to the client, so the mbox_client
+ * structure shouldn't be modified until the mbox_free_channel returns.
+ *
+ * Return: Pointer to the channel assigned to the client if successful.
+ *		ERR_PTR for request failure.
+ */
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
+{
+	struct device *dev = cl->dev;
+	struct mbox_controller *mbox;
+	struct of_phandle_args spec;
+	struct mbox_chan *chan;
+	unsigned long flags;
+	int ret;
+
+	if (!dev || !dev->of_node) {
+		pr_debug("%s: No owner device node\n", __func__);
+		return ERR_PTR(-ENODEV);
+	}
+
+	mutex_lock(&con_mutex);
+
+	if (of_parse_phandle_with_args(dev->of_node, "mboxes",
+				       "#mbox-cells", index, &spec)) {
+		dev_dbg(dev, "%s: can't parse \"mboxes\" property\n", __func__);
+		mutex_unlock(&con_mutex);
+		return ERR_PTR(-ENODEV);
+	}
+
+	chan = NULL;
+	list_for_each_entry(mbox, &mbox_cons, node)
+		if (mbox->dev->of_node == spec.np) {
+			chan = mbox->of_xlate(mbox, &spec);
+			break;
+		}
+
+	of_node_put(spec.np);
+
+	if (!chan || chan->cl || !try_module_get(mbox->dev->driver->owner)) {
+		dev_dbg(dev, "%s: mailbox not free\n", __func__);
+		mutex_unlock(&con_mutex);
+		return ERR_PTR(-EBUSY);
+	}
+
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->msg_free = 0;
+	chan->msg_count = 0;
+	chan->active_req = NULL;
+	chan->cl = cl;
+	init_completion(&chan->tx_complete);
+
+	if (chan->txdone_method	== TXDONE_BY_POLL && cl->knows_txdone)
+		chan->txdone_method |= TXDONE_BY_ACK;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	ret = chan->mbox->ops->startup(chan);
+	if (ret) {
+		dev_err(dev, "Unable to startup the chan (%d)\n", ret);
+		mbox_free_channel(chan);
+		chan = ERR_PTR(ret);
+	}
+
+	mutex_unlock(&con_mutex);
+	return chan;
+}
+EXPORT_SYMBOL_GPL(mbox_request_channel);
+
+/**
+ * mbox_free_channel - The client relinquishes control of a mailbox
+ *			channel by this call.
+ * @chan: The mailbox channel to be freed.
+ */
+void mbox_free_channel(struct mbox_chan *chan)
+{
+	unsigned long flags;
+
+	if (!chan || !chan->cl)
+		return;
+
+	chan->mbox->ops->shutdown(chan);
+
+	/* The queued TX requests are simply aborted, no callbacks are made */
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->cl = NULL;
+	chan->active_req = NULL;
+	if (chan->txdone_method == (TXDONE_BY_POLL | TXDONE_BY_ACK))
+		chan->txdone_method = TXDONE_BY_POLL;
+
+	module_put(chan->mbox->dev->driver->owner);
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mbox_free_channel);
+
+static struct mbox_chan *
+of_mbox_index_xlate(struct mbox_controller *mbox,
+		    const struct of_phandle_args *sp)
+{
+	int ind = sp->args[0];
+
+	if (ind >= mbox->num_chans)
+		return NULL;
+
+	return &mbox->chans[ind];
+}
+
+/**
+ * mbox_controller_register - Register the mailbox controller
+ * @mbox:	Pointer to the mailbox controller.
+ *
+ * The controller driver registers its communication channels
+ */
+int mbox_controller_register(struct mbox_controller *mbox)
+{
+	int i, txdone;
+
+	/* Sanity check */
+	if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans)
+		return -EINVAL;
+
+	if (mbox->txdone_irq)
+		txdone = TXDONE_BY_IRQ;
+	else if (mbox->txdone_poll)
+		txdone = TXDONE_BY_POLL;
+	else /* It has to be ACK then */
+		txdone = TXDONE_BY_ACK;
+
+	if (txdone == TXDONE_BY_POLL) {
+		mbox->poll.function = &poll_txdone;
+		mbox->poll.data = (unsigned long)mbox;
+		init_timer(&mbox->poll);
+	}
+
+	for (i = 0; i < mbox->num_chans; i++) {
+		struct mbox_chan *chan = &mbox->chans[i];
+
+		chan->cl = NULL;
+		chan->mbox = mbox;
+		chan->txdone_method = txdone;
+		spin_lock_init(&chan->lock);
+	}
+
+	if (!mbox->of_xlate)
+		mbox->of_xlate = of_mbox_index_xlate;
+
+	mutex_lock(&con_mutex);
+	list_add_tail(&mbox->node, &mbox_cons);
+	mutex_unlock(&con_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mbox_controller_register);
+
+/**
+ * mbox_controller_unregister - Unregister the mailbox controller
+ * @mbox:	Pointer to the mailbox controller.
+ */
+void mbox_controller_unregister(struct mbox_controller *mbox)
+{
+	int i;
+
+	if (!mbox)
+		return;
+
+	mutex_lock(&con_mutex);
+
+	list_del(&mbox->node);
+
+	for (i = 0; i < mbox->num_chans; i++)
+		mbox_free_channel(&mbox->chans[i]);
+
+	if (mbox->txdone_poll)
+		del_timer_sync(&mbox->poll);
+
+	mutex_unlock(&con_mutex);
+}
+EXPORT_SYMBOL_GPL(mbox_controller_unregister);
diff --git a/drivers/mailbox/pl320-ipc.c b/drivers/mailbox/pl320-ipc.c
index d873cbae2fbb..f3755e0aa935 100644
--- a/drivers/mailbox/pl320-ipc.c
+++ b/drivers/mailbox/pl320-ipc.c
@@ -26,7 +26,7 @@
 #include <linux/device.h>
 #include <linux/amba/bus.h>
 
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 
 #define IPCMxSOURCE(m)		((m) * 0x40)
 #define IPCMxDSET(m)		(((m) * 0x40) + 0x004)
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 3bfc8f1da9fe..29cff90096ad 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -176,8 +176,12 @@ config MD_FAULTY
 
 source "drivers/md/bcache/Kconfig"
 
+config BLK_DEV_DM_BUILTIN
+	boolean
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
+	select BLK_DEV_DM_BUILTIN
 	---help---
 	  Device-mapper is a low level volume manager.  It works by allowing
 	  people to specify mappings for ranges of logical sectors.  Various
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 1439fd4ad9b1..3591a7292381 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
+obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
 obj-$(CONFIG_DM_BIO_PRISON)	+= dm-bio-prison.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index c42b14b2304c..6bc016eabdc9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -499,7 +499,7 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	struct ratelimit	writeback_rate;
+	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
 	/*
@@ -508,10 +508,9 @@ struct cached_dev {
 	 */
 	sector_t		last_read;
 
-	/* Number of writeback bios in flight */
-	atomic_t		in_flight;
+	/* Limit number of writeback bios in flight */
+	struct semaphore	in_flight;
 	struct closure_with_timer writeback;
-	struct closure_waitlist	writeback_wait;
 
 	struct keybuf		writeback_keys;
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index cb4578a327b9..1b27cbd822e1 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -918,29 +918,59 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
 
 /* Mergesort */
 
-static void btree_sort_fixup(struct btree_iter *iter)
+static void sort_key_next(struct btree_iter *iter,
+			  struct btree_iter_set *i)
+{
+	i->k = bkey_next(i->k);
+
+	if (i->k == i->end)
+		*i = iter->data[--iter->used];
+}
+
+static struct bkey *btree_sort_fixup(struct btree_iter *iter, struct bkey *tmp)
 {
 	while (iter->used > 1) {
 		struct btree_iter_set *top = iter->data, *i = top + 1;
-		struct bkey *k;
 
 		if (iter->used > 2 &&
 		    btree_iter_cmp(i[0], i[1]))
 			i++;
 
-		for (k = i->k;
-		     k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
-		     k = bkey_next(k))
-			if (top->k > i->k)
-				__bch_cut_front(top->k, k);
-			else if (KEY_SIZE(k))
-				bch_cut_back(&START_KEY(k), top->k);
-
-		if (top->k < i->k || k == i->k)
+		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
 			break;
 
-		heap_sift(iter, i - top, btree_iter_cmp);
+		if (!KEY_SIZE(i->k)) {
+			sort_key_next(iter, i);
+			heap_sift(iter, i - top, btree_iter_cmp);
+			continue;
+		}
+
+		if (top->k > i->k) {
+			if (bkey_cmp(top->k, i->k) >= 0)
+				sort_key_next(iter, i);
+			else
+				bch_cut_front(top->k, i->k);
+
+			heap_sift(iter, i - top, btree_iter_cmp);
+		} else {
+			/* can't happen because of comparison func */
+			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
+
+			if (bkey_cmp(i->k, top->k) < 0) {
+				bkey_copy(tmp, top->k);
+
+				bch_cut_back(&START_KEY(i->k), tmp);
+				bch_cut_front(i->k, top->k);
+				heap_sift(iter, 0, btree_iter_cmp);
+
+				return tmp;
+			} else {
+				bch_cut_back(&START_KEY(i->k), top->k);
+			}
+		}
 	}
+
+	return NULL;
 }
 
 static void btree_mergesort(struct btree *b, struct bset *out,
@@ -948,15 +978,20 @@ static void btree_mergesort(struct btree *b, struct bset *out,
 			    bool fixup, bool remove_stale)
 {
 	struct bkey *k, *last = NULL;
+	BKEY_PADDED(k) tmp;
 	bool (*bad)(struct btree *, const struct bkey *) = remove_stale
 		? bch_ptr_bad
 		: bch_ptr_invalid;
 
 	while (!btree_iter_end(iter)) {
 		if (fixup && !b->level)
-			btree_sort_fixup(iter);
+			k = btree_sort_fixup(iter, &tmp.k);
+		else
+			k = NULL;
+
+		if (!k)
+			k = bch_btree_iter_next(iter);
 
-		k = bch_btree_iter_next(iter);
 		if (bad(b, k))
 			continue;
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 833c590806ba..7d3deab11fce 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -633,7 +633,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
 		return mca_can_free(c) * c->btree_pages;
 
 	/* Return -1 if we can't do anything right now */
-	if (sc->gfp_mask & __GFP_WAIT)
+	if (sc->gfp_mask & __GFP_IO)
 		mutex_lock(&c->bucket_lock);
 	else if (!mutex_trylock(&c->bucket_lock))
 		return -1;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index b49abb246bb6..151a4ab90dd4 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -151,7 +151,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
 		pr_debug("%u journal buckets", ca->sb.njournal_buckets);
 
-		/* Read journal buckets ordered by golden ratio hash to quickly
+		/*
+		 * Read journal buckets ordered by golden ratio hash to quickly
 		 * find a sequence of buckets with valid journal entries
 		 */
 		for (i = 0; i < ca->sb.njournal_buckets; i++) {
@@ -164,18 +165,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 				goto bsearch;
 		}
 
-		/* If that fails, check all the buckets we haven't checked
+		/*
+		 * If that fails, check all the buckets we haven't checked
 		 * already
 		 */
 		pr_debug("falling back to linear search");
 
-		for (l = 0; l < ca->sb.njournal_buckets; l++) {
-			if (test_bit(l, bitmap))
-				continue;
-
+		for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
+		     l < ca->sb.njournal_buckets;
+		     l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
 			if (read_bucket(l))
 				goto bsearch;
-		}
+
+		if (list_empty(list))
+			continue;
 bsearch:
 		/* Binary search */
 		m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
@@ -195,10 +198,12 @@ bsearch:
 				r = m;
 		}
 
-		/* Read buckets in reverse order until we stop finding more
+		/*
+		 * Read buckets in reverse order until we stop finding more
 		 * journal entries
 		 */
-		pr_debug("finishing up");
+		pr_debug("finishing up: m %u njournal_buckets %u",
+			 m, ca->sb.njournal_buckets);
 		l = m;
 
 		while (1) {
@@ -226,9 +231,10 @@ bsearch:
 			}
 	}
 
-	c->journal.seq = list_entry(list->prev,
-				    struct journal_replay,
-				    list)->j.seq;
+	if (!list_empty(list))
+		c->journal.seq = list_entry(list->prev,
+					    struct journal_replay,
+					    list)->j.seq;
 
 	return 0;
 #undef read_bucket
@@ -425,7 +431,7 @@ static void do_journal_discard(struct cache *ca)
 		return;
 	}
 
-	switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) {
+	switch (atomic_read(&ja->discard_in_flight)) {
 	case DISCARD_IN_FLIGHT:
 		return;
 
@@ -686,6 +692,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl)
 		if (cl)
 			BUG_ON(!closure_wait(&w->wait, cl));
 
+		closure_flush(&c->journal.io);
 		__journal_try_write(c, true);
 	}
 }
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index afb9a998a737..a30a0f8a41c0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1055,17 +1055,19 @@ static void request_write(struct cached_dev *dc, struct search *s)
 	} else {
 		trace_bcache_writeback(s->orig_bio);
 		bch_writeback_add(dc, bio_sectors(bio));
+		s->op.cache_bio = bio;
 
-		if (s->op.flush_journal) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			/* Also need to send a flush to the backing device */
-			s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
-							   dc->disk.bio_split);
-
-			bio->bi_size = 0;
-			bio->bi_vcnt = 0;
-			closure_bio_submit(bio, cl, s->d);
-		} else {
-			s->op.cache_bio = bio;
+			struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0,
+							     dc->disk.bio_split);
+
+			flush->bi_rw	= WRITE_FLUSH;
+			flush->bi_bdev	= bio->bi_bdev;
+			flush->bi_end_io = request_endio;
+			flush->bi_private = cl;
+
+			closure_bio_submit(flush, cl, s->d);
 		}
 	}
 out:
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4d9cca47e4c6..e9bd6c0cca5b 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -214,7 +214,13 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_label) {
-		memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+		if (size > SB_LABEL_SIZE)
+			return -EINVAL;
+		memcpy(dc->sb.label, buf, size);
+		if (size < SB_LABEL_SIZE)
+			dc->sb.label[size] = '\0';
+		if (size && dc->sb.label[size - 1] == '\n')
+			dc->sb.label[size - 1] = '\0';
 		bch_write_bdev_super(dc, NULL);
 		if (dc->disk.c) {
 			memcpy(dc->disk.c->uuids[dc->disk.id].label,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index da3a99e85b1e..38a43f8d36ec 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time)
 	stats->last = now ?: 1;
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
+/**
+ * bch_next_delay() - increment @d by the amount of work done, and return how
+ * long to delay until the next time to do some work.
+ *
+ * @d - the struct bch_ratelimit to update
+ * @done - the amount of work done, in arbitrary units
+ *
+ * Returns the amount of time to delay by, in jiffies
+ */
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 577393e38c3a..43fd78affcea 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -452,17 +452,23 @@ read_attribute(name ## _last_ ## frequency_units)
 	(ewma) >> factor;						\
 })
 
-struct ratelimit {
+struct bch_ratelimit {
+	/* Next time we want to do some work, in nanoseconds */
 	uint64_t		next;
+
+	/*
+	 * Rate at which we want to do work, in units per nanosecond
+	 * The units here correspond to the units passed to bch_next_delay()
+	 */
 	unsigned		rate;
 };
 
-static inline void ratelimit_reset(struct ratelimit *d)
+static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
 {
 	d->next = local_clock();
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done);
 
 #define __DIV_SAFE(n, d, zero)						\
 ({									\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 2714ed3991d1..841f0490d4ef 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -91,11 +91,15 @@ static void update_writeback_rate(struct work_struct *work)
 
 static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
 {
+	uint64_t ret;
+
 	if (atomic_read(&dc->disk.detaching) ||
 	    !dc->writeback_percent)
 		return 0;
 
-	return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+	ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+
+	return min_t(uint64_t, ret, HZ);
 }
 
 /* Background writeback */
@@ -165,7 +169,7 @@ static void refill_dirty(struct closure *cl)
 
 	up_write(&dc->writeback_lock);
 
-	ratelimit_reset(&dc->writeback_rate);
+	bch_ratelimit_reset(&dc->writeback_rate);
 
 	/* Punt to workqueue only so we don't recurse and blow the stack */
 	continue_at(cl, read_dirty, dirty_wq);
@@ -246,9 +250,7 @@ static void write_dirty_finish(struct closure *cl)
 	}
 
 	bch_keybuf_del(&dc->writeback_keys, w);
-	atomic_dec_bug(&dc->in_flight);
-
-	closure_wake_up(&dc->writeback_wait);
+	up(&dc->in_flight);
 
 	closure_return_with_destructor(cl, dirty_io_destructor);
 }
@@ -278,7 +280,7 @@ static void write_dirty(struct closure *cl)
 	trace_bcache_write_dirty(&io->bio);
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty_finish, dirty_wq);
+	continue_at(cl, write_dirty_finish, system_wq);
 }
 
 static void read_dirty_endio(struct bio *bio, int error)
@@ -299,7 +301,7 @@ static void read_dirty_submit(struct closure *cl)
 	trace_bcache_read_dirty(&io->bio);
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty, dirty_wq);
+	continue_at(cl, write_dirty, system_wq);
 }
 
 static void read_dirty(struct closure *cl)
@@ -324,12 +326,8 @@ static void read_dirty(struct closure *cl)
 
 		if (delay > 0 &&
 		    (KEY_START(&w->key) != dc->last_read ||
-		     jiffies_to_msecs(delay) > 50)) {
-			w->private = NULL;
-
-			closure_delay(&dc->writeback, delay);
-			continue_at(cl, read_dirty, dirty_wq);
-		}
+		     jiffies_to_msecs(delay) > 50))
+			delay = schedule_timeout_uninterruptible(delay);
 
 		dc->last_read	= KEY_OFFSET(&w->key);
 
@@ -354,15 +352,10 @@ static void read_dirty(struct closure *cl)
 
 		pr_debug("%s", pkey(&w->key));
 
-		closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
+		down(&dc->in_flight);
+		closure_call(&io->cl, read_dirty_submit, NULL, cl);
 
 		delay = writeback_delay(dc, KEY_SIZE(&w->key));
-
-		atomic_inc(&dc->in_flight);
-
-		if (!closure_wait_event(&dc->writeback_wait, cl,
-					atomic_read(&dc->in_flight) < 64))
-			continue_at(cl, read_dirty, dirty_wq);
 	}
 
 	if (0) {
@@ -372,11 +365,16 @@ err:
 		bch_keybuf_del(&dc->writeback_keys, w);
 	}
 
-	refill_dirty(cl);
+	/*
+	 * Wait for outstanding writeback IOs to finish (and keybuf slots to be
+	 * freed) before refilling again
+	 */
+	continue_at(cl, refill_dirty, dirty_wq);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
 {
+	sema_init(&dc->in_flight, 64);
 	closure_init_unlocked(&dc->writeback);
 	init_rwsem(&dc->writeback_lock);
 
@@ -406,7 +404,7 @@ void bch_writeback_exit(void)
 
 int __init bch_writeback_init(void)
 {
-	dirty_wq = create_singlethread_workqueue("bcache_writeback");
+	dirty_wq = create_workqueue("bcache_writeback");
 	if (!dirty_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 5a2c75499824..a79cbd6038f6 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -883,7 +883,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
-	int wait = 0;
 
 	if (!bitmap || !bitmap->storage.filemap ||
 	    test_bit(BITMAP_STALE, &bitmap->flags))
@@ -901,16 +900,13 @@ void bitmap_unplug(struct bitmap *bitmap)
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			write_page(bitmap, bitmap->storage.filemap[i], 0);
 		}
-		if (dirty)
-			wait = 1;
-	}
-	if (wait) { /* if any writes were performed, we need to wait on them */
-		if (bitmap->storage.file)
-			wait_event(bitmap->write_wait,
-				   atomic_read(&bitmap->pending_writes)==0);
-		else
-			md_super_wait(bitmap->mddev);
 	}
+	if (bitmap->storage.file)
+		wait_event(bitmap->write_wait,
+			   atomic_read(&bitmap->pending_writes)==0);
+	else
+		md_super_wait(bitmap->mddev);
+
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 0387e05cdb98..e855a190270d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -462,6 +462,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	c->n_buffers[dirty]++;
 	b->list_mode = dirty;
 	list_move(&b->lru_list, &c->lru[dirty]);
+	b->last_accessed = jiffies;
 }
 
 /*----------------------------------------------------------------
@@ -528,6 +529,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 		end_io(&b->bio, r);
 }
 
+static void inline_endio(struct bio *bio, int error)
+{
+	bio_end_io_t *end_fn = bio->bi_private;
+
+	/*
+	 * Reset the bio to free any attached resources
+	 * (e.g. bio integrity profiles).
+	 */
+	bio_reset(bio);
+
+	end_fn(bio, error);
+}
+
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 			   bio_end_io_t *end_io)
 {
@@ -539,7 +553,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
 	b->bio.bi_sector = block << b->c->sectors_per_block_bits;
 	b->bio.bi_bdev = b->c->bdev;
-	b->bio.bi_end_io = end_io;
+	b->bio.bi_end_io = inline_endio;
+	/*
+	 * Use of .bi_private isn't a problem here because
+	 * the dm_buffer's inline bio is local to bufio.
+	 */
+	b->bio.bi_private = end_io;
 
 	/*
 	 * We assume that if len >= PAGE_SIZE ptr is page-aligned.
@@ -1660,6 +1679,11 @@ static int __init dm_bufio_init(void)
 {
 	__u64 mem;
 
+	dm_bufio_allocated_kmem_cache = 0;
+	dm_bufio_allocated_get_free_pages = 0;
+	dm_bufio_allocated_vmalloc = 0;
+	dm_bufio_current_allocated = 0;
+
 	memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches);
 	memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names);
 
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
new file mode 100644
index 000000000000..6c9049c51b2b
--- /dev/null
+++ b/drivers/md/dm-builtin.c
@@ -0,0 +1,48 @@
+#include "dm.h"
+
+/*
+ * The kobject release method must not be placed in the module itself,
+ * otherwise we are subject to module unload races.
+ *
+ * The release method is called when the last reference to the kobject is
+ * dropped. It may be called by any other kernel code that drops the last
+ * reference.
+ *
+ * The release method suffers from module unload race. We may prevent the
+ * module from being unloaded at the start of the release method (using
+ * increased module reference count or synchronizing against the release
+ * method), however there is no way to prevent the module from being
+ * unloaded at the end of the release method.
+ *
+ * If this code were placed in the dm module, the following race may
+ * happen:
+ *  1. Some other process takes a reference to dm kobject
+ *  2. The user issues ioctl function to unload the dm device
+ *  3. dm_sysfs_exit calls kobject_put, however the object is not released
+ *     because of the other reference taken at step 1
+ *  4. dm_sysfs_exit waits on the completion
+ *  5. The other process that took the reference in step 1 drops it,
+ *     dm_kobject_release is called from this process
+ *  6. dm_kobject_release calls complete()
+ *  7. a reschedule happens before dm_kobject_release returns
+ *  8. dm_sysfs_exit continues, the dm device is unloaded, module reference
+ *     count is decremented
+ *  9. The user unloads the dm module
+ * 10. The other process that was rescheduled in step 7 continues to run,
+ *     it is now executing code in unloaded module, so it crashes
+ *
+ * Note that if the process that takes the foreign reference to dm kobject
+ * has a low priority and the system is sufficiently loaded with
+ * higher-priority processes that prevent the low-priority process from
+ * being scheduled long enough, this bug may really happen.
+ *
+ * In order to fix this module unload race, we place the release method
+ * into a helper code that is compiled directly into the kernel.
+ */
+
+void dm_kobject_release(struct kobject *kobj)
+{
+	complete(dm_get_completion_from_kobject(kobj));
+}
+
+EXPORT_SYMBOL(dm_kobject_release);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 1af7255bbffb..de737ba1d351 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -384,6 +384,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)cmd->data_block_size);
+		r = -EINVAL;
+		goto bad;
+	}
+
 	r = __check_incompat_features(disk_super, cmd);
 	if (r < 0)
 		goto bad;
@@ -511,8 +520,9 @@ static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
 	disk_super = dm_block_data(sblock);
 	update_flags(disk_super, mutator);
 	read_superblock_fields(cmd, disk_super);
+	dm_bm_unlock(sblock);
 
-	return dm_bm_flush_and_unlock(cmd->bm, sblock);
+	return dm_bm_flush(cmd->bm);
 }
 
 static int __begin_transaction(struct dm_cache_metadata *cmd)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index df44b60e66f2..677973641d2b 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -151,6 +151,9 @@ struct cache {
 	atomic_t nr_migrations;
 	wait_queue_head_t migration_wait;
 
+	wait_queue_head_t quiescing_wait;
+	atomic_t quiescing_ack;
+
 	/*
 	 * cache_size entries, dirty if set
 	 */
@@ -742,8 +745,9 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
 
 static void cleanup_migration(struct dm_cache_migration *mg)
 {
-	dec_nr_migrations(mg->cache);
+	struct cache *cache = mg->cache;
 	free_migration(mg);
+	dec_nr_migrations(cache);
 }
 
 static void migration_failure(struct dm_cache_migration *mg)
@@ -857,12 +861,13 @@ static void issue_copy_real(struct dm_cache_migration *mg)
 	int r;
 	struct dm_io_region o_region, c_region;
 	struct cache *cache = mg->cache;
+	sector_t cblock = from_cblock(mg->cblock);
 
 	o_region.bdev = cache->origin_dev->bdev;
 	o_region.count = cache->sectors_per_block;
 
 	c_region.bdev = cache->cache_dev->bdev;
-	c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+	c_region.sector = cblock * cache->sectors_per_block;
 	c_region.count = cache->sectors_per_block;
 
 	if (mg->writeback || mg->demote) {
@@ -1340,34 +1345,51 @@ static void writeback_some_dirty_blocks(struct cache *cache)
 /*----------------------------------------------------------------
  * Main worker loop
  *--------------------------------------------------------------*/
-static void start_quiescing(struct cache *cache)
+static bool is_quiescing(struct cache *cache)
 {
+	int r;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	cache->quiescing = 1;
+	r = cache->quiescing;
 	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return r;
 }
 
-static void stop_quiescing(struct cache *cache)
+static void ack_quiescing(struct cache *cache)
+{
+	if (is_quiescing(cache)) {
+		atomic_inc(&cache->quiescing_ack);
+		wake_up(&cache->quiescing_wait);
+	}
+}
+
+static void wait_for_quiescing_ack(struct cache *cache)
+{
+	wait_event(cache->quiescing_wait, atomic_read(&cache->quiescing_ack));
+}
+
+static void start_quiescing(struct cache *cache)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	cache->quiescing = 0;
+	cache->quiescing = true;
 	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wait_for_quiescing_ack(cache);
 }
 
-static bool is_quiescing(struct cache *cache)
+static void stop_quiescing(struct cache *cache)
 {
-	int r;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	r = cache->quiescing;
+	cache->quiescing = false;
 	spin_unlock_irqrestore(&cache->lock, flags);
 
-	return r;
+	atomic_set(&cache->quiescing_ack, 0);
 }
 
 static void wait_for_migrations(struct cache *cache)
@@ -1414,16 +1436,15 @@ static void do_worker(struct work_struct *ws)
 	struct cache *cache = container_of(ws, struct cache, worker);
 
 	do {
-		if (!is_quiescing(cache))
+		if (!is_quiescing(cache)) {
+			writeback_some_dirty_blocks(cache);
+			process_deferred_writethrough_bios(cache);
 			process_deferred_bios(cache);
+		}
 
 		process_migrations(cache, &cache->quiesced_migrations, issue_copy);
 		process_migrations(cache, &cache->completed_migrations, complete_migration);
 
-		writeback_some_dirty_blocks(cache);
-
-		process_deferred_writethrough_bios(cache);
-
 		if (commit_if_needed(cache)) {
 			process_deferred_flush_bios(cache, false);
 
@@ -1436,6 +1457,9 @@ static void do_worker(struct work_struct *ws)
 			process_migrations(cache, &cache->need_commit_migrations,
 					   migration_success_post_commit);
 		}
+
+		ack_quiescing(cache);
+
 	} while (more_work(cache));
 }
 
@@ -1930,6 +1954,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	ti->num_discard_bios = 1;
 	ti->discards_supported = true;
 	ti->discard_zeroes_data_unsupported = true;
+	/* Discard bios must be split on a block boundary */
+	ti->split_discard_bios = true;
 
 	cache->features = ca->features;
 	ti->per_bio_data_size = get_per_bio_data_size(cache);
@@ -1998,6 +2024,9 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	atomic_set(&cache->nr_migrations, 0);
 	init_waitqueue_head(&cache->migration_wait);
 
+	init_waitqueue_head(&cache->quiescing_wait);
+	atomic_set(&cache->quiescing_ack, 0);
+
 	r = -ENOMEM;
 	cache->nr_dirty = 0;
 	cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
@@ -2148,20 +2177,18 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 	bool discarded_block;
 	struct dm_bio_prison_cell *cell;
 	struct policy_result lookup_result;
-	struct per_bio_data *pb;
+	struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
 
-	if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+	if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
 		/*
 		 * This can only occur if the io goes to a partial block at
 		 * the end of the origin device.  We don't cache these.
 		 * Just remap to the origin and carry on.
 		 */
-		remap_to_origin_clear_discard(cache, bio, block);
+		remap_to_origin(cache, bio);
 		return DM_MAPIO_REMAPPED;
 	}
 
-	pb = init_per_bio_data(bio, pb_data_size);
-
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
 		defer_bio(cache, bio);
 		return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6d2d41ae9e32..7409d79729ee 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -18,7 +18,6 @@
 #include <linux/crypto.h>
 #include <linux/workqueue.h>
 #include <linux/backing-dev.h>
-#include <linux/percpu.h>
 #include <linux/atomic.h>
 #include <linux/scatterlist.h>
 #include <asm/page.h>
@@ -44,6 +43,7 @@ struct convert_context {
 	unsigned int idx_out;
 	sector_t cc_sector;
 	atomic_t cc_pending;
+	struct ablkcipher_request *req;
 };
 
 /*
@@ -105,15 +105,7 @@ struct iv_lmk_private {
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
 
 /*
- * Duplicated per-CPU state for cipher.
- */
-struct crypt_cpu {
-	struct ablkcipher_request *req;
-};
-
-/*
- * The fields in here must be read only after initialization,
- * changing state should be in crypt_cpu.
+ * The fields in here must be read only after initialization.
  */
 struct crypt_config {
 	struct dm_dev *dev;
@@ -143,12 +135,6 @@ struct crypt_config {
 	sector_t iv_offset;
 	unsigned int iv_size;
 
-	/*
-	 * Duplicated per cpu state. Access through
-	 * per_cpu_ptr() only.
-	 */
-	struct crypt_cpu __percpu *cpu;
-
 	/* ESSIV: struct crypto_cipher *essiv_tfm */
 	void *iv_private;
 	struct crypto_ablkcipher **tfms;
@@ -184,11 +170,6 @@ static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
 static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
 
-static struct crypt_cpu *this_crypt_config(struct crypt_config *cc)
-{
-	return this_cpu_ptr(cc->cpu);
-}
-
 /*
  * Use this to access cipher attributes that are the same for each CPU.
  */
@@ -738,16 +719,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 static void crypt_alloc_req(struct crypt_config *cc,
 			    struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
-	if (!this_cc->req)
-		this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO);
+	if (!ctx->req)
+		ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
 
-	ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]);
-	ablkcipher_request_set_callback(this_cc->req,
+	ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+	ablkcipher_request_set_callback(ctx->req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-	    kcryptd_async_done, dmreq_of_req(cc, this_cc->req));
+	    kcryptd_async_done, dmreq_of_req(cc, ctx->req));
 }
 
 /*
@@ -756,7 +736,6 @@ static void crypt_alloc_req(struct crypt_config *cc,
 static int crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	int r;
 
 	atomic_set(&ctx->cc_pending, 1);
@@ -768,7 +747,7 @@ static int crypt_convert(struct crypt_config *cc,
 
 		atomic_inc(&ctx->cc_pending);
 
-		r = crypt_convert_block(cc, ctx, this_cc->req);
+		r = crypt_convert_block(cc, ctx, ctx->req);
 
 		switch (r) {
 		/* async */
@@ -777,7 +756,7 @@ static int crypt_convert(struct crypt_config *cc,
 			INIT_COMPLETION(ctx->restart);
 			/* fall through*/
 		case -EINPROGRESS:
-			this_cc->req = NULL;
+			ctx->req = NULL;
 			ctx->cc_sector++;
 			continue;
 
@@ -876,6 +855,7 @@ static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc,
 	io->sector = sector;
 	io->error = 0;
 	io->base_io = NULL;
+	io->ctx.req = NULL;
 	atomic_set(&io->io_pending, 0);
 
 	return io;
@@ -901,6 +881,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (io->ctx.req)
+		mempool_free(io->ctx.req, cc->req_pool);
 	mempool_free(io, cc->io_pool);
 
 	if (likely(!base_io))
@@ -1326,8 +1308,6 @@ static int crypt_wipe_key(struct crypt_config *cc)
 static void crypt_dtr(struct dm_target *ti)
 {
 	struct crypt_config *cc = ti->private;
-	struct crypt_cpu *cpu_cc;
-	int cpu;
 
 	ti->private = NULL;
 
@@ -1339,13 +1319,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->crypt_queue)
 		destroy_workqueue(cc->crypt_queue);
 
-	if (cc->cpu)
-		for_each_possible_cpu(cpu) {
-			cpu_cc = per_cpu_ptr(cc->cpu, cpu);
-			if (cpu_cc->req)
-				mempool_free(cpu_cc->req, cc->req_pool);
-		}
-
 	crypt_free_tfms(cc);
 
 	if (cc->bs)
@@ -1364,9 +1337,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->dev)
 		dm_put_device(ti, cc->dev);
 
-	if (cc->cpu)
-		free_percpu(cc->cpu);
-
 	kzfree(cc->cipher);
 	kzfree(cc->cipher_string);
 
@@ -1421,13 +1391,6 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	if (tmp)
 		DMWARN("Ignoring unexpected additional cipher options");
 
-	cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)),
-				 __alignof__(struct crypt_cpu));
-	if (!cc->cpu) {
-		ti->error = "Cannot allocate per cpu state";
-		goto bad_mem;
-	}
-
 	/*
 	 * For compatibility with the original dm-crypt mapping format, if
 	 * only the cipher name is supplied, use cbc-plain.
@@ -1543,6 +1506,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned int key_size, opt_params;
 	unsigned long long tmpll;
 	int ret;
+	size_t iv_size_padding;
 	struct dm_arg_set as;
 	const char *opt_string;
 	char dummy;
@@ -1579,12 +1543,23 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	cc->dmreq_start = sizeof(struct ablkcipher_request);
 	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
-	cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment());
-	cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
-			   ~(crypto_tfm_ctx_alignment() - 1);
+	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+
+	if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+		/* Allocate the padding exactly */
+		iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+				& crypto_ablkcipher_alignmask(any_tfm(cc));
+	} else {
+		/*
+		 * If the cipher requires greater alignment than kmalloc
+		 * alignment, we don't know the exact position of the
+		 * initialization vector. We must assume worst case.
+		 */
+		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+	}
 
 	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
-			sizeof(struct dm_crypt_request) + cc->iv_size);
+			sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
 	if (!cc->req_pool) {
 		ti->error = "Cannot allocate crypt request mempool";
 		goto bad;
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 496d5f3646a5..2f91d6d4a2cc 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -20,6 +20,7 @@
 struct delay_c {
 	struct timer_list delay_timer;
 	struct mutex timer_lock;
+	struct workqueue_struct *kdelayd_wq;
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
 	atomic_t may_delay;
@@ -45,14 +46,13 @@ struct dm_delay_info {
 
 static DEFINE_MUTEX(delayed_bios_lock);
 
-static struct workqueue_struct *kdelayd_wq;
 static struct kmem_cache *delayed_cache;
 
 static void handle_delayed_timer(unsigned long data)
 {
 	struct delay_c *dc = (struct delay_c *)data;
 
-	queue_work(kdelayd_wq, &dc->flush_expired_bios);
+	queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
 }
 
 static void queue_timeout(struct delay_c *dc, unsigned long expires)
@@ -191,6 +191,12 @@ out:
 		goto bad_dev_write;
 	}
 
+	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+	if (!dc->kdelayd_wq) {
+		DMERR("Couldn't start kdelayd");
+		goto bad_queue;
+	}
+
 	setup_timer(&dc->delay_timer, handle_delayed_timer, (unsigned long)dc);
 
 	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
@@ -203,6 +209,8 @@ out:
 	ti->private = dc;
 	return 0;
 
+bad_queue:
+	mempool_destroy(dc->delayed_pool);
 bad_dev_write:
 	if (dc->dev_write)
 		dm_put_device(ti, dc->dev_write);
@@ -217,7 +225,7 @@ static void delay_dtr(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	flush_workqueue(kdelayd_wq);
+	destroy_workqueue(dc->kdelayd_wq);
 
 	dm_put_device(ti, dc->dev_read);
 
@@ -350,12 +358,6 @@ static int __init dm_delay_init(void)
 {
 	int r = -ENOMEM;
 
-	kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
-	if (!kdelayd_wq) {
-		DMERR("Couldn't start kdelayd");
-		goto bad_queue;
-	}
-
 	delayed_cache = KMEM_CACHE(dm_delay_info, 0);
 	if (!delayed_cache) {
 		DMERR("Couldn't create delayed bio cache.");
@@ -373,8 +375,6 @@ static int __init dm_delay_init(void)
 bad_register:
 	kmem_cache_destroy(delayed_cache);
 bad_memcache:
-	destroy_workqueue(kdelayd_wq);
-bad_queue:
 	return r;
 }
 
@@ -382,7 +382,6 @@ static void __exit dm_delay_exit(void)
 {
 	dm_unregister_target(&delay_target);
 	kmem_cache_destroy(delayed_cache);
-	destroy_workqueue(kdelayd_wq);
 }
 
 /* Module hooks */
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index ea49834377c8..d1de1626a9d2 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -10,6 +10,7 @@
 #include <linux/device-mapper.h>
 
 #include <linux/bio.h>
+#include <linux/completion.h>
 #include <linux/mempool.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -34,7 +35,7 @@ struct dm_io_client {
 struct io {
 	unsigned long error_bits;
 	atomic_t count;
-	struct task_struct *sleeper;
+	struct completion *wait;
 	struct dm_io_client *client;
 	io_notify_fn callback;
 	void *context;
@@ -122,8 +123,8 @@ static void dec_count(struct io *io, unsigned int region, int error)
 			invalidate_kernel_vmap_range(io->vma_invalidate_address,
 						     io->vma_invalidate_size);
 
-		if (io->sleeper)
-			wake_up_process(io->sleeper);
+		if (io->wait)
+			complete(io->wait);
 
 		else {
 			unsigned long r = io->error_bits;
@@ -386,6 +387,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	 */
 	volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1];
 	struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io));
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
 		WARN_ON(1);
@@ -394,7 +396,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = current;
+	io->wait = &wait;
 	io->client = client;
 
 	io->vma_invalidate_address = dp->vma_invalidate_address;
@@ -402,15 +404,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	dispatch_io(rw, num_regions, where, dp, io, 1);
 
-	while (1) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-
-		if (!atomic_read(&io->count))
-			break;
-
-		io_schedule();
-	}
-	set_current_state(TASK_RUNNING);
+	wait_for_completion_io(&wait);
 
 	if (error_bits)
 		*error_bits = io->error_bits;
@@ -433,7 +427,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = NULL;
+	io->wait = NULL;
 	io->client = client;
 	io->callback = fn;
 	io->context = context;
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 08d9a207259a..c69d0b787746 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void)
 
 	r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback);
 	if (r) {
-		cn_del_callback(&ulog_cn_id);
+		kfree(prealloced_cn_msg);
 		return r;
 	}
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 5adede17ddf6..0ba21b0f3972 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -86,6 +86,7 @@ struct multipath {
 	unsigned queue_if_no_path:1;	/* Queue I/O if last path fails? */
 	unsigned saved_queue_if_no_path:1; /* Saved state during suspension */
 	unsigned retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */
+	unsigned pg_init_disabled:1;	/* pg_init is not currently allowed */
 
 	unsigned pg_init_retries;	/* Number of times to retry pg_init */
 	unsigned pg_init_count;		/* Number of times pg_init called */
@@ -497,7 +498,8 @@ static void process_queued_ios(struct work_struct *work)
 	    (!pgpath && !m->queue_if_no_path))
 		must_queue = 0;
 
-	if (m->pg_init_required && !m->pg_init_in_progress && pgpath)
+	if (m->pg_init_required && !m->pg_init_in_progress && pgpath &&
+	    !m->pg_init_disabled)
 		__pg_init_all_paths(m);
 
 	spin_unlock_irqrestore(&m->lock, flags);
@@ -942,10 +944,20 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m)
 
 static void flush_multipath_work(struct multipath *m)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&m->lock, flags);
+	m->pg_init_disabled = 1;
+	spin_unlock_irqrestore(&m->lock, flags);
+
 	flush_workqueue(kmpath_handlerd);
 	multipath_wait_for_pg_init_completion(m);
 	flush_workqueue(kmultipathd);
 	flush_work(&m->trigger_event);
+
+	spin_lock_irqsave(&m->lock, flags);
+	m->pg_init_disabled = 0;
+	spin_unlock_irqrestore(&m->lock, flags);
 }
 
 static void multipath_dtr(struct dm_target *ti)
@@ -1164,7 +1176,7 @@ static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath)
 
 	spin_lock_irqsave(&m->lock, flags);
 
-	if (m->pg_init_count <= m->pg_init_retries)
+	if (m->pg_init_count <= m->pg_init_retries && !m->pg_init_disabled)
 		m->pg_init_required = 1;
 	else
 		limit_reached = 1;
@@ -1284,8 +1296,17 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	if (!error && !clone->errors)
 		return 0;	/* I/O complete */
 
-	if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ)
+	if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ) {
+		if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+		    !clone->q->limits.max_write_same_sectors) {
+			struct queue_limits *limits;
+
+			/* device doesn't really support WRITE SAME, disable it */
+			limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+			limits->max_write_same_sectors = 0;
+		}
 		return error;
+	}
 
 	if (mpio->pgpath)
 		fail_path(mpio->pgpath);
@@ -1587,8 +1608,11 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 	/*
 	 * Only pass ioctls through if the device sizes match exactly.
 	 */
-	if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
-		r = scsi_verify_blk_ioctl(NULL, cmd);
+	if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
+		int err = scsi_verify_blk_ioctl(NULL, cmd);
+		if (err)
+			r = err;
+	}
 
 	if (r == -ENOTCONN && !fatal_signal_pending(current))
 		queue_work(kmultipathd, &m->process_queued_ios);
@@ -1690,7 +1714,7 @@ out:
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 5, 1},
+	.version = {1, 6, 0},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1d3fe1a40a9b..84cddccc0249 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -380,7 +380,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 static int validate_raid_redundancy(struct raid_set *rs)
 {
 	unsigned i, rebuild_cnt = 0;
-	unsigned rebuilds_per_group, copies, d;
+	unsigned rebuilds_per_group = 0, copies, d;
 	unsigned group_size, last_group_start;
 
 	for (i = 0; i < rs->md.raid_disks; i++)
@@ -785,8 +785,7 @@ struct dm_raid_superblock {
 	__le32 layout;
 	__le32 stripe_sectors;
 
-	__u8 pad[452];		/* Round struct to 512 bytes. */
-				/* Always set to 0 when writing. */
+	/* Remainder of a logical block is zero-filled when writing (see super_sync()). */
 } __packed;
 
 static int read_disk_sb(struct md_rdev *rdev, int size)
@@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
 		    test_bit(Faulty, &(rs->dev[i].rdev.flags)))
 			failed_devices |= (1ULL << i);
 
-	memset(sb, 0, sizeof(*sb));
+	memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
 
 	sb->magic = cpu_to_le32(DM_RAID_MAGIC);
 	sb->features = cpu_to_le32(0);	/* No features yet */
@@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 	uint64_t events_sb, events_refsb;
 
 	rdev->sb_start = 0;
-	rdev->sb_size = sizeof(*sb);
+	rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
+	if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
+		DMERR("superblock size of a logical block is no longer valid");
+		return -EINVAL;
+	}
 
 	ret = read_disk_sb(rdev, rdev->sb_size);
 	if (ret)
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3ac415675b6c..2d2b1b7588d7 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 	 */
 	INIT_WORK_ONSTACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
-	flush_work(&req.work);
+	flush_workqueue(ps->metadata_wq);
 
 	return req.result;
 }
@@ -269,6 +269,14 @@ static chunk_t area_location(struct pstore *ps, chunk_t area)
 	return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area);
 }
 
+static void skip_metadata(struct pstore *ps)
+{
+	uint32_t stride = ps->exceptions_per_area + 1;
+	chunk_t next_free = ps->next_free;
+	if (sector_div(next_free, stride) == NUM_SNAPSHOT_HDR_CHUNKS)
+		ps->next_free++;
+}
+
 /*
  * Read or write a metadata area.  Remembering to skip the first
  * chunk which holds the header.
@@ -502,6 +510,8 @@ static int read_exceptions(struct pstore *ps,
 
 	ps->current_area--;
 
+	skip_metadata(ps);
+
 	return 0;
 }
 
@@ -616,8 +626,6 @@ static int persistent_prepare_exception(struct dm_exception_store *store,
 					struct dm_exception *e)
 {
 	struct pstore *ps = get_info(store);
-	uint32_t stride;
-	chunk_t next_free;
 	sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev);
 
 	/* Is there enough room ? */
@@ -630,10 +638,8 @@ static int persistent_prepare_exception(struct dm_exception_store *store,
 	 * Move onto the next free pending, making sure to take
 	 * into account the location of the metadata chunks.
 	 */
-	stride = (ps->exceptions_per_area + 1);
-	next_free = ++ps->next_free;
-	if (sector_div(next_free, stride) == 1)
-		ps->next_free++;
+	ps->next_free++;
+	skip_metadata(ps);
 
 	atomic_inc(&ps->pending_count);
 	return 0;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c434e5aab2df..944690bafd93 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -66,6 +66,18 @@ struct dm_snapshot {
 
 	atomic_t pending_exceptions_count;
 
+	/* Protected by "lock" */
+	sector_t exception_start_sequence;
+
+	/* Protected by kcopyd single-threaded callback */
+	sector_t exception_complete_sequence;
+
+	/*
+	 * A list of pending exceptions that completed out of order.
+	 * Protected by kcopyd single-threaded callback.
+	 */
+	struct list_head out_of_order_list;
+
 	mempool_t *pending_pool;
 
 	struct dm_exception_table pending;
@@ -173,6 +185,14 @@ struct dm_snap_pending_exception {
 	 */
 	int started;
 
+	/* There was copying error. */
+	int copy_error;
+
+	/* A sequence number, it is used for in-order completion. */
+	sector_t exception_sequence;
+
+	struct list_head out_of_order_entry;
+
 	/*
 	 * For writing a complete chunk, bypassing the copy.
 	 */
@@ -725,17 +745,16 @@ static int calc_max_buckets(void)
  */
 static int init_hash_tables(struct dm_snapshot *s)
 {
-	sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets;
+	sector_t hash_size, cow_dev_size, max_buckets;
 
 	/*
 	 * Calculate based on the size of the original volume or
 	 * the COW volume...
 	 */
 	cow_dev_size = get_dev_size(s->cow->bdev);
-	origin_dev_size = get_dev_size(s->origin->bdev);
 	max_buckets = calc_max_buckets();
 
-	hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
+	hash_size = cow_dev_size >> s->store->chunk_shift;
 	hash_size = min(hash_size, max_buckets);
 
 	if (hash_size < 64)
@@ -1095,6 +1114,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	s->valid = 1;
 	s->active = 0;
 	atomic_set(&s->pending_exceptions_count, 0);
+	s->exception_start_sequence = 0;
+	s->exception_complete_sequence = 0;
+	INIT_LIST_HEAD(&s->out_of_order_list);
 	init_rwsem(&s->lock);
 	INIT_LIST_HEAD(&s->list);
 	spin_lock_init(&s->pe_lock);
@@ -1444,6 +1466,19 @@ static void commit_callback(void *context, int success)
 	pending_complete(pe, success);
 }
 
+static void complete_exception(struct dm_snap_pending_exception *pe)
+{
+	struct dm_snapshot *s = pe->snap;
+
+	if (unlikely(pe->copy_error))
+		pending_complete(pe, 0);
+
+	else
+		/* Update the metadata if we are persistent */
+		s->store->type->commit_exception(s->store, &pe->e,
+						 commit_callback, pe);
+}
+
 /*
  * Called when the copy I/O has finished.  kcopyd actually runs
  * this code so don't block.
@@ -1453,13 +1488,32 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
 	struct dm_snap_pending_exception *pe = context;
 	struct dm_snapshot *s = pe->snap;
 
-	if (read_err || write_err)
-		pending_complete(pe, 0);
+	pe->copy_error = read_err || write_err;
 
-	else
-		/* Update the metadata if we are persistent */
-		s->store->type->commit_exception(s->store, &pe->e,
-						 commit_callback, pe);
+	if (pe->exception_sequence == s->exception_complete_sequence) {
+		s->exception_complete_sequence++;
+		complete_exception(pe);
+
+		while (!list_empty(&s->out_of_order_list)) {
+			pe = list_entry(s->out_of_order_list.next,
+					struct dm_snap_pending_exception, out_of_order_entry);
+			if (pe->exception_sequence != s->exception_complete_sequence)
+				break;
+			s->exception_complete_sequence++;
+			list_del(&pe->out_of_order_entry);
+			complete_exception(pe);
+		}
+	} else {
+		struct list_head *lh;
+		struct dm_snap_pending_exception *pe2;
+
+		list_for_each_prev(lh, &s->out_of_order_list) {
+			pe2 = list_entry(lh, struct dm_snap_pending_exception, out_of_order_entry);
+			if (pe2->exception_sequence < pe->exception_sequence)
+				break;
+		}
+		list_add(&pe->out_of_order_entry, lh);
+	}
 }
 
 /*
@@ -1554,6 +1608,8 @@ __find_pending_exception(struct dm_snapshot *s,
 		return NULL;
 	}
 
+	pe->exception_sequence = s->exception_start_sequence++;
+
 	dm_insert_exception(&s->pending, &pe->e);
 
 	return pe;
@@ -2193,7 +2249,7 @@ static struct target_type origin_target = {
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 11, 1},
+	.version = {1, 12, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 84d2b91e4efb..c62c5ab6aed5 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -86,6 +86,7 @@ static const struct sysfs_ops dm_sysfs_ops = {
 static struct kobj_type dm_ktype = {
 	.sysfs_ops	= &dm_sysfs_ops,
 	.default_attrs	= dm_attrs,
+	.release	= dm_kobject_release,
 };
 
 /*
@@ -104,5 +105,7 @@ int dm_sysfs_init(struct mapped_device *md)
  */
 void dm_sysfs_exit(struct mapped_device *md)
 {
-	kobject_put(dm_kobject(md));
+	struct kobject *kobj = dm_kobject(md);
+	kobject_put(kobj);
+	wait_for_completion(dm_get_completion_from_kobject(kobj));
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 1ff252ab7d46..bd88d3dade1e 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -215,6 +215,11 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
 	num_targets = dm_round_up(num_targets, KEYS_PER_NODE);
 
+	if (!num_targets) {
+		kfree(t);
+		return -ENOMEM;
+	}
+
 	if (alloc_targets(t, num_targets)) {
 		kfree(t);
 		return -ENOMEM;
@@ -580,14 +585,28 @@ static int adjoin(struct dm_table *table, struct dm_target *ti)
 
 /*
  * Used to dynamically allocate the arg array.
+ *
+ * We do first allocation with GFP_NOIO because dm-mpath and dm-thin must
+ * process messages even if some device is suspended. These messages have a
+ * small fixed number of arguments.
+ *
+ * On the other hand, dm-switch needs to process bulk data using messages and
+ * excessive use of GFP_NOIO could cause trouble.
  */
 static char **realloc_argv(unsigned *array_size, char **old_argv)
 {
 	char **argv;
 	unsigned new_size;
+	gfp_t gfp;
 
-	new_size = *array_size ? *array_size * 2 : 64;
-	argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL);
+	if (*array_size) {
+		new_size = *array_size * 2;
+		gfp = GFP_KERNEL;
+	} else {
+		new_size = 8;
+		gfp = GFP_NOIO;
+	}
+	argv = kmalloc(new_size * sizeof(*argv), gfp);
 	if (argv) {
 		memcpy(argv, old_argv, *array_size * sizeof(*argv));
 		*array_size = new_size;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 60bce435f4fa..3b1503dc1f13 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -591,6 +591,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)pmd->data_block_size);
+		r = -EINVAL;
+		goto bad_unlock_sblock;
+	}
+
 	r = __check_incompat_features(disk_super, pmd);
 	if (r < 0)
 		goto bad_unlock_sblock;
@@ -1349,6 +1358,12 @@ dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
 	return td->id;
 }
 
+/*
+ * Check whether @time (of block creation) is older than @td's last snapshot.
+ * If so then the associated block is shared with the last snapshot device.
+ * Any block on a device created *after* the device last got snapshotted is
+ * necessarily not shared.
+ */
 static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
 {
 	return td->snapshotted_time > time;
@@ -1458,6 +1473,20 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
 	return r;
 }
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
+{
+	int r;
+	uint32_t ref_count;
+
+	down_read(&pmd->root_lock);
+	r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+	if (!r)
+		*result = (ref_count != 0);
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 {
 	int r;
@@ -1469,6 +1498,23 @@ bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 	return r;
 }
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
+{
+	bool r = false;
+	struct dm_thin_device *td, *tmp;
+
+	down_read(&pmd->root_lock);
+	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+		if (td->changed) {
+			r = td->changed;
+			break;
+		}
+	}
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td)
 {
 	bool r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 845ebbe589a9..8f4d62baf09b 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -161,6 +161,8 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block);
  */
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td);
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd);
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td);
 
 int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
@@ -181,6 +183,8 @@ int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
 
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+
 /*
  * Returns -ENOSPC if the new size is too small and already allocated
  * blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 88f2f802d528..86a2a5e3b26b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@ struct dm_thin_new_mapping {
 	unsigned quiesced:1;
 	unsigned prepared:1;
 	unsigned pass_discard:1;
+	unsigned definitely_not_shared:1;
 
 	struct thin_c *tc;
 	dm_block_t virt_block;
@@ -640,7 +641,9 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	 */
 	r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block);
 	if (r) {
-		DMERR_LIMIT("dm_thin_insert_block() failed");
+		DMERR_LIMIT("%s: dm_thin_insert_block() failed: error = %d",
+			    dm_device_name(pool->pool_md), r);
+		set_pool_mode(pool, PM_READ_ONLY);
 		cell_error(pool, m->cell);
 		goto out;
 	}
@@ -681,7 +684,15 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	cell_defer_no_holder(tc, m->cell2);
 
 	if (m->pass_discard)
-		remap_and_issue(tc, m->bio, m->data_block);
+		if (m->definitely_not_shared)
+			remap_and_issue(tc, m->bio, m->data_block);
+		else {
+			bool used = false;
+			if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
+				bio_endio(m->bio, 0);
+			else
+				remap_and_issue(tc, m->bio, m->data_block);
+		}
 	else
 		bio_endio(m->bio, 0);
 
@@ -749,13 +760,17 @@ static int ensure_next_mapping(struct pool *pool)
 
 static struct dm_thin_new_mapping *get_next_mapping(struct pool *pool)
 {
-	struct dm_thin_new_mapping *r = pool->next_mapping;
+	struct dm_thin_new_mapping *m = pool->next_mapping;
 
 	BUG_ON(!pool->next_mapping);
 
+	memset(m, 0, sizeof(struct dm_thin_new_mapping));
+	INIT_LIST_HEAD(&m->list);
+	m->bio = NULL;
+
 	pool->next_mapping = NULL;
 
-	return r;
+	return m;
 }
 
 static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
@@ -767,15 +782,10 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
-	m->quiesced = 0;
-	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_dest;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	if (!dm_deferred_set_add_work(pool->shared_read_ds, &m->list))
 		m->quiesced = 1;
@@ -838,15 +848,12 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
 	m->quiesced = 1;
 	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_block;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	/*
 	 * If the whole block of data is being overwritten or we are not
@@ -1030,12 +1037,12 @@ static void process_discard(struct thin_c *tc, struct bio *bio)
 			 */
 			m = get_next_mapping(pool);
 			m->tc = tc;
-			m->pass_discard = (!lookup_result.shared) && pool->pf.discard_passdown;
+			m->pass_discard = pool->pf.discard_passdown;
+			m->definitely_not_shared = !lookup_result.shared;
 			m->virt_block = block;
 			m->data_block = lookup_result.block;
 			m->cell = cell;
 			m->cell2 = cell2;
-			m->err = 0;
 			m->bio = bio;
 
 			if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list)) {
@@ -1315,9 +1322,9 @@ static void process_deferred_bios(struct pool *pool)
 		 */
 		if (ensure_next_mapping(pool)) {
 			spin_lock_irqsave(&pool->lock, flags);
+			bio_list_add(&pool->deferred_bios, bio);
 			bio_list_merge(&pool->deferred_bios, &bios);
 			spin_unlock_irqrestore(&pool->lock, flags);
-
 			break;
 		}
 
@@ -1337,7 +1344,8 @@ static void process_deferred_bios(struct pool *pool)
 	bio_list_init(&pool->deferred_flush_bios);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
+	if (bio_list_empty(&bios) &&
+	    !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
 		return;
 
 	if (commit_or_fallback(pool)) {
@@ -2639,7 +2647,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
 	 */
 	if (pt->adjusted_pf.discard_passdown) {
 		data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
-		limits->discard_granularity = data_limits->discard_granularity;
+		limits->discard_granularity = max(data_limits->discard_granularity,
+						  pool->sectors_per_block << SECTOR_SHIFT);
 	} else
 		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 }
@@ -2776,6 +2785,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	if (get_pool_mode(tc->pool) == PM_FAIL) {
 		ti->error = "Couldn't open thin device, Pool is in fail mode";
+		r = -EINVAL;
 		goto bad_thin_open;
 	}
 
@@ -2787,7 +2797,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block);
 	if (r)
-		goto bad_thin_open;
+		goto bad_target_max_io_len;
 
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
@@ -2808,6 +2818,8 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	return 0;
 
+bad_target_max_io_len:
+	dm_pool_close_thin_device(tc->td);
 bad_thin_open:
 	__pool_dec(tc->pool);
 bad_pool_lookup:
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 33f20103d8d5..204a59fd872f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -184,8 +184,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -1904,6 +1904,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2219,6 +2220,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 }
 
 /*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+	BUG_ON(!atomic_read(&md->holders));
+	return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
  * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
  */
 static int dm_init_request_based_queue(struct mapped_device *md)
@@ -2724,20 +2736,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 45b97da1bd06..9b3222f44835 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -15,6 +15,8 @@
 #include <linux/list.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
 
 /*
  * Suspend feature flags
@@ -125,12 +127,27 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
 
 /*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
+
+/*
  * Targets for linear and striped mappings
  */
 int dm_linear_init(void);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 51f0345a4ba4..aaf77b07bb72 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1118,6 +1118,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1196,6 +1197,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -1604,6 +1607,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1686,6 +1690,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -2829,6 +2835,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		else
 			rdev->saved_raid_disk = -1;
 		clear_bit(In_sync, &rdev->flags);
+		clear_bit(Bitmap_sync, &rdev->flags);
 		err = rdev->mddev->pers->
 			hot_add_disk(rdev->mddev, rdev);
 		if (err) {
@@ -3619,6 +3626,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->in_sync = 1;
 		del_timer_sync(&mddev->safemode_timer);
 	}
+	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	mddev_resume(mddev);
@@ -5760,6 +5768,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 			    info->raid_disk < mddev->raid_disks) {
 				rdev->raid_disk = info->raid_disk;
 				set_bit(In_sync, &rdev->flags);
+				clear_bit(Bitmap_sync, &rdev->flags);
 			} else
 				rdev->raid_disk = -1;
 		} else
@@ -7329,8 +7338,10 @@ void md_do_sync(struct md_thread *thread)
 	/* just incase thread restarts... */
 	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
-	if (mddev->ro) /* never try to sync a read-only array */
+	if (mddev->ro) {/* never try to sync a read-only array */
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return;
+	}
 
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 		if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
@@ -7436,6 +7447,19 @@ void md_do_sync(struct md_thread *thread)
 			    rdev->recovery_offset < j)
 				j = rdev->recovery_offset;
 		rcu_read_unlock();
+
+		/* If there is a bitmap, we need to make sure all
+		 * writes that started before we added a spare
+		 * complete before we start doing a recovery.
+		 * Otherwise the write might complete and (via
+		 * bitmap_endwrite) set a bit in the bitmap after the
+		 * recovery has checked that bit and skipped that
+		 * region.
+		 */
+		if (mddev->bitmap) {
+			mddev->pers->quiesce(mddev, 1);
+			mddev->pers->quiesce(mddev, 0);
+		}
 	}
 
 	printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -7693,7 +7717,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
 		if (mddev->ro &&
-		    rdev->saved_raid_disk < 0)
+		    ! (rdev->saved_raid_disk >= 0 &&
+		       !test_bit(Bitmap_sync, &rdev->flags)))
 			continue;
 
 		rdev->recovery_offset = 0;
@@ -7774,9 +7799,13 @@ void md_check_recovery(struct mddev *mddev)
 			 * As we only add devices that are already in-sync,
 			 * we can activate the spares immediately.
 			 */
-			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			remove_and_add_spares(mddev, NULL);
-			mddev->pers->spare_active(mddev);
+			/* There is no thread, but we need to call
+			 * ->spare_active and clear saved_raid_disk
+			 */
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+			md_reap_sync_thread(mddev);
+			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			goto unlock;
 		}
 
@@ -8072,6 +8101,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
 	u64 *p;
 	int lo, hi;
 	int rv = 1;
+	unsigned long flags;
 
 	if (bb->shift < 0)
 		/* badblocks are disabled */
@@ -8086,7 +8116,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
 		sectors = next - s;
 	}
 
-	write_seqlock_irq(&bb->lock);
+	write_seqlock_irqsave(&bb->lock, flags);
 
 	p = bb->page;
 	lo = 0;
@@ -8202,7 +8232,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
 	bb->changed = 1;
 	if (!acknowledged)
 		bb->unacked_exist = 1;
-	write_sequnlock_irq(&bb->lock);
+	write_sequnlock_irqrestore(&bb->lock, flags);
 
 	return rv;
 }
@@ -8467,7 +8497,8 @@ static int md_notify_reboot(struct notifier_block *this,
 		if (mddev_trylock(mddev)) {
 			if (mddev->pers)
 				__md_stop_writes(mddev);
-			mddev->safemode = 2;
+			if (mddev->persistent)
+				mddev->safemode = 2;
 			mddev_unlock(mddev);
 		}
 		need_delay = 1;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 653f992b687a..ebe748e57416 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -129,6 +129,9 @@ struct md_rdev {
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
 	In_sync,		/* device is in_sync with rest of array */
+	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
+				 * bitmap-based recovery to get fully in sync
+				 */
 	Unmerged,		/* device is being added to array and should
 				 * be considerred for bvec_merge_fn but not
 				 * yet for actual IO
diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
index 172147eb1d40..1d75b1dc1e2e 100644
--- a/drivers/md/persistent-data/dm-array.c
+++ b/drivers/md/persistent-data/dm-array.c
@@ -317,8 +317,16 @@ static int shadow_ablock(struct dm_array_info *info, dm_block_t *root,
 	 * The shadow op will often be a noop.  Only insert if it really
 	 * copied data.
 	 */
-	if (dm_block_location(*block) != b)
+	if (dm_block_location(*block) != b) {
+		/*
+		 * dm_tm_shadow_block will have already decremented the old
+		 * block, but it is still referenced by the btree.  We
+		 * increment to stop the insert decrementing it below zero
+		 * when overwriting the old value.
+		 */
+		dm_tm_inc(info->btree_info.tm, b);
 		r = insert_ablock(info, index, *block, root);
+	}
 
 	return r;
 }
@@ -509,15 +517,18 @@ static int grow_add_tail_block(struct resize *resize)
 static int grow_needs_more_blocks(struct resize *resize)
 {
 	int r;
+	unsigned old_nr_blocks = resize->old_nr_full_blocks;
 
 	if (resize->old_nr_entries_in_last_block > 0) {
+		old_nr_blocks++;
+
 		r = grow_extend_tail_block(resize, resize->max_entries);
 		if (r)
 			return r;
 	}
 
 	r = insert_full_ablocks(resize->info, resize->size_of_block,
-				resize->old_nr_full_blocks,
+				old_nr_blocks,
 				resize->new_nr_full_blocks,
 				resize->max_entries, resize->value,
 				&resize->root);
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 81b513890e2b..6372d0bea532 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b)
 }
 EXPORT_SYMBOL_GPL(dm_bm_unlock);
 
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
 {
-	int r;
-
 	if (bm->read_only)
 		return -EPERM;
 
-	r = dm_bufio_write_dirty_buffers(bm->bufio);
-	if (unlikely(r)) {
-		dm_bm_unlock(superblock);
-		return r;
-	}
-
-	dm_bm_unlock(superblock);
-
 	return dm_bufio_write_dirty_buffers(bm->bufio);
 }
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
 
 void dm_bm_set_read_only(struct dm_block_manager *bm)
 {
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index be5bff61be28..f74c0462e5e4 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b);
  *
  * This method always blocks.
  */
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
 
 /*
  * Switches the bm to a read only mode.  Once read-only mode
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 37d367bb9aa8..bf2b80d5c470 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -42,6 +42,12 @@ struct btree_node {
 } __packed;
 
 
+/*
+ * Locks a block using the btree node validator.
+ */
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+		 struct dm_block **result);
+
 void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
 		  struct dm_btree_value_type *vt);
 
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index cf9fd676ae44..1b5e13ec7f96 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = {
 
 /*----------------------------------------------------------------*/
 
-static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
 		 struct dm_block **result)
 {
 	return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 35865425e4b4..0a7592e88811 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -812,22 +812,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_highest_key);
  * FIXME: We shouldn't use a recursive algorithm when we have limited stack
  * space.  Also this only works for single level trees.
  */
-static int walk_node(struct ro_spine *s, dm_block_t block,
+static int walk_node(struct dm_btree_info *info, dm_block_t block,
 		     int (*fn)(void *context, uint64_t *keys, void *leaf),
 		     void *context)
 {
 	int r;
 	unsigned i, nr;
+	struct dm_block *node;
 	struct btree_node *n;
 	uint64_t keys;
 
-	r = ro_step(s, block);
-	n = ro_node(s);
+	r = bn_read_lock(info, block, &node);
+	if (r)
+		return r;
+
+	n = dm_block_data(node);
 
 	nr = le32_to_cpu(n->header.nr_entries);
 	for (i = 0; i < nr; i++) {
 		if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) {
-			r = walk_node(s, value64(n, i), fn, context);
+			r = walk_node(info, value64(n, i), fn, context);
 			if (r)
 				goto out;
 		} else {
@@ -839,7 +843,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block,
 	}
 
 out:
-	ro_pop(s);
+	dm_tm_unlock(info->tm, node);
 	return r;
 }
 
@@ -847,15 +851,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root,
 		  int (*fn)(void *context, uint64_t *keys, void *leaf),
 		  void *context)
 {
-	int r;
-	struct ro_spine spine;
-
 	BUG_ON(info->levels > 1);
-
-	init_ro_spine(&spine, info);
-	r = walk_node(&spine, root, fn, context);
-	exit_ro_spine(&spine);
-
-	return r;
+	return walk_node(info, root, fn, context);
 }
 EXPORT_SYMBOL_GPL(dm_btree_walk);
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index 3e7a88d99eb0..0d240373ffab 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -245,6 +245,10 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		return -EINVAL;
 	}
 
+	/*
+	 * We need to set this before the dm_tm_new_block() call below.
+	 */
+	ll->nr_blocks = nr_blocks;
 	for (i = old_blocks; i < blocks; i++) {
 		struct dm_block *b;
 		struct disk_index_entry idx;
@@ -252,6 +256,7 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b);
 		if (r < 0)
 			return r;
+
 		idx.blocknr = cpu_to_le64(dm_block_location(b));
 
 		r = dm_tm_unlock(ll->tm, b);
@@ -266,7 +271,6 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 			return r;
 	}
 
-	ll->nr_blocks = nr_blocks;
 	return 0;
 }
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 1c959684caef..056d09c33af1 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -384,12 +384,16 @@ static int sm_metadata_new_block(struct dm_space_map *sm, dm_block_t *b)
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
 	int r = sm_metadata_new_block_(sm, b);
-	if (r)
+	if (r) {
 		DMERR("unable to allocate new metadata block");
+		return r;
+	}
 
 	r = sm_metadata_get_nr_free(sm, &count);
-	if (r)
+	if (r) {
 		DMERR("couldn't get free block count");
+		return r;
+	}
 
 	check_threshold(&smm->threshold, count);
 
@@ -489,7 +493,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count
 {
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	return smm->ll.nr_blocks;
+	*count = smm->ll.nr_blocks;
+
+	return 0;
 }
 
 static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
@@ -604,20 +610,38 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 	 * Flick into a mode where all blocks get allocated in the new area.
 	 */
 	smm->begin = old_len;
-	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
+	memcpy(sm, &bootstrap_ops, sizeof(*sm));
 
 	/*
 	 * Extend.
 	 */
 	r = sm_ll_extend(&smm->ll, extra_blocks);
+	if (r)
+		goto out;
 
 	/*
-	 * Switch back to normal behaviour.
+	 * We repeatedly increment then commit until the commit doesn't
+	 * allocate any new blocks.
 	 */
-	memcpy(&smm->sm, &ops, sizeof(smm->sm));
-	for (i = old_len; !r && i < smm->begin; i++)
-		r = sm_ll_inc(&smm->ll, i, &ev);
+	do {
+		for (i = old_len; !r && i < smm->begin; i++) {
+			r = sm_ll_inc(&smm->ll, i, &ev);
+			if (r)
+				goto out;
+		}
+		old_len = smm->begin;
 
+		r = sm_ll_commit(&smm->ll);
+		if (r)
+			goto out;
+
+	} while (old_len != smm->begin);
+
+out:
+	/*
+	 * Switch back to normal behaviour.
+	 */
+	memcpy(sm, &ops, sizeof(*sm));
 	return r;
 }
 
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26042e..3bc30a0ae3d6 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm)
 	if (r < 0)
 		return r;
 
-	return 0;
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
 
@@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
 		return -EWOULDBLOCK;
 
 	wipe_shadow_table(tm);
+	dm_bm_unlock(root);
 
-	return dm_bm_flush_and_unlock(tm->bm, root);
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_commit);
 
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b139076ca5..2772ed2a781a 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac
 /*
  * We use a 2-phase commit here.
  *
- * i) In the first phase the block manager is told to start flushing, and
- * the changes to the space map are written to disk.  You should interrogate
- * your particular space map to get detail of its root node etc. to be
- * included in your superblock.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
  *
- * ii) @root will be committed last.  You shouldn't use more than the
- * first 512 bytes of @root if you wish the transaction to survive a power
- * failure.  You *must* have a write lock held on @root for both stage (i)
- * and (ii).  The commit will drop the write lock.
+ * ii) Lock your superblock.  Update.  Then call dm_tm_commit() which will
+ * unlock the superblock and flush it.  No other blocks should be updated
+ * during this period.  Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
  */
 int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
 
 /*
  * These methods are the only way to get hold of a writeable block.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6f4824426e86..e885dbf08c40 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -94,6 +94,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	struct pool_info *pi = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
+	int need_pages;
 	int i, j;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
@@ -116,15 +117,15 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * RESYNC_PAGES for each bio.
 	 */
 	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		j = pi->raid_disks;
+		need_pages = pi->raid_disks;
 	else
-		j = 1;
-	while(j--) {
+		need_pages = 1;
+	for (j = 0; j < need_pages; j++) {
 		bio = r1_bio->bios[j];
 		bio->bi_vcnt = RESYNC_PAGES;
 
 		if (bio_alloc_pages(bio, gfp_flags))
-			goto out_free_bio;
+			goto out_free_pages;
 	}
 	/* If not user-requests, copy the page pointers to all bios */
 	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
@@ -138,6 +139,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 	return r1_bio;
 
+out_free_pages:
+	while (--j >= 0) {
+		struct bio_vec *bv;
+
+		bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+			__free_page(bv->bv_page);
+	}
+
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
@@ -1397,12 +1406,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-		/*
-		 * if recovery is running, make sure it aborts.
-		 */
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	/*
+	 * if recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
@@ -1479,6 +1488,7 @@ static int raid1_spare_active(struct mddev *mddev)
 			}
 		}
 		if (rdev
+		    && rdev->recovery_offset == MaxSector
 		    && !test_bit(Faulty, &rdev->flags)
 		    && !test_and_set_bit(In_sync, &rdev->flags)) {
 			count++;
@@ -1853,11 +1863,15 @@ static int process_checks(struct r1bio *r1_bio)
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		int size;
+		int uptodate;
 		struct bio *b = r1_bio->bios[i];
 		if (b->bi_end_io != end_sync_read)
 			continue;
-		/* fixup the bio for reuse */
+		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
+		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
 		bio_reset(b);
+		if (!uptodate)
+			clear_bit(BIO_UPTODATE, &b->bi_flags);
 		b->bi_vcnt = vcnt;
 		b->bi_size = r1_bio->sectors << 9;
 		b->bi_sector = r1_bio->sector +
@@ -1890,11 +1904,14 @@ static int process_checks(struct r1bio *r1_bio)
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
+		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
+		/* Now we can 'fixup' the BIO_UPTODATE flag */
+		set_bit(BIO_UPTODATE, &sbio->bi_flags);
 
-		if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+		if (uptodate) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
@@ -1909,7 +1926,7 @@ static int process_checks(struct r1bio *r1_bio)
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+			      && uptodate)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
@@ -2034,7 +2051,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags))
+			    !test_bit(Faulty, &rdev->flags))
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
 		}
@@ -2046,7 +2063,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags)) {
+			    !test_bit(Faulty, &rdev->flags)) {
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 081bb3345353..a1ea2a753912 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1321,7 +1321,7 @@ read_again:
 			/* Could not read all from this device, so we will
 			 * need another r10_bio.
 			 */
-			sectors_handled = (r10_bio->sectors + max_sectors
+			sectors_handled = (r10_bio->sector + max_sectors
 					   - bio->bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
@@ -1329,7 +1329,7 @@ read_again:
 				bio->bi_phys_segments = 2;
 			else
 				bio->bi_phys_segments++;
-			spin_unlock(&conf->device_lock);
+			spin_unlock_irq(&conf->device_lock);
 			/* Cannot call generic_make_request directly
 			 * as that will be queued in __generic_make_request
 			 * and subsequent mempool_alloc might block
@@ -1681,11 +1681,11 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-		/*
-		 * if recovery is running, make sure it aborts.
-		 */
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	}
+	/*
+	 * If recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1762,6 +1762,7 @@ static int raid10_spare_active(struct mddev *mddev)
 			}
 			sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
 		} else if (tmp->rdev
+			   && tmp->rdev->recovery_offset == MaxSector
 			   && !test_bit(Faulty, &tmp->rdev->flags)
 			   && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
 			count++;
@@ -2947,6 +2948,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		 */
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
 			end_reshape(conf);
+			close_sync(conf);
 			return 0;
 		}
 
@@ -3197,10 +3199,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
-				put_buf(r10_bio);
-				if (rb2)
-					atomic_dec(&rb2->remaining);
-				r10_bio = rb2;
 				if (any_working) {
 					/* problem is that there are bad blocks
 					 * on other device(s)
@@ -3232,6 +3230,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
 				}
+				put_buf(r10_bio);
+				if (rb2)
+					atomic_dec(&rb2->remaining);
+				r10_bio = rb2;
 				break;
 			}
 		}
@@ -4397,7 +4399,7 @@ read_more:
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
-	read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
 	read_bio->bi_flags |= 1 << BIO_UPTODATE;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_size = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a35b846af4f8..2332b5ced0dd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -60,6 +60,10 @@
 #include "raid0.h"
 #include "bitmap.h"
 
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 /*
  * Stripe cache
  */
@@ -668,6 +672,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
 			bi->bi_size = STRIPE_SIZE;
+			/*
+			 * If this is discard request, set bi_vcnt 0. We don't
+			 * want to confuse SCSI because SCSI will replace payload
+			 */
+			if (rw & REQ_DISCARD)
+				bi->bi_vcnt = 0;
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
@@ -706,6 +716,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_size = STRIPE_SIZE;
+			/*
+			 * If this is discard request, set bi_vcnt 0. We don't
+			 * want to confuse SCSI because SCSI will replace payload
+			 */
+			if (rw & REQ_DISCARD)
+				rbi->bi_vcnt = 0;
 			if (conf->mddev->gendisk)
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
 						      rbi, disk_devt(conf->mddev->gendisk),
@@ -1881,6 +1897,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (!uptodate) {
+			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -2800,6 +2817,14 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 		}
 		/* now that discard is done we can proceed with any sync */
 		clear_bit(STRIPE_DISCARD, &sh->state);
+		/*
+		 * SCSI discard will change some bio fields and the stripe has
+		 * no updated data, so remove it from hash list and the stripe
+		 * will be reinitialized
+		 */
+		spin_lock_irq(&conf->device_lock);
+		remove_hash(sh);
+		spin_unlock_irq(&conf->device_lock);
 		if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
 			set_bit(STRIPE_HANDLE, &sh->state);
 
@@ -3371,7 +3396,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			 */
 			set_bit(R5_Insync, &dev->flags);
 
-		if (rdev && test_bit(R5_WriteError, &dev->flags)) {
+		if (test_bit(R5_WriteError, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(
@@ -3384,7 +3409,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			} else
 				clear_bit(R5_WriteError, &dev->flags);
 		}
-		if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
+		if (test_bit(R5_MadeGood, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(
@@ -3540,6 +3565,8 @@ static void handle_stripe(struct stripe_head *sh)
 				set_bit(R5_Wantwrite, &dev->flags);
 				if (prexor)
 					continue;
+				if (s.failed > 1)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
 				    ((i == sh->pd_idx || i == sh->qd_idx)  &&
 				     s.failed == 0))
@@ -5016,23 +5043,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	safe_put_page(percpu->spare_page);
+	kfree(percpu->scribble);
+	percpu->spare_page = NULL;
+	percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	if (conf->level == 6 && !percpu->spare_page)
+		percpu->spare_page = alloc_page(GFP_KERNEL);
+	if (!percpu->scribble)
+		percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+	if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+		free_scratch_buffer(conf, percpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void raid5_free_percpu(struct r5conf *conf)
 {
-	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
 	if (!conf->percpu)
 		return;
 
-	get_online_cpus();
-	for_each_possible_cpu(cpu) {
-		percpu = per_cpu_ptr(conf->percpu, cpu);
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-	}
 #ifdef CONFIG_HOTPLUG_CPU
 	unregister_cpu_notifier(&conf->cpu_notify);
 #endif
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu)
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 	put_online_cpus();
 
 	free_percpu(conf->percpu);
@@ -5058,15 +5105,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (conf->level == 6 && !percpu->spare_page)
-			percpu->spare_page = alloc_page(GFP_KERNEL);
-		if (!percpu->scribble)
-			percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
-		if (!percpu->scribble ||
-		    (conf->level == 6 && !percpu->spare_page)) {
-			safe_put_page(percpu->spare_page);
-			kfree(percpu->scribble);
+		if (alloc_scratch_buffer(conf, percpu)) {
 			pr_err("%s: failed memory allocation for cpu%ld\n",
 			       __func__, cpu);
 			return notifier_from_errno(-ENOMEM);
@@ -5074,10 +5113,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-		percpu->spare_page = NULL;
-		percpu->scribble = NULL;
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 		break;
 	default:
 		break;
@@ -5089,40 +5125,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 static int raid5_alloc_percpu(struct r5conf *conf)
 {
 	unsigned long cpu;
-	struct page *spare_page;
-	struct raid5_percpu __percpu *allcpus;
-	void *scribble;
-	int err;
+	int err = 0;
 
-	allcpus = alloc_percpu(struct raid5_percpu);
-	if (!allcpus)
+	conf->percpu = alloc_percpu(struct raid5_percpu);
+	if (!conf->percpu)
 		return -ENOMEM;
-	conf->percpu = allcpus;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	conf->cpu_notify.notifier_call = raid456_cpu_notify;
+	conf->cpu_notify.priority = 0;
+	err = register_cpu_notifier(&conf->cpu_notify);
+	if (err)
+		return err;
+#endif
 
 	get_online_cpus();
-	err = 0;
 	for_each_present_cpu(cpu) {
-		if (conf->level == 6) {
-			spare_page = alloc_page(GFP_KERNEL);
-			if (!spare_page) {
-				err = -ENOMEM;
-				break;
-			}
-			per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
-		}
-		scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-		if (!scribble) {
-			err = -ENOMEM;
+		err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+		if (err) {
+			pr_err("%s: failed memory allocation for cpu%ld\n",
+			       __func__, cpu);
 			break;
 		}
-		per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
 	}
-#ifdef CONFIG_HOTPLUG_CPU
-	conf->cpu_notify.notifier_call = raid456_cpu_notify;
-	conf->cpu_notify.priority = 0;
-	if (err == 0)
-		err = register_cpu_notifier(&conf->cpu_notify);
-#endif
 	put_online_cpus();
 
 	return err;
@@ -5590,7 +5615,7 @@ static int run(struct mddev *mddev)
 		mddev->queue->limits.discard_granularity = stripe;
 		/*
 		 * unaligned part of discard request will be ignored, so can't
-		 * guarantee discard_zerors_data
+		 * guarantee discard_zeroes_data
 		 */
 		mddev->queue->limits.discard_zeroes_data = 0;
 
@@ -5615,6 +5640,18 @@ static int run(struct mddev *mddev)
 			    !bdev_get_queue(rdev->bdev)->
 						limits.discard_zeroes_data)
 				discard_supported = false;
+			/* Unfortunately, discard_zeroes_data is not currently
+			 * a guarantee - just a hint.  So we only allow DISCARD
+			 * if the sysadmin has confirmed that only safe devices
+			 * are in use by setting a module parameter.
+			 */
+			if (!devices_handle_discard_safely) {
+				if (discard_supported) {
+					pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+					pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+				}
+				discard_supported = false;
+			}
 		}
 
 		if (discard_supported &&
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index a204f2828820..fb504f1e9125 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -24,6 +24,9 @@
 
 #include "af9013_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct af9013_state {
 	struct i2c_adapter *i2c;
 	struct dvb_frontend fe;
@@ -50,16 +53,23 @@ static int af9013_wr_regs_i2c(struct af9013_state *priv, u8 mbox, u16 reg,
 	const u8 *val, int len)
 {
 	int ret;
-	u8 buf[3+len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->config.i2c_addr,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 3 + len,
 			.buf = buf,
 		}
 	};
 
+	if (3 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = (reg >> 8) & 0xff;
 	buf[1] = (reg >> 0) & 0xff;
 	buf[2] = mbox;
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index a777b4b944eb..65728c25ea05 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -21,6 +21,9 @@
 
 #include "af9033_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct af9033_state {
 	struct i2c_adapter *i2c;
 	struct dvb_frontend fe;
@@ -40,16 +43,23 @@ static int af9033_wr_regs(struct af9033_state *state, u32 reg, const u8 *val,
 		int len)
 {
 	int ret;
-	u8 buf[3 + len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = state->cfg.i2c_addr,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 3 + len,
 			.buf = buf,
 		}
 	};
 
+	if (3 + len > sizeof(buf)) {
+		dev_warn(&state->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = (reg >> 16) & 0xff;
 	buf[1] = (reg >>  8) & 0xff;
 	buf[2] = (reg >>  0) & 0xff;
@@ -160,11 +170,18 @@ static int af9033_rd_reg_mask(struct af9033_state *state, u32 reg, u8 *val,
 static int af9033_wr_reg_val_tab(struct af9033_state *state,
 		const struct reg_val *tab, int tab_len)
 {
+#define MAX_TAB_LEN 212
 	int ret, i, j;
-	u8 buf[tab_len];
+	u8 buf[1 + MAX_TAB_LEN];
 
 	dev_dbg(&state->i2c->dev, "%s: tab_len=%d\n", __func__, tab_len);
 
+	if (tab_len > sizeof(buf)) {
+		dev_warn(&state->i2c->dev, "%s: tab len %d is too big\n",
+				KBUILD_MODNAME, tab_len);
+		return -EINVAL;
+	}
+
 	for (i = 0, j = 0; i < tab_len; i++) {
 		buf[j] = tab[i].val;
 
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 1b77909c0c71..39a29dd29519 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -44,6 +44,9 @@
 #include "bcm3510.h"
 #include "bcm3510_priv.h"
 
+/* Max transfer size done by bcm3510_do_hab_cmd() function */
+#define MAX_XFER_SIZE	128
+
 struct bcm3510_state {
 
 	struct i2c_adapter* i2c;
@@ -201,9 +204,19 @@ static int bcm3510_hab_send_request(struct bcm3510_state *st, u8 *buf, int len)
 
 static int bcm3510_do_hab_cmd(struct bcm3510_state *st, u8 cmd, u8 msgid, u8 *obuf, u8 olen, u8 *ibuf, u8 ilen)
 {
-	u8 ob[olen+2],ib[ilen+2];
+	u8 ob[MAX_XFER_SIZE], ib[MAX_XFER_SIZE];
 	int ret = 0;
 
+	if (ilen + 2 > sizeof(ib)) {
+		deb_hab("do_hab_cmd: ilen=%d is too big!\n", ilen);
+		return -EINVAL;
+	}
+
+	if (olen + 2 > sizeof(ob)) {
+		deb_hab("do_hab_cmd: olen=%d is too big!\n", olen);
+		return -EINVAL;
+	}
+
 	ob[0] = cmd;
 	ob[1] = msgid;
 	memcpy(&ob[2],obuf,olen);
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index 7ca5c69dd200..03930d5e9fea 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -21,21 +21,31 @@
 
 #include "cxd2820r_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /* write multiple registers */
 static int cxd2820r_wr_regs_i2c(struct cxd2820r_priv *priv, u8 i2c, u8 reg,
 	u8 *val, int len)
 {
 	int ret;
-	u8 buf[len+1];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = i2c,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = len + 1,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
@@ -55,7 +65,7 @@ static int cxd2820r_rd_regs_i2c(struct cxd2820r_priv *priv, u8 i2c, u8 reg,
 	u8 *val, int len)
 {
 	int ret;
-	u8 buf[len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[2] = {
 		{
 			.addr = i2c,
@@ -65,11 +75,18 @@ static int cxd2820r_rd_regs_i2c(struct cxd2820r_priv *priv, u8 i2c, u8 reg,
 		}, {
 			.addr = i2c,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = len,
 			.buf = buf,
 		}
 	};
 
+	if (len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, buf, len);
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index a54182dd0e91..362de38a7d8e 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -157,15 +157,10 @@ static u16 dib8000_i2c_read16(struct i2c_device *i2c, u16 reg)
 	return ret;
 }
 
-static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+static u16 __dib8000_read_word(struct dib8000_state *state, u16 reg)
 {
 	u16 ret;
 
-	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
-		dprintk("could not acquire lock");
-		return 0;
-	}
-
 	state->i2c_write_buffer[0] = reg >> 8;
 	state->i2c_write_buffer[1] = reg & 0xff;
 
@@ -183,6 +178,21 @@ static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
 		dprintk("i2c read error on %d", reg);
 
 	ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+
+	return ret;
+}
+
+static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+{
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
+	ret = __dib8000_read_word(state, reg);
+
 	mutex_unlock(&state->i2c_buffer_lock);
 
 	return ret;
@@ -192,8 +202,15 @@ static u32 dib8000_read32(struct dib8000_state *state, u16 reg)
 {
 	u16 rw[2];
 
-	rw[0] = dib8000_read_word(state, reg + 0);
-	rw[1] = dib8000_read_word(state, reg + 1);
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
+	rw[0] = __dib8000_read_word(state, reg + 0);
+	rw[1] = __dib8000_read_word(state, reg + 1);
+
+	mutex_unlock(&state->i2c_buffer_lock);
 
 	return ((rw[0] << 16) | (rw[1]));
 }
@@ -2445,7 +2462,8 @@ static int dib8000_autosearch_start(struct dvb_frontend *fe)
 	if (state->revision == 0x8090)
 		internal = dib8000_read32(state, 23) / 1000;
 
-	if (state->autosearch_state == AS_SEARCHING_FFT) {
+	if ((state->revision >= 0x8002) &&
+	    (state->autosearch_state == AS_SEARCHING_FFT)) {
 		dib8000_write_word(state,  37, 0x0065); /* P_ctrl_pha_off_max default values */
 		dib8000_write_word(state, 116, 0x0000); /* P_ana_gain to 0 */
 
@@ -2481,7 +2499,8 @@ static int dib8000_autosearch_start(struct dvb_frontend *fe)
 		dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (1 << 13)); /* P_restart_ccg = 1 */
 		dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (0 << 13)); /* P_restart_ccg = 0 */
 		dib8000_write_word(state, 0, (dib8000_read_word(state, 0) & 0x7ff) | (0 << 15) | (1 << 13)); /* P_restart_search = 0; */
-	} else if (state->autosearch_state == AS_SEARCHING_GUARD) {
+	} else if ((state->revision >= 0x8002) &&
+		   (state->autosearch_state == AS_SEARCHING_GUARD)) {
 		c->transmission_mode = TRANSMISSION_MODE_8K;
 		c->guard_interval = GUARD_INTERVAL_1_8;
 		c->inversion = 0;
@@ -2583,7 +2602,8 @@ static int dib8000_autosearch_irq(struct dvb_frontend *fe)
 	struct dib8000_state *state = fe->demodulator_priv;
 	u16 irq_pending = dib8000_read_word(state, 1284);
 
-	if (state->autosearch_state == AS_SEARCHING_FFT) {
+	if ((state->revision >= 0x8002) &&
+	    (state->autosearch_state == AS_SEARCHING_FFT)) {
 		if (irq_pending & 0x1) {
 			dprintk("dib8000_autosearch_irq: max correlation result available");
 			return 3;
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 1e344b033277..22e8c2032f6d 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -864,6 +864,13 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config,
 	memcpy(&state->frontend.ops, &ds3000_ops,
 			sizeof(struct dvb_frontend_ops));
 	state->frontend.demodulator_priv = state;
+
+	/*
+	 * Some devices like T480 starts with voltage on. Be sure
+	 * to turn voltage off during init, as this can otherwise
+	 * interfere with Unicable SCR systems.
+	 */
+	ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF);
 	return &state->frontend;
 
 error3:
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index c1c3400b2173..cadcae4cff89 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -31,6 +31,9 @@
 #include "itd1000.h"
 #include "itd1000_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static int debug;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off debugging (default:off).");
@@ -52,10 +55,18 @@ MODULE_PARM_DESC(debug, "Turn on/off debugging (default:off).");
 /* don't write more than one byte with flexcop behind */
 static int itd1000_write_regs(struct itd1000_state *state, u8 reg, u8 v[], u8 len)
 {
-	u8 buf[1+len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg = {
 		.addr = state->cfg->i2c_address, .flags = 0, .buf = buf, .len = len+1
 	};
+
+	if (1 + len > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "itd1000: i2c wr reg=%04x: len=%d is too big!\n",
+		       reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], v, len);
 
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 4da5272075cb..c7a1c8eba475 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -110,28 +110,94 @@ static u8 m88rs2000_readreg(struct m88rs2000_state *state, u8 reg)
 	return b1[0];
 }
 
+static u32 m88rs2000_get_mclk(struct dvb_frontend *fe)
+{
+	struct m88rs2000_state *state = fe->demodulator_priv;
+	u32 mclk;
+	u8 reg;
+	/* Must not be 0x00 or 0xff */
+	reg = m88rs2000_readreg(state, 0x86);
+	if (!reg || reg == 0xff)
+		return 0;
+
+	reg /= 2;
+	reg += 1;
+
+	mclk = (u32)(reg * RS2000_FE_CRYSTAL_KHZ + 28 / 2) / 28;
+
+	return mclk;
+}
+
+static int m88rs2000_set_carrieroffset(struct dvb_frontend *fe, s16 offset)
+{
+	struct m88rs2000_state *state = fe->demodulator_priv;
+	u32 mclk;
+	s32 tmp;
+	u8 reg;
+	int ret;
+
+	mclk = m88rs2000_get_mclk(fe);
+	if (!mclk)
+		return -EINVAL;
+
+	tmp = (offset * 4096 + (s32)mclk / 2) / (s32)mclk;
+	if (tmp < 0)
+		tmp += 4096;
+
+	/* Carrier Offset */
+	ret = m88rs2000_writereg(state, 0x9c, (u8)(tmp >> 4));
+
+	reg = m88rs2000_readreg(state, 0x9d);
+	reg &= 0xf;
+	reg |= (u8)(tmp & 0xf) << 4;
+
+	ret |= m88rs2000_writereg(state, 0x9d, reg);
+
+	return ret;
+}
+
 static int m88rs2000_set_symbolrate(struct dvb_frontend *fe, u32 srate)
 {
 	struct m88rs2000_state *state = fe->demodulator_priv;
 	int ret;
-	u32 temp;
+	u64 temp;
+	u32 mclk;
 	u8 b[3];
 
 	if ((srate < 1000000) || (srate > 45000000))
 		return -EINVAL;
 
+	mclk = m88rs2000_get_mclk(fe);
+	if (!mclk)
+		return -EINVAL;
+
 	temp = srate / 1000;
-	temp *= 11831;
-	temp /= 68;
-	temp -= 3;
+	temp *= 1 << 24;
+
+	do_div(temp, mclk);
 
 	b[0] = (u8) (temp >> 16) & 0xff;
 	b[1] = (u8) (temp >> 8) & 0xff;
 	b[2] = (u8) temp & 0xff;
+
 	ret = m88rs2000_writereg(state, 0x93, b[2]);
 	ret |= m88rs2000_writereg(state, 0x94, b[1]);
 	ret |= m88rs2000_writereg(state, 0x95, b[0]);
 
+	if (srate > 10000000)
+		ret |= m88rs2000_writereg(state, 0xa0, 0x20);
+	else
+		ret |= m88rs2000_writereg(state, 0xa0, 0x60);
+
+	ret |= m88rs2000_writereg(state, 0xa1, 0xe0);
+
+	if (srate > 12000000)
+		ret |= m88rs2000_writereg(state, 0xa3, 0x20);
+	else if (srate > 2800000)
+		ret |= m88rs2000_writereg(state, 0xa3, 0x98);
+	else
+		ret |= m88rs2000_writereg(state, 0xa3, 0x90);
+
 	deb_info("m88rs2000: m88rs2000_set_symbolrate\n");
 	return ret;
 }
@@ -261,8 +327,6 @@ struct inittab m88rs2000_shutdown[] = {
 
 struct inittab fe_reset[] = {
 	{DEMOD_WRITE, 0x00, 0x01},
-	{DEMOD_WRITE, 0xf1, 0xbf},
-	{DEMOD_WRITE, 0x00, 0x01},
 	{DEMOD_WRITE, 0x20, 0x81},
 	{DEMOD_WRITE, 0x21, 0x80},
 	{DEMOD_WRITE, 0x10, 0x33},
@@ -305,9 +369,6 @@ struct inittab fe_trigger[] = {
 	{DEMOD_WRITE, 0x9b, 0x64},
 	{DEMOD_WRITE, 0x9e, 0x00},
 	{DEMOD_WRITE, 0x9f, 0xf8},
-	{DEMOD_WRITE, 0xa0, 0x20},
-	{DEMOD_WRITE, 0xa1, 0xe0},
-	{DEMOD_WRITE, 0xa3, 0x38},
 	{DEMOD_WRITE, 0x98, 0xff},
 	{DEMOD_WRITE, 0xc0, 0x0f},
 	{DEMOD_WRITE, 0x89, 0x01},
@@ -540,9 +601,8 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	fe_status_t status;
 	int i, ret = 0;
-	s32 tmp;
 	u32 tuner_freq;
-	u16 offset = 0;
+	s16 offset = 0;
 	u8 reg;
 
 	state->no_lock_count = 0;
@@ -567,29 +627,26 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 	if (ret < 0)
 		return -ENODEV;
 
-	offset = tuner_freq - c->frequency;
-
-	/* calculate offset assuming 96000kHz*/
-	tmp = offset;
-	tmp *= 65536;
+	offset = (s16)((s32)tuner_freq - c->frequency);
 
-	tmp = (2 * tmp + 96000) / (2 * 96000);
-	if (tmp < 0)
-		tmp += 65536;
-
-	offset = tmp & 0xffff;
+	/* default mclk value 96.4285 * 2 * 1000 = 192857 */
+	if (((c->frequency % 192857) >= (192857 - 3000)) ||
+				(c->frequency % 192857) <= 3000)
+		ret = m88rs2000_writereg(state, 0x86, 0xc2);
+	else
+		ret = m88rs2000_writereg(state, 0x86, 0xc6);
 
-	ret = m88rs2000_writereg(state, 0x9a, 0x30);
-	/* Unknown usually 0xc6 sometimes 0xc1 */
-	reg = m88rs2000_readreg(state, 0x86);
-	ret |= m88rs2000_writereg(state, 0x86, reg);
-	/* Offset lower nibble always 0 */
-	ret |= m88rs2000_writereg(state, 0x9c, (offset >> 8));
-	ret |= m88rs2000_writereg(state, 0x9d, offset & 0xf0);
+	ret |= m88rs2000_set_carrieroffset(fe, offset);
+	if (ret < 0)
+		return -ENODEV;
 
+	/* Reset demod by symbol rate */
+	if (c->symbol_rate > 27500000)
+		ret = m88rs2000_writereg(state, 0xf1, 0xa4);
+	else
+		ret = m88rs2000_writereg(state, 0xf1, 0xbf);
 
-	/* Reset Demod */
-	ret = m88rs2000_tab_set(state, fe_reset);
+	ret |= m88rs2000_tab_set(state, fe_reset);
 	if (ret < 0)
 		return -ENODEV;
 
@@ -655,6 +712,22 @@ static int m88rs2000_get_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
+static int m88rs2000_get_tune_settings(struct dvb_frontend *fe,
+	struct dvb_frontend_tune_settings *tune)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	if (c->symbol_rate > 3000000)
+		tune->min_delay_ms = 2000;
+	else
+		tune->min_delay_ms = 3000;
+
+	tune->step_size = c->symbol_rate / 16000;
+	tune->max_drift = c->symbol_rate / 2000;
+
+	return 0;
+}
+
 static int m88rs2000_i2c_gate_ctrl(struct dvb_frontend *fe, int enable)
 {
 	struct m88rs2000_state *state = fe->demodulator_priv;
@@ -686,7 +759,7 @@ static struct dvb_frontend_ops m88rs2000_ops = {
 		.symbol_rate_tolerance	= 500,	/* ppm */
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
-		      FE_CAN_QPSK |
+		      FE_CAN_QPSK | FE_CAN_INVERSION_AUTO |
 		      FE_CAN_FEC_AUTO
 	},
 
@@ -706,6 +779,7 @@ static struct dvb_frontend_ops m88rs2000_ops = {
 
 	.set_frontend = m88rs2000_set_frontend,
 	.get_frontend = m88rs2000_get_frontend,
+	.get_tune_settings = m88rs2000_get_tune_settings,
 };
 
 struct dvb_frontend *m88rs2000_attach(const struct m88rs2000_config *config,
diff --git a/drivers/media/dvb-frontends/m88rs2000.h b/drivers/media/dvb-frontends/m88rs2000.h
index 14ce31e76ae6..0a50ea90736b 100644
--- a/drivers/media/dvb-frontends/m88rs2000.h
+++ b/drivers/media/dvb-frontends/m88rs2000.h
@@ -53,6 +53,8 @@ static inline struct dvb_frontend *m88rs2000_attach(
 }
 #endif /* CONFIG_DVB_M88RS2000 */
 
+#define RS2000_FE_CRYSTAL_KHZ 27000
+
 enum {
 	DEMOD_WRITE = 0x1,
 	WRITE_DELAY = 0x10,
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index ec388c1d6913..a74ac0ddb833 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -36,6 +36,8 @@
 #include "mt312_priv.h"
 #include "mt312.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
 
 struct mt312_state {
 	struct i2c_adapter *i2c;
@@ -96,9 +98,15 @@ static int mt312_write(struct mt312_state *state, const enum mt312_reg_addr reg,
 		       const u8 *src, const size_t count)
 {
 	int ret;
-	u8 buf[count + 1];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg;
 
+	if (1 + count > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "mt312: write: len=%zd is too big!\n", count);
+		return -EINVAL;
+	}
+
 	if (debug) {
 		int i;
 		dprintk("W(%d):", reg & 0x7f);
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index 8e288940a61f..4bf057544607 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -39,6 +39,9 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  256
+
 #define NXT2002_DEFAULT_FIRMWARE "dvb-fe-nxt2002.fw"
 #define NXT2004_DEFAULT_FIRMWARE "dvb-fe-nxt2004.fw"
 #define CRC_CCIT_MASK 0x1021
@@ -95,10 +98,16 @@ static int i2c_readbytes(struct nxt200x_state *state, u8 addr, u8 *buf, u8 len)
 static int nxt200x_writebytes (struct nxt200x_state* state, u8 reg,
 			       const u8 *buf, u8 len)
 {
-	u8 buf2 [len+1];
+	u8 buf2[MAX_XFER_SIZE];
 	int err;
 	struct i2c_msg msg = { .addr = state->config->demod_address, .flags = 0, .buf = buf2, .len = len + 1 };
 
+	if (1 + len > sizeof(buf2)) {
+		pr_warn("%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 __func__, reg, len);
+		return -EINVAL;
+	}
+
 	buf2[0] = reg;
 	memcpy(&buf2[1], buf, len);
 
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index 362d26d11e82..7efb796c472c 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -27,20 +27,30 @@
 
 #include "rtl2830_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /* write multiple hardware registers */
 static int rtl2830_wr(struct rtl2830_priv *priv, u8 reg, const u8 *val, int len)
 {
 	int ret;
-	u8 buf[1+len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg.i2c_addr,
 			.flags = 0,
-			.len = 1+len,
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index facb84841518..b8dd0a135461 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -22,6 +22,9 @@
 #include "dvb_math.h"
 #include <linux/bitops.h>
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 int rtl2832_debug;
 module_param_named(debug, rtl2832_debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
@@ -162,16 +165,23 @@ static const struct rtl2832_reg_entry registers[] = {
 static int rtl2832_wr(struct rtl2832_priv *priv, u8 reg, u8 *val, int len)
 {
 	int ret;
-	u8 buf[1+len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg.i2c_addr,
 			.flags = 0,
-			.len = 1+len,
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index e2fec9ebf947..93eeaf7118fd 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -836,9 +836,16 @@ static u32 s5h1420_tuner_i2c_func(struct i2c_adapter *adapter)
 static int s5h1420_tuner_i2c_tuner_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msg[], int num)
 {
 	struct s5h1420_state *state = i2c_get_adapdata(i2c_adap);
-	struct i2c_msg m[1 + num];
+	struct i2c_msg m[3];
 	u8 tx_open[2] = { CON_1, state->CON_1_val | 1 }; /* repeater stops once there was a stop condition */
 
+	if (1 + num > ARRAY_SIZE(m)) {
+		printk(KERN_WARNING
+		       "%s: i2c xfer: num=%d is too big!\n",
+		       KBUILD_MODNAME, num);
+		return  -EOPNOTSUPP;
+	}
+
 	memset(m, 0, sizeof(struct i2c_msg) * (1 + num));
 
 	m[0].addr = state->config->demod_address;
@@ -847,7 +854,7 @@ static int s5h1420_tuner_i2c_tuner_xfer(struct i2c_adapter *i2c_adap, struct i2c
 
 	memcpy(&m[1], msg, sizeof(struct i2c_msg) * num);
 
-	return i2c_transfer(state->i2c, m, 1+num) == 1 + num ? num : -EIO;
+	return i2c_transfer(state->i2c, m, 1 + num) == 1 + num ? num : -EIO;
 }
 
 static struct i2c_algorithm s5h1420_tuner_i2c_algo = {
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index cc278b3d6d5a..2a979cfac146 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -32,6 +32,9 @@
 #include "stb0899_priv.h"
 #include "stb0899_reg.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static unsigned int verbose = 0;//1;
 module_param(verbose, int, 0644);
 
@@ -499,7 +502,7 @@ err:
 int stb0899_write_regs(struct stb0899_state *state, unsigned int reg, u8 *data, u32 count)
 {
 	int ret;
-	u8 buf[2 + count];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg i2c_msg = {
 		.addr	= state->config->demod_address,
 		.flags	= 0,
@@ -507,6 +510,13 @@ int stb0899_write_regs(struct stb0899_state *state, unsigned int reg, u8 *data,
 		.len	= 2 + count
 	};
 
+	if (2 + count > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr reg=%04x: len=%d is too big!\n",
+		       KBUILD_MODNAME, reg, count);
+		return -EINVAL;
+	}
+
 	buf[0] = reg >> 8;
 	buf[1] = reg & 0xff;
 	memcpy(&buf[2], data, count);
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 45f9523f968f..cea175d19890 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -31,6 +31,8 @@
 static unsigned int verbose;
 module_param(verbose, int, 0644);
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
 
 #define FE_ERROR		0
 #define FE_NOTICE		1
@@ -183,7 +185,7 @@ static int stb6100_read_reg(struct stb6100_state *state, u8 reg)
 static int stb6100_write_reg_range(struct stb6100_state *state, u8 buf[], int start, int len)
 {
 	int rc;
-	u8 cmdbuf[len + 1];
+	u8 cmdbuf[MAX_XFER_SIZE];
 	struct i2c_msg msg = {
 		.addr	= state->config->tuner_address,
 		.flags	= 0,
@@ -191,6 +193,13 @@ static int stb6100_write_reg_range(struct stb6100_state *state, u8 buf[], int st
 		.len	= len + 1
 	};
 
+	if (1 + len > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr: len=%d is too big!\n",
+		       KBUILD_MODNAME, len);
+		return -EINVAL;
+	}
+
 	if (unlikely(start < 1 || start + len > STB6100_NUMREGS)) {
 		dprintk(verbose, FE_ERROR, 1, "Invalid register range %d:%d",
 			start, len);
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 0c8e45949b11..f6c7277999fe 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -33,6 +33,9 @@
 #include "stv0367_regs.h"
 #include "stv0367_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static int stvdebug;
 module_param_named(debug, stvdebug, int, 0644);
 
@@ -767,7 +770,7 @@ static struct st_register def0367cab[STV0367CAB_NBREGS] = {
 static
 int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len)
 {
-	u8 buf[len + 2];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg = {
 		.addr = state->config->demod_address,
 		.flags = 0,
@@ -776,6 +779,14 @@ int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len)
 	};
 	int ret;
 
+	if (2 + len > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr reg=%04x: len=%d is too big!\n",
+		       KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
+
 	buf[0] = MSB(reg);
 	buf[1] = LSB(reg);
 	memcpy(buf + 2, data, len);
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index 56d470ad5a82..23e872f84742 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -35,6 +35,9 @@
 #include "stv090x.h"
 #include "stv090x_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static unsigned int verbose;
 module_param(verbose, int, 0644);
 
@@ -722,9 +725,16 @@ static int stv090x_write_regs(struct stv090x_state *state, unsigned int reg, u8
 {
 	const struct stv090x_config *config = state->config;
 	int ret;
-	u8 buf[2 + count];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg i2c_msg = { .addr = config->address, .flags = 0, .buf = buf, .len = 2 + count };
 
+	if (2 + count > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr reg=%04x: len=%d is too big!\n",
+		       KBUILD_MODNAME, reg, count);
+		return -EINVAL;
+	}
+
 	buf[0] = reg >> 8;
 	buf[1] = reg & 0xff;
 	memcpy(&buf[2], data, count);
diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c
index 20b5fa92c53e..b1425830a24e 100644
--- a/drivers/media/dvb-frontends/stv6110.c
+++ b/drivers/media/dvb-frontends/stv6110.c
@@ -30,6 +30,9 @@
 
 #include "stv6110.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static int debug;
 
 struct stv6110_priv {
@@ -68,7 +71,7 @@ static int stv6110_write_regs(struct dvb_frontend *fe, u8 buf[],
 {
 	struct stv6110_priv *priv = fe->tuner_priv;
 	int rc;
-	u8 cmdbuf[len + 1];
+	u8 cmdbuf[MAX_XFER_SIZE];
 	struct i2c_msg msg = {
 		.addr	= priv->i2c_address,
 		.flags	= 0,
@@ -78,6 +81,13 @@ static int stv6110_write_regs(struct dvb_frontend *fe, u8 buf[],
 
 	dprintk("%s\n", __func__);
 
+	if (1 + len > sizeof(cmdbuf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr: len=%d is too big!\n",
+		       KBUILD_MODNAME, len);
+		return -EINVAL;
+	}
+
 	if (start + len > 8)
 		return -EINVAL;
 
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index f36cab12bdc7..e66154e5c1d7 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -32,6 +32,9 @@
 #include "stv6110x.h"
 #include "stv6110x_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static unsigned int verbose;
 module_param(verbose, int, 0644);
 MODULE_PARM_DESC(verbose, "Set Verbosity level");
@@ -61,7 +64,8 @@ static int stv6110x_write_regs(struct stv6110x_state *stv6110x, int start, u8 da
 {
 	int ret;
 	const struct stv6110x_config *config = stv6110x->config;
-	u8 buf[len + 1];
+	u8 buf[MAX_XFER_SIZE];
+
 	struct i2c_msg msg = {
 		.addr = config->addr,
 		.flags = 0,
@@ -69,6 +73,13 @@ static int stv6110x_write_regs(struct stv6110x_state *stv6110x, int start, u8 da
 		.len = len + 1
 	};
 
+	if (1 + len > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr: len=%d is too big!\n",
+		       KBUILD_MODNAME, len);
+		return -EINVAL;
+	}
+
 	if (start + len > 8)
 		return -EINVAL;
 
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 2521f7e23018..def7812d7b22 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -20,6 +20,9 @@
 
 #include "tda10071_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static struct dvb_frontend_ops tda10071_ops;
 
 /* write multiple registers */
@@ -27,16 +30,23 @@ static int tda10071_wr_regs(struct tda10071_priv *priv, u8 reg, u8 *val,
 	int len)
 {
 	int ret;
-	u8 buf[len+1];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg.demod_i2c_addr,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
@@ -56,7 +66,7 @@ static int tda10071_rd_regs(struct tda10071_priv *priv, u8 reg, u8 *val,
 	int len)
 {
 	int ret;
-	u8 buf[len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[2] = {
 		{
 			.addr = priv->cfg.demod_i2c_addr,
@@ -66,11 +76,18 @@ static int tda10071_rd_regs(struct tda10071_priv *priv, u8 reg, u8 *val,
 		}, {
 			.addr = priv->cfg.demod_i2c_addr,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = len,
 			.buf = buf,
 		}
 	};
 
+	if (len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, buf, len);
@@ -650,6 +667,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
 	u8 mode, rolloff, pilot, inversion, div;
+	fe_modulation_t modulation;
 
 	dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d " \
 		"frequency=%d symbol_rate=%d inversion=%d pilot=%d " \
@@ -684,10 +702,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	switch (c->delivery_system) {
 	case SYS_DVBS:
+		modulation = QPSK;
 		rolloff = 0;
 		pilot = 2;
 		break;
 	case SYS_DVBS2:
+		modulation = c->modulation;
+
 		switch (c->rolloff) {
 		case ROLLOFF_20:
 			rolloff = 2;
@@ -732,7 +753,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) {
 		if (c->delivery_system == TDA10071_MODCOD[i].delivery_system &&
-			c->modulation == TDA10071_MODCOD[i].modulation &&
+			modulation == TDA10071_MODCOD[i].modulation &&
 			c->fec_inner == TDA10071_MODCOD[i].fec) {
 			mode = TDA10071_MODCOD[i].val;
 			dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n",
diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c
index d281f77d5c28..2c54586ac07f 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.c
+++ b/drivers/media/dvb-frontends/tda18271c2dd.c
@@ -34,6 +34,9 @@
 #include "dvb_frontend.h"
 #include "tda18271c2dd.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct SStandardParam {
 	s32   m_IFFrequency;
 	u32   m_BandWidth;
@@ -139,11 +142,18 @@ static int i2c_write(struct i2c_adapter *adap, u8 adr, u8 *data, int len)
 static int WriteRegs(struct tda_state *state,
 		     u8 SubAddr, u8 *Regs, u16 nRegs)
 {
-	u8 data[nRegs+1];
+	u8 data[MAX_XFER_SIZE];
+
+	if (1 + nRegs > sizeof(data)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr: len=%d is too big!\n",
+		       KBUILD_MODNAME, nRegs);
+		return -EINVAL;
+	}
 
 	data[0] = SubAddr;
 	memcpy(data + 1, Regs, nRegs);
-	return i2c_write(state->i2c, state->adr, data, nRegs+1);
+	return i2c_write(state->i2c, state->adr, data, nRegs + 1);
 }
 
 static int WriteReg(struct tda_state *state, u8 SubAddr, u8 Reg)
diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c
index eff9c5fde50a..91b6b2e9b792 100644
--- a/drivers/media/dvb-frontends/zl10039.c
+++ b/drivers/media/dvb-frontends/zl10039.c
@@ -30,6 +30,9 @@
 
 static int debug;
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 #define dprintk(args...) \
 	do { \
 		if (debug) \
@@ -98,7 +101,7 @@ static int zl10039_write(struct zl10039_state *state,
 			const enum zl10039_reg_addr reg, const u8 *src,
 			const size_t count)
 {
-	u8 buf[count + 1];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg = {
 		.addr = state->i2c_addr,
 		.flags = 0,
@@ -106,6 +109,13 @@ static int zl10039_write(struct zl10039_state *state,
 		.len = count + 1,
 	};
 
+	if (1 + count > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr reg=%04x: len=%zd is too big!\n",
+		       KBUILD_MODNAME, reg, count);
+		return -EINVAL;
+	}
+
 	dprintk("%s\n", __func__);
 	/* Write register address and data in one go */
 	buf[0] = reg;
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 617ad3fff4aa..3ead3a83f04a 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1110,7 +1110,7 @@ static int ov7670_enum_framesizes(struct v4l2_subdev *sd,
 	 * windows that fall outside that.
 	 */
 	for (i = 0; i < n_win_sizes; i++) {
-		struct ov7670_win_size *win = &info->devtype->win_sizes[index];
+		struct ov7670_win_size *win = &info->devtype->win_sizes[i];
 		if (info->min_width && win->width < info->min_width)
 			continue;
 		if (info->min_height && win->height < info->min_height)
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index cae4f4683851..b280216de31b 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2139,7 +2139,7 @@ static int smiapp_set_selection(struct v4l2_subdev *subdev,
 		ret = smiapp_set_compose(subdev, fh, sel);
 		break;
 	default:
-		BUG();
+		ret = -EINVAL;
 	}
 
 	mutex_unlock(&sensor->mutex);
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 28b5121881f5..09f4387dbc49 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl)
 		if (t->mute->val) {
 			lf |= TDA7432_MUTE;
 			lr |= TDA7432_MUTE;
-			lf |= TDA7432_MUTE;
+			rf |= TDA7432_MUTE;
 			rr |= TDA7432_MUTE;
 		}
 		/* Mute & update balance*/
diff --git a/drivers/media/i2c/wm8775.c b/drivers/media/i2c/wm8775.c
index 27c27b4ae238..e5f3a78cf55b 100644
--- a/drivers/media/i2c/wm8775.c
+++ b/drivers/media/i2c/wm8775.c
@@ -131,12 +131,10 @@ static int wm8775_s_routing(struct v4l2_subdev *sd,
 		return -EINVAL;
 	}
 	state->input = input;
-	if (!v4l2_ctrl_g_ctrl(state->mute))
+	if (v4l2_ctrl_g_ctrl(state->mute))
 		return 0;
 	if (!v4l2_ctrl_g_ctrl(state->vol))
 		return 0;
-	if (!v4l2_ctrl_g_ctrl(state->bal))
-		return 0;
 	wm8775_set_audio(sd, 1);
 	return 0;
 }
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 1957c0df08fd..fdb5840f034b 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -93,6 +93,7 @@ static long media_device_enum_entities(struct media_device *mdev,
 	struct media_entity *ent;
 	struct media_entity_desc u_ent;
 
+	memset(&u_ent, 0, sizeof(u_ent));
 	if (copy_from_user(&u_ent.id, &uent->id, sizeof(u_ent.id)))
 		return -EFAULT;
 
@@ -105,8 +106,6 @@ static long media_device_enum_entities(struct media_device *mdev,
 	if (ent->name) {
 		strncpy(u_ent.name, ent->name, sizeof(u_ent.name));
 		u_ent.name[sizeof(u_ent.name) - 1] = '\0';
-	} else {
-		memset(u_ent.name, 0, sizeof(u_ent.name));
 	}
 	u_ent.type = ent->type;
 	u_ent.revision = ent->revision;
diff --git a/drivers/media/pci/Kconfig b/drivers/media/pci/Kconfig
index d4e2ed3f27e5..53196f1366f3 100644
--- a/drivers/media/pci/Kconfig
+++ b/drivers/media/pci/Kconfig
@@ -1,6 +1,7 @@
+if PCI && MEDIA_SUPPORT
+
 menuconfig MEDIA_PCI_SUPPORT
 	bool "Media PCI Adapters"
-	depends on PCI && MEDIA_SUPPORT
 	help
 	  Enable media drivers for PCI/PCIe bus.
 	  If you have such devices, say Y.
@@ -45,3 +46,4 @@ source "drivers/media/pci/ddbridge/Kconfig"
 endif
 
 endif #MEDIA_PCI_SUPPORT
+endif #PCI
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index e7d088413411..e2633d9270b7 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -4226,7 +4226,8 @@ static int bttv_probe(struct pci_dev *dev, const struct pci_device_id *pci_id)
 	}
 	btv->std = V4L2_STD_PAL;
 	init_irqreg(btv);
-	v4l2_ctrl_handler_setup(hdl);
+	if (!bttv_tvcards[btv->c.type].no_video)
+		v4l2_ctrl_handler_setup(hdl);
 	if (hdl->error) {
 		result = hdl->error;
 		goto fail2;
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 67b61cf3e03a..018cb9045330 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -324,23 +324,27 @@ static void cx18_eeprom_dump(struct cx18 *cx, unsigned char *eedata, int len)
 /* Hauppauge card? get values from tveeprom */
 void cx18_read_eeprom(struct cx18 *cx, struct tveeprom *tv)
 {
-	struct i2c_client c;
+	struct i2c_client *c;
 	u8 eedata[256];
 
-	memset(&c, 0, sizeof(c));
-	strlcpy(c.name, "cx18 tveeprom tmp", sizeof(c.name));
-	c.adapter = &cx->i2c_adap[0];
-	c.addr = 0xA0 >> 1;
-
 	memset(tv, 0, sizeof(*tv));
-	if (tveeprom_read(&c, eedata, sizeof(eedata)))
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
 		return;
 
+	strlcpy(c->name, "cx18 tveeprom tmp", sizeof(c->name));
+	c->adapter = &cx->i2c_adap[0];
+	c->addr = 0xa0 >> 1;
+
+	if (tveeprom_read(c, eedata, sizeof(eedata)))
+		goto ret;
+
 	switch (cx->card->type) {
 	case CX18_CARD_HVR_1600_ESMT:
 	case CX18_CARD_HVR_1600_SAMSUNG:
 	case CX18_CARD_HVR_1600_S5H1411:
-		tveeprom_hauppauge_analog(&c, tv, eedata);
+		tveeprom_hauppauge_analog(c, tv, eedata);
 		break;
 	case CX18_CARD_YUAN_MPC718:
 	case CX18_CARD_GOTVIEW_PCI_DVD3:
@@ -354,6 +358,9 @@ void cx18_read_eeprom(struct cx18 *cx, struct tveeprom *tv)
 		cx18_eeprom_dump(cx, eedata, sizeof(eedata));
 		break;
 	}
+
+ret:
+	kfree(c);
 }
 
 static void cx18_process_eeprom(struct cx18 *cx)
@@ -1085,6 +1092,7 @@ static int cx18_probe(struct pci_dev *pci_dev,
 		setup.addr = ADDR_UNSET;
 		setup.type = cx->options.tuner;
 		setup.mode_mask = T_ANALOG_TV;  /* matches TV tuners */
+		setup.config = NULL;
 		if (cx->options.radio > 0)
 			setup.mode_mask |= T_RADIO;
 		setup.tuner_callback = (setup.type == TUNER_XC2028) ?
diff --git a/drivers/media/pci/cx23885/cimax2.c b/drivers/media/pci/cx23885/cimax2.c
index 7344849183a7..16fa7ea4d4aa 100644
--- a/drivers/media/pci/cx23885/cimax2.c
+++ b/drivers/media/pci/cx23885/cimax2.c
@@ -26,6 +26,10 @@
 #include "cx23885.h"
 #include "cimax2.h"
 #include "dvb_ca_en50221.h"
+
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /**** Bit definitions for MC417_RWD and MC417_OEN registers  ***
   bits 31-16
 +-----------+
@@ -125,7 +129,7 @@ static int netup_write_i2c(struct i2c_adapter *i2c_adap, u8 addr, u8 reg,
 						u8 *buf, int len)
 {
 	int ret;
-	u8 buffer[len + 1];
+	u8 buffer[MAX_XFER_SIZE];
 
 	struct i2c_msg msg = {
 		.addr	= addr,
@@ -134,6 +138,13 @@ static int netup_write_i2c(struct i2c_adapter *i2c_adap, u8 addr, u8 reg,
 		.len	= len + 1
 	};
 
+	if (1 + len > sizeof(buffer)) {
+		printk(KERN_WARNING
+		       "%s: i2c wr reg=%04x: len=%d is too big!\n",
+		       KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buffer[0] = reg;
 	memcpy(&buffer[1], buf, len);
 
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 9c5ed10b2c5e..bb291c661143 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1249,6 +1249,10 @@ static int dvb_register(struct cx23885_tsport *port)
 		fe0->dvb.frontend = dvb_attach(ds3000_attach,
 					&tevii_ds3000_config,
 					&i2c_bus->i2c_adap);
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(ts2020_attach, fe0->dvb.frontend,
+				&tevii_ts2020_config, &i2c_bus->i2c_adap);
+		}
 		break;
 	case CX23885_BOARD_PROF_8000:
 		i2c_bus = &dev->i2c_bus[0];
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index e1863dbf4edc..7a9b98bc208b 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -159,6 +159,12 @@ static int snd_ivtv_pcm_capture_open(struct snd_pcm_substream *substream)
 
 	/* Instruct the CX2341[56] to start sending packets */
 	snd_ivtv_lock(itvsc);
+
+	if (ivtv_init_on_first_open(itv)) {
+		snd_ivtv_unlock(itvsc);
+		return -ENXIO;
+	}
+
 	s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM];
 
 	v4l2_fh_init(&item.fh, s->vdev);
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index d45e7f6ff332..e87a734637a9 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -8045,8 +8045,8 @@ int saa7134_board_init2(struct saa7134_dev *dev)
 		break;
 	} /* switch() */
 
-	/* initialize tuner */
-	if (TUNER_ABSENT != dev->tuner_type) {
+	/* initialize tuner (don't do this when resuming) */
+	if (!dev->insuspend && TUNER_ABSENT != dev->tuner_type) {
 		int has_demod = (dev->tda9887_conf & TDA9887_PRESENT);
 
 		/* Note: radio tuner address is always filled in,
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 7618fdae811e..62141b8f1e1a 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1348,9 +1348,11 @@ static int saa7164_initdev(struct pci_dev *pci_dev,
 		if (fw_debug) {
 			dev->kthread = kthread_run(saa7164_thread_function, dev,
 				"saa7164 debug");
-			if (!dev->kthread)
+			if (IS_ERR(dev->kthread)) {
+				dev->kthread = NULL;
 				printk(KERN_ERR "%s() Failed to create "
 					"debug kernel thread\n", __func__);
+			}
 		}
 
 	} /* != BOARD_UNKNOWN */
diff --git a/drivers/media/pci/ttpci/av7110_hw.c b/drivers/media/pci/ttpci/av7110_hw.c
index f1cbfe526989..6299d5dadb82 100644
--- a/drivers/media/pci/ttpci/av7110_hw.c
+++ b/drivers/media/pci/ttpci/av7110_hw.c
@@ -22,7 +22,7 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at http://www.linuxtv.org/
  */
 
 /* for debugging ARM communication: */
@@ -40,6 +40,14 @@
 
 #define _NOHANDSHAKE
 
+/*
+ * Max transfer size done by av7110_fw_cmd()
+ *
+ * The maximum size passed to this function is 6 bytes. The buffer also
+ * uses two additional ones for type and size. So, 8 bytes is enough.
+ */
+#define MAX_XFER_SIZE  8
+
 /****************************************************************************
  * DEBI functions
  ****************************************************************************/
@@ -488,11 +496,18 @@ static int av7110_send_fw_cmd(struct av7110 *av7110, u16* buf, int length)
 int av7110_fw_cmd(struct av7110 *av7110, int type, int com, int num, ...)
 {
 	va_list args;
-	u16 buf[num + 2];
+	u16 buf[MAX_XFER_SIZE];
 	int i, ret;
 
 //	dprintk(4, "%p\n", av7110);
 
+	if (2 + num > sizeof(buf)) {
+		printk(KERN_WARNING
+		       "%s: %s len=%d is too big!\n",
+		       KBUILD_MODNAME, __func__, num);
+		return -EINVAL;
+	}
+
 	buf[0] = ((type << 8) | com);
 	buf[1] = num;
 
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 1d7dbd5c0fba..3e8ef11f67aa 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -2249,6 +2249,7 @@ static int isp_probe(struct platform_device *pdev)
 	ret = iommu_attach_device(isp->domain, &pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "can't attach iommu device: %d\n", ret);
+		ret = -EPROBE_DEFER;
 		goto free_domain;
 	}
 
@@ -2287,6 +2288,7 @@ detach_dev:
 	iommu_detach_device(isp->domain, &pdev->dev);
 free_domain:
 	iommu_domain_free(isp->domain);
+	isp->domain = NULL;
 error_isp:
 	isp_xclk_cleanup(isp);
 	omap3isp_put(isp);
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index cd8831aebdeb..e2e4610d5550 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1079,6 +1079,7 @@ static void preview_config_input_format(struct isp_prev_device *prev,
  */
 static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
 {
+	const struct v4l2_mbus_framefmt *format = &prev->formats[PREV_PAD_SINK];
 	struct isp_device *isp = to_isp_device(prev);
 	unsigned int sph = prev->crop.left;
 	unsigned int eph = prev->crop.left + prev->crop.width - 1;
@@ -1086,6 +1087,14 @@ static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
 	unsigned int elv = prev->crop.top + prev->crop.height - 1;
 	u32 features;
 
+	if (format->code != V4L2_MBUS_FMT_Y8_1X8 &&
+	    format->code != V4L2_MBUS_FMT_Y10_1X10) {
+		sph -= 2;
+		eph += 2;
+		slv -= 2;
+		elv += 2;
+	}
+
 	features = (prev->params.params[0].features & active)
 		 | (prev->params.params[1].features & ~active);
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index d12faa691af8..961d7ff75427 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -177,21 +177,6 @@ unlock:
 		mutex_unlock(&dev->mfc_mutex);
 }
 
-static enum s5p_mfc_node_type s5p_mfc_get_node_type(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	if (!vdev) {
-		mfc_err("failed to get video_device");
-		return MFCNODE_INVALID;
-	}
-	if (vdev->index == 0)
-		return MFCNODE_DECODER;
-	else if (vdev->index == 1)
-		return MFCNODE_ENCODER;
-	return MFCNODE_INVALID;
-}
-
 static void s5p_mfc_clear_int_flags(struct s5p_mfc_dev *dev)
 {
 	mfc_write(dev, 0, S5P_FIMV_RISC_HOST_INT);
@@ -701,6 +686,7 @@ irq_cleanup_hw:
 /* Open an MFC node */
 static int s5p_mfc_open(struct file *file)
 {
+	struct video_device *vdev = video_devdata(file);
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_ctx *ctx = NULL;
 	struct vb2_queue *q;
@@ -738,7 +724,7 @@ static int s5p_mfc_open(struct file *file)
 	/* Mark context as idle */
 	clear_work_bit_irqsave(ctx);
 	dev->ctx[ctx->num] = ctx;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		ctx->type = MFCINST_DECODER;
 		ctx->c_ops = get_dec_codec_ops();
 		s5p_mfc_dec_init(ctx);
@@ -748,7 +734,7 @@ static int s5p_mfc_open(struct file *file)
 			mfc_err("Failed to setup mfc controls\n");
 			goto err_ctrls_setup;
 		}
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		ctx->type = MFCINST_ENCODER;
 		ctx->c_ops = get_enc_codec_ops();
 		/* only for encoder */
@@ -793,10 +779,10 @@ static int s5p_mfc_open(struct file *file)
 	q = &ctx->vq_dst;
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	q->drv_priv = &ctx->fh;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		q->io_modes = VB2_MMAP;
 		q->ops = get_dec_queue_ops();
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		q->io_modes = VB2_MMAP | VB2_USERPTR;
 		q->ops = get_enc_queue_ops();
 	} else {
@@ -815,10 +801,10 @@ static int s5p_mfc_open(struct file *file)
 	q->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
 	q->io_modes = VB2_MMAP;
 	q->drv_priv = &ctx->fh;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		q->io_modes = VB2_MMAP;
 		q->ops = get_dec_queue_ops();
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		q->io_modes = VB2_MMAP | VB2_USERPTR;
 		q->ops = get_enc_queue_ops();
 	} else {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index ef4074cd5316..f804c1faa7ff 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -113,15 +113,6 @@ enum s5p_mfc_fmt_type {
 };
 
 /**
- * enum s5p_mfc_node_type - The type of an MFC device node.
- */
-enum s5p_mfc_node_type {
-	MFCNODE_INVALID = -1,
-	MFCNODE_DECODER = 0,
-	MFCNODE_ENCODER = 1,
-};
-
-/**
  * enum s5p_mfc_inst_type - The type of an MFC instance.
  */
 enum s5p_mfc_inst_type {
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 7d0235069c87..5d538e7cd1bb 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -776,7 +776,7 @@ static int sh_vou_try_fmt_vid_out(struct file *file, void *priv,
 	v4l_bound_align_image(&pix->width, 0, VOU_MAX_IMAGE_WIDTH, 1,
 			      &pix->height, 0, VOU_MAX_IMAGE_HEIGHT, 1, 0);
 
-	for (i = 0; ARRAY_SIZE(vou_fmt); i++)
+	for (i = 0; i < ARRAY_SIZE(vou_fmt); i++)
 		if (vou_fmt[i].pfmt == pix->pixelformat)
 			return 0;
 
diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c
index 1b33ed368abe..c4ce45007810 100644
--- a/drivers/media/tuners/e4000.c
+++ b/drivers/media/tuners/e4000.c
@@ -20,20 +20,30 @@
 
 #include "e4000_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /* write multiple registers */
 static int e4000_wr_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
 {
 	int ret;
-	u8 buf[1 + len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg->i2c_addr,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
@@ -52,7 +62,7 @@ static int e4000_wr_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
 static int e4000_rd_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
 {
 	int ret;
-	u8 buf[len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[2] = {
 		{
 			.addr = priv->cfg->i2c_addr,
@@ -62,11 +72,18 @@ static int e4000_rd_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
 		}, {
 			.addr = priv->cfg->i2c_addr,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = len,
 			.buf = buf,
 		}
 	};
 
+	if (len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c rd reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, buf, len);
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 81f38aae9c66..f0c9c42867de 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -20,6 +20,9 @@
 
 #include "fc2580_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /*
  * TODO:
  * I2C write and read works only for one single register. Multiple registers
@@ -41,16 +44,23 @@
 static int fc2580_wr_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
 {
 	int ret;
-	u8 buf[1 + len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg->i2c_addr,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
@@ -69,7 +79,7 @@ static int fc2580_wr_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
 static int fc2580_rd_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
 {
 	int ret;
-	u8 buf[len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[2] = {
 		{
 			.addr = priv->cfg->i2c_addr,
@@ -79,11 +89,18 @@ static int fc2580_rd_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
 		}, {
 			.addr = priv->cfg->i2c_addr,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = len,
 			.buf = buf,
 		}
 	};
 
+	if (len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c rd reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, buf, len);
@@ -178,7 +195,7 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 
 	f_ref = 2UL * priv->cfg->clock / r_val;
 	n_val = div_u64_rem(f_vco, f_ref, &k_val);
-	k_val_reg = 1UL * k_val * (1 << 20) / f_ref;
+	k_val_reg = div_u64(1ULL * k_val * (1 << 20), f_ref);
 
 	ret = fc2580_wr_reg(priv, 0x18, r18_val | ((k_val_reg >> 16) & 0xff));
 	if (ret < 0)
@@ -331,8 +348,8 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 	if (ret < 0)
 		goto err;
 
-	ret = fc2580_wr_reg(priv, 0x37, 1UL * priv->cfg->clock * \
-			fc2580_if_filter_lut[i].mul / 1000000000);
+	ret = fc2580_wr_reg(priv, 0x37, div_u64(1ULL * priv->cfg->clock *
+			fc2580_if_filter_lut[i].mul, 1000000000));
 	if (ret < 0)
 		goto err;
 
diff --git a/drivers/media/tuners/fc2580_priv.h b/drivers/media/tuners/fc2580_priv.h
index be38a9e637e0..646c99452136 100644
--- a/drivers/media/tuners/fc2580_priv.h
+++ b/drivers/media/tuners/fc2580_priv.h
@@ -22,6 +22,7 @@
 #define FC2580_PRIV_H
 
 #include "fc2580.h"
+#include <linux/math64.h>
 
 struct fc2580_reg_val {
 	u8 reg;
diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c
index e4a84ee231cf..abe256e1f843 100644
--- a/drivers/media/tuners/tda18212.c
+++ b/drivers/media/tuners/tda18212.c
@@ -20,6 +20,9 @@
 
 #include "tda18212.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct tda18212_priv {
 	struct tda18212_config *cfg;
 	struct i2c_adapter *i2c;
@@ -32,16 +35,23 @@ static int tda18212_wr_regs(struct tda18212_priv *priv, u8 reg, u8 *val,
 	int len)
 {
 	int ret;
-	u8 buf[len+1];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg->i2c_address,
 			.flags = 0,
-			.len = sizeof(buf),
+			.len = 1 + len,
 			.buf = buf,
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	buf[0] = reg;
 	memcpy(&buf[1], val, len);
 
@@ -61,7 +71,7 @@ static int tda18212_rd_regs(struct tda18212_priv *priv, u8 reg, u8 *val,
 	int len)
 {
 	int ret;
-	u8 buf[len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[2] = {
 		{
 			.addr = priv->cfg->i2c_address,
@@ -71,11 +81,18 @@ static int tda18212_rd_regs(struct tda18212_priv *priv, u8 reg, u8 *val,
 		}, {
 			.addr = priv->cfg->i2c_address,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = len,
 			.buf = buf,
 		}
 	};
 
+	if (len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c rd reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, buf, len);
diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c
index 2d31aeb6b088..9300e9361e3b 100644
--- a/drivers/media/tuners/tda18218.c
+++ b/drivers/media/tuners/tda18218.c
@@ -20,11 +20,14 @@
 
 #include "tda18218_priv.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /* write multiple registers */
 static int tda18218_wr_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
 {
 	int ret = 0, len2, remaining;
-	u8 buf[1 + len];
+	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
 			.addr = priv->cfg->i2c_address,
@@ -33,6 +36,13 @@ static int tda18218_wr_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
 		}
 	};
 
+	if (1 + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	for (remaining = len; remaining > 0;
 			remaining -= (priv->cfg->i2c_wr_max - 1)) {
 		len2 = remaining;
@@ -63,7 +73,7 @@ static int tda18218_wr_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
 static int tda18218_rd_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
 {
 	int ret;
-	u8 buf[reg+len]; /* we must start read always from reg 0x00 */
+	u8 buf[MAX_XFER_SIZE]; /* we must start read always from reg 0x00 */
 	struct i2c_msg msg[2] = {
 		{
 			.addr = priv->cfg->i2c_address,
@@ -73,11 +83,18 @@ static int tda18218_rd_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
 		}, {
 			.addr = priv->cfg->i2c_address,
 			.flags = I2C_M_RD,
-			.len = sizeof(buf),
+			.len = reg + len,
 			.buf = buf,
 		}
 	};
 
+	if (reg + len > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
+			 KBUILD_MODNAME, reg, len);
+		return -EINVAL;
+	}
+
 	ret = i2c_transfer(priv->i2c, msg, 2);
 	if (ret == 2) {
 		memcpy(val, &buf[reg], len);
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 878d2c4d9e8e..9771cd83c06e 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -24,6 +24,9 @@
 #include <linux/dvb/frontend.h>
 #include "dvb_frontend.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  80
+
 /* Registers (Write-only) */
 #define XREG_INIT         0x00
 #define XREG_RF_FREQ      0x02
@@ -547,7 +550,10 @@ static int load_firmware(struct dvb_frontend *fe, unsigned int type,
 {
 	struct xc2028_data *priv = fe->tuner_priv;
 	int                pos, rc;
-	unsigned char      *p, *endp, buf[priv->ctrl.max_len];
+	unsigned char      *p, *endp, buf[MAX_XFER_SIZE];
+
+	if (priv->ctrl.max_len > sizeof(buf))
+		priv->ctrl.max_len = sizeof(buf);
 
 	tuner_dbg("%s called\n", __func__);
 
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 2018befabb5a..e71decbfd0af 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -93,7 +93,7 @@ struct xc4000_priv {
 	struct firmware_description *firm;
 	int	firm_size;
 	u32	if_khz;
-	u32	freq_hz;
+	u32	freq_hz, freq_offset;
 	u32	bandwidth;
 	u8	video_standard;
 	u8	rf_mode;
@@ -1157,14 +1157,14 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 	case SYS_ATSC:
 		dprintk(1, "%s() VSB modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_AIR;
-		priv->freq_hz = c->frequency - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = XC4000_DTV6;
 		type = DTV6;
 		break;
 	case SYS_DVBC_ANNEX_B:
 		dprintk(1, "%s() QAM modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_CABLE;
-		priv->freq_hz = c->frequency - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = XC4000_DTV6;
 		type = DTV6;
 		break;
@@ -1173,23 +1173,23 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 		dprintk(1, "%s() OFDM\n", __func__);
 		if (bw == 0) {
 			if (c->frequency < 400000000) {
-				priv->freq_hz = c->frequency - 2250000;
+				priv->freq_offset = 2250000;
 			} else {
-				priv->freq_hz = c->frequency - 2750000;
+				priv->freq_offset = 2750000;
 			}
 			priv->video_standard = XC4000_DTV7_8;
 			type = DTV78;
 		} else if (bw <= 6000000) {
 			priv->video_standard = XC4000_DTV6;
-			priv->freq_hz = c->frequency - 1750000;
+			priv->freq_offset = 1750000;
 			type = DTV6;
 		} else if (bw <= 7000000) {
 			priv->video_standard = XC4000_DTV7;
-			priv->freq_hz = c->frequency - 2250000;
+			priv->freq_offset = 2250000;
 			type = DTV7;
 		} else {
 			priv->video_standard = XC4000_DTV8;
-			priv->freq_hz = c->frequency - 2750000;
+			priv->freq_offset = 2750000;
 			type = DTV8;
 		}
 		priv->rf_mode = XC_RF_MODE_AIR;
@@ -1200,6 +1200,8 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 		goto fail;
 	}
 
+	priv->freq_hz = c->frequency - priv->freq_offset;
+
 	dprintk(1, "%s() frequency=%d (compensated)\n",
 		__func__, priv->freq_hz);
 
@@ -1520,7 +1522,7 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq)
 {
 	struct xc4000_priv *priv = fe->tuner_priv;
 
-	*freq = priv->freq_hz;
+	*freq = priv->freq_hz + priv->freq_offset;
 
 	if (debug) {
 		mutex_lock(&priv->lock);
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 5cd09a681b6a..b2d9e9cb97f7 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -55,7 +55,7 @@ struct xc5000_priv {
 
 	u32 if_khz;
 	u16 xtal_khz;
-	u32 freq_hz;
+	u32 freq_hz, freq_offset;
 	u32 bandwidth;
 	u8  video_standard;
 	u8  rf_mode;
@@ -755,13 +755,13 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 	case SYS_ATSC:
 		dprintk(1, "%s() VSB modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_AIR;
-		priv->freq_hz = freq - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = DTV6;
 		break;
 	case SYS_DVBC_ANNEX_B:
 		dprintk(1, "%s() QAM modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_CABLE;
-		priv->freq_hz = freq - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = DTV6;
 		break;
 	case SYS_ISDBT:
@@ -776,15 +776,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		switch (bw) {
 		case 6000000:
 			priv->video_standard = DTV6;
-			priv->freq_hz = freq - 1750000;
+			priv->freq_offset = 1750000;
 			break;
 		case 7000000:
 			priv->video_standard = DTV7;
-			priv->freq_hz = freq - 2250000;
+			priv->freq_offset = 2250000;
 			break;
 		case 8000000:
 			priv->video_standard = DTV8;
-			priv->freq_hz = freq - 2750000;
+			priv->freq_offset = 2750000;
 			break;
 		default:
 			printk(KERN_ERR "xc5000 bandwidth not set!\n");
@@ -798,15 +798,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		priv->rf_mode = XC_RF_MODE_CABLE;
 		if (bw <= 6000000) {
 			priv->video_standard = DTV6;
-			priv->freq_hz = freq - 1750000;
+			priv->freq_offset = 1750000;
 			b = 6;
 		} else if (bw <= 7000000) {
 			priv->video_standard = DTV7;
-			priv->freq_hz = freq - 2250000;
+			priv->freq_offset = 2250000;
 			b = 7;
 		} else {
 			priv->video_standard = DTV7_8;
-			priv->freq_hz = freq - 2750000;
+			priv->freq_offset = 2750000;
 			b = 8;
 		}
 		dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__,
@@ -817,6 +817,8 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		return -EINVAL;
 	}
 
+	priv->freq_hz = freq - priv->freq_offset;
+
 	dprintk(1, "%s() frequency=%d (compensated to %d)\n",
 		__func__, freq, priv->freq_hz);
 
@@ -1067,7 +1069,7 @@ static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
 	dprintk(1, "%s()\n", __func__);
-	*freq = priv->freq_hz;
+	*freq = priv->freq_hz + priv->freq_offset;
 	return 0;
 }
 
diff --git a/drivers/media/usb/Kconfig b/drivers/media/usb/Kconfig
index 0a7d520636a9..7cac453e34c7 100644
--- a/drivers/media/usb/Kconfig
+++ b/drivers/media/usb/Kconfig
@@ -1,6 +1,7 @@
+if USB && MEDIA_SUPPORT
+
 menuconfig MEDIA_USB_SUPPORT
 	bool "Media USB Adapters"
-	depends on USB && MEDIA_SUPPORT
 	help
 	  Enable media drivers for USB bus.
 	  If you have such devices, say Y.
@@ -52,3 +53,4 @@ source "drivers/media/usb/em28xx/Kconfig"
 endif
 
 endif #MEDIA_USB_SUPPORT
+endif #USB
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 75ac9947cdac..98e1b937b500 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -788,11 +788,27 @@ static int au0828_i2s_init(struct au0828_dev *dev)
 
 /*
  * Auvitek au0828 analog stream enable
- * Please set interface0 to AS5 before enable the stream
  */
 static int au0828_analog_stream_enable(struct au0828_dev *d)
 {
+	struct usb_interface *iface;
+	int ret;
+
 	dprintk(1, "au0828_analog_stream_enable called\n");
+
+	iface = usb_ifnum_to_if(d->usbdev, 0);
+	if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) {
+		dprintk(1, "Changing intf#0 to alt 5\n");
+		/* set au0828 interface0 to AS5 here again */
+		ret = usb_set_interface(d->usbdev, 0, 5);
+		if (ret < 0) {
+			printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
+			return -EBUSY;
+		}
+	}
+
+	/* FIXME: size should be calculated using d->width, d->height */
+
 	au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00);
 	au0828_writereg(d, 0x106, 0x00);
 	/* set x position */
@@ -1003,15 +1019,6 @@ static int au0828_v4l2_open(struct file *filp)
 		return -ERESTARTSYS;
 	}
 	if (dev->users == 0) {
-		/* set au0828 interface0 to AS5 here again */
-		ret = usb_set_interface(dev->usbdev, 0, 5);
-		if (ret < 0) {
-			mutex_unlock(&dev->lock);
-			printk(KERN_INFO "Au0828 can't set alternate to 5!\n");
-			kfree(fh);
-			return -EBUSY;
-		}
-
 		au0828_analog_stream_enable(dev);
 		au0828_analog_stream_reset(dev);
 
@@ -1253,13 +1260,6 @@ static int au0828_set_format(struct au0828_dev *dev, unsigned int cmd,
 		}
 	}
 
-	/* set au0828 interface0 to AS5 here again */
-	ret = usb_set_interface(dev->usbdev, 0, 5);
-	if (ret < 0) {
-		printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
-		return -EBUSY;
-	}
-
 	au0828_analog_stream_enable(dev);
 
 	return 0;
diff --git a/drivers/media/usb/dvb-usb-v2/af9015.c b/drivers/media/usb/dvb-usb-v2/af9015.c
index d556042cf312..da47d2392f2a 100644
--- a/drivers/media/usb/dvb-usb-v2/af9015.c
+++ b/drivers/media/usb/dvb-usb-v2/af9015.c
@@ -397,12 +397,13 @@ error:
 	return ret;
 }
 
+#define AF9015_EEPROM_SIZE 256
+
 /* hash (and dump) eeprom */
 static int af9015_eeprom_hash(struct dvb_usb_device *d)
 {
 	struct af9015_state *state = d_to_priv(d);
 	int ret, i;
-	static const unsigned int AF9015_EEPROM_SIZE = 256;
 	u8 buf[AF9015_EEPROM_SIZE];
 	struct req_t req = {READ_I2C, AF9015_I2C_EEPROM, 0, 0, 1, 1, NULL};
 
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index b638fc1cd574..2e93ba5598c4 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -21,6 +21,9 @@
 
 #include "af9035.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 static u16 af9035_checksum(const u8 *buf, size_t len)
@@ -125,9 +128,15 @@ exit:
 /* write multiple registers */
 static int af9035_wr_regs(struct dvb_usb_device *d, u32 reg, u8 *val, int len)
 {
-	u8 wbuf[6 + len];
+	u8 wbuf[MAX_XFER_SIZE];
 	u8 mbox = (reg >> 16) & 0xff;
-	struct usb_req req = { CMD_MEM_WR, mbox, sizeof(wbuf), wbuf, 0, NULL };
+	struct usb_req req = { CMD_MEM_WR, mbox, 6 + len, wbuf, 0, NULL };
+
+	if (6 + len > sizeof(wbuf)) {
+		dev_warn(&d->udev->dev, "%s: i2c wr: len=%d is too big!\n",
+			 KBUILD_MODNAME, len);
+		return -EOPNOTSUPP;
+	}
 
 	wbuf[0] = len;
 	wbuf[1] = 2;
@@ -227,9 +236,17 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 					msg[1].len);
 		} else {
 			/* I2C */
-			u8 buf[5 + msg[0].len];
-			struct usb_req req = { CMD_I2C_RD, 0, sizeof(buf),
+			u8 buf[MAX_XFER_SIZE];
+			struct usb_req req = { CMD_I2C_RD, 0, 5 + msg[0].len,
 					buf, msg[1].len, msg[1].buf };
+
+			if (5 + msg[0].len > sizeof(buf)) {
+				dev_warn(&d->udev->dev,
+					 "%s: i2c xfer: len=%d is too big!\n",
+					 KBUILD_MODNAME, msg[0].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			req.mbox |= ((msg[0].addr & 0x80)  >>  3);
 			buf[0] = msg[1].len;
 			buf[1] = msg[0].addr << 1;
@@ -256,9 +273,17 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 					msg[0].len - 3);
 		} else {
 			/* I2C */
-			u8 buf[5 + msg[0].len];
-			struct usb_req req = { CMD_I2C_WR, 0, sizeof(buf), buf,
-					0, NULL };
+			u8 buf[MAX_XFER_SIZE];
+			struct usb_req req = { CMD_I2C_WR, 0, 5 + msg[0].len,
+					buf, 0, NULL };
+
+			if (5 + msg[0].len > sizeof(buf)) {
+				dev_warn(&d->udev->dev,
+					 "%s: i2c xfer: len=%d is too big!\n",
+					 KBUILD_MODNAME, msg[0].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			req.mbox |= ((msg[0].addr & 0x80)  >>  3);
 			buf[0] = msg[0].len;
 			buf[1] = msg[0].addr << 1;
@@ -277,6 +302,7 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 		ret = -EOPNOTSUPP;
 	}
 
+unlock:
 	mutex_unlock(&d->i2c_mutex);
 
 	if (ret < 0)
@@ -1489,6 +1515,10 @@ static const struct usb_device_id af9035_id_table[] = {
 	/* XXX: that same ID [0ccd:0099] is used by af9015 driver too */
 	{ DVB_USB_DEVICE(USB_VID_TERRATEC, 0x0099,
 		&af9035_props, "TerraTec Cinergy T Stick Dual RC (rev. 2)", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_LEADTEK, 0x6a05,
+		&af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900,
+		&af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index 90cfa35ef6e6..eeab79bdd2aa 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -442,6 +442,7 @@ static struct cxd2820r_config anysee_cxd2820r_config = {
  * IOD[0] ZL10353 1=enabled
  * IOE[0] tuner 0=enabled
  * tuner is behind ZL10353 I2C-gate
+ * tuner is behind TDA10023 I2C-gate
  *
  * E7 TC VID=1c73 PID=861f HW=18 FW=0.7 AMTCI=0.5 "anysee-E7TC(LP)"
  * PCB: 508TC (rev0.6)
@@ -956,7 +957,7 @@ static int anysee_tuner_attach(struct dvb_usb_adapter *adap)
 
 		if (fe && adap->fe[1]) {
 			/* attach tuner for 2nd FE */
-			fe = dvb_attach(dvb_pll_attach, adap->fe[0],
+			fe = dvb_attach(dvb_pll_attach, adap->fe[1],
 					(0xc0 >> 1), &d->i2c_adap,
 					DVB_PLL_SAMSUNG_DTOS403IH102A);
 		}
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
index 90f583e5d6a6..a8f65d88c9e7 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
@@ -68,7 +68,7 @@ struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
 #else
 static inline
 struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
-					   struct mxl111sf_state *mxl_state
+					   struct mxl111sf_state *mxl_state,
 					   struct mxl111sf_tuner_config *cfg)
 {
 	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index efdcb15358f1..419a7c7ed059 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -23,6 +23,9 @@
 #include "lgdt3305.h"
 #include "lg2160.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 int dvb_usb_mxl111sf_debug;
 module_param_named(debug, dvb_usb_mxl111sf_debug, int, 0644);
 MODULE_PARM_DESC(debug, "set debugging level "
@@ -63,7 +66,12 @@ int mxl111sf_ctrl_msg(struct dvb_usb_device *d,
 {
 	int wo = (rbuf == NULL || rlen == 0); /* write-only */
 	int ret;
-	u8 sndbuf[1+wlen];
+	u8 sndbuf[MAX_XFER_SIZE];
+
+	if (1 + wlen > sizeof(sndbuf)) {
+		pr_warn("%s: len=%d is too big!\n", __func__, wlen);
+		return -EOPNOTSUPP;
+	}
 
 	deb_adv("%s(wlen = %d, rlen = %d)\n", __func__, wlen, rlen);
 
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 3940bb0f9ef6..a1c641e18362 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -43,6 +43,9 @@
 #include "lgs8gxx.h"
 #include "atbm8830.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 /* debug */
 static int dvb_usb_cxusb_debug;
 module_param_named(debug, dvb_usb_cxusb_debug, int, 0644);
@@ -57,7 +60,14 @@ static int cxusb_ctrl_msg(struct dvb_usb_device *d,
 			  u8 cmd, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
 {
 	int wo = (rbuf == NULL || rlen == 0); /* write-only */
-	u8 sndbuf[1+wlen];
+	u8 sndbuf[MAX_XFER_SIZE];
+
+	if (1 + wlen > sizeof(sndbuf)) {
+		warn("i2c wr: len=%d is too big!\n",
+		     wlen);
+		return -EOPNOTSUPP;
+	}
+
 	memset(sndbuf, 0, 1+wlen);
 
 	sndbuf[0] = cmd;
@@ -139,6 +149,7 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 			  int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int ret;
 	int i;
 
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
@@ -158,7 +169,14 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 
 		if (msg[i].flags & I2C_M_RD) {
 			/* read only */
-			u8 obuf[3], ibuf[1+msg[i].len];
+			u8 obuf[3], ibuf[MAX_XFER_SIZE];
+
+			if (1 + msg[i].len > sizeof(ibuf)) {
+				warn("i2c rd: len=%d is too big!\n",
+				     msg[i].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			obuf[0] = 0;
 			obuf[1] = msg[i].len;
 			obuf[2] = msg[i].addr;
@@ -172,7 +190,20 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		} else if (i+1 < num && (msg[i+1].flags & I2C_M_RD) &&
 			   msg[i].addr == msg[i+1].addr) {
 			/* write to then read from same address */
-			u8 obuf[3+msg[i].len], ibuf[1+msg[i+1].len];
+			u8 obuf[MAX_XFER_SIZE], ibuf[MAX_XFER_SIZE];
+
+			if (3 + msg[i].len > sizeof(obuf)) {
+				warn("i2c wr: len=%d is too big!\n",
+				     msg[i].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
+			if (1 + msg[i + 1].len > sizeof(ibuf)) {
+				warn("i2c rd: len=%d is too big!\n",
+				     msg[i + 1].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			obuf[0] = msg[i].len;
 			obuf[1] = msg[i+1].len;
 			obuf[2] = msg[i].addr;
@@ -191,7 +222,14 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 			i++;
 		} else {
 			/* write only */
-			u8 obuf[2+msg[i].len], ibuf;
+			u8 obuf[MAX_XFER_SIZE], ibuf;
+
+			if (2 + msg[i].len > sizeof(obuf)) {
+				warn("i2c wr: len=%d is too big!\n",
+				     msg[i].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			obuf[0] = msg[i].addr;
 			obuf[1] = msg[i].len;
 			memcpy(&obuf[2], msg[i].buf, msg[i].len);
@@ -204,8 +242,14 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		}
 	}
 
+	if (i == num)
+		ret = num;
+	else
+		ret = -EREMOTEIO;
+
+unlock:
 	mutex_unlock(&d->i2c_mutex);
-	return i == num ? num : -EREMOTEIO;
+	return ret;
 }
 
 static u32 cxusb_i2c_func(struct i2c_adapter *adapter)
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index c2dded92f1d3..6d68af0c49c8 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -12,6 +12,9 @@
 #include <linux/kconfig.h>
 #include "dibusb.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 static int debug;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "set debugging level (1=info (|-able))." DVB_USB_DEBUG_STATUS);
@@ -105,11 +108,16 @@ EXPORT_SYMBOL(dibusb2_0_power_ctrl);
 static int dibusb_i2c_msg(struct dvb_usb_device *d, u8 addr,
 			  u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
 {
-	u8 sndbuf[wlen+4]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
+	u8 sndbuf[MAX_XFER_SIZE]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
 	/* write only ? */
 	int wo = (rbuf == NULL || rlen == 0),
 		len = 2 + wlen + (wo ? 0 : 2);
 
+	if (4 + wlen > sizeof(sndbuf)) {
+		warn("i2c wr: len=%d is too big!\n", wlen);
+		return -EOPNOTSUPP;
+	}
+
 	sndbuf[0] = wo ? DIBUSB_REQ_I2C_WRITE : DIBUSB_REQ_I2C_READ;
 	sndbuf[1] = (addr << 1) | (wo ? 0 : 1);
 
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 6e237b6dd0a8..4170a45d17e0 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -30,6 +30,9 @@
 #include "stb6100_proc.h"
 #include "m88rs2000.h"
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 #ifndef USB_PID_DW2102
 #define USB_PID_DW2102 0x2102
 #endif
@@ -298,6 +301,7 @@ static int dw2102_serit_i2c_transfer(struct i2c_adapter *adap,
 static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int ret;
 
 	if (!d)
 		return -ENODEV;
@@ -308,7 +312,15 @@ static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg ms
 	case 2: {
 		/* read */
 		/* first write first register number */
-		u8 ibuf[msg[1].len + 2], obuf[3];
+		u8 ibuf[MAX_XFER_SIZE], obuf[3];
+
+		if (2 + msg[1].len > sizeof(ibuf)) {
+			warn("i2c rd: len=%d is too big!\n",
+			     msg[1].len);
+			ret = -EOPNOTSUPP;
+			goto unlock;
+		}
+
 		obuf[0] = msg[0].addr << 1;
 		obuf[1] = msg[0].len;
 		obuf[2] = msg[0].buf[0];
@@ -325,7 +337,15 @@ static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg ms
 		switch (msg[0].addr) {
 		case 0x68: {
 			/* write to register */
-			u8 obuf[msg[0].len + 2];
+			u8 obuf[MAX_XFER_SIZE];
+
+			if (2 + msg[0].len > sizeof(obuf)) {
+				warn("i2c wr: len=%d is too big!\n",
+				     msg[1].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
+
 			obuf[0] = msg[0].addr << 1;
 			obuf[1] = msg[0].len;
 			memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -335,7 +355,15 @@ static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg ms
 		}
 		case 0x61: {
 			/* write to tuner */
-			u8 obuf[msg[0].len + 2];
+			u8 obuf[MAX_XFER_SIZE];
+
+			if (2 + msg[0].len > sizeof(obuf)) {
+				warn("i2c wr: len=%d is too big!\n",
+				     msg[1].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
+
 			obuf[0] = msg[0].addr << 1;
 			obuf[1] = msg[0].len;
 			memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -362,15 +390,17 @@ static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg ms
 
 		break;
 	}
+	ret = num;
 
+unlock:
 	mutex_unlock(&d->i2c_mutex);
-	return num;
+	return ret;
 }
 
 static int dw2104_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
-	int len, i, j;
+	int len, i, j, ret;
 
 	if (!d)
 		return -ENODEV;
@@ -401,7 +431,15 @@ static int dw2104_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], i
 		default: {
 			if (msg[j].flags == I2C_M_RD) {
 				/* read registers */
-				u8  ibuf[msg[j].len + 2];
+				u8  ibuf[MAX_XFER_SIZE];
+
+				if (2 + msg[j].len > sizeof(ibuf)) {
+					warn("i2c rd: len=%d is too big!\n",
+					     msg[j].len);
+					ret = -EOPNOTSUPP;
+					goto unlock;
+				}
+
 				dw210x_op_rw(d->udev, 0xc3,
 						(msg[j].addr << 1) + 1, 0,
 						ibuf, msg[j].len + 2,
@@ -430,7 +468,15 @@ static int dw2104_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], i
 				} while (len > 0);
 			} else {
 				/* write registers */
-				u8 obuf[msg[j].len + 2];
+				u8 obuf[MAX_XFER_SIZE];
+
+				if (2 + msg[j].len > sizeof(obuf)) {
+					warn("i2c wr: len=%d is too big!\n",
+					     msg[j].len);
+					ret = -EOPNOTSUPP;
+					goto unlock;
+				}
+
 				obuf[0] = msg[j].addr << 1;
 				obuf[1] = msg[j].len;
 				memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -443,15 +489,18 @@ static int dw2104_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], i
 		}
 
 	}
+	ret = num;
 
+unlock:
 	mutex_unlock(&d->i2c_mutex);
-	return num;
+	return ret;
 }
 
 static int dw3101_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 								int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int ret;
 	int i;
 
 	if (!d)
@@ -463,7 +512,14 @@ static int dw3101_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 	case 2: {
 		/* read */
 		/* first write first register number */
-		u8 ibuf[msg[1].len + 2], obuf[3];
+		u8 ibuf[MAX_XFER_SIZE], obuf[3];
+
+		if (2 + msg[1].len > sizeof(ibuf)) {
+			warn("i2c rd: len=%d is too big!\n",
+			     msg[1].len);
+			ret = -EOPNOTSUPP;
+			goto unlock;
+		}
 		obuf[0] = msg[0].addr << 1;
 		obuf[1] = msg[0].len;
 		obuf[2] = msg[0].buf[0];
@@ -481,7 +537,14 @@ static int dw3101_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		case 0x60:
 		case 0x0c: {
 			/* write to register */
-			u8 obuf[msg[0].len + 2];
+			u8 obuf[MAX_XFER_SIZE];
+
+			if (2 + msg[0].len > sizeof(obuf)) {
+				warn("i2c wr: len=%d is too big!\n",
+				     msg[0].len);
+				ret = -EOPNOTSUPP;
+				goto unlock;
+			}
 			obuf[0] = msg[0].addr << 1;
 			obuf[1] = msg[0].len;
 			memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -506,9 +569,11 @@ static int dw3101_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 				msg[i].flags == 0 ? ">>>" : "<<<");
 		debug_dump(msg[i].buf, msg[i].len, deb_xfer);
 	}
+	ret = num;
 
+unlock:
 	mutex_unlock(&d->i2c_mutex);
-	return num;
+	return ret;
 }
 
 static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
@@ -516,7 +581,7 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
 	struct usb_device *udev;
-	int len, i, j;
+	int len, i, j, ret;
 
 	if (!d)
 		return -ENODEV;
@@ -563,7 +628,15 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		default: {
 			if (msg[j].flags == I2C_M_RD) {
 				/* read registers */
-				u8 ibuf[msg[j].len];
+				u8 ibuf[MAX_XFER_SIZE];
+
+				if (msg[j].len > sizeof(ibuf)) {
+					warn("i2c rd: len=%d is too big!\n",
+					     msg[j].len);
+					ret = -EOPNOTSUPP;
+					goto unlock;
+				}
+
 				dw210x_op_rw(d->udev, 0x91, 0, 0,
 						ibuf, msg[j].len,
 						DW210X_READ_MSG);
@@ -590,7 +663,15 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 				} while (len > 0);
 			} else if (j < (num - 1)) {
 				/* write register addr before read */
-				u8 obuf[msg[j].len + 2];
+				u8 obuf[MAX_XFER_SIZE];
+
+				if (2 + msg[j].len > sizeof(obuf)) {
+					warn("i2c wr: len=%d is too big!\n",
+					     msg[j].len);
+					ret = -EOPNOTSUPP;
+					goto unlock;
+				}
+
 				obuf[0] = msg[j + 1].len;
 				obuf[1] = (msg[j].addr << 1);
 				memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -602,7 +683,14 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 				break;
 			} else {
 				/* write registers */
-				u8 obuf[msg[j].len + 2];
+				u8 obuf[MAX_XFER_SIZE];
+
+				if (2 + msg[j].len > sizeof(obuf)) {
+					warn("i2c wr: len=%d is too big!\n",
+					     msg[j].len);
+					ret = -EOPNOTSUPP;
+					goto unlock;
+				}
 				obuf[0] = msg[j].len + 1;
 				obuf[1] = (msg[j].addr << 1);
 				memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -615,9 +703,11 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		}
 		}
 	}
+	ret = num;
 
+unlock:
 	mutex_unlock(&d->i2c_mutex);
-	return num;
+	return ret;
 }
 
 static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index b22f8fed8127..c4d669648dc7 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -673,7 +673,8 @@ static void pctv_520e_init(struct em28xx *dev)
 static int em28xx_pctv_290e_set_lna(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	struct em28xx *dev = fe->dvb->priv;
+	struct em28xx_i2c_bus *i2c_bus = fe->dvb->priv;
+	struct em28xx *dev = i2c_bus->dev;
 #ifdef CONFIG_GPIOLIB
 	struct em28xx_dvb *dvb = dev->dvb;
 	int ret;
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 32d60e5546bc..a2737b4b090b 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -696,13 +696,16 @@ static int em28xx_stop_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vid_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vid_buf = NULL;
+	}
 	while (!list_empty(&vidq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vidq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vid_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 
 	return 0;
@@ -724,13 +727,16 @@ int em28xx_stop_vbi_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vbi_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vbi_buf = NULL;
+	}
 	while (!list_empty(&vbiq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vbiq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vbi_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 
 	return 0;
diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c
index 6008c8d546a3..20d9c15a305d 100644
--- a/drivers/media/usb/gspca/pac7302.c
+++ b/drivers/media/usb/gspca/pac7302.c
@@ -945,6 +945,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x093a, 0x2620)},
 	{USB_DEVICE(0x093a, 0x2621)},
 	{USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP},
+	{USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2625)},
 	{USB_DEVICE(0x093a, 0x2626)},
diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c
index ead9a1f58513..8b59e5d37bae 100644
--- a/drivers/media/usb/gspca/sn9c20x.c
+++ b/drivers/media/usb/gspca/sn9c20x.c
@@ -2394,6 +2394,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)},
 	{USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)},
 	{USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)},
+	{USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)},
 	{USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)},
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 774ba0e820be..eed70a4d24e6 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -81,7 +81,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb)
 }
 
 /*=========================================================================*/
-/* bufffer bits */
+/* buffer bits */
 
 /* function expects dev->io_mutex to be hold by caller */
 int hdpvr_cancel_queue(struct hdpvr_device *dev)
@@ -921,7 +921,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_AUDIO_ENCODING:
 		if (dev->flags & HDPVR_FLAG_AC3_CAP) {
 			opt->audio_codec = ctrl->val;
-			return hdpvr_set_audio(dev, opt->audio_input,
+			return hdpvr_set_audio(dev, opt->audio_input + 1,
 					      opt->audio_codec);
 		}
 		return 0;
@@ -1191,7 +1191,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent,
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_AUDIO_ENCODING,
 		ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC,
-		0x7, V4L2_MPEG_AUDIO_ENCODING_AAC);
+		0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC);
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_ENCODING,
 		V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3,
diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c
index 34a26e0cfe77..03504dcf3c52 100644
--- a/drivers/media/usb/stk1160/stk1160-core.c
+++ b/drivers/media/usb/stk1160/stk1160-core.c
@@ -67,17 +67,25 @@ int stk1160_read_reg(struct stk1160 *dev, u16 reg, u8 *value)
 {
 	int ret;
 	int pipe = usb_rcvctrlpipe(dev->udev, 0);
+	u8 *buf;
 
 	*value = 0;
+
+	buf = kmalloc(sizeof(u8), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 	ret = usb_control_msg(dev->udev, pipe, 0x00,
 			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			0x00, reg, value, sizeof(u8), HZ);
+			0x00, reg, buf, sizeof(u8), HZ);
 	if (ret < 0) {
 		stk1160_err("read failed on reg 0x%x (%d)\n",
 			reg, ret);
+		kfree(buf);
 		return ret;
 	}
 
+	*value = *buf;
+	kfree(buf);
 	return 0;
 }
 
diff --git a/drivers/media/usb/stk1160/stk1160.h b/drivers/media/usb/stk1160/stk1160.h
index 05b05b160e1e..abdea484c998 100644
--- a/drivers/media/usb/stk1160/stk1160.h
+++ b/drivers/media/usb/stk1160/stk1160.h
@@ -143,7 +143,6 @@ struct stk1160 {
 	int num_alt;
 
 	struct stk1160_isoc_ctl isoc_ctl;
-	char urb_buf[255];	 /* urb control msg buffer */
 
 	/* frame properties */
 	int width;		  /* current frame width */
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 5c45c9d0712d..9c29552aedec 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc
 		   0x00, 0x00, 0x00, 0x00,
 		   0x00, 0x00 };
 
+	if (cmd->msg_len > sizeof(b) - 4)
+		return -EINVAL;
+
 	memcpy(&b[4], cmd->msg, cmd->msg_len);
 
 	state->config->send_command(fe, 0x72,
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 3394c3432011..c081812ac5c0 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -361,6 +361,14 @@ static int uvc_commit_video(struct uvc_streaming *stream,
  * Clocks and timestamps
  */
 
+static inline void uvc_video_get_ts(struct timespec *ts)
+{
+	if (uvc_clock_param == CLOCK_MONOTONIC)
+		ktime_get_ts(ts);
+	else
+		ktime_get_real_ts(ts);
+}
+
 static void
 uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 		       const __u8 *data, int len)
@@ -420,7 +428,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 	stream->clock.last_sof = dev_sof;
 
 	host_sof = usb_get_current_frame_number(stream->dev->udev);
-	ktime_get_ts(&ts);
+	uvc_video_get_ts(&ts);
 
 	/* The UVC specification allows device implementations that can't obtain
 	 * the USB frame number to keep their own frame counters as long as they
@@ -1010,10 +1018,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 			return -ENODATA;
 		}
 
-		if (uvc_clock_param == CLOCK_MONOTONIC)
-			ktime_get_ts(&ts);
-		else
-			ktime_get_real_ts(&ts);
+		uvc_video_get_ts(&ts);
 
 		buf->buf.v4l2_buf.sequence = stream->sequence;
 		buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
@@ -1846,7 +1851,25 @@ int uvc_video_enable(struct uvc_streaming *stream, int enable)
 
 	if (!enable) {
 		uvc_uninit_video(stream, 1);
-		usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+		if (stream->intf->num_altsetting > 1) {
+			usb_set_interface(stream->dev->udev,
+					  stream->intfnum, 0);
+		} else {
+			/* UVC doesn't specify how to inform a bulk-based device
+			 * when the video stream is stopped. Windows sends a
+			 * CLEAR_FEATURE(HALT) request to the video streaming
+			 * bulk endpoint, mimic the same behaviour.
+			 */
+			unsigned int epnum = stream->header.bEndpointAddress
+					   & USB_ENDPOINT_NUMBER_MASK;
+			unsigned int dir = stream->header.bEndpointAddress
+					 & USB_ENDPOINT_DIR_MASK;
+			unsigned int pipe;
+
+			pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir;
+			usb_clear_halt(stream->dev->udev, pipe);
+		}
+
 		uvc_queue_enable(&stream->queue, 0);
 		uvc_video_clock_cleanup(stream);
 		return 0;
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 3fed63f4e026..ec9a4fa3bc86 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -485,16 +485,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min,
 	/* Bits that must be zero to be aligned */
 	unsigned int mask = ~((1 << align) - 1);
 
+	/* Clamp to aligned min and max */
+	x = clamp(x, (min + ~mask) & mask, max & mask);
+
 	/* Round to nearest aligned value */
 	if (align)
 		x = (x + (1 << (align - 1))) & mask;
 
-	/* Clamp to aligned value of min and max */
-	if (x < min)
-		x = (min + ~mask) & mask;
-	else if (x > max)
-		x = max & mask;
-
 	return x;
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index f1295519f285..e2b0a0969ebb 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -178,6 +178,9 @@ struct v4l2_create_buffers32 {
 
 static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
+	if (get_user(kp->type, &up->type))
+		return -EFAULT;
+
 	switch (kp->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
@@ -204,17 +207,16 @@ static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us
 
 static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)) ||
-			get_user(kp->type, &up->type))
-			return -EFAULT;
+	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)))
+		return -EFAULT;
 	return __get_v4l2_format32(kp, up);
 }
 
 static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) ||
-	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format.fmt)))
-			return -EFAULT;
+	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format)))
+		return -EFAULT;
 	return __get_v4l2_format32(&kp->format, &up->format);
 }
 
@@ -787,8 +789,8 @@ static int put_v4l2_subdev_edid32(struct v4l2_subdev_edid *kp, struct v4l2_subde
 #define VIDIOC_DQBUF32		_IOWR('V', 17, struct v4l2_buffer32)
 #define VIDIOC_ENUMSTD32	_IOWR('V', 25, struct v4l2_standard32)
 #define VIDIOC_ENUMINPUT32	_IOWR('V', 26, struct v4l2_input32)
-#define VIDIOC_SUBDEV_G_EDID32	_IOWR('V', 63, struct v4l2_subdev_edid32)
-#define VIDIOC_SUBDEV_S_EDID32	_IOWR('V', 64, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_G_EDID32	_IOWR('V', 40, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_S_EDID32	_IOWR('V', 41, struct v4l2_subdev_edid32)
 #define VIDIOC_TRY_FMT32      	_IOWR('V', 64, struct v4l2_format32)
 #define VIDIOC_G_EXT_CTRLS32    _IOWR('V', 71, struct v4l2_ext_controls32)
 #define VIDIOC_S_EXT_CTRLS32    _IOWR('V', 72, struct v4l2_ext_controls32)
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index e3bdc3be91e1..5e47ba479e53 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -666,6 +666,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	 * to the userspace.
 	 */
 	req->count = allocated_buffers;
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	return 0;
 }
@@ -714,6 +715,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = create->memory;
+		q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 	}
 
 	num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1355,6 +1357,7 @@ int vb2_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	 * dequeued in dqbuf.
 	 */
 	list_add_tail(&vb->queued_entry, &q->queued_list);
+	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 
 	/*
@@ -1724,6 +1727,7 @@ int vb2_streamoff(struct vb2_queue *q, enum v4l2_buf_type type)
 	 * and videobuf, effectively returning control over them to userspace.
 	 */
 	__vb2_queue_cancel(q);
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	dprintk(3, "Streamoff successful\n");
 	return 0;
@@ -2009,9 +2013,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait)
 	}
 
 	/*
-	 * There is nothing to wait for if no buffers have already been queued.
+	 * There is nothing to wait for if the queue isn't streaming.
 	 */
-	if (list_empty(&q->queued_list))
+	if (!vb2_is_streaming(q))
+		return res | POLLERR;
+	/*
+	 * For compatibility with vb1: if QBUF hasn't been called yet, then
+	 * return POLLERR as well. This only affects capture queues, output
+	 * queues will always initialize waiting_for_buffers to false.
+	 */
+	if (q->waiting_for_buffers)
 		return res | POLLERR;
 
 	if (list_empty(&q->done_list))
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 5653e505f91f..424f51d1e2ce 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_mptspi_probe;
         }
 
+	/* VMWare emulation doesn't properly implement WRITE_SAME
+	 */
+	if (pdev->subsystem_vendor == 0x15AD)
+		sh->no_write_same = 1;
+
 	spin_lock_irqsave(&ioc->FreeQlock, flags);
 
 	/* Attach the SCSI Host to the IOC structure
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index 31ca55548ef9..30cf7eef2a8f 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -1179,12 +1179,18 @@ static int pm860x_probe(struct i2c_client *client,
 		chip->companion_addr = pdata->companion_addr;
 		chip->companion = i2c_new_dummy(chip->client->adapter,
 						chip->companion_addr);
+		if (!chip->companion) {
+			dev_err(&client->dev,
+				"Failed to allocate I2C companion device\n");
+			return -ENODEV;
+		}
 		chip->regmap_companion = regmap_init_i2c(chip->companion,
 							&pm860x_regmap_config);
 		if (IS_ERR(chip->regmap_companion)) {
 			ret = PTR_ERR(chip->regmap_companion);
 			dev_err(&chip->companion->dev,
 				"Failed to allocate register map: %d\n", ret);
+			i2c_unregister_device(chip->companion);
 			return ret;
 		}
 		i2c_set_clientdata(chip->companion, chip);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d54e985748b7..a5e54f0d6a73 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1144,7 +1144,15 @@ config MCP_UCB1200_TS
 endmenu
 
 config VEXPRESS_CONFIG
-	bool
+	bool "ARM Versatile Express platform infrastructure"
+	depends on ARM || ARM64
 	help
 	  Platform configuration infrastructure for the ARM Ltd.
 	  Versatile Express.
+
+config VEXPRESS_SPC
+	bool "Versatile Express SPC driver support"
+	depends on ARM
+	depends on VEXPRESS_CONFIG
+	help
+	  Serial Power Controller driver for ARM Ltd. test chips.
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 718e94a2a9a7..3a0120315aa3 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -153,5 +153,6 @@ obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
 obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o vexpress-sysreg.o
+obj-$(CONFIG_VEXPRESS_SPC)	+= vexpress-spc.o
 obj-$(CONFIG_MFD_RETU)		+= retu-mfd.o
 obj-$(CONFIG_MFD_AS3711)	+= as3711.o
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 9f12f91d6296..4be5be34194f 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -51,6 +51,8 @@
  *	document number TBD : Lynx Point
  *	document number TBD : Lynx Point-LP
  *	document number TBD : Wellsburg
+ *	document number TBD : Avoton SoC
+ *	document number TBD : Coleto Creek
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -207,6 +209,8 @@ enum lpc_chipsets {
 	LPC_LPT,	/* Lynx Point */
 	LPC_LPT_LP,	/* Lynx Point-LP */
 	LPC_WBG,	/* Wellsburg */
+	LPC_AVN,	/* Avoton SoC */
+	LPC_COLETO,	/* Coleto Creek */
 };
 
 struct lpc_ich_info lpc_chipset_info[] = {
@@ -491,6 +495,14 @@ struct lpc_ich_info lpc_chipset_info[] = {
 		.name = "Wellsburg",
 		.iTCO_version = 2,
 	},
+	[LPC_AVN] = {
+		.name = "Avoton SoC",
+		.iTCO_version = 1,
+	},
+	[LPC_COLETO] = {
+		.name = "Coleto Creek",
+		.iTCO_version = 2,
+	},
 };
 
 /*
@@ -704,6 +716,11 @@ static DEFINE_PCI_DEVICE_TABLE(lpc_ich_ids) = {
 	{ PCI_VDEVICE(INTEL, 0x8d5d), LPC_WBG},
 	{ PCI_VDEVICE(INTEL, 0x8d5e), LPC_WBG},
 	{ PCI_VDEVICE(INTEL, 0x8d5f), LPC_WBG},
+	{ PCI_VDEVICE(INTEL, 0x1f38), LPC_AVN},
+	{ PCI_VDEVICE(INTEL, 0x1f39), LPC_AVN},
+	{ PCI_VDEVICE(INTEL, 0x1f3a), LPC_AVN},
+	{ PCI_VDEVICE(INTEL, 0x1f3b), LPC_AVN},
+	{ PCI_VDEVICE(INTEL, 0x2390), LPC_COLETO},
 	{ 0, },			/* End of list */
 };
 MODULE_DEVICE_TABLE(pci, lpc_ich_ids);
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index 1cbb17609c8b..1b6f45a14109 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -102,7 +102,7 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 	max77686->irq_gpio = pdata->irq_gpio;
 	max77686->irq = i2c->irq;
 
-	max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config);
+	max77686->regmap = devm_regmap_init_i2c(i2c, &max77686_regmap_config);
 	if (IS_ERR(max77686->regmap)) {
 		ret = PTR_ERR(max77686->regmap);
 		dev_err(max77686->dev, "Failed to allocate register map: %d\n",
@@ -121,6 +121,10 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 		dev_info(max77686->dev, "device found\n");
 
 	max77686->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max77686->rtc) {
+		dev_err(max77686->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max77686->rtc, max77686);
 
 	max77686_irq_init(max77686);
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index 9e60fed5ff82..299970f99588 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -149,9 +149,18 @@ static int max77693_i2c_probe(struct i2c_client *i2c,
 		dev_info(max77693->dev, "device ID: 0x%x\n", reg_data);
 
 	max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max77693->muic) {
+		dev_err(max77693->dev, "Failed to allocate I2C device for MUIC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max77693->muic, max77693);
 
 	max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max77693->haptic) {
+		dev_err(max77693->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max77693->haptic, max77693);
 
 	/*
@@ -187,8 +196,9 @@ err_mfd:
 	max77693_irq_exit(max77693);
 err_irq:
 err_regmap_muic:
-	i2c_unregister_device(max77693->muic);
 	i2c_unregister_device(max77693->haptic);
+err_i2c_haptic:
+	i2c_unregister_device(max77693->muic);
 	return ret;
 }
 
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 92bbebd31598..c94d3337bdfd 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -180,9 +180,18 @@ static int max8925_probe(struct i2c_client *client,
 	mutex_init(&chip->io_lock);
 
 	chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR);
+	if (!chip->rtc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->rtc, chip);
 
 	chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR);
+	if (!chip->adc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for ADC\n");
+		i2c_unregister_device(chip->rtc);
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->adc, chip);
 
 	device_init_wakeup(&client->dev, 1);
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index 14714058f2d2..ea1defbcf2cb 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -218,10 +218,26 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8997->iolock);
 
 	max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max8997->rtc) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8997->rtc, max8997);
+
 	max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max8997->haptic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max8997->haptic, max8997);
+
 	max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max8997->muic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n");
+		ret = -ENODEV;
+		goto err_i2c_muic;
+	}
 	i2c_set_clientdata(max8997->muic, max8997);
 
 	pm_runtime_set_active(max8997->dev);
@@ -248,7 +264,9 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 err_mfd:
 	mfd_remove_devices(max8997->dev);
 	i2c_unregister_device(max8997->muic);
+err_i2c_muic:
 	i2c_unregister_device(max8997->haptic);
+err_i2c_haptic:
 	i2c_unregister_device(max8997->rtc);
 err:
 	kfree(max8997);
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index d7218cc90945..8381a76c69c0 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -152,6 +152,10 @@ static int max8998_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8998->iolock);
 
 	max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!max8998->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8998->rtc, max8998);
 
 	max8998_irq_init(max8998);
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 759fae3ca7fb..a36f3f282ae7 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -445,7 +445,7 @@ static unsigned omap_usbhs_rev1_hostconfig(struct usbhs_hcd_omap *omap,
 
 		for (i = 0; i < omap->nports; i++) {
 			if (is_ehci_phy_mode(pdata->port_mode[i])) {
-				reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
+				reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
 				break;
 			}
 		}
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index e968c01ca2ac..7e28bd0de554 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1137,7 +1137,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->msi_en = msi_en;
 	if (pcr->msi_en) {
 		ret = pci_enable_msi(pcidev);
-		if (ret < 0)
+		if (ret)
 			pcr->msi_en = false;
 	}
 
@@ -1195,8 +1195,14 @@ static void rtsx_pci_remove(struct pci_dev *pcidev)
 
 	pcr->remove_pci = true;
 
-	cancel_delayed_work(&pcr->carddet_work);
-	cancel_delayed_work(&pcr->idle_work);
+	/* Disable interrupts at the pcr level */
+	spin_lock_irq(&pcr->lock);
+	rtsx_pci_writel(pcr, RTSX_BIER, 0);
+	pcr->bier = 0;
+	spin_unlock_irq(&pcr->lock);
+
+	cancel_delayed_work_sync(&pcr->carddet_work);
+	cancel_delayed_work_sync(&pcr->idle_work);
 
 	mfd_remove_devices(&pcidev->dev);
 
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 77ee26ef5941..81cfe8817fe0 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -199,6 +199,10 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 	}
 
 	sec_pmic->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!sec_pmic->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(sec_pmic->rtc, sec_pmic);
 
 	if (pdata && pdata->cfg_pmic_irq)
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 15e1463e5e13..17fe83e81ea4 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
 	return 0;
 }
 
+static int tc6393xb_ohci_suspend(struct platform_device *dev)
+{
+	struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
+
+	/* We can't properly store/restore OHCI state, so fail here */
+	if (tcpd->resume_restore)
+		return -EBUSY;
+
+	return tc6393xb_ohci_disable(dev);
+}
+
 static int tc6393xb_fb_enable(struct platform_device *dev)
 {
 	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = {
 		.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
 		.resources = tc6393xb_ohci_resources,
 		.enable = tc6393xb_ohci_enable,
-		.suspend = tc6393xb_ohci_disable,
+		.suspend = tc6393xb_ohci_suspend,
 		.resume = tc6393xb_ohci_enable,
 		.disable = tc6393xb_ohci_disable,
 	},
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index d79277204835..de87eafbeb05 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -254,8 +254,10 @@ static int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 	ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
 		IRQF_ONESHOT, pdata->irq_base,
 		tps6591x_irqs_chip, &tps65910->irq_data);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_warn(tps65910->dev, "Failed to add irq_chip %d\n", ret);
+		tps65910->chip_irq = 0;
+	}
 	return ret;
 }
 
diff --git a/drivers/mfd/vexpress-config.c b/drivers/mfd/vexpress-config.c
index 84ce6b9daa3d..1af2b0e0182f 100644
--- a/drivers/mfd/vexpress-config.c
+++ b/drivers/mfd/vexpress-config.c
@@ -86,29 +86,13 @@ void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge)
 }
 EXPORT_SYMBOL(vexpress_config_bridge_unregister);
 
-
-struct vexpress_config_func {
-	struct vexpress_config_bridge *bridge;
-	void *func;
-};
-
-struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
-		struct device_node *node)
+static struct vexpress_config_bridge *
+		vexpress_config_bridge_find(struct device_node *node)
 {
-	struct device_node *bridge_node;
-	struct vexpress_config_func *func;
 	int i;
+	struct vexpress_config_bridge *res = NULL;
+	struct device_node *bridge_node = of_node_get(node);
 
-	if (WARN_ON(dev && node && dev->of_node != node))
-		return NULL;
-	if (dev && !node)
-		node = dev->of_node;
-
-	func = kzalloc(sizeof(*func), GFP_KERNEL);
-	if (!func)
-		return NULL;
-
-	bridge_node = of_node_get(node);
 	while (bridge_node) {
 		const __be32 *prop = of_get_property(bridge_node,
 				"arm,vexpress,config-bridge", NULL);
@@ -129,13 +113,46 @@ struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
 
 		if (test_bit(i, vexpress_config_bridges_map) &&
 				bridge->node == bridge_node) {
-			func->bridge = bridge;
-			func->func = bridge->info->func_get(dev, node);
+			res = bridge;
 			break;
 		}
 	}
 	mutex_unlock(&vexpress_config_bridges_mutex);
 
+	return res;
+}
+
+
+struct vexpress_config_func {
+	struct vexpress_config_bridge *bridge;
+	void *func;
+};
+
+struct vexpress_config_func *__vexpress_config_func_get(
+		struct vexpress_config_bridge *bridge,
+		struct device *dev,
+		struct device_node *node,
+		const char *id)
+{
+	struct vexpress_config_func *func;
+
+	if (WARN_ON(dev && node && dev->of_node != node))
+		return NULL;
+	if (dev && !node)
+		node = dev->of_node;
+
+	if (!bridge)
+		bridge = vexpress_config_bridge_find(node);
+	if (!bridge)
+		return NULL;
+
+	func = kzalloc(sizeof(*func), GFP_KERNEL);
+	if (!func)
+		return NULL;
+
+	func->bridge = bridge;
+	func->func = bridge->info->func_get(dev, node, id);
+
 	if (!func->func) {
 		of_node_put(node);
 		kfree(func);
diff --git a/drivers/mfd/vexpress-spc.c b/drivers/mfd/vexpress-spc.c
new file mode 100644
index 000000000000..0c6718abf1ba
--- /dev/null
+++ b/drivers/mfd/vexpress-spc.c
@@ -0,0 +1,633 @@
+/*
+ * Versatile Express Serial Power Controller (SPC) support
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * Authors: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+ *          Achin Gupta           <achin.gupta@arm.com>
+ *          Lorenzo Pieralisi     <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/vexpress.h>
+
+#include <asm/cacheflush.h>
+
+#define SCC_CFGREG19		0x120
+#define SCC_CFGREG20		0x124
+#define A15_CONF		0x400
+#define A7_CONF			0x500
+#define SYS_INFO		0x700
+#define PERF_LVL_A15		0xB00
+#define PERF_REQ_A15		0xB04
+#define PERF_LVL_A7		0xB08
+#define PERF_REQ_A7		0xB0c
+#define SYS_CFGCTRL		0xB10
+#define SYS_CFGCTRL_REQ		0xB14
+#define PWC_STATUS		0xB18
+#define PWC_FLAG		0xB1c
+#define WAKE_INT_MASK		0xB24
+#define WAKE_INT_RAW		0xB28
+#define WAKE_INT_STAT		0xB2c
+#define A15_PWRDN_EN		0xB30
+#define A7_PWRDN_EN		0xB34
+#define A7_PWRDNACK		0xB54
+#define A15_BX_ADDR0		0xB68
+#define SYS_CFG_WDATA		0xB70
+#define SYS_CFG_RDATA		0xB74
+#define A7_BX_ADDR0		0xB78
+
+#define GBL_WAKEUP_INT_MSK	(0x3 << 10)
+
+#define CLKF_SHIFT		16
+#define CLKF_MASK		0x1FFF
+#define CLKR_SHIFT		0
+#define CLKR_MASK		0x3F
+#define CLKOD_SHIFT		8
+#define CLKOD_MASK		0xF
+
+#define OPP_FUNCTION		6
+#define OPP_BASE_DEVICE		0x300
+#define OPP_A15_OFFSET		0x4
+#define OPP_A7_OFFSET		0xc
+
+#define SYS_CFGCTRL_START	(1 << 31)
+#define SYS_CFGCTRL_WRITE	(1 << 30)
+#define SYS_CFGCTRL_FUNC(n)	(((n) & 0x3f) << 20)
+#define SYS_CFGCTRL_DEVICE(n)	(((n) & 0xfff) << 0)
+
+#define MAX_OPPS	8
+#define MAX_CLUSTERS	2
+
+enum {
+	A15_OPP_TYPE		= 0,
+	A7_OPP_TYPE		= 1,
+	SYS_CFGCTRL_TYPE	= 2,
+	INVALID_TYPE
+};
+
+#define STAT_COMPLETE(type)	((1 << 0) << (type << 2))
+#define STAT_ERR(type)		((1 << 1) << (type << 2))
+#define RESPONSE_MASK(type)	(STAT_COMPLETE(type) | STAT_ERR(type))
+
+struct vexpress_spc_drvdata {
+	void __iomem *baseaddr;
+	u32 a15_clusid;
+	int irq;
+	u32 cur_req_type;
+	u32 freqs[MAX_CLUSTERS][MAX_OPPS];
+	int freqs_cnt[MAX_CLUSTERS];
+};
+
+enum spc_func_type {
+	CONFIG_FUNC = 0,
+	PERF_FUNC   = 1,
+};
+
+struct vexpress_spc_func {
+	enum spc_func_type type;
+	u32 function;
+	u32 device;
+};
+
+static struct vexpress_spc_drvdata *info;
+static u32 *vexpress_spc_config_data;
+static struct vexpress_config_bridge *vexpress_spc_config_bridge;
+static struct vexpress_config_func *opp_func, *perf_func;
+
+static int vexpress_spc_load_result = -EAGAIN;
+
+static bool vexpress_spc_initialized(void)
+{
+	return vexpress_spc_load_result == 0;
+}
+
+/**
+ * vexpress_spc_write_resume_reg() - set the jump address used for warm boot
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @addr: physical resume address
+ */
+void vexpress_spc_write_resume_reg(u32 cluster, u32 cpu, u32 addr)
+{
+	void __iomem *baseaddr;
+
+	if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+		return;
+
+	if (cluster != info->a15_clusid)
+		baseaddr = info->baseaddr + A7_BX_ADDR0 + (cpu << 2);
+	else
+		baseaddr = info->baseaddr + A15_BX_ADDR0 + (cpu << 2);
+
+	writel_relaxed(addr, baseaddr);
+}
+
+/**
+ * vexpress_spc_get_nb_cpus() - get number of cpus in a cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ *
+ * Return: number of cpus in the cluster
+ *         -EINVAL if cluster number invalid
+ */
+int vexpress_spc_get_nb_cpus(u32 cluster)
+{
+	u32 val;
+
+	if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+		return -EINVAL;
+
+	val = readl_relaxed(info->baseaddr + SYS_INFO);
+	val = (cluster != info->a15_clusid) ? (val >> 20) : (val >> 16);
+	return val & 0xf;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_nb_cpus);
+
+/**
+ * vexpress_spc_get_performance - get current performance level of cluster
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: pointer to the performance level to be assigned
+ *
+ * Return: 0 on success
+ *         < 0 on read error
+ */
+int vexpress_spc_get_performance(u32 cluster, u32 *freq)
+{
+	u32 perf_cfg_reg;
+	int perf, ret;
+
+	if (!vexpress_spc_initialized() || (cluster >= MAX_CLUSTERS))
+		return -EINVAL;
+
+	perf_cfg_reg = cluster != info->a15_clusid ? PERF_LVL_A7 : PERF_LVL_A15;
+	ret = vexpress_config_read(perf_func, perf_cfg_reg, &perf);
+
+	if (!ret)
+		*freq = info->freqs[cluster][perf];
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_performance);
+
+/**
+ * vexpress_spc_get_perf_index - get performance level corresponding to
+ *				 a frequency
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: frequency to be looked-up
+ *
+ * Return: perf level index on success
+ *         -EINVAL on error
+ */
+static int vexpress_spc_find_perf_index(u32 cluster, u32 freq)
+{
+	int idx;
+
+	for (idx = 0; idx < info->freqs_cnt[cluster]; idx++)
+		if (info->freqs[cluster][idx] == freq)
+			break;
+	return (idx == info->freqs_cnt[cluster]) ? -EINVAL : idx;
+}
+
+/**
+ * vexpress_spc_set_performance - set current performance level of cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: performance level to be programmed
+ *
+ * Returns: 0 on success
+ *          < 0 on write error
+ */
+int vexpress_spc_set_performance(u32 cluster, u32 freq)
+{
+	int ret, perf, offset;
+
+	if (!vexpress_spc_initialized() || (cluster >= MAX_CLUSTERS))
+		return -EINVAL;
+
+	offset = (cluster != info->a15_clusid) ? PERF_LVL_A7 : PERF_LVL_A15;
+
+	perf = vexpress_spc_find_perf_index(cluster, freq);
+
+	if (perf < 0 || perf >= MAX_OPPS)
+		return -EINVAL;
+
+	ret = vexpress_config_write(perf_func, offset, perf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_set_performance);
+
+static void vexpress_spc_set_wake_intr(u32 mask)
+{
+	writel_relaxed(mask & VEXPRESS_SPC_WAKE_INTR_MASK,
+		       info->baseaddr + WAKE_INT_MASK);
+}
+
+static inline void reg_bitmask(u32 *reg, u32 mask, bool set)
+{
+	if (set)
+		*reg |= mask;
+	else
+		*reg &= ~mask;
+}
+
+/**
+ * vexpress_spc_set_global_wakeup_intr()
+ *
+ * Function to set/clear global wakeup IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @set: if true, global wake-up IRQs are set, if false they are cleared
+ */
+void vexpress_spc_set_global_wakeup_intr(bool set)
+{
+	u32 wake_int_mask_reg = 0;
+
+	wake_int_mask_reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+	reg_bitmask(&wake_int_mask_reg, GBL_WAKEUP_INT_MSK, set);
+	vexpress_spc_set_wake_intr(wake_int_mask_reg);
+}
+
+/**
+ * vexpress_spc_set_cpu_wakeup_irq()
+ *
+ * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @set: if true, wake-up IRQs are set, if false they are cleared
+ */
+void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster, bool set)
+{
+	u32 mask = 0;
+	u32 wake_int_mask_reg = 0;
+
+	mask = 1 << cpu;
+	if (info->a15_clusid != cluster)
+		mask <<= 4;
+
+	wake_int_mask_reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+	reg_bitmask(&wake_int_mask_reg, mask, set);
+	vexpress_spc_set_wake_intr(wake_int_mask_reg);
+}
+
+/**
+ * vexpress_spc_powerdown_enable()
+ *
+ * Function to enable/disable cluster powerdown. Not protected by locking
+ * since it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @enable: if true enables powerdown, if false disables it
+ */
+void vexpress_spc_powerdown_enable(u32 cluster, bool enable)
+{
+	u32 pwdrn_reg = 0;
+
+	if (cluster >= MAX_CLUSTERS)
+		return;
+	pwdrn_reg = cluster != info->a15_clusid ? A7_PWRDN_EN : A15_PWRDN_EN;
+	writel_relaxed(enable, info->baseaddr + pwdrn_reg);
+}
+
+irqreturn_t vexpress_spc_irq_handler(int irq, void *data)
+{
+	int ret;
+	u32 status = readl_relaxed(info->baseaddr + PWC_STATUS);
+
+	if (!(status & RESPONSE_MASK(info->cur_req_type)))
+		return IRQ_NONE;
+
+	if ((status == STAT_COMPLETE(SYS_CFGCTRL_TYPE))
+			&& vexpress_spc_config_data) {
+		*vexpress_spc_config_data =
+				readl_relaxed(info->baseaddr + SYS_CFG_RDATA);
+		vexpress_spc_config_data = NULL;
+	}
+
+	ret = STAT_COMPLETE(info->cur_req_type) ? 0 : -EIO;
+	info->cur_req_type = INVALID_TYPE;
+	vexpress_config_complete(vexpress_spc_config_bridge, ret);
+	return IRQ_HANDLED;
+}
+
+/**
+ * Based on the firmware documentation, this is always fixed to 20
+ * All the 4 OSC: A15 PLL0/1, A7 PLL0/1 must be programmed same
+ * values for both control and value registers.
+ * This function uses A15 PLL 0 registers to compute multiple factor
+ * F out = F in * (CLKF + 1) / ((CLKOD + 1) * (CLKR + 1))
+ */
+static inline int __get_mult_factor(void)
+{
+	int i_div, o_div, f_div;
+	u32 tmp;
+
+	tmp = readl(info->baseaddr + SCC_CFGREG19);
+	f_div = (tmp >> CLKF_SHIFT) & CLKF_MASK;
+
+	tmp = readl(info->baseaddr + SCC_CFGREG20);
+	o_div = (tmp >> CLKOD_SHIFT) & CLKOD_MASK;
+	i_div = (tmp >> CLKR_SHIFT) & CLKR_MASK;
+
+	return (f_div + 1) / ((o_div + 1) * (i_div + 1));
+}
+
+/**
+ * vexpress_spc_populate_opps() - initialize opp tables from microcontroller
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ *
+ * Return: 0 on success
+ *         < 0 on error
+ */
+static int vexpress_spc_populate_opps(u32 cluster)
+{
+	u32 data = 0, ret, i, offset;
+	int mult_fact = __get_mult_factor();
+
+	if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+		return -EINVAL;
+
+	offset = cluster != info->a15_clusid ? OPP_A7_OFFSET : OPP_A15_OFFSET;
+	for (i = 0; i < MAX_OPPS; i++) {
+		ret = vexpress_config_read(opp_func, i + offset, &data);
+		if (!ret)
+			info->freqs[cluster][i] = (data & 0xFFFFF) * mult_fact;
+		else
+			break;
+	}
+
+	info->freqs_cnt[cluster] = i;
+	return ret;
+}
+
+/**
+ * vexpress_spc_get_freq_table() - Retrieve a pointer to the frequency
+ *				   table for a given cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @fptr: pointer to be initialized
+ * Return: operating points count on success
+ *         -EINVAL on pointer error
+ */
+int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr)
+{
+	if (WARN_ON_ONCE(!fptr || cluster >= MAX_CLUSTERS))
+		return -EINVAL;
+	*fptr = info->freqs[cluster];
+	return info->freqs_cnt[cluster];
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_freq_table);
+
+static void *vexpress_spc_func_get(struct device *dev,
+		struct device_node *node, const char *id)
+{
+	struct vexpress_spc_func *spc_func;
+	u32 func_device[2];
+	int err = 0;
+
+	spc_func = kzalloc(sizeof(*spc_func), GFP_KERNEL);
+	if (!spc_func)
+		return NULL;
+
+	if (strcmp(id, "opp") == 0) {
+		spc_func->type = CONFIG_FUNC;
+		spc_func->function = OPP_FUNCTION;
+		spc_func->device = OPP_BASE_DEVICE;
+	} else if (strcmp(id, "perf") == 0) {
+		spc_func->type = PERF_FUNC;
+	} else if (node) {
+		of_node_get(node);
+		err = of_property_read_u32_array(node,
+				"arm,vexpress-sysreg,func", func_device,
+				ARRAY_SIZE(func_device));
+		of_node_put(node);
+		spc_func->type = CONFIG_FUNC;
+		spc_func->function = func_device[0];
+		spc_func->device = func_device[1];
+	}
+
+	if (WARN_ON(err)) {
+		kfree(spc_func);
+		return NULL;
+	}
+
+	pr_debug("func 0x%p = 0x%x, %d %d\n", spc_func,
+					     spc_func->function,
+					     spc_func->device,
+					     spc_func->type);
+
+	return spc_func;
+}
+
+static void vexpress_spc_func_put(void *func)
+{
+	kfree(func);
+}
+
+static int vexpress_spc_func_exec(void *func, int offset, bool write,
+				  u32 *data)
+{
+	struct vexpress_spc_func *spc_func = func;
+	u32 command;
+
+	if (!data)
+		return -EINVAL;
+	/*
+	 * Setting and retrieval of operating points is not part of
+	 * DCC config interface. It was made to go through the same
+	 * code path so that requests to the M3 can be serialized
+	 * properly with config reads/writes through the common
+	 * vexpress config interface
+	 */
+	switch (spc_func->type) {
+	case PERF_FUNC:
+		if (write) {
+			info->cur_req_type = (offset == PERF_LVL_A15) ?
+					A15_OPP_TYPE : A7_OPP_TYPE;
+			writel_relaxed(*data, info->baseaddr + offset);
+			return VEXPRESS_CONFIG_STATUS_WAIT;
+		} else {
+			*data = readl_relaxed(info->baseaddr + offset);
+			return VEXPRESS_CONFIG_STATUS_DONE;
+		}
+	case CONFIG_FUNC:
+		info->cur_req_type = SYS_CFGCTRL_TYPE;
+
+		command = SYS_CFGCTRL_START;
+		command |= write ? SYS_CFGCTRL_WRITE : 0;
+		command |= SYS_CFGCTRL_FUNC(spc_func->function);
+		command |= SYS_CFGCTRL_DEVICE(spc_func->device + offset);
+
+		pr_debug("command %x\n", command);
+
+		if (!write)
+			vexpress_spc_config_data = data;
+		else
+			writel_relaxed(*data, info->baseaddr + SYS_CFG_WDATA);
+		writel_relaxed(command, info->baseaddr + SYS_CFGCTRL);
+
+		return VEXPRESS_CONFIG_STATUS_WAIT;
+	default:
+		return -EINVAL;
+	}
+}
+
+struct vexpress_config_bridge_info vexpress_spc_config_bridge_info = {
+	.name = "vexpress-spc",
+	.func_get = vexpress_spc_func_get,
+	.func_put = vexpress_spc_func_put,
+	.func_exec = vexpress_spc_func_exec,
+};
+
+static const struct of_device_id vexpress_spc_ids[] __initconst = {
+	{ .compatible = "arm,vexpress-spc,v2p-ca15_a7" },
+	{ .compatible = "arm,vexpress-spc" },
+	{},
+};
+
+static int __init vexpress_spc_init(void)
+{
+	int ret;
+	struct device_node *node = of_find_matching_node(NULL,
+							 vexpress_spc_ids);
+
+	if (!node)
+		return -ENODEV;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		pr_err("%s: unable to allocate mem\n", __func__);
+		return -ENOMEM;
+	}
+	info->cur_req_type = INVALID_TYPE;
+
+	info->baseaddr = of_iomap(node, 0);
+	if (WARN_ON(!info->baseaddr)) {
+		ret = -ENXIO;
+		goto mem_free;
+	}
+
+	info->irq = irq_of_parse_and_map(node, 0);
+
+	if (WARN_ON(!info->irq)) {
+		ret = -ENXIO;
+		goto unmap;
+	}
+
+	readl_relaxed(info->baseaddr + PWC_STATUS);
+
+	ret = request_irq(info->irq, vexpress_spc_irq_handler,
+		IRQF_DISABLED | IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+		"arm-spc", info);
+
+	if (ret) {
+		pr_err("IRQ %d request failed\n", info->irq);
+		ret = -ENODEV;
+		goto unmap;
+	}
+
+	info->a15_clusid = readl_relaxed(info->baseaddr + A15_CONF) & 0xf;
+
+	vexpress_spc_config_bridge = vexpress_config_bridge_register(
+			node, &vexpress_spc_config_bridge_info);
+
+	if (WARN_ON(!vexpress_spc_config_bridge)) {
+		ret = -ENODEV;
+		goto unmap;
+	}
+
+	opp_func = vexpress_config_func_get(vexpress_spc_config_bridge, "opp");
+	perf_func =
+		vexpress_config_func_get(vexpress_spc_config_bridge, "perf");
+
+	if (!opp_func || !perf_func) {
+		ret = -ENODEV;
+		goto unmap;
+	}
+
+	if (vexpress_spc_populate_opps(0) || vexpress_spc_populate_opps(1)) {
+		if (info->irq)
+			free_irq(info->irq, info);
+		pr_err("failed to build OPP table\n");
+		ret = -ENODEV;
+		goto unmap;
+	}
+	/*
+	 * Multi-cluster systems may need this data when non-coherent, during
+	 * cluster power-up/power-down. Make sure it reaches main memory:
+	 */
+	sync_cache_w(info);
+	sync_cache_w(&info);
+	pr_info("vexpress-spc loaded at %p\n", info->baseaddr);
+	return 0;
+
+unmap:
+	iounmap(info->baseaddr);
+
+mem_free:
+	kfree(info);
+	return ret;
+}
+
+static bool __init __vexpress_spc_check_loaded(void);
+/*
+ * Pointer spc_check_loaded is swapped after init hence it is safe
+ * to initialize it to a function in the __init section
+ */
+static bool (*spc_check_loaded)(void) __refdata = &__vexpress_spc_check_loaded;
+
+static bool __init __vexpress_spc_check_loaded(void)
+{
+	if (vexpress_spc_load_result == -EAGAIN)
+		vexpress_spc_load_result = vexpress_spc_init();
+	spc_check_loaded = &vexpress_spc_initialized;
+	return vexpress_spc_initialized();
+}
+
+/*
+ * Function exported to manage early_initcall ordering.
+ * SPC code is needed very early in the boot process
+ * to bring CPUs out of reset and initialize power
+ * management back-end. After boot swap pointers to
+ * make the functionality check available to loadable
+ * modules, when early boot init functions have been
+ * already freed from kernel address space.
+ */
+bool vexpress_spc_check_loaded(void)
+{
+	return spc_check_loaded();
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_check_loaded);
+
+static int __init vexpress_spc_early_init(void)
+{
+	__vexpress_spc_check_loaded();
+	return vexpress_spc_load_result;
+}
+early_initcall(vexpress_spc_early_init);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Serial Power Controller (SPC) support");
diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c
index 96a020b1dcd1..7f429afce112 100644
--- a/drivers/mfd/vexpress-sysreg.c
+++ b/drivers/mfd/vexpress-sysreg.c
@@ -165,7 +165,7 @@ static u32 *vexpress_sysreg_config_data;
 static int vexpress_sysreg_config_tries;
 
 static void *vexpress_sysreg_config_func_get(struct device *dev,
-		struct device_node *node)
+		struct device_node *node, const char *id)
 {
 	struct vexpress_sysreg_config_func *config_func;
 	u32 site;
@@ -351,6 +351,8 @@ void __init vexpress_sysreg_of_early_init(void)
 }
 
 
+#ifdef CONFIG_GPIOLIB
+
 #define VEXPRESS_SYSREG_GPIO(_name, _reg, _value) \
 	[VEXPRESS_GPIO_##_name] = { \
 		.reg = _reg, \
@@ -445,6 +447,8 @@ struct gpio_led_platform_data vexpress_sysreg_leds_pdata = {
 	.leds = vexpress_sysreg_leds,
 };
 
+#endif
+
 
 static ssize_t vexpress_sysreg_sys_id_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -480,6 +484,9 @@ static int vexpress_sysreg_probe(struct platform_device *pdev)
 	setup_timer(&vexpress_sysreg_config_timer,
 			vexpress_sysreg_config_complete, 0);
 
+	vexpress_sysreg_dev = &pdev->dev;
+
+#ifdef CONFIG_GPIOLIB
 	vexpress_sysreg_gpio_chip.dev = &pdev->dev;
 	err = gpiochip_add(&vexpress_sysreg_gpio_chip);
 	if (err) {
@@ -490,11 +497,10 @@ static int vexpress_sysreg_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	vexpress_sysreg_dev = &pdev->dev;
-
 	platform_device_register_data(vexpress_sysreg_dev, "leds-gpio",
 			PLATFORM_DEVID_AUTO, &vexpress_sysreg_leds_pdata,
 			sizeof(vexpress_sysreg_leds_pdata));
+#endif
 
 	device_create_file(vexpress_sysreg_dev, &dev_attr_sys_id);
 
diff --git a/drivers/misc/atmel_pwm.c b/drivers/misc/atmel_pwm.c
index 494d0500bda6..a6dc56e1bc58 100644
--- a/drivers/misc/atmel_pwm.c
+++ b/drivers/misc/atmel_pwm.c
@@ -90,8 +90,10 @@ int pwm_channel_alloc(int index, struct pwm_channel *ch)
 	unsigned long	flags;
 	int		status = 0;
 
-	/* insist on PWM init, with this signal pinned out */
-	if (!pwm || !(pwm->mask & 1 << index))
+	if (!pwm)
+		return -EPROBE_DEFER;
+
+	if (!(pwm->mask & 1 << index))
 		return -ENODEV;
 
 	if (index < 0 || index >= PWM_NCHAN || !ch)
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 00e5fcac8fdf..cbee842f8b6b 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -198,6 +198,13 @@ static void enclosure_remove_links(struct enclosure_component *cdev)
 {
 	char name[ENCLOSURE_NAME_SIZE];
 
+	/*
+	 * In odd circumstances, like multipath devices, something else may
+	 * already have removed the links, so check for this condition first.
+	 */
+	if (!cdev->dev->kobj.sd)
+		return;
+
 	enclosure_link_name(cdev, name);
 	sysfs_remove_link(&cdev->dev->kobj, name);
 	sysfs_remove_link(&cdev->cdev.kobj, "device");
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index b3e50984d2c8..3db9291849f1 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -57,6 +57,7 @@ void mei_amthif_reset_params(struct mei_device *dev)
 	dev->iamthif_ioctl = false;
 	dev->iamthif_state = MEI_IAMTHIF_IDLE;
 	dev->iamthif_timer = 0;
+	dev->iamthif_stall_timer = 0;
 }
 
 /**
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 9ecd49a7be1b..0513ea0906dd 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev)
 
 	dev_dbg(dev, "Device probe\n");
 
-	strncpy(id.name, dev_name(dev), MEI_CL_NAME_SIZE);
+	strlcpy(id.name, dev_name(dev), sizeof(id.name));
 
 	return driver->probe(device, &id);
 }
@@ -295,10 +295,13 @@ int __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length)
 
 	if (cl->reading_state != MEI_READ_COMPLETE &&
 	    !waitqueue_active(&cl->rx_wait)) {
+
 		mutex_unlock(&dev->device_lock);
 
 		if (wait_event_interruptible(cl->rx_wait,
-				(MEI_READ_COMPLETE == cl->reading_state))) {
+				cl->reading_state == MEI_READ_COMPLETE  ||
+				mei_cl_is_transitioning(cl))) {
+
 			if (signal_pending(current))
 				return -EINTR;
 			return -ERESTARTSYS;
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index e310ca6ed1a3..07ed4b5b1659 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -405,6 +405,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
 			dev_err(&dev->pdev->dev, "failed to disconnect.\n");
 			goto free;
 		}
+		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		mdelay(10); /* Wait for hardware disconnection ready */
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
@@ -511,6 +512,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file)
 		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
+		cl->state = MEI_FILE_INITIALIZING;
 		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
 
@@ -664,7 +666,6 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length)
 		goto err;
 
 	cb->fop_type = MEI_FOP_READ;
-	cl->read_cb = cb;
 	if (dev->hbuf_is_ready) {
 		dev->hbuf_is_ready = false;
 		if (mei_hbm_cl_flow_control_req(dev, cl)) {
@@ -675,6 +676,9 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length)
 	} else {
 		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
+
+	cl->read_cb = cb;
+
 	return rets;
 err:
 	mei_io_cb_free(cb);
@@ -799,7 +803,6 @@ void mei_cl_all_disconnect(struct mei_device *dev)
 	list_for_each_entry_safe(cl, next, &dev->file_list, link) {
 		cl->state = MEI_FILE_DISCONNECTED;
 		cl->mei_flow_ctrl_creds = 0;
-		cl->read_cb = NULL;
 		cl->timer_count = 0;
 	}
 }
@@ -829,8 +832,16 @@ void mei_cl_all_read_wakeup(struct mei_device *dev)
 void mei_cl_all_write_clear(struct mei_device *dev)
 {
 	struct mei_cl_cb *cb, *next;
+	struct list_head *list;
+
+	list = &dev->write_list.list;
+	list_for_each_entry_safe(cb, next, list, list) {
+		list_del(&cb->list);
+		mei_io_cb_free(cb);
+	}
 
-	list_for_each_entry_safe(cb, next, &dev->write_list.list, list) {
+	list = &dev->write_waiting_list.list;
+	list_for_each_entry_safe(cb, next, list, list) {
 		list_del(&cb->list);
 		mei_io_cb_free(cb);
 	}
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index cfdb144526aa..467d9dda97fa 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -76,6 +76,12 @@ static inline bool mei_cl_cmp_id(const struct mei_cl *cl1,
 		(cl1->host_client_id == cl2->host_client_id) &&
 		(cl1->me_client_id == cl2->me_client_id);
 }
+static inline bool mei_cl_is_transitioning(struct mei_cl *cl)
+{
+	return (MEI_FILE_INITIALIZING == cl->state ||
+		MEI_FILE_DISCONNECTED == cl->state ||
+		MEI_FILE_DISCONNECTING == cl->state);
+}
 
 
 int mei_cl_flow_ctrl_creds(struct mei_cl *cl);
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index 6916045166eb..23b5b7bcba9f 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -35,11 +35,15 @@ static void mei_hbm_me_cl_allocate(struct mei_device *dev)
 	struct mei_me_client *clients;
 	int b;
 
+	dev->me_clients_num = 0;
+	dev->me_client_presentation_num = 0;
+	dev->me_client_index = 0;
+
 	/* count how many ME clients we have */
 	for_each_set_bit(b, dev->me_clients_map, MEI_CLIENTS_MAX)
 		dev->me_clients_num++;
 
-	if (dev->me_clients_num <= 0)
+	if (dev->me_clients_num == 0)
 		return;
 
 	kfree(dev->me_clients);
@@ -221,7 +225,7 @@ static int mei_hbm_prop_req(struct mei_device *dev)
 	struct hbm_props_request *prop_req;
 	const size_t len = sizeof(struct hbm_props_request);
 	unsigned long next_client_index;
-	u8 client_num;
+	unsigned long client_num;
 
 
 	client_num = dev->me_client_presentation_num;
@@ -650,8 +654,6 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr)
 		if (dev->dev_state == MEI_DEV_INIT_CLIENTS &&
 		    dev->hbm_state == MEI_HBM_ENUM_CLIENTS) {
 				dev->init_clients_timer = 0;
-				dev->me_client_presentation_num = 0;
-				dev->me_client_index = 0;
 				mei_hbm_me_cl_allocate(dev);
 				dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES;
 
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 6a203b6e8346..cabc04383685 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -109,8 +109,17 @@
 #define MEI_DEV_ID_PPT_2      0x1CBA  /* Panther Point */
 #define MEI_DEV_ID_PPT_3      0x1DBA  /* Panther Point */
 
-#define MEI_DEV_ID_LPT        0x8C3A  /* Lynx Point */
+#define MEI_DEV_ID_LPT_H      0x8C3A  /* Lynx Point H */
+#define MEI_DEV_ID_LPT_W      0x8D3A  /* Lynx Point - Wellsburg */
 #define MEI_DEV_ID_LPT_LP     0x9C3A  /* Lynx Point LP */
+#define MEI_DEV_ID_LPT_HR     0x8CBA  /* Lynx Point H Refresh */
+
+#define MEI_DEV_ID_WPT_LP     0x9CBA  /* Wildcat Point LP */
+
+/* Host Firmware Status Registers in PCI Config Space */
+#define PCI_CFG_HFS_1         0x40
+#define PCI_CFG_HFS_2         0x48
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 1bf3f8b5ce3a..297cc10a26da 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -164,6 +164,9 @@ static void mei_me_hw_reset_release(struct mei_device *dev)
 	hcsr |= H_IG;
 	hcsr &= ~H_RST;
 	mei_hcsr_set(hw, hcsr);
+
+	/* complete this write before we set host ready on another CPU */
+	mmiowb();
 }
 /**
  * mei_me_hw_reset - resets fw via mei csr register.
@@ -183,9 +186,22 @@ static void mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 	else
 		hcsr &= ~H_IE;
 
+	dev->recvd_hw_ready = false;
 	mei_me_reg_write(hw, H_CSR, hcsr);
 
-	if (dev->dev_state == MEI_DEV_POWER_DOWN)
+	/*
+	 * Host reads the H_CSR once to ensure that the
+	 * posted write to H_CSR completes.
+	 */
+	hcsr = mei_hcsr_read(hw);
+
+	if ((hcsr & H_RST) == 0)
+		dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr);
+
+	if ((hcsr & H_RDY) == H_RDY)
+		dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr);
+
+	if (intr_enable == false)
 		mei_me_hw_reset_release(dev);
 
 	dev_dbg(&dev->pdev->dev, "current HCSR = 0x%08x.\n", mei_hcsr_read(hw));
@@ -201,6 +217,7 @@ static void mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 static void mei_me_host_set_ready(struct mei_device *dev)
 {
 	struct mei_me_hw *hw = to_me_hw(dev);
+	hw->host_hw_state = mei_hcsr_read(hw);
 	hw->host_hw_state |= H_IE | H_IG | H_RDY;
 	mei_hcsr_set(hw, hw->host_hw_state);
 }
@@ -233,10 +250,7 @@ static bool mei_me_hw_is_ready(struct mei_device *dev)
 static int mei_me_hw_ready_wait(struct mei_device *dev)
 {
 	int err;
-	if (mei_me_hw_is_ready(dev))
-		return 0;
 
-	dev->recvd_hw_ready = false;
 	mutex_unlock(&dev->device_lock);
 	err = wait_event_interruptible_timeout(dev->wait_hw_ready,
 			dev->recvd_hw_ready,
@@ -496,19 +510,15 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/*  check if we need to start the dev */
 	if (!mei_host_is_ready(dev)) {
 		if (mei_hw_is_ready(dev)) {
+			mei_me_hw_reset_release(dev);
 			dev_dbg(&dev->pdev->dev, "we need to start the dev.\n");
 
 			dev->recvd_hw_ready = true;
 			wake_up_interruptible(&dev->wait_hw_ready);
-
-			mutex_unlock(&dev->device_lock);
-			return IRQ_HANDLED;
 		} else {
-			dev_dbg(&dev->pdev->dev, "Reset Completed.\n");
-			mei_me_hw_reset_release(dev);
-			mutex_unlock(&dev->device_lock);
-			return IRQ_HANDLED;
+			dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n");
 		}
+		goto end;
 	}
 	/* check slots available for reading */
 	slots = mei_count_full_read_slots(dev);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 6eec689ba97e..878bc1c29d2b 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -164,6 +164,9 @@ void mei_reset(struct mei_device *dev, int interrupts_enabled)
 		memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg));
 	}
 
+	/* we're already in reset, cancel the init timer */
+	dev->init_clients_timer = 0;
+
 	dev->me_clients_num = 0;
 	dev->rd_msg_hdr = 0;
 	dev->wd_pending = false;
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 053139f61086..701698de5ac7 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -262,19 +262,16 @@ static ssize_t mei_read(struct file *file, char __user *ubuf,
 		mutex_unlock(&dev->device_lock);
 
 		if (wait_event_interruptible(cl->rx_wait,
-			(MEI_READ_COMPLETE == cl->reading_state ||
-			 MEI_FILE_INITIALIZING == cl->state ||
-			 MEI_FILE_DISCONNECTED == cl->state ||
-			 MEI_FILE_DISCONNECTING == cl->state))) {
+				MEI_READ_COMPLETE == cl->reading_state ||
+				mei_cl_is_transitioning(cl))) {
+
 			if (signal_pending(current))
 				return -EINTR;
 			return -ERESTARTSYS;
 		}
 
 		mutex_lock(&dev->device_lock);
-		if (MEI_FILE_INITIALIZING == cl->state ||
-		    MEI_FILE_DISCONNECTED == cl->state ||
-		    MEI_FILE_DISCONNECTING == cl->state) {
+		if (mei_cl_is_transitioning(cl)) {
 			rets = -EBUSY;
 			goto out;
 		}
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 4de5140e7379..73c7700aee21 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -402,9 +402,9 @@ struct mei_device {
 	struct mei_me_client *me_clients; /* Note: memory has to be allocated */
 	DECLARE_BITMAP(me_clients_map, MEI_CLIENTS_MAX);
 	DECLARE_BITMAP(host_clients_map, MEI_CLIENTS_MAX);
-	u8 me_clients_num;
-	u8 me_client_presentation_num;
-	u8 me_client_index;
+	unsigned long me_clients_num;
+	unsigned long me_client_presentation_num;
+	unsigned long me_client_index;
 
 	struct mei_cl wd_cl;
 	enum mei_wd_states wd_state;
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index d0c6907dfd92..4b7ea3fb143c 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -342,9 +342,10 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	ndev = (struct mei_nfc_dev *) cldev->priv_data;
 	dev = ndev->cl->dev;
 
+	err = -ENOMEM;
 	mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL);
 	if (!mei_buf)
-		return -ENOMEM;
+		goto out;
 
 	hdr = (struct mei_nfc_hci_hdr *) mei_buf;
 	hdr->cmd = MEI_NFC_CMD_HCI_SEND;
@@ -354,12 +355,9 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	hdr->data_size = length;
 
 	memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length);
-
 	err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE);
 	if (err < 0)
-		return err;
-
-	kfree(mei_buf);
+		goto out;
 
 	if (!wait_event_interruptible_timeout(ndev->send_wq,
 				ndev->recv_req_id == ndev->req_id, HZ)) {
@@ -368,7 +366,8 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	} else {
 		ndev->req_id++;
 	}
-
+out:
+	kfree(mei_buf);
 	return err;
 }
 
@@ -485,8 +484,11 @@ int mei_nfc_host_init(struct mei_device *dev)
 	if (ndev->cl_info)
 		return 0;
 
-	cl_info = mei_cl_allocate(dev);
-	cl = mei_cl_allocate(dev);
+	ndev->cl_info = mei_cl_allocate(dev);
+	ndev->cl = mei_cl_allocate(dev);
+
+	cl = ndev->cl;
+	cl_info = ndev->cl_info;
 
 	if (!cl || !cl_info) {
 		ret = -ENOMEM;
@@ -527,10 +529,9 @@ int mei_nfc_host_init(struct mei_device *dev)
 
 	cl->device_uuid = mei_nfc_guid;
 
+
 	list_add_tail(&cl->device_link, &dev->device_list);
 
-	ndev->cl_info = cl_info;
-	ndev->cl = cl;
 	ndev->req_id = 1;
 
 	INIT_WORK(&ndev->init_work, mei_nfc_init);
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 0f268329bd3a..3c9e257982e3 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -79,8 +79,11 @@ static DEFINE_PCI_DEVICE_TABLE(mei_me_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_1)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_2)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_3)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_H)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_W)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_LP)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_HR)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_WPT_LP)},
 
 	/* required last entry */
 	{0, }
@@ -102,15 +105,31 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev,
 				const struct pci_device_id *ent)
 {
 	u32 reg;
-	if (ent->device == MEI_DEV_ID_PBG_1) {
-		pci_read_config_dword(pdev, 0x48, &reg);
-		/* make sure that bit 9 is up and bit 10 is down */
-		if ((reg & 0x600) == 0x200) {
-			dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
-			return false;
-		}
+	/* Cougar Point || Patsburg */
+	if (ent->device == MEI_DEV_ID_CPT_1 ||
+	    ent->device == MEI_DEV_ID_PBG_1) {
+		pci_read_config_dword(pdev, PCI_CFG_HFS_2, &reg);
+		/* make sure that bit 9 (NM) is up and bit 10 (DM) is down */
+		if ((reg & 0x600) == 0x200)
+			goto no_mei;
 	}
+
+	/* Lynx Point */
+	if (ent->device == MEI_DEV_ID_LPT_H  ||
+	    ent->device == MEI_DEV_ID_LPT_W  ||
+	    ent->device == MEI_DEV_ID_LPT_HR) {
+		/* Read ME FW Status check for SPS Firmware */
+		pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+		/* if bits [19:16] = 15, running SPS Firmware */
+		if ((reg & 0xf0000) == 0xf0000)
+			goto no_mei;
+	}
+
 	return true;
+
+no_mei:
+	dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
+	return false;
 }
 /**
  * mei_probe - Device Initialization Routine
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index dd27b0783d52..7ad66823d022 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -257,7 +257,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr,
 	int ret;
 	struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
 
-	ret = snprintf(buf, PAGE_SIZE, "%d",
+	ret = snprintf(buf, PAGE_SIZE, "%d\n",
 		       get_disk_ro(dev_to_disk(dev)) ^
 		       md->read_only);
 	mmc_blk_put(md);
@@ -769,7 +769,7 @@ static int mmc_blk_cmd_error(struct request *req, const char *name, int error,
  * Otherwise we don't understand what happened, so abort.
  */
 static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
-	struct mmc_blk_request *brq, int *ecc_err)
+	struct mmc_blk_request *brq, int *ecc_err, int *gen_err)
 {
 	bool prev_cmd_status_valid = true;
 	u32 status, stop_status = 0;
@@ -807,6 +807,16 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
 	    (brq->cmd.resp[0] & R1_CARD_ECC_FAILED))
 		*ecc_err = 1;
 
+	/* Flag General errors */
+	if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ)
+		if ((status & R1_ERROR) ||
+			(brq->stop.resp[0] & R1_ERROR)) {
+			pr_err("%s: %s: general error sending stop or status command, stop cmd response %#x, card status %#x\n",
+			       req->rq_disk->disk_name, __func__,
+			       brq->stop.resp[0], status);
+			*gen_err = 1;
+		}
+
 	/*
 	 * Check the current card state.  If it is in some data transfer
 	 * mode, tell it to stop (and hopefully transition back to TRAN.)
@@ -826,6 +836,13 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
 			return ERR_ABORT;
 		if (stop_status & R1_CARD_ECC_FAILED)
 			*ecc_err = 1;
+		if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ)
+			if (stop_status & R1_ERROR) {
+				pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n",
+				       req->rq_disk->disk_name, __func__,
+				       stop_status);
+				*gen_err = 1;
+			}
 	}
 
 	/* Check for set block count errors */
@@ -1069,7 +1086,7 @@ static int mmc_blk_err_check(struct mmc_card *card,
 						    mmc_active);
 	struct mmc_blk_request *brq = &mq_mrq->brq;
 	struct request *req = mq_mrq->req;
-	int ecc_err = 0;
+	int ecc_err = 0, gen_err = 0;
 
 	/*
 	 * sbc.error indicates a problem with the set block count
@@ -1083,7 +1100,7 @@ static int mmc_blk_err_check(struct mmc_card *card,
 	 */
 	if (brq->sbc.error || brq->cmd.error || brq->stop.error ||
 	    brq->data.error) {
-		switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err)) {
+		switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err, &gen_err)) {
 		case ERR_RETRY:
 			return MMC_BLK_RETRY;
 		case ERR_ABORT:
@@ -1115,6 +1132,14 @@ static int mmc_blk_err_check(struct mmc_card *card,
 		u32 status;
 		unsigned long timeout;
 
+		/* Check stop command response */
+		if (brq->stop.resp[0] & R1_ERROR) {
+			pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n",
+			       req->rq_disk->disk_name, __func__,
+			       brq->stop.resp[0]);
+			gen_err = 1;
+		}
+
 		timeout = jiffies + msecs_to_jiffies(MMC_BLK_TIMEOUT_MS);
 		do {
 			int err = get_card_status(card, &status, 5);
@@ -1124,6 +1149,13 @@ static int mmc_blk_err_check(struct mmc_card *card,
 				return MMC_BLK_CMD_ERR;
 			}
 
+			if (status & R1_ERROR) {
+				pr_err("%s: %s: general error sending status command, card status %#x\n",
+				       req->rq_disk->disk_name, __func__,
+				       status);
+				gen_err = 1;
+			}
+
 			/* Timeout if the device never becomes ready for data
 			 * and never leaves the program state.
 			 */
@@ -1143,6 +1175,13 @@ static int mmc_blk_err_check(struct mmc_card *card,
 			 (R1_CURRENT_STATE(status) == R1_STATE_PRG));
 	}
 
+	/* if general error occurs, retry the write operation. */
+	if (gen_err) {
+		pr_warn("%s: retrying write for general error\n",
+				req->rq_disk->disk_name);
+		return MMC_BLK_RETRY;
+	}
+
 	if (brq->data.error) {
 		pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n",
 		       req->rq_disk->disk_name, brq->data.error,
@@ -1892,6 +1931,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
+	unsigned int cmd_flags = req ? req->cmd_flags : 0;
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -1907,7 +1947,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	}
 
 	mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
-	if (req && req->cmd_flags & REQ_DISCARD) {
+	if (cmd_flags & REQ_DISCARD) {
 		/* complete ongoing async transfer before issuing discard */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
@@ -1916,7 +1956,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 			ret = mmc_blk_issue_secdiscard_rq(mq, req);
 		else
 			ret = mmc_blk_issue_discard_rq(mq, req);
-	} else if (req && req->cmd_flags & REQ_FLUSH) {
+	} else if (cmd_flags & REQ_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
@@ -1932,7 +1972,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 
 out:
 	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
-	     (req && (req->cmd_flags & MMC_REQ_SPECIAL_MASK)))
+	     (cmd_flags & MMC_REQ_SPECIAL_MASK))
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index aca59d93d5a9..84b054b08462 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -584,6 +584,13 @@ static void atmci_timeout_timer(unsigned long data)
 	if (host->mrq->cmd->data) {
 		host->mrq->cmd->data->error = -ETIMEDOUT;
 		host->data = NULL;
+		/*
+		 * With some SDIO modules, sometimes DMA transfer hangs. If
+		 * stop_transfer() is not called then the DMA request is not
+		 * removed, following ones are queued and never computed.
+		 */
+		if (host->state == STATE_DATA_XFER)
+			host->stop_transfer(host);
 	} else {
 		host->mrq->cmd->error = -ETIMEDOUT;
 		host->cmd = NULL;
@@ -1181,11 +1188,22 @@ static void atmci_start_request(struct atmel_mci *host,
 	iflags |= ATMCI_CMDRDY;
 	cmd = mrq->cmd;
 	cmdflags = atmci_prepare_command(slot->mmc, cmd);
-	atmci_send_command(host, cmd, cmdflags);
+
+	/*
+	 * DMA transfer should be started before sending the command to avoid
+	 * unexpected errors especially for read operations in SDIO mode.
+	 * Unfortunately, in PDC mode, command has to be sent before starting
+	 * the transfer.
+	 */
+	if (host->submit_data != &atmci_submit_data_dma)
+		atmci_send_command(host, cmd, cmdflags);
 
 	if (data)
 		host->submit_data(host, data);
 
+	if (host->submit_data == &atmci_submit_data_dma)
+		atmci_send_command(host, cmd, cmdflags);
+
 	if (mrq->stop) {
 		host->stop_cmdr = atmci_prepare_command(slot->mmc, mrq->stop);
 		host->stop_cmdr |= ATMCI_CMDR_STOP_XFER;
@@ -1787,12 +1805,14 @@ static void atmci_tasklet_func(unsigned long priv)
 			if (unlikely(status)) {
 				host->stop_transfer(host);
 				host->data = NULL;
-				if (status & ATMCI_DTOE) {
-					data->error = -ETIMEDOUT;
-				} else if (status & ATMCI_DCRCE) {
-					data->error = -EILSEQ;
-				} else {
-					data->error = -EIO;
+				if (data) {
+					if (status & ATMCI_DTOE) {
+						data->error = -ETIMEDOUT;
+					} else if (status & ATMCI_DCRCE) {
+						data->error = -EILSEQ;
+					} else {
+						data->error = -EIO;
+					}
 				}
 			}
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index ad13f4240c49..4c65a5a4d8f4 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -247,6 +247,9 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	case MMC_RSP_R1:
 		rsp_type = SD_RSP_TYPE_R1;
 		break;
+	case MMC_RSP_R1 & ~MMC_RSP_CRC:
+		rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
+		break;
 	case MMC_RSP_R1B:
 		rsp_type = SD_RSP_TYPE_R1b;
 		break;
@@ -338,6 +341,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	}
 
 	if (rsp_type == SD_RSP_TYPE_R2) {
+		/*
+		 * The controller offloads the last byte {CRC-7, end bit 1'b1}
+		 * of response type R2. Assign dummy CRC, 0, and end bit to the
+		 * byte(ptr[16], goes into the LSB of resp[3] later).
+		 */
+		ptr[16] = 1;
+
 		for (i = 0; i < 4; i++) {
 			cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4);
 			dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n",
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 19d637266fcd..71e4f6ccae2f 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -1075,7 +1075,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 			return;
 	}
 
-	ftl_freepart(partition);
 	kfree(partition);
 }
 
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 2d23d2929438..cc69e415df35 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -1096,6 +1096,7 @@ static int __init atmel_pmecc_nand_init_params(struct platform_device *pdev,
 		goto err_pmecc_data_alloc;
 	}
 
+	nand_chip->options |= NAND_NO_SUBPAGE_WRITE;
 	nand_chip->ecc.read_page = atmel_nand_pmecc_read_page;
 	nand_chip->ecc.write_page = atmel_nand_pmecc_write_page;
 
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 20657209a472..c31d183820c5 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -725,6 +725,19 @@ static int fsl_elbc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return 0;
 }
 
+/* ECC will be calculated automatically, and errors will be detected in
+ * waitfunc.
+ */
+static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				uint32_t offset, uint32_t data_len,
+				const uint8_t *buf, int oob_required)
+{
+	fsl_elbc_write_buf(mtd, buf, mtd->writesize);
+	fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+	return 0;
+}
+
 static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 {
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
@@ -763,6 +776,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 
 	chip->ecc.read_page = fsl_elbc_read_page;
 	chip->ecc.write_page = fsl_elbc_write_page;
+	chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
 	/* If CS Base Register selects full hardware ECC then use it */
 	if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 25ecfa1822a8..ab6581f1bc28 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -264,8 +264,6 @@ static void dma_irq_callback(void *param)
 	struct gpmi_nand_data *this = param;
 	struct completion *dma_c = &this->dma_done;
 
-	complete(dma_c);
-
 	switch (this->dma_type) {
 	case DMA_FOR_COMMAND:
 		dma_unmap_sg(this->dev, &this->cmd_sgl, 1, DMA_TO_DEVICE);
@@ -290,6 +288,8 @@ static void dma_irq_callback(void *param)
 	default:
 		pr_err("in wrong DMA operation.\n");
 	}
+
+	complete(dma_c);
 }
 
 int start_dma_without_bch_irq(struct gpmi_nand_data *this,
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 07e5784e5cd3..9896b636c4eb 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -676,7 +676,6 @@ static int mxc_nand_correct_data_v2_v3(struct mtd_info *mtd, u_char *dat,
 		ecc_stat >>= 4;
 	} while (--no_subpages);
 
-	mtd->ecc_stats.corrected += ret;
 	pr_debug("%d Symbol Correctable RS-ECC Error\n", ret);
 
 	return ret;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index fb8c4deaac27..633db8830c13 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2904,10 +2904,21 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 	sanitize_string(p->model, sizeof(p->model));
 	if (!mtd->name)
 		mtd->name = p->model;
+
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
-	mtd->erasesize = le32_to_cpu(p->pages_per_block) * mtd->writesize;
+
+	/*
+	 * pages_per_block and blocks_per_lun may not be a power-of-2 size
+	 * (don't ask me who thought of this...). MTD assumes that these
+	 * dimensions will be power-of-2, so just truncate the remaining area.
+	 */
+	mtd->erasesize = 1 << (fls(le32_to_cpu(p->pages_per_block)) - 1);
+	mtd->erasesize *= mtd->writesize;
+
 	mtd->oobsize = le16_to_cpu(p->spare_bytes_per_page);
-	chip->chipsize = le32_to_cpu(p->blocks_per_lun);
+
+	/* See erasesize comment */
+	chip->chipsize = 1 << (fls(le32_to_cpu(p->blocks_per_lun)) - 1);
 	chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
 	*busw = 0;
 	if (le16_to_cpu(p->features) & 1)
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index cd6be2ed53a8..14203f3bb0cd 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -225,7 +225,7 @@ static void nuc900_nand_enable(struct nuc900_nand *nand)
 	val = __raw_readl(nand->reg + REG_FMICSR);
 
 	if (!(val & NAND_EN))
-		__raw_writel(val | NAND_EN, REG_FMICSR);
+		__raw_writel(val | NAND_EN, nand->reg + REG_FMICSR);
 
 	val = __raw_readl(nand->reg + REG_SMCSR);
 
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 81b80af55872..e9b1797cdb5f 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -948,7 +948,7 @@ static int omap_calculate_ecc(struct mtd_info *mtd, const u_char *dat,
 	u32 val;
 
 	val = readl(info->reg.gpmc_ecc_config);
-	if (((val >> ECC_CONFIG_CS_SHIFT)  & ~CS_MASK) != info->gpmc_cs)
+	if (((val >> ECC_CONFIG_CS_SHIFT) & CS_MASK) != info->gpmc_cs)
 		return -EINVAL;
 
 	/* read ecc result */
@@ -1463,7 +1463,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 
 	/* Check if any error reported */
 	if (!is_error_reported)
-		return 0;
+		return stat;
 
 	/* Decode BCH error using ELM module */
 	elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec);
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index f9d5615c5727..4b55cd45287b 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -59,15 +59,12 @@ struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	struct attribute_group *attr_group;
 	struct attribute **attributes;
 	struct sm_sysfs_attribute *vendor_attribute;
+	char *vendor;
 
-	int vendor_len = strnlen(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
-					SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET);
-
-	char *vendor = kmalloc(vendor_len, GFP_KERNEL);
+	vendor = kstrndup(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
+			  SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET, GFP_KERNEL);
 	if (!vendor)
 		goto error1;
-	memcpy(vendor, ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, vendor_len);
-	vendor[vendor_len] = 0;
 
 	/* Initialize sysfs attributes */
 	vendor_attribute =
@@ -78,7 +75,7 @@ struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	sysfs_attr_init(&vendor_attribute->dev_attr.attr);
 
 	vendor_attribute->data = vendor;
-	vendor_attribute->len = vendor_len;
+	vendor_attribute->len = strlen(vendor);
 	vendor_attribute->dev_attr.attr.name = "vendor";
 	vendor_attribute->dev_attr.attr.mode = S_IRUGO;
 	vendor_attribute->dev_attr.show = sm_attr_show;
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 0648c6996d43..bf8108d65b73 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -330,6 +330,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		av = tmp_av;
 	else {
 		ubi_err("orphaned volume in fastmap pool!");
+		kmem_cache_free(ai->aeb_slab_cache, new_aeb);
 		return UBI_BAD_FASTMAP;
 	}
 
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index ec2c2dc1c1ca..2a1b6e037e1a 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -133,6 +133,10 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 	ubi_assert(!vol->updating && !vol->changing_leb);
 	vol->updating = 1;
 
+	vol->upd_buf = vmalloc(ubi->leb_size);
+	if (!vol->upd_buf)
+		return -ENOMEM;
+
 	err = set_update_marker(ubi, vol);
 	if (err)
 		return err;
@@ -152,14 +156,12 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
+
+		vfree(vol->upd_buf);
 		vol->updating = 0;
 		return 0;
 	}
 
-	vol->upd_buf = vmalloc(ubi->leb_size);
-	if (!vol->upd_buf)
-		return -ENOMEM;
-
 	vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1,
 			       vol->usable_leb_size);
 	vol->upd_bytes = bytes;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index c95bfb183c62..49e570abe58b 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1209,7 +1209,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 
 	err = do_sync_erase(ubi, e1, vol_id, lnum, 0);
 	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e1);
 		if (e2)
 			kmem_cache_free(ubi_wl_entry_slab, e2);
 		goto out_ro;
@@ -1223,10 +1222,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 		dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase",
 		       e2->pnum, vol_id, lnum);
 		err = do_sync_erase(ubi, e2, vol_id, lnum, 0);
-		if (err) {
-			kmem_cache_free(ubi_wl_entry_slab, e2);
+		if (err)
 			goto out_ro;
-		}
 	}
 
 	dbg_wl("done");
@@ -1262,10 +1259,9 @@ out_not_moved:
 
 	ubi_free_vid_hdr(ubi, vid_hdr);
 	err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
-	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e2);
+	if (err)
 		goto out_ro;
-	}
+
 	mutex_unlock(&ubi->move_mutex);
 	return 0;
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 3835321b8cf3..3bc3ebc0882f 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -139,6 +139,7 @@ config MACVLAN
 config MACVTAP
 	tristate "MAC-VLAN based tap driver"
 	depends on MACVLAN
+	depends on INET
 	help
 	  This adds a specialized tap character device driver that is based
 	  on the MAC-VLAN network interface, called macvtap. A macvtap device
@@ -209,6 +210,7 @@ config RIONET_RX_SIZE
 
 config TUN
 	tristate "Universal TUN/TAP device driver support"
+	depends on INET
 	select CRC32
 	---help---
 	  TUN/TAP provides packet reception and transmission for user space
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 390061d09693..00c6c089b935 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1854,8 +1854,6 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
 	BOND_AD_INFO(bond).agg_select_timer = timeout;
 }
 
-static u16 aggregator_identifier;
-
 /**
  * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
  * @bond: bonding struct to work on
@@ -1869,7 +1867,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
 	if (MAC_ADDRESS_COMPARE(&(BOND_AD_INFO(bond).system.sys_mac_addr),
 				bond->dev->dev_addr)) {
 
-		aggregator_identifier = 0;
+		BOND_AD_INFO(bond).aggregator_identifier = 0;
 
 		BOND_AD_INFO(bond).system.sys_priority = 0xFFFF;
 		BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr);
@@ -1940,7 +1938,7 @@ int bond_3ad_bind_slave(struct slave *slave)
 		ad_initialize_agg(aggregator);
 
 		aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr);
-		aggregator->aggregator_identifier = (++aggregator_identifier);
+		aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier;
 		aggregator->slave = slave;
 		aggregator->is_active = 0;
 		aggregator->num_of_ports = 0;
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 5d91ad0cc041..1f081c89753f 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -253,6 +253,7 @@ struct ad_system {
 struct ad_bond_info {
 	struct ad_system system;	    /* 802.3ad system structure */
 	u32 agg_select_timer;	    // Timer to select aggregator after all adapter's hand shakes
+	u16 aggregator_identifier;
 };
 
 struct ad_slave_info {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 666cf3a49b6d..b143ce91e081 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1991,6 +1991,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
 	struct sockaddr addr;
+	int old_flags = bond_dev->flags;
 	netdev_features_t old_features = bond_dev->features;
 
 	/* slave is not a slave or master is not master of this slave */
@@ -2123,12 +2124,18 @@ static int __bond_release_one(struct net_device *bond_dev,
 	 * already taken care of above when we detached the slave
 	 */
 	if (!USES_PRIMARY(bond->params.mode)) {
-		/* unset promiscuity level from slave */
-		if (bond_dev->flags & IFF_PROMISC)
+		/* unset promiscuity level from slave
+		 * NOTE: The NETDEV_CHANGEADDR call above may change the value
+		 * of the IFF_PROMISC flag in the bond_dev, but we need the
+		 * value of that flag before that change, as that was the value
+		 * when this slave was attached, so we cache at the start of the
+		 * function and use it here. Same goes for ALLMULTI below
+		 */
+		if (old_flags & IFF_PROMISC)
 			dev_set_promiscuity(slave_dev, -1);
 
 		/* unset allmulti level from slave */
-		if (bond_dev->flags & IFF_ALLMULTI)
+		if (old_flags & IFF_ALLMULTI)
 			dev_set_allmulti(slave_dev, -1);
 
 		/* flush master's mc_list from slave */
@@ -4988,6 +4995,7 @@ static int __init bonding_init(void)
 out:
 	return res;
 err:
+	bond_destroy_debugfs();
 	rtnl_link_unregister(&bond_link_ops);
 err_link:
 	unregister_pernet_subsys(&bond_net_ops);
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index d7434e0a610e..a88d04b3a77a 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -537,8 +537,9 @@ static ssize_t bonding_store_arp_interval(struct device *d,
 		goto out;
 	}
 	if (bond->params.mode == BOND_MODE_ALB ||
-	    bond->params.mode == BOND_MODE_TLB) {
-		pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
+	    bond->params.mode == BOND_MODE_TLB ||
+	    bond->params.mode == BOND_MODE_8023AD) {
+		pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
 			bond->dev->name, bond->dev->name);
 		ret = -EINVAL;
 		goto out;
@@ -696,6 +697,8 @@ static ssize_t bonding_store_downdelay(struct device *d,
 	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
 	if (!(bond->params.miimon)) {
 		pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
 		       bond->dev->name);
@@ -729,6 +732,7 @@ static ssize_t bonding_store_downdelay(struct device *d,
 	}
 
 out:
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,
@@ -751,6 +755,8 @@ static ssize_t bonding_store_updelay(struct device *d,
 	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
 	if (!(bond->params.miimon)) {
 		pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
 		       bond->dev->name);
@@ -784,6 +790,7 @@ static ssize_t bonding_store_updelay(struct device *d,
 	}
 
 out:
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index db52f4414def..535d5dd8d816 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -1409,10 +1409,10 @@ static int at91_can_remove(struct platform_device *pdev)
 
 static const struct platform_device_id at91_can_id_table[] = {
 	{
-		.name = "at91_can",
+		.name = "at91sam9x5_can",
 		.driver_data = (kernel_ulong_t)&at91_at91sam9x5_data,
 	}, {
-		.name = "at91sam9x5_can",
+		.name = "at91_can",
 		.driver_data = (kernel_ulong_t)&at91_at91sam9263_data,
 	}, {
 		/* sentinel */
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index a668cd491cb3..e59c42b446a9 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -712,22 +712,31 @@ static int c_can_set_mode(struct net_device *dev, enum can_mode mode)
 	return 0;
 }
 
-static int c_can_get_berr_counter(const struct net_device *dev,
-					struct can_berr_counter *bec)
+static int __c_can_get_berr_counter(const struct net_device *dev,
+				    struct can_berr_counter *bec)
 {
 	unsigned int reg_err_counter;
 	struct c_can_priv *priv = netdev_priv(dev);
 
-	c_can_pm_runtime_get_sync(priv);
-
 	reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
 	bec->rxerr = (reg_err_counter & ERR_CNT_REC_MASK) >>
 				ERR_CNT_REC_SHIFT;
 	bec->txerr = reg_err_counter & ERR_CNT_TEC_MASK;
 
+	return 0;
+}
+
+static int c_can_get_berr_counter(const struct net_device *dev,
+				  struct can_berr_counter *bec)
+{
+	struct c_can_priv *priv = netdev_priv(dev);
+	int err;
+
+	c_can_pm_runtime_get_sync(priv);
+	err = __c_can_get_berr_counter(dev, bec);
 	c_can_pm_runtime_put_sync(priv);
 
-	return 0;
+	return err;
 }
 
 /*
@@ -814,9 +823,6 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota)
 			msg_ctrl_save = priv->read_reg(priv,
 					C_CAN_IFACE(MSGCTRL_REG, 0));
 
-			if (msg_ctrl_save & IF_MCONT_EOB)
-				return num_rx_pkts;
-
 			if (msg_ctrl_save & IF_MCONT_MSGLST) {
 				c_can_handle_lost_msg_obj(dev, 0, msg_obj);
 				num_rx_pkts++;
@@ -824,6 +830,9 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota)
 				continue;
 			}
 
+			if (msg_ctrl_save & IF_MCONT_EOB)
+				return num_rx_pkts;
+
 			if (!(msg_ctrl_save & IF_MCONT_NEWDAT))
 				continue;
 
@@ -872,7 +881,7 @@ static int c_can_handle_state_change(struct net_device *dev,
 	if (unlikely(!skb))
 		return 0;
 
-	c_can_get_berr_counter(dev, &bec);
+	__c_can_get_berr_counter(dev, &bec);
 	reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
 	rx_err_passive = (reg_err_counter & ERR_CNT_RP_MASK) >>
 				ERR_CNT_RP_SHIFT;
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index f9cba4123c66..9bf47a064cdf 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -324,19 +324,10 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (!priv->echo_skb[idx]) {
-		struct sock *srcsk = skb->sk;
 
-		if (atomic_read(&skb->users) != 1) {
-			struct sk_buff *old_skb = skb;
-
-			skb = skb_clone(old_skb, GFP_ATOMIC);
-			kfree_skb(old_skb);
-			if (!skb)
-				return;
-		} else
-			skb_orphan(skb);
-
-		skb->sk = srcsk;
+		skb = can_create_echo_skb(skb);
+		if (!skb)
+			return;
 
 		/* make settings for echo to reduce code in irq context */
 		skb->protocol = htons(ETH_P_CAN);
@@ -394,7 +385,7 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx)
 	BUG_ON(idx >= priv->echo_skb_max);
 
 	if (priv->echo_skb[idx]) {
-		kfree_skb(priv->echo_skb[idx]);
+		dev_kfree_skb_any(priv->echo_skb[idx]);
 		priv->echo_skb[idx] = NULL;
 	}
 }
@@ -705,14 +696,14 @@ static size_t can_get_size(const struct net_device *dev)
 	size_t size;
 
 	size = nla_total_size(sizeof(u32));   /* IFLA_CAN_STATE */
-	size += sizeof(struct can_ctrlmode);  /* IFLA_CAN_CTRLMODE */
+	size += nla_total_size(sizeof(struct can_ctrlmode));  /* IFLA_CAN_CTRLMODE */
 	size += nla_total_size(sizeof(u32));  /* IFLA_CAN_RESTART_MS */
-	size += sizeof(struct can_bittiming); /* IFLA_CAN_BITTIMING */
-	size += sizeof(struct can_clock);     /* IFLA_CAN_CLOCK */
+	size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */
+	size += nla_total_size(sizeof(struct can_clock));     /* IFLA_CAN_CLOCK */
 	if (priv->do_get_berr_counter)        /* IFLA_CAN_BERR_COUNTER */
-		size += sizeof(struct can_berr_counter);
+		size += nla_total_size(sizeof(struct can_berr_counter));
 	if (priv->bittiming_const)	      /* IFLA_CAN_BITTIMING_CONST */
-		size += sizeof(struct can_bittiming_const);
+		size += nla_total_size(sizeof(struct can_bittiming_const));
 
 	return size;
 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 769d29ed106d..6d388cff8455 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -63,7 +63,7 @@
 #define FLEXCAN_MCR_BCC			BIT(16)
 #define FLEXCAN_MCR_LPRIO_EN		BIT(13)
 #define FLEXCAN_MCR_AEN			BIT(12)
-#define FLEXCAN_MCR_MAXMB(x)		((x) & 0xf)
+#define FLEXCAN_MCR_MAXMB(x)		((x) & 0x1f)
 #define FLEXCAN_MCR_IDAM_A		(0 << 8)
 #define FLEXCAN_MCR_IDAM_B		(1 << 8)
 #define FLEXCAN_MCR_IDAM_C		(2 << 8)
@@ -711,7 +711,6 @@ static int flexcan_chip_start(struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct flexcan_regs __iomem *regs = priv->base;
-	unsigned int i;
 	int err;
 	u32 reg_mcr, reg_ctrl;
 
@@ -745,9 +744,11 @@ static int flexcan_chip_start(struct net_device *dev)
 	 *
 	 */
 	reg_mcr = flexcan_read(&regs->mcr);
+	reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
 	reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_FEN | FLEXCAN_MCR_HALT |
 		FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN |
-		FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS;
+		FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS |
+		FLEXCAN_MCR_MAXMB(FLEXCAN_TX_BUF_ID);
 	netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr);
 	flexcan_write(reg_mcr, &regs->mcr);
 
@@ -781,16 +782,9 @@ static int flexcan_chip_start(struct net_device *dev)
 	netdev_dbg(dev, "%s: writing ctrl=0x%08x", __func__, reg_ctrl);
 	flexcan_write(reg_ctrl, &regs->ctrl);
 
-	for (i = 0; i < ARRAY_SIZE(regs->cantxfg); i++) {
-		flexcan_write(0, &regs->cantxfg[i].can_ctrl);
-		flexcan_write(0, &regs->cantxfg[i].can_id);
-		flexcan_write(0, &regs->cantxfg[i].data[0]);
-		flexcan_write(0, &regs->cantxfg[i].data[1]);
-
-		/* put MB into rx queue */
-		flexcan_write(FLEXCAN_MB_CNT_CODE(0x4),
-			&regs->cantxfg[i].can_ctrl);
-	}
+	/* Abort any pending TX, mark Mailbox as INACTIVE */
+	flexcan_write(FLEXCAN_MB_CNT_CODE(0x4),
+		      &regs->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl);
 
 	/* acceptance mask/acceptance code (accept everything) */
 	flexcan_write(0x0, &regs->rxgmask);
@@ -868,7 +862,7 @@ static int flexcan_open(struct net_device *dev)
 	/* start chip and queuing */
 	err = flexcan_chip_start(dev);
 	if (err)
-		goto out_close;
+		goto out_free_irq;
 
 	can_led_event(dev, CAN_LED_EVENT_OPEN);
 
@@ -877,6 +871,8 @@ static int flexcan_open(struct net_device *dev)
 
 	return 0;
 
+ out_free_irq:
+	free_irq(dev->irq, dev);
  out_close:
 	close_candev(dev);
  out:
@@ -983,9 +979,9 @@ static void unregister_flexcandev(struct net_device *dev)
 }
 
 static const struct of_device_id flexcan_of_match[] = {
-	{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
-	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
 	{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
+	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
+	{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index c4bc1d2e2033..b08383f485a5 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -19,6 +19,7 @@
 #include <linux/netdevice.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
+#include <linux/can/skb.h>
 #include <linux/can/error.h>
 
 #include <linux/mfd/janz.h>
@@ -1134,20 +1135,9 @@ static void ican3_handle_message(struct ican3_dev *mod, struct ican3_msg *msg)
  */
 static void ican3_put_echo_skb(struct ican3_dev *mod, struct sk_buff *skb)
 {
-	struct sock *srcsk = skb->sk;
-
-	if (atomic_read(&skb->users) != 1) {
-		struct sk_buff *old_skb = skb;
-
-		skb = skb_clone(old_skb, GFP_ATOMIC);
-		kfree_skb(old_skb);
-		if (!skb)
-			return;
-	} else {
-		skb_orphan(skb);
-	}
-
-	skb->sk = srcsk;
+	skb = can_create_echo_skb(skb);
+	if (!skb)
+		return;
 
 	/* save this skb for tx interrupt echo handling */
 	skb_queue_tail(&mod->echoq, skb);
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 6b6f0ad75090..7042f5faddd7 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -551,7 +551,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct sja1000_priv *priv;
 	struct peak_pci_chan *chan;
-	struct net_device *dev;
+	struct net_device *dev, *prev_dev;
 	void __iomem *cfg_base, *reg_base;
 	u16 sub_sys_id, icr;
 	int i, err, channels;
@@ -687,11 +687,13 @@ failure_remove_channels:
 	writew(0x0, cfg_base + PITA_ICR + 2);
 
 	chan = NULL;
-	for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) {
-		unregister_sja1000dev(dev);
-		free_sja1000dev(dev);
+	for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) {
 		priv = netdev_priv(dev);
 		chan = priv->priv;
+		prev_dev = chan->prev_dev;
+
+		unregister_sja1000dev(dev);
+		free_sja1000dev(dev);
 	}
 
 	/* free any PCIeC resources too */
@@ -725,10 +727,12 @@ static void peak_pci_remove(struct pci_dev *pdev)
 
 	/* Loop over all registered devices */
 	while (1) {
+		struct net_device *prev_dev = chan->prev_dev;
+
 		dev_info(&pdev->dev, "removing device %s\n", dev->name);
 		unregister_sja1000dev(dev);
 		free_sja1000dev(dev);
-		dev = chan->prev_dev;
+		dev = prev_dev;
 
 		if (!dev) {
 			/* do that only for first channel */
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 7164a999f50f..f17c3018b7c7 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -494,20 +494,20 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 	uint8_t isrc, status;
 	int n = 0;
 
-	/* Shared interrupts and IRQ off? */
-	if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
-		return IRQ_NONE;
-
 	if (priv->pre_irq)
 		priv->pre_irq(priv);
 
+	/* Shared interrupts and IRQ off? */
+	if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
+		goto out;
+
 	while ((isrc = priv->read_reg(priv, SJA1000_IR)) &&
 	       (n < SJA1000_MAX_IRQ)) {
-		n++;
+
 		status = priv->read_reg(priv, SJA1000_SR);
 		/* check for absent controller due to hw unplug */
 		if (status == 0xFF && sja1000_is_absent(priv))
-			return IRQ_NONE;
+			goto out;
 
 		if (isrc & IRQ_WUI)
 			netdev_warn(dev, "wakeup interrupt\n");
@@ -535,7 +535,7 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 				status = priv->read_reg(priv, SJA1000_SR);
 				/* check for absent controller */
 				if (status == 0xFF && sja1000_is_absent(priv))
-					return IRQ_NONE;
+					goto out;
 			}
 		}
 		if (isrc & (IRQ_DOI | IRQ_EI | IRQ_BEI | IRQ_EPI | IRQ_ALI)) {
@@ -543,8 +543,9 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 			if (sja1000_err(dev, isrc, status))
 				break;
 		}
+		n++;
 	}
-
+out:
 	if (priv->post_irq)
 		priv->post_irq(priv);
 
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 6aa7b3266c80..d5455c760618 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -1132,6 +1132,7 @@ static void esd_usb2_disconnect(struct usb_interface *intf)
 			}
 		}
 		unlink_all_urbs(dev);
+		kfree(dev);
 	}
 }
 
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 3b9546588240..cc3df8aebb87 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -474,6 +474,8 @@ static int kvaser_usb_get_card_info(struct kvaser_usb *dev)
 		return err;
 
 	dev->nchannels = msg.u.cardinfo.nchannels;
+	if (dev->nchannels > MAX_NET_DEVICES)
+		return -EINVAL;
 
 	return 0;
 }
@@ -1544,9 +1546,9 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 	return 0;
 }
 
-static void kvaser_usb_get_endpoints(const struct usb_interface *intf,
-				     struct usb_endpoint_descriptor **in,
-				     struct usb_endpoint_descriptor **out)
+static int kvaser_usb_get_endpoints(const struct usb_interface *intf,
+				    struct usb_endpoint_descriptor **in,
+				    struct usb_endpoint_descriptor **out)
 {
 	const struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor *endpoint;
@@ -1557,12 +1559,18 @@ static void kvaser_usb_get_endpoints(const struct usb_interface *intf,
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
 
-		if (usb_endpoint_is_bulk_in(endpoint))
+		if (!*in && usb_endpoint_is_bulk_in(endpoint))
 			*in = endpoint;
 
-		if (usb_endpoint_is_bulk_out(endpoint))
+		if (!*out && usb_endpoint_is_bulk_out(endpoint))
 			*out = endpoint;
+
+		/* use first bulk endpoint for in and out */
+		if (*in && *out)
+			return 0;
 	}
+
+	return -ENODEV;
 }
 
 static int kvaser_usb_probe(struct usb_interface *intf,
@@ -1576,8 +1584,8 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	if (!dev)
 		return -ENOMEM;
 
-	kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
-	if (!dev->bulk_in || !dev->bulk_out) {
+	err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
+	if (err) {
 		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
 		return err;
 	}
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index a0f647f92bf5..3a220d2f2ee1 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -727,7 +727,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
 	if (!dev->cmd_buf) {
 		err = -ENOMEM;
-		goto lbl_set_intf_data;
+		goto lbl_free_candev;
 	}
 
 	dev->udev = usb_dev;
@@ -766,7 +766,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	err = register_candev(netdev);
 	if (err) {
 		dev_err(&intf->dev, "couldn't register CAN device: %d\n", err);
-		goto lbl_free_cmd_buf;
+		goto lbl_restore_intf_data;
 	}
 
 	if (dev->prev_siblings)
@@ -779,14 +779,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	if (dev->adapter->dev_init) {
 		err = dev->adapter->dev_init(dev);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* set bus off */
 	if (dev->adapter->dev_set_bus) {
 		err = dev->adapter->dev_set_bus(dev, 0);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* get device number early */
@@ -798,11 +798,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 
 	return 0;
 
-lbl_free_cmd_buf:
-	kfree(dev->cmd_buf);
+lbl_unregister_candev:
+	unregister_candev(netdev);
 
-lbl_set_intf_data:
+lbl_restore_intf_data:
 	usb_set_intfdata(intf, dev->prev_siblings);
+	kfree(dev->cmd_buf);
+
+lbl_free_candev:
 	free_candev(netdev);
 
 	return err;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 8ee9d1556e6e..f7f796a2c50b 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -333,8 +333,6 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	if (!(dev->state & PCAN_USB_STATE_CONNECTED))
 		return 0;
 
-	memset(req_addr, '\0', req_size);
-
 	req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER;
 
 	switch (req_id) {
@@ -345,6 +343,7 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	default:
 		p = usb_rcvctrlpipe(dev->udev, 0);
 		req_type |= USB_DIR_IN;
+		memset(req_addr, '\0', req_size);
 		break;
 	}
 
@@ -927,6 +926,9 @@ static int pcan_usb_pro_init(struct peak_usb_device *dev)
 	/* set LED in default state (end of init phase) */
 	pcan_usb_pro_set_led(dev, 0, 1);
 
+	kfree(bi);
+	kfree(fi);
+
 	return 0;
 
  err_out:
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 0a2a5ee79a17..4e94057ef5cf 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -46,6 +46,7 @@
 #include <linux/if_ether.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
+#include <linux/can/skb.h>
 #include <linux/slab.h>
 #include <net/rtnetlink.h>
 
@@ -109,25 +110,23 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev)
 			stats->rx_packets++;
 			stats->rx_bytes += cfd->len;
 		}
-		kfree_skb(skb);
+		consume_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
 	/* perform standard echo handling for CAN network interfaces */
 
 	if (loop) {
-		struct sock *srcsk = skb->sk;
 
-		skb = skb_share_check(skb, GFP_ATOMIC);
+		skb = can_create_echo_skb(skb);
 		if (!skb)
 			return NETDEV_TX_OK;
 
 		/* receive with packet counting */
-		skb->sk = srcsk;
 		vcan_rx(skb, dev);
 	} else {
 		/* no looped packets => no counting */
-		kfree_skb(skb);
+		consume_skb(skb);
 	}
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index eec0af45b859..1c6bc9678774 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -908,7 +908,7 @@ static void bgmac_chip_reset(struct bgmac *bgmac)
 		struct bcma_drv_cc *cc = &bgmac->core->bus->drv_cc;
 		u8 et_swtype = 0;
 		u8 sw_type = BGMAC_CHIPCTL_1_SW_TYPE_EPHY |
-			     BGMAC_CHIPCTL_1_IF_TYPE_RMII;
+			     BGMAC_CHIPCTL_1_IF_TYPE_MII;
 		char buf[2];
 
 		if (bcm47xx_nvram_getenv("et_swtype", buf, 1) > 0) {
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 98d4b5fcc070..12a35cf9bb81 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -333,7 +333,7 @@
 
 #define BGMAC_CHIPCTL_1_IF_TYPE_MASK		0x00000030
 #define BGMAC_CHIPCTL_1_IF_TYPE_RMII		0x00000000
-#define BGMAC_CHIPCTL_1_IF_TYPE_MI		0x00000010
+#define BGMAC_CHIPCTL_1_IF_TYPE_MII		0x00000010
 #define BGMAC_CHIPCTL_1_IF_TYPE_RGMII		0x00000020
 #define BGMAC_CHIPCTL_1_SW_TYPE_MASK		0x000000C0
 #define BGMAC_CHIPCTL_1_SW_TYPE_EPHY		0x00000000
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 3dba2a70a00e..ec86177be1df 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -312,6 +312,7 @@ struct sw_tx_bd {
 	u8		flags;
 /* Set on the first BD descriptor when there is a split BD */
 #define BNX2X_TSO_SPLIT_BD		(1<<0)
+#define BNX2X_HAS_SECOND_PBD		(1<<1)
 };
 
 struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 638e55435b04..372a7557e1fa 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -153,6 +153,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	struct sk_buff *skb = tx_buf->skb;
 	u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons;
 	int nbd;
+	u16 split_bd_len = 0;
 
 	/* prefetch skb end pointer to speedup dev_kfree_skb() */
 	prefetch(&skb->end);
@@ -160,10 +161,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	DP(NETIF_MSG_TX_DONE, "fp[%d]: pkt_idx %d  buff @(%p)->skb %p\n",
 	   txdata->txq_index, idx, tx_buf, skb);
 
-	/* unmap first bd */
 	tx_start_bd = &txdata->tx_desc_ring[bd_idx].start_bd;
-	dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
-			 BD_UNMAP_LEN(tx_start_bd), DMA_TO_DEVICE);
 
 
 	nbd = le16_to_cpu(tx_start_bd->nbd) - 1;
@@ -182,12 +180,25 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	--nbd;
 	bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 
-	/* ...and the TSO split header bd since they have no mapping */
+	if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+		/* Skip second parse bd... */
+		--nbd;
+		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+	}
+
+	/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
 	if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
+		tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
+		split_bd_len = BD_UNMAP_LEN(tx_data_bd);
 		--nbd;
 		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 	}
 
+	/* unmap first bd */
+	dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
+			 BD_UNMAP_LEN(tx_start_bd) + split_bd_len,
+			 DMA_TO_DEVICE);
+
 	/* now free frags */
 	while (nbd > 0) {
 
@@ -670,6 +681,7 @@ static void bnx2x_gro_receive(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 		}
 	}
 #endif
+	skb_record_rx_queue(skb, fp->rx_queue);
 	napi_gro_receive(&fp->napi, skb);
 }
 
@@ -739,7 +751,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 		return;
 	}
-	bnx2x_frag_free(fp, new_data);
+	if (new_data)
+		bnx2x_frag_free(fp, new_data);
 drop:
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
@@ -3748,6 +3761,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			/* set encapsulation flag in start BD */
 			SET_FLAG(tx_start_bd->general_data,
 				 ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+			tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
 			nbd++;
 		} else if (xmit_type & XMIT_CSUM) {
 			/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 32a9609cc98b..fd50781e996c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -1038,9 +1038,6 @@ static void bnx2x_set_one_vlan_mac_e1h(struct bnx2x *bp,
 				     ETH_VLAN_FILTER_CLASSIFY, config);
 }
 
-#define list_next_entry(pos, member) \
-	list_entry((pos)->member.next, typeof(*(pos)), member)
-
 /**
  * bnx2x_vlan_mac_restore - reconfigure next MAC/VLAN/VLAN-MAC element
  *
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 0877a052e3ee..5501cad30cfa 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6687,8 +6687,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 
 		work_mask |= opaque_key;
 
-		if ((desc->err_vlan & RXD_ERR_MASK) != 0 &&
-		    (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) {
+		if (desc->err_vlan & RXD_ERR_MASK) {
 		drop_it:
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
@@ -6722,12 +6721,6 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 			pci_unmap_single(tp->pdev, dma_addr, skb_size,
 					 PCI_DMA_FROMDEVICE);
 
-			skb = build_skb(data, frag_size);
-			if (!skb) {
-				tg3_frag_free(frag_size != 0, data);
-				goto drop_it_no_recycle;
-			}
-			skb_reserve(skb, TG3_RX_OFFSET(tp));
 			/* Ensure that the update to the data happens
 			 * after the usage of the old DMA mapping.
 			 */
@@ -6735,6 +6728,12 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 
 			ri->data = NULL;
 
+			skb = build_skb(data, frag_size);
+			if (!skb) {
+				tg3_frag_free(frag_size != 0, data);
+				goto drop_it_no_recycle;
+			}
+			skb_reserve(skb, TG3_RX_OFFSET(tp));
 		} else {
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
@@ -6768,7 +6767,8 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 		skb->protocol = eth_type_trans(skb, tp->dev);
 
 		if (len > (tp->dev->mtu + ETH_HLEN) &&
-		    skb->protocol != htons(ETH_P_8021Q)) {
+		    skb->protocol != htons(ETH_P_8021Q) &&
+		    skb->protocol != htons(ETH_P_8021AD)) {
 			dev_kfree_skb(skb);
 			goto drop_it_no_recycle;
 		}
@@ -7482,7 +7482,7 @@ static inline int tg3_4g_overflow_test(dma_addr_t mapping, int len)
 {
 	u32 base = (u32) mapping & 0xffffffff;
 
-	return (base > 0xffffdcc0) && (base + len + 8 < base);
+	return base + len + 8 < base;
 }
 
 /* Test for TSO DMA buffers that cross into regions which are within MSS bytes
@@ -7760,8 +7760,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	entry = tnapi->tx_prod;
 	base_flags = 0;
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		base_flags |= TXD_FLAG_TCPUDP_CSUM;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
@@ -7777,6 +7775,13 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN;
 
+		/* HW/FW can not correctly segment packets that have been
+		 * vlan encapsulated.
+		 */
+		if (skb->protocol == htons(ETH_P_8021Q) ||
+		    skb->protocol == htons(ETH_P_8021AD))
+			return tg3_tso_bug(tp, skb);
+
 		if (!skb_is_gso_v6(skb)) {
 			iph->check = 0;
 			iph->tot_len = htons(mss + hdr_len);
@@ -7823,6 +7828,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				base_flags |= tsflags << 12;
 			}
 		}
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		/* HW/FW can not correctly checksum packets that have been
+		 * vlan encapsulated.
+		 */
+		if (skb->protocol == htons(ETH_P_8021Q) ||
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (skb_checksum_help(skb))
+				goto drop;
+		} else  {
+			base_flags |= TXD_FLAG_TCPUDP_CSUM;
+		}
 	}
 
 	if (tg3_flag(tp, USE_JUMBO_BDFLAG) &&
@@ -8376,7 +8392,8 @@ static int tg3_init_rings(struct tg3 *tp)
 		if (tnapi->rx_rcb)
 			memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
 
-		if (tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
+		if (tnapi->prodring.rx_std &&
+		    tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
 			tg3_free_rings(tp);
 			return -ENOMEM;
 		}
@@ -12074,7 +12091,9 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 	if (tg3_flag(tp, MAX_RXPEND_64) &&
 	    tp->rx_pending > 63)
 		tp->rx_pending = 63;
-	tp->rx_jumbo_pending = ering->rx_jumbo_pending;
+
+	if (tg3_flag(tp, JUMBO_RING_ENABLE))
+		tp->rx_jumbo_pending = ering->rx_jumbo_pending;
 
 	for (i = 0; i < tp->irq_max; i++)
 		tp->napi[i].tx_pending = ering->tx_pending;
@@ -13777,12 +13796,12 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 
 	tg3_netif_stop(tp);
 
+	tg3_set_mtu(dev, tp, new_mtu);
+
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
 
-	tg3_set_mtu(dev, tp, new_mtu);
-
 	/* Reset PHY, otherwise the read DMA engine will be in a mode that
 	 * breaks all requests to 256 bytes.
 	 */
@@ -16297,6 +16316,9 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 	/* Clear this out for sanity. */
 	tw32(TG3PCI_MEM_WIN_BASE_ADDR, 0);
 
+	/* Clear TG3PCI_REG_BASE_ADDR to prevent hangs. */
+	tw32(TG3PCI_REG_BASE_ADDR, 0);
+
 	pci_read_config_dword(tp->pdev, TG3PCI_PCISTATE,
 			      &pci_state_reg);
 	if ((pci_state_reg & PCISTATE_CONV_PCI_MODE) == 0 &&
@@ -17306,8 +17328,6 @@ static int tg3_init_one(struct pci_dev *pdev,
 
 	tg3_init_bufmgr_config(tp);
 
-	features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
 	/* 5700 B0 chips do not support checksumming correctly due
 	 * to hardware bugs.
 	 */
@@ -17339,7 +17359,8 @@ static int tg3_init_one(struct pci_dev *pdev,
 			features |= NETIF_F_TSO_ECN;
 	}
 
-	dev->features |= features;
+	dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features |= features;
 
 	/*
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ff6e30eeae35..046059c56713 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2587,7 +2587,11 @@ struct tg3_rx_buffer_desc {
 #define RXD_ERR_TOO_SMALL		0x00400000
 #define RXD_ERR_NO_RESOURCES		0x00800000
 #define RXD_ERR_HUGE_FRAME		0x01000000
-#define RXD_ERR_MASK			0xffff0000
+
+#define RXD_ERR_MASK	(RXD_ERR_BAD_CRC | RXD_ERR_COLLISION |		\
+			 RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE |	\
+			 RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL |		\
+			 RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME)
 
 	u32				reserved;
 	u32				opaque;
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index f12e6b85a653..f057a189d975 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -1600,7 +1600,8 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 	flits = skb_transport_offset(skb) / 8;
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
 	sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
-			     skb->tail - skb->transport_header,
+			     skb_tail_pointer(skb) -
+			     skb_transport_header(skb),
 			     adap->pdev);
 	if (need_skb_unmap()) {
 		setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 1db2df61b8af..696674edbdc4 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1150,7 +1150,6 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo)
 
 	if (lancer_chip(adapter)) {
 		req->hdr.version = 1;
-		req->if_id = cpu_to_le16(adapter->if_handle);
 	} else if (BEx_chip(adapter)) {
 		if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC)
 			req->hdr.version = 2;
@@ -1158,6 +1157,8 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo)
 		req->hdr.version = 2;
 	}
 
+	if (req->hdr.version > 0)
+		req->if_id = cpu_to_le16(adapter->if_handle);
 	req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size);
 	req->ulp_num = BE_ULP1_NUM;
 	req->type = BE_ETH_TX_RING_TYPE_STANDARD;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 7371626c56a1..d81a7dbfeef6 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2663,7 +2663,7 @@ static int be_open(struct net_device *netdev)
 
 	for_all_evt_queues(adapter, eqo, i) {
 		napi_enable(&eqo->napi);
-		be_eq_notify(adapter, eqo->q.id, true, false, 0);
+		be_eq_notify(adapter, eqo->q.id, true, true, 0);
 	}
 	adapter->flags |= BE_FLAGS_NAPI_ENABLED;
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d48099f03b7f..fbd0d7df67d8 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -371,6 +371,8 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	else
 		bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
 
+	skb_tx_timestamp(skb);
+
 	fep->cur_tx = bdp;
 
 	if (fep->cur_tx == fep->dirty_tx)
@@ -379,8 +381,6 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* Trigger transmission start */
 	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
 
-	skb_tx_timestamp(skb);
-
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 90ea0b1673ca..716dae7b9d8e 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3023,7 +3023,7 @@ static struct ehea_port *ehea_setup_single_port(struct ehea_adapter *adapter,
 
 	dev->hw_features = NETIF_F_SG | NETIF_F_TSO |
 		      NETIF_F_IP_CSUM | NETIF_F_HW_VLAN_CTAG_TX;
-	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_TSO |
+	dev->features = NETIF_F_SG | NETIF_F_TSO |
 		      NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
 		      NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 		      NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 70fd55968844..040ecf2027cd 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -293,6 +293,18 @@ failure:
 	atomic_add(buffers_added, &(pool->available));
 }
 
+/*
+ * The final 8 bytes of the buffer list is a counter of frames dropped
+ * because there was not a buffer in the buffer list capable of holding
+ * the frame.
+ */
+static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
+{
+	__be64 *p = adapter->buffer_list_addr + 4096 - 8;
+
+	adapter->rx_no_buffer = be64_to_cpup(p);
+}
+
 /* replenish routine */
 static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
 {
@@ -308,8 +320,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
 			ibmveth_replenish_buffer_pool(adapter, pool);
 	}
 
-	adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) +
-						4096 - 8);
+	ibmveth_update_rx_no_buffer(adapter);
 }
 
 /* empty and free ana buffer pool - also used to do cleanup in error paths */
@@ -689,8 +700,7 @@ static int ibmveth_close(struct net_device *netdev)
 
 	free_irq(netdev->irq, netdev);
 
-	adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) +
-						4096 - 8);
+	ibmveth_update_rx_no_buffer(adapter);
 
 	ibmveth_cleanup(adapter);
 
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index d2bea3f07c73..69d3f59f8728 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3039,7 +3039,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake)
 		*enable_wake = false;
 	}
 
-	pci_disable_device(pdev);
+	pci_clear_master(pdev);
 }
 
 static int __e100_power_off(struct pci_dev *pdev, bool wake)
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 59c76a6815a0..be4d7c1e3c14 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1757,19 +1757,23 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 		 * it across the board.
 		 */
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
-		if (ret_val)
+		if (ret_val) {
 			/* If the first read fails, another entity may have
 			 * ownership of the resources, wait and try again to
 			 * see if they have relinquished the resources yet.
 			 */
-			udelay(usec_interval);
+			if (usec_interval >= 1000)
+				msleep(usec_interval / 1000);
+			else
+				udelay(usec_interval);
+		}
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
 		if (ret_val)
 			break;
 		if (phy_status & BMSR_LSTATUS)
 			break;
 		if (usec_interval >= 1000)
-			mdelay(usec_interval / 1000);
+			msleep(usec_interval / 1000);
 		else
 			udelay(usec_interval);
 	}
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 115b0da6e013..5dec66a96793 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1595,7 +1595,10 @@ s32 igb_phy_has_link(struct e1000_hw *hw, u32 iterations,
 			 * ownership of the resources, wait and try again to
 			 * see if they have relinquished the resources yet.
 			 */
-			udelay(usec_interval);
+			if (usec_interval >= 1000)
+				mdelay(usec_interval/1000);
+			else
+				udelay(usec_interval);
 		}
 		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
 		if (ret_val)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 64cbe0dfe043..3f342fbe9ccf 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1584,6 +1584,8 @@ void igb_power_up_link(struct igb_adapter *adapter)
 		igb_power_up_phy_copper(&adapter->hw);
 	else
 		igb_power_up_serdes_link_82575(&adapter->hw);
+
+	igb_setup_link(&adapter->hw);
 }
 
 /**
@@ -7229,6 +7231,8 @@ static int igb_sriov_reinit(struct pci_dev *dev)
 
 	if (netif_running(netdev))
 		igb_close(netdev);
+	else
+		igb_reset(adapter);
 
 	igb_clear_interrupt_scheme(adapter);
 
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index d1cbfb12c1ca..4be11ff516a0 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1125,15 +1125,13 @@ static void mib_counters_update(struct mv643xx_eth_private *mp)
 	p->rx_discard += rdlp(mp, RX_DISCARD_FRAME_CNT);
 	p->rx_overrun += rdlp(mp, RX_OVERRUN_FRAME_CNT);
 	spin_unlock_bh(&mp->mib_counters_lock);
-
-	mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
 }
 
 static void mib_counters_timer_wrapper(unsigned long _mp)
 {
 	struct mv643xx_eth_private *mp = (void *)_mp;
-
 	mib_counters_update(mp);
+	mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
 }
 
 
@@ -2231,6 +2229,7 @@ static int mv643xx_eth_open(struct net_device *dev)
 		mp->int_mask |= INT_TX_END_0 << i;
 	}
 
+	add_timer(&mp->mib_counters_timer);
 	port_start(mp);
 
 	wrlp(mp, INT_MASK_EXT, INT_EXT_LINK_PHY | INT_EXT_TX);
@@ -2739,7 +2738,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	mp->mib_counters_timer.data = (unsigned long)mp;
 	mp->mib_counters_timer.function = mib_counters_timer_wrapper;
 	mp->mib_counters_timer.expires = jiffies + 30 * HZ;
-	add_timer(&mp->mib_counters_timer);
 
 	spin_lock_init(&mp->mib_counters_lock);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 254f255204f9..8b6c9237eda4 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -99,16 +99,56 @@
 #define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
 #define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
 #define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))
+
+/* Exception Interrupt Port/Queue Cause register */
+
 #define MVNETA_INTR_NEW_CAUSE                    0x25a0
-#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
 #define MVNETA_INTR_NEW_MASK                     0x25a4
+
+/* bits  0..7  = TXQ SENT, one bit per queue.
+ * bits  8..15 = RXQ OCCUP, one bit per queue.
+ * bits 16..23 = RXQ FREE, one bit per queue.
+ * bit  29 = OLD_REG_SUM, see old reg ?
+ * bit  30 = TX_ERR_SUM, one bit for 4 ports
+ * bit  31 = MISC_SUM,   one bit for 4 ports
+ */
+#define      MVNETA_TX_INTR_MASK(nr_txqs)        (((1 << nr_txqs) - 1) << 0)
+#define      MVNETA_TX_INTR_MASK_ALL             (0xff << 0)
+#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
+#define      MVNETA_RX_INTR_MASK_ALL             (0xff << 8)
+
 #define MVNETA_INTR_OLD_CAUSE                    0x25a8
 #define MVNETA_INTR_OLD_MASK                     0x25ac
+
+/* Data Path Port/Queue Cause Register */
 #define MVNETA_INTR_MISC_CAUSE                   0x25b0
 #define MVNETA_INTR_MISC_MASK                    0x25b4
+
+#define      MVNETA_CAUSE_PHY_STATUS_CHANGE      BIT(0)
+#define      MVNETA_CAUSE_LINK_CHANGE            BIT(1)
+#define      MVNETA_CAUSE_PTP                    BIT(4)
+
+#define      MVNETA_CAUSE_INTERNAL_ADDR_ERR      BIT(7)
+#define      MVNETA_CAUSE_RX_OVERRUN             BIT(8)
+#define      MVNETA_CAUSE_RX_CRC_ERROR           BIT(9)
+#define      MVNETA_CAUSE_RX_LARGE_PKT           BIT(10)
+#define      MVNETA_CAUSE_TX_UNDERUN             BIT(11)
+#define      MVNETA_CAUSE_PRBS_ERR               BIT(12)
+#define      MVNETA_CAUSE_PSC_SYNC_CHANGE        BIT(13)
+#define      MVNETA_CAUSE_SERDES_SYNC_ERR        BIT(14)
+
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT    16
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_ALL_MASK   (0xF << MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT)
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_MASK(pool) (1 << (MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT + (pool)))
+
+#define      MVNETA_CAUSE_TXQ_ERROR_SHIFT        24
+#define      MVNETA_CAUSE_TXQ_ERROR_ALL_MASK     (0xFF << MVNETA_CAUSE_TXQ_ERROR_SHIFT)
+#define      MVNETA_CAUSE_TXQ_ERROR_MASK(q)      (1 << (MVNETA_CAUSE_TXQ_ERROR_SHIFT + (q)))
+
 #define MVNETA_INTR_ENABLE                       0x25b8
 #define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
-#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000  // note: neta says it's 0x000000FF
+
 #define MVNETA_RXQ_CMD                           0x2680
 #define      MVNETA_RXQ_DISABLE_SHIFT            8
 #define      MVNETA_RXQ_ENABLE_MASK              0x000000ff
@@ -119,7 +159,7 @@
 #define      MVNETA_GMAC_MAX_RX_SIZE_MASK        0x7ffc
 #define      MVNETA_GMAC0_PORT_ENABLE            BIT(0)
 #define MVNETA_GMAC_CTRL_2                       0x2c08
-#define      MVNETA_GMAC2_PSC_ENABLE             BIT(3)
+#define      MVNETA_GMAC2_PCS_ENABLE             BIT(3)
 #define      MVNETA_GMAC2_PORT_RGMII             BIT(4)
 #define      MVNETA_GMAC2_PORT_RESET             BIT(6)
 #define MVNETA_GMAC_STATUS                       0x2c10
@@ -170,13 +210,10 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		16
+#define MVNETA_TXDONE_COAL_PKTS		1
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
-/* Timer */
-#define MVNETA_TX_DONE_TIMER_PERIOD	10
-
 /* Napi polling weight */
 #define MVNETA_RX_POLL_WEIGHT		64
 
@@ -219,10 +256,12 @@
 
 #define MVNETA_RX_BUF_SIZE(pkt_size)   ((pkt_size) + NET_SKB_PAD)
 
-struct mvneta_stats {
+struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
-	u64	packets;
-	u64	bytes;
+	u64	rx_packets;
+	u64	rx_bytes;
+	u64	tx_packets;
+	u64	tx_bytes;
 };
 
 struct mvneta_port {
@@ -230,16 +269,11 @@ struct mvneta_port {
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
 	struct mvneta_tx_queue *txqs;
-	struct timer_list tx_done_timer;
 	struct net_device *dev;
 
 	u32 cause_rx_tx;
 	struct napi_struct napi;
 
-	/* Flags */
-	unsigned long flags;
-#define MVNETA_F_TX_DONE_TIMER_BIT  0
-
 	/* Napi weight */
 	int weight;
 
@@ -248,8 +282,7 @@ struct mvneta_port {
 	u8 mcast_count[256];
 	u16 tx_ring_size;
 	u16 rx_ring_size;
-	struct mvneta_stats tx_stats;
-	struct mvneta_stats rx_stats;
+	struct mvneta_pcpu_stats *stats;
 
 	struct mii_bus *mii_bus;
 	struct phy_device *phy_dev;
@@ -428,21 +461,29 @@ struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 	unsigned int start;
+	int cpu;
 
-	memset(stats, 0, sizeof(struct rtnl_link_stats64));
-
-	do {
-		start = u64_stats_fetch_begin_bh(&pp->rx_stats.syncp);
-		stats->rx_packets = pp->rx_stats.packets;
-		stats->rx_bytes	= pp->rx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&pp->rx_stats.syncp, start));
+	for_each_possible_cpu(cpu) {
+		struct mvneta_pcpu_stats *cpu_stats;
+		u64 rx_packets;
+		u64 rx_bytes;
+		u64 tx_packets;
+		u64 tx_bytes;
 
+		cpu_stats = per_cpu_ptr(pp->stats, cpu);
+		do {
+			start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+			rx_packets = cpu_stats->rx_packets;
+			rx_bytes   = cpu_stats->rx_bytes;
+			tx_packets = cpu_stats->tx_packets;
+			tx_bytes   = cpu_stats->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
 
-	do {
-		start = u64_stats_fetch_begin_bh(&pp->tx_stats.syncp);
-		stats->tx_packets = pp->tx_stats.packets;
-		stats->tx_bytes	= pp->tx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&pp->tx_stats.syncp, start));
+		stats->rx_packets += rx_packets;
+		stats->rx_bytes   += rx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_bytes   += tx_bytes;
+	}
 
 	stats->rx_errors	= dev->stats.rx_errors;
 	stats->rx_dropped	= dev->stats.rx_dropped;
@@ -655,7 +696,7 @@ static void mvneta_port_sgmii_config(struct mvneta_port *pp)
 	u32 val;
 
 	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-	val |= MVNETA_GMAC2_PSC_ENABLE;
+	val |= MVNETA_GMAC2_PCS_ENABLE;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
 }
 
@@ -1063,17 +1104,6 @@ static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp,
 	txq->done_pkts_coal = value;
 }
 
-/* Trigger tx done timer in MVNETA_TX_DONE_TIMER_PERIOD msecs */
-static void mvneta_add_tx_done_timer(struct mvneta_port *pp)
-{
-	if (test_and_set_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags) == 0) {
-		pp->tx_done_timer.expires = jiffies +
-			msecs_to_jiffies(MVNETA_TX_DONE_TIMER_PERIOD);
-		add_timer(&pp->tx_done_timer);
-	}
-}
-
-
 /* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
 static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
 				u32 phys_addr, u32 cookie)
@@ -1145,7 +1175,7 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 	command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
 	command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
 
-	if (l3_proto == swab16(ETH_P_IP))
+	if (l3_proto == htons(ETH_P_IP))
 		command |= MVNETA_TXD_IP_CSUM;
 	else
 		command |= MVNETA_TX_L3_IP6;
@@ -1354,6 +1384,8 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 {
 	struct net_device *dev = pp->dev;
 	int rx_done, rx_filled;
+	u32 rcvd_pkts = 0;
+	u32 rcvd_bytes = 0;
 
 	/* Get number of received packets */
 	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
@@ -1391,10 +1423,8 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 
 		rx_bytes = rx_desc->data_size -
 			(ETH_FCS_LEN + MVNETA_MH_SIZE);
-		u64_stats_update_begin(&pp->rx_stats.syncp);
-		pp->rx_stats.packets++;
-		pp->rx_stats.bytes += rx_bytes;
-		u64_stats_update_end(&pp->rx_stats.syncp);
+		rcvd_pkts++;
+		rcvd_bytes += rx_bytes;
 
 		/* Linux processing */
 		skb_reserve(skb, MVNETA_MH_SIZE);
@@ -1415,6 +1445,15 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		}
 	}
 
+	if (rcvd_pkts) {
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->rx_packets += rcvd_pkts;
+		stats->rx_bytes   += rcvd_bytes;
+		u64_stats_update_end(&stats->syncp);
+	}
+
 	/* Update rxq management counters */
 	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
 
@@ -1545,25 +1584,17 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 
 out:
 	if (frags > 0) {
-		u64_stats_update_begin(&pp->tx_stats.syncp);
-		pp->tx_stats.packets++;
-		pp->tx_stats.bytes += skb->len;
-		u64_stats_update_end(&pp->tx_stats.syncp);
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 
+		u64_stats_update_begin(&stats->syncp);
+		stats->tx_packets++;
+		stats->tx_bytes  += skb->len;
+		u64_stats_update_end(&stats->syncp);
 	} else {
 		dev->stats.tx_dropped++;
 		dev_kfree_skb_any(skb);
 	}
 
-	if (txq->count >= MVNETA_TXDONE_COAL_PKTS)
-		mvneta_txq_done(pp, txq);
-
-	/* If after calling mvneta_txq_done, count equals
-	 * frags, we need to set the timer
-	 */
-	if (txq->count == frags && frags > 0)
-		mvneta_add_tx_done_timer(pp);
-
 	return NETDEV_TX_OK;
 }
 
@@ -1839,14 +1870,22 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 
 	/* Read cause register */
 	cause_rx_tx = mvreg_read(pp, MVNETA_INTR_NEW_CAUSE) &
-		MVNETA_RX_INTR_MASK(rxq_number);
+		(MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
+
+	/* Release Tx descriptors */
+	if (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL) {
+		int tx_todo = 0;
+
+		mvneta_tx_done_gbe(pp, (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL), &tx_todo);
+		cause_rx_tx &= ~MVNETA_TX_INTR_MASK_ALL;
+	}
 
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
 	cause_rx_tx |= pp->cause_rx_tx;
 	if (rxq_number > 1) {
-		while ((cause_rx_tx != 0) && (budget > 0)) {
+		while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) {
 			int count;
 			struct mvneta_rx_queue *rxq;
 			/* get rx queue number from cause_rx_tx */
@@ -1878,7 +1917,7 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 		napi_complete(napi);
 		local_irq_save(flags);
 		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			    MVNETA_RX_INTR_MASK(rxq_number));
+			    MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
 		local_irq_restore(flags);
 	}
 
@@ -1886,26 +1925,6 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	return rx_done;
 }
 
-/* tx done timer callback */
-static void mvneta_tx_done_timer_callback(unsigned long data)
-{
-	struct net_device *dev = (struct net_device *)data;
-	struct mvneta_port *pp = netdev_priv(dev);
-	int tx_done = 0, tx_todo = 0;
-
-	if (!netif_running(dev))
-		return ;
-
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
-	tx_done = mvneta_tx_done_gbe(pp,
-				     (((1 << txq_number) - 1) &
-				      MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK),
-				     &tx_todo);
-	if (tx_todo > 0)
-		mvneta_add_tx_done_timer(pp);
-}
-
 /* Handle rxq fill: allocates rxq skbs; called when initializing a port */
 static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 			   int num)
@@ -2155,7 +2174,7 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	/* Unmask interrupts */
 	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-		    MVNETA_RX_INTR_MASK(rxq_number));
+		    MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
 
 	phy_start(pp->phy_dev);
 	netif_tx_start_all_queues(pp->dev);
@@ -2188,16 +2207,6 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 	mvneta_rx_reset(pp);
 }
 
-/* tx timeout callback - display a message and stop/start the network device */
-static void mvneta_tx_timeout(struct net_device *dev)
-{
-	struct mvneta_port *pp = netdev_priv(dev);
-
-	netdev_info(dev, "tx timeout\n");
-	mvneta_stop_dev(pp);
-	mvneta_start_dev(pp);
-}
-
 /* Return positive if MTU is valid */
 static int mvneta_check_mtu_valid(struct net_device *dev, int mtu)
 {
@@ -2306,7 +2315,7 @@ static void mvneta_adjust_link(struct net_device *ndev)
 
 			if (phydev->speed == SPEED_1000)
 				val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
-			else
+			else if (phydev->speed == SPEED_100)
 				val |= MVNETA_GMAC_CONFIG_MII_SPEED;
 
 			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
@@ -2426,8 +2435,6 @@ static int mvneta_stop(struct net_device *dev)
 	free_irq(dev->irq, pp);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
-	del_timer(&pp->tx_done_timer);
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
 
 	return 0;
 }
@@ -2548,7 +2555,6 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
-	.ndo_tx_timeout      = mvneta_tx_timeout,
 	.ndo_get_stats64     = mvneta_get_stats64,
 };
 
@@ -2729,10 +2735,6 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp = netdev_priv(dev);
 
-	pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
-	init_timer(&pp->tx_done_timer);
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
 	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
@@ -2751,7 +2753,12 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	clk_prepare_enable(pp->clk);
 
-	pp->tx_done_timer.data = (unsigned long)dev;
+	/* Alloc per-cpu stats */
+	pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
+	if (!pp->stats) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -2762,7 +2769,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = mvneta_init(pp, phy_addr);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't init eth hal\n");
-		goto err_clk;
+		goto err_free_stats;
 	}
 	mvneta_port_power_up(pp, phy_mode);
 
@@ -2791,6 +2798,8 @@ static int mvneta_probe(struct platform_device *pdev)
 
 err_deinit:
 	mvneta_deinit(pp);
+err_free_stats:
+	free_percpu(pp->stats);
 err_clk:
 	clk_disable_unprepare(pp->clk);
 err_unmap:
@@ -2811,6 +2820,7 @@ static int mvneta_remove(struct platform_device *pdev)
 	unregister_netdev(dev);
 	mvneta_deinit(pp);
 	clk_disable_unprepare(pp->clk);
+	free_percpu(pp->stats);
 	iounmap(pp->base);
 	irq_dispose_mapping(dev->irq);
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0e572a527154..28d706bd12eb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1544,7 +1544,7 @@ static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave
 			vp_oper->vlan_idx = NO_INDX;
 		}
 		if (NO_INDX != vp_oper->mac_idx) {
-			__mlx4_unregister_mac(&priv->dev, port, vp_oper->mac_idx);
+			__mlx4_unregister_mac(&priv->dev, port, vp_oper->state.mac);
 			vp_oper->mac_idx = NO_INDX;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1e6c594d6d04..58c18d3a4880 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -55,7 +55,6 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 
 	cq->ring = ring;
 	cq->is_tx = mode;
-	spin_lock_init(&cq->lock);
 
 	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
 				cq->buf_size, 2 * PAGE_SIZE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index a5c9df07a7d0..c72e214eb47c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -264,6 +264,10 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
 		mdev->port_cnt++;
 
+	/* Initialize time stamp mechanism */
+	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+		mlx4_en_init_timestamp(mdev);
+
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
 		if (!dev->caps.comp_pool) {
 			mdev->profile.prof[i].rx_ring_num =
@@ -301,10 +305,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 			mdev->pndev[i] = NULL;
 	}
 
-	/* Initialize time stamp mechanism */
-	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
-		mlx4_en_init_timestamp(mdev);
-
 	return mdev;
 
 err_mr:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 89c47ea84b50..063f3f4d4867 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1190,15 +1190,11 @@ static void mlx4_en_netpoll(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_cq *cq;
-	unsigned long flags;
 	int i;
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		cq = &priv->rx_cq[i];
-		spin_lock_irqsave(&cq->lock, flags);
-		napi_synchronize(&cq->napi);
-		mlx4_en_process_rx_cq(dev, cq, 0);
-		spin_unlock_irqrestore(&cq->lock, flags);
+		napi_schedule(&cq->napi);
 	}
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4e6877a032a8..bd8800c85525 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -191,6 +191,39 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
+			      struct mlx4_en_tx_ring *ring, int index,
+			      u8 owner)
+{
+	__be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
+	struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
+	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
+	void *end = ring->buf + ring->buf_size;
+	__be32 *ptr = (__be32 *)tx_desc;
+	int i;
+
+	/* Optimize the common case when there are no wraparounds */
+	if (likely((void *)tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
+		/* Stamp the freed descriptor */
+		for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+		     i += STAMP_STRIDE) {
+			*ptr = stamp;
+			ptr += STAMP_DWORDS;
+		}
+	} else {
+		/* Stamp the freed descriptor */
+		for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+		     i += STAMP_STRIDE) {
+			*ptr = stamp;
+			ptr += STAMP_DWORDS;
+			if ((void *)ptr >= end) {
+				ptr = ring->buf;
+				stamp ^= cpu_to_be32(0x80000000);
+			}
+		}
+	}
+}
+
 
 static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 				struct mlx4_en_tx_ring *ring,
@@ -205,8 +238,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	void *end = ring->buf + ring->buf_size;
 	int frags = skb_shinfo(skb)->nr_frags;
 	int i;
-	__be32 *ptr = (__be32 *)tx_desc;
-	__be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
 	struct skb_shared_hwtstamps hwts;
 
 	if (timestamp) {
@@ -232,12 +263,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 					skb_frag_size(frag), PCI_DMA_TODEVICE);
 			}
 		}
-		/* Stamp the freed descriptor */
-		for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
-			*ptr = stamp;
-			ptr += STAMP_DWORDS;
-		}
-
 	} else {
 		if (!tx_info->inl) {
 			if ((void *) data >= end) {
@@ -263,16 +288,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 				++data;
 			}
 		}
-		/* Stamp the freed descriptor */
-		for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
-			*ptr = stamp;
-			ptr += STAMP_DWORDS;
-			if ((void *) ptr >= end) {
-				ptr = ring->buf;
-				stamp ^= cpu_to_be32(0x80000000);
-			}
-		}
-
 	}
 	dev_kfree_skb_any(skb);
 	return tx_info->nr_txbb;
@@ -318,8 +333,9 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 	struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
 	struct mlx4_cqe *cqe;
 	u16 index;
-	u16 new_index, ring_index;
+	u16 new_index, ring_index, stamp_index;
 	u32 txbbs_skipped = 0;
+	u32 txbbs_stamp = 0;
 	u32 cons_index = mcq->cons_index;
 	int size = cq->size;
 	u32 size_mask = ring->size_mask;
@@ -335,6 +351,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 	index = cons_index & size_mask;
 	cqe = &buf[(index << factor) + factor];
 	ring_index = ring->cons & size_mask;
+	stamp_index = ring_index;
 
 	/* Process all completed CQEs */
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
@@ -359,6 +376,12 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 					priv, ring, ring_index,
 					!!((ring->cons + txbbs_skipped) &
 					ring->size), timestamp);
+
+			mlx4_en_stamp_wqe(priv, ring, stamp_index,
+					  !!((ring->cons + txbbs_stamp) &
+						ring->size));
+			stamp_index = ring_index;
+			txbbs_stamp = txbbs_skipped;
 			packets++;
 			bytes += ring->tx_info[ring_index].nr_bytes;
 		} while (ring_index != new_index);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 1b195fc7f411..3fb2643d05b4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2129,13 +2129,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	/* Allow large DMA segments, up to the firmware limit of 1 GB */
 	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
-
-	dev       = &priv->dev;
+	dev       = pci_get_drvdata(pdev);
+	priv      = mlx4_priv(dev);
 	dev->pdev = pdev;
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
@@ -2300,8 +2295,7 @@ slave_start:
 	mlx4_sense_init(dev);
 	mlx4_start_sense(dev);
 
-	priv->pci_dev_data = pci_dev_data;
-	pci_set_drvdata(pdev, dev);
+	priv->removed = 0;
 
 	return 0;
 
@@ -2367,84 +2361,110 @@ err_disable_pdev:
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct mlx4_priv *priv;
+	struct mlx4_dev *dev;
+
 	printk_once(KERN_INFO "%s", mlx4_version);
 
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev       = &priv->dev;
+	pci_set_drvdata(pdev, dev);
+	priv->pci_dev_data = id->driver_data;
+
 	return __mlx4_init_one(pdev, id->driver_data);
 }
 
-static void mlx4_remove_one(struct pci_dev *pdev)
+static void __mlx4_remove_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               pci_dev_data;
 	int p;
 
-	if (dev) {
-		/* in SRIOV it is not allowed to unload the pf's
-		 * driver while there are alive vf's */
-		if (mlx4_is_master(dev)) {
-			if (mlx4_how_many_lives_vf(dev))
-				printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
-		}
-		mlx4_stop_sense(dev);
-		mlx4_unregister_device(dev);
+	if (priv->removed)
+		return;
 
-		for (p = 1; p <= dev->caps.num_ports; p++) {
-			mlx4_cleanup_port_info(&priv->port[p]);
-			mlx4_CLOSE_PORT(dev, p);
-		}
+	pci_dev_data = priv->pci_dev_data;
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_SLAVES_ONLY);
-
-		mlx4_cleanup_counters_table(dev);
-		mlx4_cleanup_mcg_table(dev);
-		mlx4_cleanup_qp_table(dev);
-		mlx4_cleanup_srq_table(dev);
-		mlx4_cleanup_cq_table(dev);
-		mlx4_cmd_use_polling(dev);
-		mlx4_cleanup_eq_table(dev);
-		mlx4_cleanup_mr_table(dev);
-		mlx4_cleanup_xrcd_table(dev);
-		mlx4_cleanup_pd_table(dev);
+	/* in SRIOV it is not allowed to unload the pf's
+	 * driver while there are alive vf's */
+	if (mlx4_is_master(dev)) {
+		if (mlx4_how_many_lives_vf(dev))
+			printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+	}
+	mlx4_stop_sense(dev);
+	mlx4_unregister_device(dev);
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_STRUCTS_ONLY);
-
-		iounmap(priv->kar);
-		mlx4_uar_free(dev, &priv->driver_uar);
-		mlx4_cleanup_uar_table(dev);
-		if (!mlx4_is_slave(dev))
-			mlx4_clear_steering(dev);
-		mlx4_free_eq_table(dev);
-		if (mlx4_is_master(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_close_hca(dev);
-		if (mlx4_is_slave(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_cmd_cleanup(dev);
-
-		if (dev->flags & MLX4_FLAG_MSI_X)
-			pci_disable_msix(pdev);
-		if (dev->flags & MLX4_FLAG_SRIOV) {
-			mlx4_warn(dev, "Disabling SR-IOV\n");
-			pci_disable_sriov(pdev);
-		}
+	for (p = 1; p <= dev->caps.num_ports; p++) {
+		mlx4_cleanup_port_info(&priv->port[p]);
+		mlx4_CLOSE_PORT(dev, p);
+	}
+
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_SLAVES_ONLY);
+
+	mlx4_cleanup_counters_table(dev);
+	mlx4_cleanup_qp_table(dev);
+	mlx4_cleanup_srq_table(dev);
+	mlx4_cleanup_cq_table(dev);
+	mlx4_cmd_use_polling(dev);
+	mlx4_cleanup_eq_table(dev);
+	mlx4_cleanup_mcg_table(dev);
+	mlx4_cleanup_mr_table(dev);
+	mlx4_cleanup_xrcd_table(dev);
+	mlx4_cleanup_pd_table(dev);
 
-		if (!mlx4_is_slave(dev))
-			mlx4_free_ownership(dev);
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_STRUCTS_ONLY);
 
-		kfree(dev->caps.qp0_tunnel);
-		kfree(dev->caps.qp0_proxy);
-		kfree(dev->caps.qp1_tunnel);
-		kfree(dev->caps.qp1_proxy);
+	iounmap(priv->kar);
+	mlx4_uar_free(dev, &priv->driver_uar);
+	mlx4_cleanup_uar_table(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_clear_steering(dev);
+	mlx4_free_eq_table(dev);
+	if (mlx4_is_master(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_close_hca(dev);
+	if (mlx4_is_slave(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_cmd_cleanup(dev);
 
-		kfree(priv);
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		pci_set_drvdata(pdev, NULL);
+	if (dev->flags & MLX4_FLAG_MSI_X)
+		pci_disable_msix(pdev);
+	if (dev->flags & MLX4_FLAG_SRIOV) {
+		mlx4_warn(dev, "Disabling SR-IOV\n");
+		pci_disable_sriov(pdev);
 	}
+
+	if (!mlx4_is_slave(dev))
+		mlx4_free_ownership(dev);
+
+	kfree(dev->caps.qp0_tunnel);
+	kfree(dev->caps.qp0_proxy);
+	kfree(dev->caps.qp1_tunnel);
+	kfree(dev->caps.qp1_proxy);
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	memset(priv, 0, sizeof(*priv));
+	priv->pci_dev_data = pci_dev_data;
+	priv->removed = 1;
+}
+
+static void mlx4_remove_one(struct pci_dev *pdev)
+{
+	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	__mlx4_remove_one(pdev);
+	kfree(priv);
+	pci_set_drvdata(pdev, NULL);
 }
 
 int mlx4_restart_one(struct pci_dev *pdev)
@@ -2454,7 +2474,7 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	int		  pci_dev_data;
 
 	pci_dev_data = priv->pci_dev_data;
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 	return __mlx4_init_one(pdev, pci_dev_data);
 }
 
@@ -2509,7 +2529,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table);
 static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -2517,7 +2537,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	int ret = __mlx4_init_one(pdev, 0);
+	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               ret;
+
+	ret = __mlx4_init_one(pdev, priv->pci_dev_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index df15bb6631cc..da4f0002fd27 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -743,6 +743,7 @@ struct mlx4_priv {
 	spinlock_t		ctx_lock;
 
 	int			pci_dev_data;
+	int                     removed;
 
 	struct list_head        pgdir_list;
 	struct mutex            pgdir_mutex;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b1d7657b2bf5..628e1f9355a8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -299,7 +299,6 @@ struct mlx4_en_cq {
 	struct mlx4_cq          mcq;
 	struct mlx4_hwq_resources wqres;
 	int                     ring;
-	spinlock_t              lock;
 	struct net_device      *dev;
 	struct napi_struct	napi;
 	int size;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 1157f028a90f..6cc808865e95 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1207,7 +1207,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 
 	switch (op) {
 	case RES_OP_RESERVE:
-		count = get_param_l(&in_param);
+		count = get_param_l(&in_param) & 0xffffff;
 		align = get_param_h(&in_param);
 		err = __mlx4_qp_reserve_range(dev, count, align, &base);
 		if (err)
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 7be9788ed0f6..4fb93c5b5563 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -856,6 +856,10 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type)
 		return -ENOMEM;
 	dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE,
 				   DMA_BIDIRECTIONAL);
+	if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) {
+		__free_page(dmatest_page);
+		return -ENOMEM;
+	}
 
 	/* Run a small DMA test.
 	 * The magic multipliers to the length tell the firmware
@@ -1191,6 +1195,7 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 			int bytes, int watchdog)
 {
 	struct page *page;
+	dma_addr_t bus;
 	int idx;
 #if MYRI10GE_ALLOC_SIZE > 4096
 	int end_offset;
@@ -1215,11 +1220,21 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 					rx->watchdog_needed = 1;
 				return;
 			}
+
+			bus = pci_map_page(mgp->pdev, page, 0,
+					   MYRI10GE_ALLOC_SIZE,
+					   PCI_DMA_FROMDEVICE);
+			if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+				__free_pages(page, MYRI10GE_ALLOC_ORDER);
+				if (rx->fill_cnt - rx->cnt < 16)
+					rx->watchdog_needed = 1;
+				return;
+			}
+
 			rx->page = page;
 			rx->page_offset = 0;
-			rx->bus = pci_map_page(mgp->pdev, page, 0,
-					       MYRI10GE_ALLOC_SIZE,
-					       PCI_DMA_FROMDEVICE);
+			rx->bus = bus;
+
 		}
 		rx->info[idx].page = rx->page;
 		rx->info[idx].page_offset = rx->page_offset;
@@ -2576,6 +2591,35 @@ myri10ge_submit_req(struct myri10ge_tx_buf *tx, struct mcp_kreq_ether_send *src,
 	mb();
 }
 
+static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp,
+				  struct myri10ge_tx_buf *tx, int idx)
+{
+	unsigned int len;
+	int last_idx;
+
+	/* Free any DMA resources we've alloced and clear out the skb slot */
+	last_idx = (idx + 1) & tx->mask;
+	idx = tx->req & tx->mask;
+	do {
+		len = dma_unmap_len(&tx->info[idx], len);
+		if (len) {
+			if (tx->info[idx].skb != NULL)
+				pci_unmap_single(mgp->pdev,
+						 dma_unmap_addr(&tx->info[idx],
+								bus), len,
+						 PCI_DMA_TODEVICE);
+			else
+				pci_unmap_page(mgp->pdev,
+					       dma_unmap_addr(&tx->info[idx],
+							      bus), len,
+					       PCI_DMA_TODEVICE);
+			dma_unmap_len_set(&tx->info[idx], len, 0);
+			tx->info[idx].skb = NULL;
+		}
+		idx = (idx + 1) & tx->mask;
+	} while (idx != last_idx);
+}
+
 /*
  * Transmit a packet.  We need to split the packet so that a single
  * segment does not cross myri10ge->tx_boundary, so this makes segment
@@ -2599,7 +2643,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb,
 	u32 low;
 	__be32 high_swapped;
 	unsigned int len;
-	int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
+	int idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
 	u16 pseudo_hdr_offset, cksum_offset, queue;
 	int cum_len, seglen, boundary, rdma_count;
 	u8 flags, odd_flag;
@@ -2696,9 +2740,12 @@ again:
 
 	/* map the skb for DMA */
 	len = skb_headlen(skb);
+	bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (unlikely(pci_dma_mapping_error(mgp->pdev, bus)))
+		goto drop;
+
 	idx = tx->req & tx->mask;
 	tx->info[idx].skb = skb;
-	bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
 	dma_unmap_addr_set(&tx->info[idx], bus, bus);
 	dma_unmap_len_set(&tx->info[idx], len, len);
 
@@ -2797,12 +2844,16 @@ again:
 			break;
 
 		/* map next fragment for DMA */
-		idx = (count + tx->req) & tx->mask;
 		frag = &skb_shinfo(skb)->frags[frag_idx];
 		frag_idx++;
 		len = skb_frag_size(frag);
 		bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len,
 				       DMA_TO_DEVICE);
+		if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+			myri10ge_unmap_tx_dma(mgp, tx, idx);
+			goto drop;
+		}
+		idx = (count + tx->req) & tx->mask;
 		dma_unmap_addr_set(&tx->info[idx], bus, bus);
 		dma_unmap_len_set(&tx->info[idx], len, len);
 	}
@@ -2833,31 +2884,8 @@ again:
 	return NETDEV_TX_OK;
 
 abort_linearize:
-	/* Free any DMA resources we've alloced and clear out the skb
-	 * slot so as to not trip up assertions, and to avoid a
-	 * double-free if linearizing fails */
+	myri10ge_unmap_tx_dma(mgp, tx, idx);
 
-	last_idx = (idx + 1) & tx->mask;
-	idx = tx->req & tx->mask;
-	tx->info[idx].skb = NULL;
-	do {
-		len = dma_unmap_len(&tx->info[idx], len);
-		if (len) {
-			if (tx->info[idx].skb != NULL)
-				pci_unmap_single(mgp->pdev,
-						 dma_unmap_addr(&tx->info[idx],
-								bus), len,
-						 PCI_DMA_TODEVICE);
-			else
-				pci_unmap_page(mgp->pdev,
-					       dma_unmap_addr(&tx->info[idx],
-							      bus), len,
-					       PCI_DMA_TODEVICE);
-			dma_unmap_len_set(&tx->info[idx], len, 0);
-			tx->info[idx].skb = NULL;
-		}
-		idx = (idx + 1) & tx->mask;
-	} while (idx != last_idx);
 	if (skb_is_gso(skb)) {
 		netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n");
 		goto drop;
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 9095ff930f29..064425d3178d 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -678,9 +678,6 @@ static void cp_tx (struct cp_private *cp)
 				 le32_to_cpu(txd->opts1) & 0xffff,
 				 PCI_DMA_TODEVICE);
 
-		bytes_compl += skb->len;
-		pkts_compl++;
-
 		if (status & LastFrag) {
 			if (status & (TxError | TxFIFOUnder)) {
 				netif_dbg(cp, tx_err, cp->dev,
@@ -702,6 +699,8 @@ static void cp_tx (struct cp_private *cp)
 				netif_dbg(cp, tx_done, cp->dev,
 					  "tx done, slot %d\n", tx_tail);
 			}
+			bytes_compl += skb->len;
+			pkts_compl++;
 			dev_kfree_skb_irq(skb);
 		}
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 393f961a013c..e9b5d77a90db 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3456,6 +3456,11 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x14, 0x9065);
 	rtl_writephy(tp, 0x14, 0x1065);
 
+	/* Check ALDPS bit, disable it if enabled */
+	rtl_writephy(tp, 0x1f, 0x0a43);
+	if (rtl_readphy(tp, 0x10) & 0x0004)
+		rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0004);
+
 	rtl_writephy(tp, 0x1f, 0x0000);
 }
 
@@ -4218,6 +4223,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_23:
 	case RTL_GIGA_MAC_VER_24:
 	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
 		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
 	case RTL_GIGA_MAC_VER_40:
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 9a95abf2dedf..540ad16d7807 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1319,6 +1319,13 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev)
 	struct efx_ptp_data *ptp = efx->ptp_data;
 	int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
 
+	if (!ptp) {
+		if (net_ratelimit())
+			netif_warn(efx, drv, efx->net_dev,
+				   "Received PTP event but PTP not set up\n");
+		return;
+	}
+
 	if (!ptp->enabled)
 		return;
 
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index bb4c1674ff99..ff9e99474039 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -97,7 +97,7 @@ config SMC911X
 
 config SMSC911X
 	tristate "SMSC LAN911x/LAN921x families embedded ethernet support"
-	depends on (ARM || SUPERH || BLACKFIN || MIPS || MN10300)
+	depends on HAS_IOMEM
 	select CRC32
 	select NET_CORE
 	select MII
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index dfbf978315df..bdd703c6bf16 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1896,7 +1896,7 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr,
 	SMC_SELECT_BANK(lp, 1);
 	val = SMC_GET_BASE(lp);
 	val = ((val & 0x1F00) >> 3) << SMC_IO_SHIFT;
-	if (((unsigned int)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) {
+	if (((unsigned long)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) {
 		printk("%s: IOADDR %p doesn't match configuration (%x).\n",
 			CARDNAME, ioaddr, val);
 	}
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 370e13dde115..51285872481c 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -46,7 +46,8 @@
     defined(CONFIG_MACH_LITTLETON) ||\
     defined(CONFIG_MACH_ZYLONITE2) ||\
     defined(CONFIG_ARCH_VIPER) ||\
-    defined(CONFIG_MACH_STARGATE2)
+    defined(CONFIG_MACH_STARGATE2) ||\
+    defined(CONFIG_ARCH_VERSATILE)
 
 #include <asm/mach-types.h>
 
@@ -154,6 +155,8 @@ static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 #define SMC_outl(v, a, r)	writel(v, (a) + (r))
 #define SMC_insl(a, r, p, l)	readsl((a) + (r), p, l)
 #define SMC_outsl(a, r, p, l)	writesl((a) + (r), p, l)
+#define SMC_insw(a, r, p, l)	readsw((a) + (r), p, l)
+#define SMC_outsw(a, r, p, l)	writesw((a) + (r), p, l)
 #define SMC_IRQ_FLAGS		(-1)	/* from resource */
 
 /* We actually can't write halfwords properly if not word aligned */
@@ -206,23 +209,6 @@ SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 #define RPC_LSA_DEFAULT		RPC_LED_TX_RX
 #define RPC_LSB_DEFAULT		RPC_LED_100_10
 
-#elif	defined(CONFIG_ARCH_VERSATILE)
-
-#define SMC_CAN_USE_8BIT	1
-#define SMC_CAN_USE_16BIT	1
-#define SMC_CAN_USE_32BIT	1
-#define SMC_NOWAIT		1
-
-#define SMC_inb(a, r)		readb((a) + (r))
-#define SMC_inw(a, r)		readw((a) + (r))
-#define SMC_inl(a, r)		readl((a) + (r))
-#define SMC_outb(v, a, r)	writeb(v, (a) + (r))
-#define SMC_outw(v, a, r)	writew(v, (a) + (r))
-#define SMC_outl(v, a, r)	writel(v, (a) + (r))
-#define SMC_insl(a, r, p, l)	readsl((a) + (r), p, l)
-#define SMC_outsl(a, r, p, l)	writesl((a) + (r), p, l)
-#define SMC_IRQ_FLAGS		(-1)	/* from resource */
-
 #elif defined(CONFIG_MN10300)
 
 /*
@@ -1124,8 +1110,7 @@ static const char * chip_ids[ 16 ] =  {
 			void __iomem *__ioaddr = ioaddr;		\
 			if (__len >= 2 && (unsigned long)__ptr & 2) {	\
 				__len -= 2;				\
-				SMC_outw(*(u16 *)__ptr, ioaddr,		\
-					DATA_REG(lp));		\
+				SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \
 				__ptr += 2;				\
 			}						\
 			if (SMC_CAN_USE_DATACS && lp->datacs)		\
@@ -1133,8 +1118,7 @@ static const char * chip_ids[ 16 ] =  {
 			SMC_outsl(__ioaddr, DATA_REG(lp), __ptr, __len>>2); \
 			if (__len & 2) {				\
 				__ptr += (__len & ~3);			\
-				SMC_outw(*((u16 *)__ptr), ioaddr,	\
-					 DATA_REG(lp));		\
+				SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \
 			}						\
 		} else if (SMC_16BIT(lp))				\
 			SMC_outsw(ioaddr, DATA_REG(lp), p, (l) >> 1);	\
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 3df56840a3b9..ade8bdfc03af 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	spin_lock_irqsave(&port->vio.lock, flags);
 
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		if (!netif_queue_stopped(dev)) {
 			netif_stop_queue(dev);
 
@@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_bytes += skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		netif_stop_queue(dev);
 		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
 			netif_wake_queue(dev);
@@ -1083,6 +1083,24 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac)
 	return vp;
 }
 
+static void vnet_cleanup(void)
+{
+	struct vnet *vp;
+	struct net_device *dev;
+
+	mutex_lock(&vnet_list_mutex);
+	while (!list_empty(&vnet_list)) {
+		vp = list_first_entry(&vnet_list, struct vnet, list);
+		list_del(&vp->list);
+		dev = vp->dev;
+		/* vio_unregister_driver() should have cleaned up port_list */
+		BUG_ON(!list_empty(&vp->port_list));
+		unregister_netdev(dev);
+		free_netdev(dev);
+	}
+	mutex_unlock(&vnet_list_mutex);
+}
+
 static const char *local_mac_prop = "local-mac-address";
 
 static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
@@ -1240,7 +1258,6 @@ static int vnet_port_remove(struct vio_dev *vdev)
 
 		kfree(port);
 
-		unregister_netdev(vp->dev);
 	}
 	return 0;
 }
@@ -1268,6 +1285,7 @@ static int __init vnet_init(void)
 static void __exit vnet_exit(void)
 {
 	vio_unregister_driver(&vnet_port_driver);
+	vnet_cleanup();
 }
 
 module_init(vnet_init);
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 571452e786d5..61a1540f1347 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2019,7 +2019,6 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		ndev->features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO
 		    | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 		    NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM
-		    /*| NETIF_F_FRAGLIST */
 		    ;
 		ndev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
 			NETIF_F_TSO | NETIF_F_HW_VLAN_CTAG_TX;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index d1a769f35f9d..b1ab3a4956a5 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1547,6 +1547,10 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
 		phyid = be32_to_cpup(parp+1);
 		mdio = of_find_device_by_node(mdio_node);
+		if (!mdio) {
+			pr_err("Missing mdio platform device\n");
+			return -EINVAL;
+		}
 		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
 			 PHY_ID_FMT, mdio->name, phyid);
 
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 860e15ddfbcb..7233610164cd 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -876,8 +876,7 @@ static void emac_dev_mcast_set(struct net_device *ndev)
 		    netdev_mc_count(ndev) > EMAC_DEF_MAX_MULTICAST_ADDRESSES) {
 			mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST);
 			emac_add_mcast(priv, EMAC_ALL_MULTI_SET, NULL);
-		}
-		if (!netdev_mc_empty(ndev)) {
+		} else if (!netdev_mc_empty(ndev)) {
 			struct netdev_hw_addr *ha;
 
 			mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST);
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ca98acabf1b4..c879969e82fb 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -32,7 +32,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #define DRV_NAME	"via-rhine"
-#define DRV_VERSION	"1.5.0"
+#define DRV_VERSION	"1.5.1"
 #define DRV_RELDATE	"2010-10-09"
 
 #include <linux/types.h>
@@ -1611,6 +1611,7 @@ static void rhine_reset_task(struct work_struct *work)
 		goto out_unlock;
 
 	napi_disable(&rp->napi);
+	netif_tx_disable(dev);
 	spin_lock_bh(&rp->lock);
 
 	/* clear all descriptors */
@@ -1694,7 +1695,12 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 		cpu_to_le32(TXDESC | (skb->len >= ETH_ZLEN ? skb->len : ETH_ZLEN));
 
 	if (unlikely(vlan_tx_tag_present(skb))) {
-		rp->tx_ring[entry].tx_status = cpu_to_le32((vlan_tx_tag_get(skb)) << 16);
+		u16 vid_pcp = vlan_tx_tag_get(skb);
+
+		/* drop CFI/DEI bit, register needs VID and PCP */
+		vid_pcp = (vid_pcp & VLAN_VID_MASK) |
+			  ((vid_pcp & VLAN_PRIO_MASK) >> 1);
+		rp->tx_ring[entry].tx_status = cpu_to_le32((vid_pcp) << 16);
 		/* request tagging */
 		rp->tx_ring[entry].desc_length |= cpu_to_le32(0x020000);
 	}
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 57c2e5ef2804..52de70bd0bba 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -297,6 +297,12 @@ static int temac_dma_bd_init(struct net_device *ndev)
 		       lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
 	lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
 
+	/* Init descriptor indexes */
+	lp->tx_bd_ci = 0;
+	lp->tx_bd_next = 0;
+	lp->tx_bd_tail = 0;
+	lp->rx_bd_ci = 0;
+
 	return 0;
 
 out:
@@ -1010,7 +1016,7 @@ static int temac_of_probe(struct platform_device *op)
 	dev_set_drvdata(&op->dev, ndev);
 	SET_NETDEV_DEV(ndev, &op->dev);
 	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
-	ndev->features = NETIF_F_SG | NETIF_F_FRAGLIST;
+	ndev->features = NETIF_F_SG;
 	ndev->netdev_ops = &temac_netdev_ops;
 	ndev->ethtool_ops = &temac_ethtool_ops;
 #if 0
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 24748e8367a1..2e2eeba37a06 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1488,7 +1488,7 @@ static int axienet_of_probe(struct platform_device *op)
 
 	SET_NETDEV_DEV(ndev, &op->dev);
 	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
-	ndev->features = NETIF_F_SG | NETIF_F_FRAGLIST;
+	ndev->features = NETIF_F_SG;
 	ndev->netdev_ops = &axienet_netdev_ops;
 	ndev->ethtool_ops = &axienet_ethtool_ops;
 
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 3169252613fa..5d78c1d08abd 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -571,6 +571,8 @@ static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HDLCDRVCTL_CALIBRATE:
 		if(!capable(CAP_SYS_RAWIO))
 			return -EPERM;
+		if (bi.data.calibrate > INT_MAX / s->par.bitrate)
+			return -EINVAL;
 		s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;
 		return 0;
 
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 0721e72f9299..82529a2658d7 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1058,6 +1058,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		break;
 
 	case SIOCYAMGCFG:
+		memset(&yi, 0, sizeof(yi));
 		yi.cfg.mask = 0xffffffff;
 		yi.cfg.iobase = yp->iobase;
 		yi.cfg.irq = yp->irq;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 23a0fff0df52..59e9c56e5b8a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -138,6 +138,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	struct hv_netvsc_packet *packet;
 	int ret;
 	unsigned int i, num_pages, npg_data;
+	u32 skb_length = skb->len;
 
 	/* Add multipages for skb->data and additional 2 for RNDIS */
 	npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
@@ -208,7 +209,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	ret = rndis_filter_send(net_device_ctx->device_ctx,
 				  packet);
 	if (ret == 0) {
-		net->stats.tx_bytes += skb->len;
+		net->stats.tx_bytes += skb_length;
 		net->stats.tx_packets++;
 	} else {
 		kfree(packet);
@@ -328,7 +329,6 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 		return -EINVAL;
 
 	nvdev->start_remove = true;
-	cancel_delayed_work_sync(&ndevctx->dwork);
 	cancel_work_sync(&ndevctx->work);
 	netif_tx_disable(ndev);
 	rndis_filter_device_remove(hdev);
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index bf0d55e2dd63..6adbef89c4b0 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -376,17 +376,20 @@ static int ieee802154fake_probe(struct platform_device *pdev)
 
 	err = wpan_phy_register(phy);
 	if (err)
-		goto out;
+		goto err_phy_reg;
 
 	err = register_netdev(dev);
-	if (err < 0)
-		goto out;
+	if (err)
+		goto err_netdev_reg;
 
 	dev_info(&pdev->dev, "Added ieee802154 HardMAC hardware\n");
 	return 0;
 
-out:
-	unregister_netdev(dev);
+err_netdev_reg:
+	wpan_phy_unregister(phy);
+err_phy_reg:
+	free_netdev(dev);
+	wpan_phy_free(phy);
 	return err;
 }
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 06eba6e480c9..9be91cb4f4a3 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -261,11 +261,9 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
-	__u8 ip_summed = skb->ip_summed;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = (void *)skb->data;
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		/* send to other bridge ports directly */
 		if (is_multicast_ether_addr(eth->h_dest)) {
@@ -283,7 +281,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 xmit_world:
-	skb->ip_summed = ip_summed;
 	skb->dev = vlan->lowerdev;
 	return dev_queue_xmit(skb);
 }
@@ -423,8 +420,10 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
 
-	if (change & IFF_ALLMULTI)
-		dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	}
 }
 
 static void macvlan_set_mac_lists(struct net_device *dev)
@@ -501,6 +500,7 @@ static int macvlan_init(struct net_device *dev)
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
 	dev->features		|= NETIF_F_LLTX;
+	dev->vlan_features	= lowerdev->vlan_features & MACVLAN_FEATURES;
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->iflink		= lowerdev->ifindex;
 	dev->hard_header_len	= lowerdev->hard_header_len;
@@ -962,7 +962,6 @@ static int macvlan_device_event(struct notifier_block *unused,
 		list_for_each_entry_safe(vlan, next, &port->vlans, list)
 			vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
 		unregister_netdevice_many(&list_kill);
-		list_del(&list_kill);
 		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlaying device to change its type. */
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 523d6b2426a8..2d255ba911d5 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -625,6 +625,8 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
 		vnet_hdr->csum_start = skb_checksum_start_offset(skb);
+		if (vlan_tx_tag_present(skb))
+			vnet_hdr->csum_start += VLAN_HLEN;
 		vnet_hdr->csum_offset = skb->csum_offset;
 	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
@@ -661,6 +663,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 				const struct iovec *iv, unsigned long total_len,
 				size_t count, int noblock)
 {
+	int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
 	struct sk_buff *skb;
 	struct macvlan_dev *vlan;
 	unsigned long len = total_len;
@@ -703,6 +706,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
 		copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+		if (copylen > good_linear)
+			copylen = good_linear;
 		linear = copylen;
 		if (iov_pages(iv, vnet_hdr_len + copylen, count)
 		    <= MAX_SKB_FRAGS)
@@ -711,7 +716,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		linear = vnet_hdr.hdr_len;
+		if (vnet_hdr.hdr_len > good_linear)
+			linear = good_linear;
+		else
+			linear = vnet_hdr.hdr_len;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
@@ -791,11 +799,10 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 				const struct sk_buff *skb,
 				const struct iovec *iv, int len)
 {
-	struct macvlan_dev *vlan;
 	int ret;
 	int vnet_hdr_len = 0;
 	int vlan_offset = 0;
-	int copied;
+	int copied, total;
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
@@ -810,7 +817,8 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
 			return -EFAULT;
 	}
-	copied = vnet_hdr_len;
+	total = copied = vnet_hdr_len;
+	total += skb->len;
 
 	if (!vlan_tx_tag_present(skb))
 		len = min_t(int, skb->len, len);
@@ -825,6 +833,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
 		len = min_t(int, skb->len + VLAN_HLEN, len);
+		total += VLAN_HLEN;
 
 		copy = min_t(int, vlan_offset, len);
 		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
@@ -842,16 +851,9 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 	}
 
 	ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
-	copied += len;
 
 done:
-	rcu_read_lock_bh();
-	vlan = rcu_dereference_bh(q->vlan);
-	if (vlan)
-		macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
-	rcu_read_unlock_bh();
-
-	return ret ? ret : copied;
+	return ret ? ret : total;
 }
 
 static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
@@ -903,7 +905,9 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
 	}
 
 	ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
-	ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */
+	ret = min_t(ssize_t, ret, len);
+	if (ret > 0)
+		iocb->ki_pos = ret;
 out:
 	return ret;
 }
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 38f0b312ff85..663d2d0448b7 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -439,7 +439,7 @@ void phy_start_machine(struct phy_device *phydev,
 {
 	phydev->adjust_state = handler;
 
-	schedule_delayed_work(&phydev->state_queue, HZ);
+	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, HZ);
 }
 
 /**
@@ -500,7 +500,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	disable_irq_nosync(irq);
 	atomic_inc(&phydev->irq_disable);
 
-	schedule_work(&phydev->phy_queue);
+	queue_work(system_power_efficient_wq, &phydev->phy_queue);
 
 	return IRQ_HANDLED;
 }
@@ -655,7 +655,7 @@ static void phy_change(struct work_struct *work)
 
 	/* reschedule state queue work to run as soon as possible */
 	cancel_delayed_work_sync(&phydev->state_queue);
-	schedule_delayed_work(&phydev->state_queue, 0);
+	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
 
 	return;
 
@@ -918,7 +918,8 @@ void phy_state_machine(struct work_struct *work)
 	if (err < 0)
 		phy_error(phydev);
 
-	schedule_delayed_work(&phydev->state_queue, PHY_STATE_TIME * HZ);
+	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
+			PHY_STATE_TIME * HZ);
 }
 
 static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 72ff14b811c6..5a1897d86e94 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -601,7 +601,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			if (file == ppp->owner)
 				ppp_shutdown_interface(ppp);
 		}
-		if (atomic_long_read(&file->f_count) <= 2) {
+		if (atomic_long_read(&file->f_count) < 2) {
 			ppp_release(NULL, file);
 			err = 0;
 		} else
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index bb07ba94c3aa..becfa3ef7fdc 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -675,7 +675,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 		po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
 				   dev->hard_header_len);
 
-		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr);
+		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
 		po->chan.private = sk;
 		po->chan.ops = &pppoe_chan_ops;
 
@@ -979,8 +979,6 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (error < 0)
 		goto end;
 
-	m->msg_namelen = 0;
-
 	if (skb) {
 		total_len = min_t(size_t, total_len, skb->len);
 		error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 162464fe86bf..0d5a5faaf83b 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	nf_reset(skb);
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(iph, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	ip_local_out(skb);
@@ -506,7 +506,9 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr,
 	int len = sizeof(struct sockaddr_pppox);
 	struct sockaddr_pppox sp;
 
-	sp.sa_family	  = AF_PPPOX;
+	memset(&sp.sa_addr, 0, sizeof(sp.sa_addr));
+
+	sp.sa_family    = AF_PPPOX;
 	sp.sa_protocol  = PX_PROTO_PPTP;
 	sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b3051052f3ad..12222290c802 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1217,6 +1217,8 @@ static int team_user_linkup_option_get(struct team *team,
 	return 0;
 }
 
+static void __team_carrier_check(struct team *team);
+
 static int team_user_linkup_option_set(struct team *team,
 				       struct team_gsetter_ctx *ctx)
 {
@@ -1224,6 +1226,7 @@ static int team_user_linkup_option_set(struct team *team,
 
 	port->user.linkup = ctx->data.bool_val;
 	team_refresh_port_linkup(port);
+	__team_carrier_check(port->team);
 	return 0;
 }
 
@@ -1243,6 +1246,7 @@ static int team_user_linkup_en_option_set(struct team *team,
 
 	port->user.linkup_enabled = ctx->data.bool_val;
 	team_refresh_port_linkup(port);
+	__team_carrier_check(port->team);
 	return 0;
 }
 
@@ -1538,6 +1542,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	 * to traverse list in reverse under rcu_read_lock
 	 */
 	mutex_lock(&team->lock);
+	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
 		if (err) {
@@ -1546,6 +1551,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 			goto unwind;
 		}
 	}
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	dev->mtu = new_mtu;
@@ -1555,6 +1561,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	return err;
@@ -2674,7 +2681,9 @@ static int team_device_event(struct notifier_block *unused,
 		break;
 	case NETDEV_CHANGEMTU:
 		/* Forbid to change mtu of underlaying device */
-		return NOTIFY_BAD;
+		if (!port->team->port_mtu_change_allowed)
+			return NOTIFY_BAD;
+		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid to change type of underlaying device */
 		return NOTIFY_BAD;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7b54f4f052d0..582497103fe8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1069,6 +1069,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	struct sk_buff *skb;
 	size_t len = total_len, align = NET_SKB_PAD, linear;
 	struct virtio_net_hdr gso = { 0 };
+	int good_linear;
 	int offset = 0;
 	int copylen;
 	bool zerocopy = false;
@@ -1109,12 +1110,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			return -EINVAL;
 	}
 
+	good_linear = SKB_MAX_HEAD(align);
+
 	if (msg_control) {
 		/* There are 256 bytes to be copied in skb, so there is
 		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
 		copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+		if (copylen > good_linear)
+			copylen = good_linear;
 		linear = copylen;
 		if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
 			zerocopy = true;
@@ -1122,7 +1127,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (!zerocopy) {
 		copylen = len;
-		linear = gso.hdr_len;
+		if (gso.hdr_len > good_linear)
+			linear = good_linear;
+		else
+			linear = gso.hdr_len;
 	}
 
 	skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
@@ -1404,6 +1412,8 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
 	ret = tun_do_read(tun, tfile, iocb, iv, len,
 			  file->f_flags & O_NONBLOCK);
 	ret = min_t(ssize_t, ret, len);
+	if (ret > 0)
+		iocb->ki_pos = ret;
 out:
 	tun_put(tun);
 	return ret;
@@ -1693,11 +1703,11 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		INIT_LIST_HEAD(&tun->disabled);
 		err = tun_attach(tun, file);
 		if (err < 0)
-			goto err_free_dev;
+			goto err_free_flow;
 
 		err = register_netdevice(tun->dev);
 		if (err < 0)
-			goto err_free_dev;
+			goto err_detach;
 
 		if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
 		    device_create_file(&tun->dev->dev, &dev_attr_owner) ||
@@ -1741,7 +1751,12 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	strcpy(ifr->ifr_name, tun->dev->name);
 	return 0;
 
- err_free_dev:
+err_detach:
+	tun_detach_all(dev);
+err_free_flow:
+	tun_flow_uninit(tun);
+	security_tun_dev_free_security(tun->security);
+err_free_dev:
 	free_netdev(dev);
 	return err;
 }
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index ad5d1e4384db..97b5de7aebdb 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -915,7 +915,8 @@ static const struct driver_info ax88178_info = {
 	.status = asix_status,
 	.link_reset = ax88178_link_reset,
 	.reset = ax88178_reset,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+		 FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 };
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index cea1f3d0311b..3b449c4ecf72 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -695,6 +695,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct sockaddr *addr = p;
+	int ret;
 
 	if (netif_running(net))
 		return -EBUSY;
@@ -704,8 +705,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p)
 	memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);
 
 	/* Set the MAC address */
-	return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
+	ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
 				 ETH_ALEN, net->dev_addr);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static const struct net_device_ops ax88179_netdev_ops = {
@@ -1109,6 +1114,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	u16 hdr_off;
 	u32 *pkt_hdr;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	skb_trim(skb, skb->len - 4);
 	memcpy(&rx_hdr, skb_tail_pointer(skb), 4);
 	le32_to_cpus(&rx_hdr);
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 04ee044dde51..b1897c7afdd8 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -709,6 +709,11 @@ static const struct usb_device_id	products [] = {
 	.bInterfaceProtocol	= USB_CDC_PROTO_NONE,
 	.driver_info = (unsigned long)&wwan_info,
 }, {
+	/* Telit modules */
+	USB_VENDOR_AND_INTERFACE_INFO(0x1bc7, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = (kernel_ulong_t) &wwan_info,
+}, {
 	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
 			USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long) &cdc_info,
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 25ba7eca9a13..7cabe4583904 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -120,6 +120,16 @@ static void cdc_mbim_unbind(struct usbnet *dev, struct usb_interface *intf)
 	cdc_ncm_unbind(dev, intf);
 }
 
+/* verify that the ethernet protocol is IPv4 or IPv6 */
+static bool is_ip_proto(__be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+		return true;
+	}
+	return false;
+}
 
 static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 {
@@ -128,6 +138,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 	struct cdc_ncm_ctx *ctx = info->ctx;
 	__le32 sign = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN);
 	u16 tci = 0;
+	bool is_ip;
 	u8 *c;
 
 	if (!ctx)
@@ -137,25 +148,32 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 		if (skb->len <= ETH_HLEN)
 			goto error;
 
+		/* Some applications using e.g. packet sockets will
+		 * bypass the VLAN acceleration and create tagged
+		 * ethernet frames directly.  We primarily look for
+		 * the accelerated out-of-band tag, but fall back if
+		 * required
+		 */
+		skb_reset_mac_header(skb);
+		if (vlan_get_tag(skb, &tci) < 0 && skb->len > VLAN_ETH_HLEN &&
+		    __vlan_get_tag(skb, &tci) == 0) {
+			is_ip = is_ip_proto(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto);
+			skb_pull(skb, VLAN_ETH_HLEN);
+		} else {
+			is_ip = is_ip_proto(eth_hdr(skb)->h_proto);
+			skb_pull(skb, ETH_HLEN);
+		}
+
 		/* mapping VLANs to MBIM sessions:
 		 *   no tag     => IPS session <0>
 		 *   1 - 255    => IPS session <vlanid>
 		 *   256 - 511  => DSS session <vlanid - 256>
 		 *   512 - 4095 => unsupported, drop
 		 */
-		vlan_get_tag(skb, &tci);
-
 		switch (tci & 0x0f00) {
 		case 0x0000: /* VLAN ID 0 - 255 */
-			/* verify that datagram is IPv4 or IPv6 */
-			skb_reset_mac_header(skb);
-			switch (eth_hdr(skb)->h_proto) {
-			case htons(ETH_P_IP):
-			case htons(ETH_P_IPV6):
-				break;
-			default:
+			if (!is_ip)
 				goto error;
-			}
 			c = (u8 *)&sign;
 			c[3] = tci;
 			break;
@@ -169,7 +187,6 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 				  "unsupported tci=0x%04x\n", tci);
 			goto error;
 		}
-		skb_pull(skb, ETH_HLEN);
 	}
 
 	spin_lock_bh(&ctx->mtx);
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 2dbb9460349d..c0bfc818c701 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -303,7 +303,7 @@ static void dm9601_set_multicast(struct net_device *net)
 		rx_ctl |= 0x02;
 	} else if (net->flags & IFF_ALLMULTI ||
 		   netdev_mc_count(net) > DM_MAX_MCAST) {
-		rx_ctl |= 0x04;
+		rx_ctl |= 0x08;
 	} else if (!netdev_mc_empty(net)) {
 		struct netdev_hw_addr *ha;
 
@@ -364,7 +364,12 @@ static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->ethtool_ops = &dm9601_ethtool_ops;
 	dev->net->hard_header_len += DM_TX_OVERHEAD;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
-	dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD;
+
+	/* dm9620/21a require room for 4 byte padding, even in dm9601
+	 * mode, so we need +1 to be able to receive full size
+	 * ethernet frames.
+	 */
+	dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD + 1;
 
 	dev->mii.dev = dev->net;
 	dev->mii.mdio_read = dm9601_mdio_read;
@@ -468,7 +473,7 @@ static int dm9601_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 				       gfp_t flags)
 {
-	int len;
+	int len, pad;
 
 	/* format:
 	   b1: packet length low
@@ -476,12 +481,23 @@ static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	   b3..n: packet data
 	*/
 
-	len = skb->len;
+	len = skb->len + DM_TX_OVERHEAD;
 
-	if (skb_headroom(skb) < DM_TX_OVERHEAD) {
+	/* workaround for dm962x errata with tx fifo getting out of
+	 * sync if a USB bulk transfer retry happens right after a
+	 * packet with odd / maxpacket length by adding up to 3 bytes
+	 * padding.
+	 */
+	while ((len & 1) || !(len % dev->maxpacket))
+		len++;
+
+	len -= DM_TX_OVERHEAD; /* hw header doesn't count as part of length */
+	pad = len - skb->len;
+
+	if (skb_headroom(skb) < DM_TX_OVERHEAD || skb_tailroom(skb) < pad) {
 		struct sk_buff *skb2;
 
-		skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, 0, flags);
+		skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, pad, flags);
 		dev_kfree_skb_any(skb);
 		skb = skb2;
 		if (!skb)
@@ -490,10 +506,10 @@ static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 
 	__skb_push(skb, DM_TX_OVERHEAD);
 
-	/* usbnet adds padding if length is a multiple of packet size
-	   if so, adjust length value in header */
-	if ((skb->len % dev->maxpacket) == 0)
-		len++;
+	if (pad) {
+		memset(skb->data + skb->len, 0, pad);
+		__skb_put(skb, pad);
+	}
 
 	skb->data[0] = len;
 	skb->data[1] = len >> 8;
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index a7e3f4e55bf3..82ab61d62804 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -86,6 +86,10 @@ static int genelink_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	u32			size;
 	u32			count;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	header = (struct gl_header *) skb->data;
 
 	// get the packet count of the received skb
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 03832d3780aa..9237c45883cd 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -529,8 +529,9 @@ static int mcs7830_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
 	u8 status;
 
-	if (skb->len == 0) {
-		dev_err(&dev->udev->dev, "unexpected empty rx frame\n");
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len) {
+		dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
 		return 0;
 	}
 
diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c
index 93e0716a118c..7f4a3a41c4f8 100644
--- a/drivers/net/usb/net1080.c
+++ b/drivers/net/usb/net1080.c
@@ -366,6 +366,10 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	struct nc_trailer	*trailer;
 	u16			hdr_len, packet_len;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	if (!(skb->len & 0x01)) {
 		netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n",
 			   skb->len, dev->net->hard_header_len, dev->hard_mtu,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 56459215a22b..43204f4be2da 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -80,10 +80,10 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
 	__be16 proto;
 
-	/* usbnet rx_complete guarantees that skb->len is at least
-	 * hard_header_len, so we can inspect the dest address without
-	 * checking skb->len
-	 */
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	switch (skb->data[0] & 0xf0) {
 	case 0x40:
 		proto = htons(ETH_P_IP);
@@ -518,11 +518,158 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
+	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x7101, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x7101, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x7101, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x7102, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x7102, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x7102, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x8000, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x8001, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9000, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9003, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9005, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x900a, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x900b, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x900c, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x900c, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x900c, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x900d, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x900f, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x900f, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x900f, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9010, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9010, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9011, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9011, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9021, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x9022, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x9025, 4)},	/* Alcatel-sbell ASB TL131 TDD LTE  (China Mobile) */
+	{QMI_FIXED_INTF(0x05c6, 0x9026, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x902e, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9031, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9032, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9033, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9033, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9033, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9033, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9034, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9034, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9034, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9034, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9034, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9035, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9036, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9037, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9038, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x903b, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x903c, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x903d, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x903e, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9043, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9046, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9046, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9046, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9047, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x9047, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9047, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9048, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9048, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9048, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9048, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9048, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x904c, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x904c, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x904c, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x904c, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9050, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9052, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9053, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9053, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9054, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9054, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9055, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9055, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9055, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9055, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9055, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9056, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9062, 9)},
+	{QMI_FIXED_INTF(0x05c6, 0x9064, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9065, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9065, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9066, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9066, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9067, 1)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 2)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9068, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9069, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9069, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9069, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9069, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9070, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9070, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9075, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9076, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9076, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9076, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9076, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9076, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9077, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9077, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9077, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9077, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9078, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9079, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x9079, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9079, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9079, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9079, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9080, 5)},
+	{QMI_FIXED_INTF(0x05c6, 0x9080, 6)},
+	{QMI_FIXED_INTF(0x05c6, 0x9080, 7)},
+	{QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
+	{QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
+	{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
+	{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
+	{QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
+	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
+	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
+	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
+	{QMI_FIXED_INTF(0x16d8, 0x6280, 0)},	/* CMOTech CHU-628 */
+	{QMI_FIXED_INTF(0x16d8, 0x7001, 0)},	/* CMOTech CHU-720S */
+	{QMI_FIXED_INTF(0x16d8, 0x7002, 0)},	/* CMOTech 7002 */
+	{QMI_FIXED_INTF(0x16d8, 0x7003, 4)},	/* CMOTech CHU-629K */
+	{QMI_FIXED_INTF(0x16d8, 0x7004, 3)},	/* CMOTech 7004 */
+	{QMI_FIXED_INTF(0x16d8, 0x7006, 5)},	/* CMOTech CGU-629 */
+	{QMI_FIXED_INTF(0x16d8, 0x700a, 4)},	/* CMOTech CHU-629S */
+	{QMI_FIXED_INTF(0x16d8, 0x7211, 0)},	/* CMOTech CHU-720I */
+	{QMI_FIXED_INTF(0x16d8, 0x7212, 0)},	/* CMOTech 7212 */
+	{QMI_FIXED_INTF(0x16d8, 0x7213, 0)},	/* CMOTech 7213 */
+	{QMI_FIXED_INTF(0x16d8, 0x7251, 1)},	/* CMOTech 7251 */
+	{QMI_FIXED_INTF(0x16d8, 0x7252, 1)},	/* CMOTech 7252 */
+	{QMI_FIXED_INTF(0x16d8, 0x7253, 1)},	/* CMOTech 7253 */
 	{QMI_FIXED_INTF(0x19d2, 0x0002, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0012, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0017, 3)},
+	{QMI_FIXED_INTF(0x19d2, 0x0019, 3)},	/* ONDA MT689DC */
 	{QMI_FIXED_INTF(0x19d2, 0x0021, 4)},
 	{QMI_FIXED_INTF(0x19d2, 0x0025, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0031, 4)},
@@ -569,21 +716,47 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1255, 3)},
 	{QMI_FIXED_INTF(0x19d2, 0x1255, 4)},
 	{QMI_FIXED_INTF(0x19d2, 0x1256, 4)},
+	{QMI_FIXED_INTF(0x19d2, 0x1270, 5)},	/* ZTE MF667 */
 	{QMI_FIXED_INTF(0x19d2, 0x1401, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1402, 2)},	/* ZTE MF60 */
 	{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
+	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 19)},	/* Sierra Wireless MC7710 in QMI mode */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 8)},	/* Sierra Wireless MC73xx */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 10)},	/* Sierra Wireless MC73xx */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 11)},	/* Sierra Wireless MC73xx */
 	{QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
+	{QMI_FIXED_INTF(0x1199, 0x901f, 8)},    /* Sierra Wireless EM7355 */
+	{QMI_FIXED_INTF(0x1199, 0x9041, 8)},	/* Sierra Wireless MC7305/MC7355 */
+	{QMI_FIXED_INTF(0x1199, 0x9051, 8)},	/* Netgear AirCard 340U */
+	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
+	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
+	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
-	{QMI_FIXED_INTF(0x1e2d, 0x12d1, 4)},	/* Cinterion PLxx */
+	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc004, 6)},	/* Olivetti Olicard 155 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},	/* Olivetti Olicard 200 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)},	/* Olivetti Olicard 160 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)},	/* Olivetti Olicard 500 */
+	{QMI_FIXED_INTF(0x1e2d, 0x0060, 4)},	/* Cinterion PLxx */
+	{QMI_FIXED_INTF(0x1e2d, 0x0053, 4)},	/* Cinterion PHxx,PXxx */
+	{QMI_FIXED_INTF(0x413c, 0x81a2, 8)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a3, 8)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
@@ -610,7 +783,6 @@ static const struct usb_device_id products[] = {
 	{QMI_GOBI_DEVICE(0x413c, 0x8186)},	/* Dell Gobi 2000 Modem device (N0218, VU936) */
 	{QMI_GOBI_DEVICE(0x413c, 0x8194)},	/* Dell Gobi 3000 Composite */
 	{QMI_GOBI_DEVICE(0x05c6, 0x920b)},	/* Generic Gobi 2000 Modem device */
-	{QMI_GOBI_DEVICE(0x05c6, 0x920d)},	/* Gobi 3000 Composite */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9225)},	/* Sony Gobi 2000 Modem device (N0279, VU730) */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9245)},	/* Samsung Gobi 2000 Modem device (VL176) */
 	{QMI_GOBI_DEVICE(0x03f0, 0x251d)},	/* HP Gobi 2000 Modem device (VP412) */
@@ -618,6 +790,7 @@ static const struct usb_device_id products[] = {
 	{QMI_GOBI_DEVICE(0x05c6, 0x9265)},	/* Asus Gobi 2000 Modem device (VR305) */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9235)},	/* Top Global Gobi 2000 Modem device (VR306) */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9275)},	/* iRex Technologies Gobi 2000 Modem device (VR307) */
+	{QMI_GOBI_DEVICE(0x0af0, 0x8120)},	/* Option GTM681W */
 	{QMI_GOBI_DEVICE(0x1199, 0x68a5)},	/* Sierra Wireless Modem */
 	{QMI_GOBI_DEVICE(0x1199, 0x68a9)},	/* Sierra Wireless Modem */
 	{QMI_GOBI_DEVICE(0x1199, 0x9001)},	/* Sierra Wireless Gobi 2000 Modem device (VT773) */
@@ -631,7 +804,6 @@ static const struct usb_device_id products[] = {
 	{QMI_GOBI_DEVICE(0x1199, 0x9009)},	/* Sierra Wireless Gobi 2000 Modem device (VT773) */
 	{QMI_GOBI_DEVICE(0x1199, 0x900a)},	/* Sierra Wireless Gobi 2000 Modem device (VT773) */
 	{QMI_GOBI_DEVICE(0x1199, 0x9011)},	/* Sierra Wireless Gobi 2000 Modem device (MC8305) */
-	{QMI_FIXED_INTF(0x1199, 0x9011, 5)},	/* alternate interface number!? */
 	{QMI_GOBI_DEVICE(0x16d8, 0x8002)},	/* CMDTech Gobi 2000 Modem device (VU922) */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9205)},	/* Gobi 2000 Modem device */
 	{QMI_GOBI_DEVICE(0x1199, 0x9013)},	/* Sierra Wireless Gobi 3000 Modem device (MC8355) */
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index cc49aac70224..691fca4e4c2d 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -494,6 +494,10 @@ EXPORT_SYMBOL_GPL(rndis_unbind);
  */
 int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	/* peripheral may have batched packets to us... */
 	while (likely(skb->len)) {
 		struct rndis_data_hdr	*hdr = (void *)skb->data;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 66ebbacf066f..12afae0451e6 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -2108,6 +2108,10 @@ static void smsc75xx_rx_csum_offload(struct usbnet *dev, struct sk_buff *skb,
 
 static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	while (skb->len > 0) {
 		u32 rx_cmd_a, rx_cmd_b, align_count, size;
 		struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 3f38ba868f61..9375b8c6410b 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1725,6 +1725,10 @@ static void smsc95xx_rx_csum_offload(struct sk_buff *skb)
 
 static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	while (skb->len > 0) {
 		u32 header, align_count;
 		struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 06ee82f557d4..3d50e7db141e 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -206,9 +206,6 @@ static void intr_complete (struct urb *urb)
 		break;
 	}
 
-	if (!netif_running (dev->net))
-		return;
-
 	status = usb_submit_urb (urb, GFP_ATOMIC);
 	if (status != 0)
 		netif_err(dev, timer, dev->net,
@@ -520,17 +517,19 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb)
 	}
 	// else network stack removes extra byte if we forced a short packet
 
-	if (skb->len) {
-		/* all data was already cloned from skb inside the driver */
-		if (dev->driver_info->flags & FLAG_MULTI_PACKET)
-			dev_kfree_skb_any(skb);
-		else
-			usbnet_skb_return(dev, skb);
+	/* all data was already cloned from skb inside the driver */
+	if (dev->driver_info->flags & FLAG_MULTI_PACKET)
+		goto done;
+
+	if (skb->len < ETH_HLEN) {
+		dev->net->stats.rx_errors++;
+		dev->net->stats.rx_length_errors++;
+		netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len);
+	} else {
+		usbnet_skb_return(dev, skb);
 		return;
 	}
 
-	netif_dbg(dev, rx_err, dev->net, "drop\n");
-	dev->net->stats.rx_errors++;
 done:
 	skb_queue_tail(&dev->done, skb);
 }
@@ -552,13 +551,6 @@ static void rx_complete (struct urb *urb)
 	switch (urb_status) {
 	/* success */
 	case 0:
-		if (skb->len < dev->net->hard_header_len) {
-			state = rx_cleanup;
-			dev->net->stats.rx_errors++;
-			dev->net->stats.rx_length_errors++;
-			netif_dbg(dev, rx_err, dev->net,
-				  "rx length %d\n", skb->len);
-		}
 		break;
 
 	/* stalls need manual reset. this is rare ... except that
@@ -735,14 +727,12 @@ EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs);
 // precondition: never called in_interrupt
 static void usbnet_terminate_urbs(struct usbnet *dev)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
 	DECLARE_WAITQUEUE(wait, current);
 	int temp;
 
 	/* ensure there are no more active urbs */
-	add_wait_queue(&unlink_wakeup, &wait);
+	add_wait_queue(&dev->wait, &wait);
 	set_current_state(TASK_UNINTERRUPTIBLE);
-	dev->wait = &unlink_wakeup;
 	temp = unlink_urbs(dev, &dev->txq) +
 		unlink_urbs(dev, &dev->rxq);
 
@@ -756,15 +746,14 @@ static void usbnet_terminate_urbs(struct usbnet *dev)
 				  "waited for %d urb completions\n", temp);
 	}
 	set_current_state(TASK_RUNNING);
-	dev->wait = NULL;
-	remove_wait_queue(&unlink_wakeup, &wait);
+	remove_wait_queue(&dev->wait, &wait);
 }
 
 int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval;
+	int			retval, pm;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -774,6 +763,8 @@ int usbnet_stop (struct net_device *net)
 		   net->stats.rx_packets, net->stats.tx_packets,
 		   net->stats.rx_errors, net->stats.tx_errors);
 
+	/* to not race resume */
+	pm = usb_autopm_get_interface(dev->intf);
 	/* allow minidriver to stop correctly (wireless devices to turn off
 	 * radio etc) */
 	if (info->stop) {
@@ -800,6 +791,9 @@ int usbnet_stop (struct net_device *net)
 	dev->flags = 0;
 	del_timer_sync (&dev->delay);
 	tasklet_kill (&dev->bh);
+	if (!pm)
+		usb_autopm_put_interface(dev->intf);
+
 	if (info->manage_power &&
 	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
 		info->manage_power(dev, 0);
@@ -1368,11 +1362,12 @@ static void usbnet_bh (unsigned long param)
 	/* restart RX again after disabling due to high error rate */
 	clear_bit(EVENT_RX_KILL, &dev->flags);
 
-	// waiting for all pending urbs to complete?
-	if (dev->wait) {
-		if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
-			wake_up (dev->wait);
-		}
+	/* waiting for all pending urbs to complete?
+	 * only then can we forgo submitting anew
+	 */
+	if (waitqueue_active(&dev->wait)) {
+		if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+			wake_up_all(&dev->wait);
 
 	// or are we maybe short a few urbs?
 	} else if (netif_running (dev->net) &&
@@ -1510,6 +1505,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->driver_name = name;
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+	init_waitqueue_head(&dev->wait);
 	skb_queue_head_init (&dev->rxq);
 	skb_queue_head_init (&dev->txq);
 	skb_queue_head_init (&dev->done);
@@ -1702,9 +1698,10 @@ int usbnet_resume (struct usb_interface *intf)
 		spin_unlock_irq(&dev->txq.lock);
 
 		if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
-			/* handle remote wakeup ASAP */
-			if (!dev->wait &&
-				netif_device_present(dev->net) &&
+			/* handle remote wakeup ASAP
+			 * we cannot race against stop
+			 */
+			if (netif_device_present(dev->net) &&
 				!timer_pending(&dev->delay) &&
 				!test_bit(EVENT_RX_HALT, &dev->flags))
 					rx_alloc_submit(dev, GFP_NOIO);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 42d670a468f8..2835bfe151b1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -294,26 +294,61 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,
 	return skb;
 }
 
-static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
+static struct sk_buff *receive_small(void *buf, unsigned int len)
 {
-	struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
-	struct page *page;
-	int num_buf, i, len;
+	struct sk_buff * skb = buf;
+
+	len -= sizeof(struct virtio_net_hdr);
+	skb_trim(skb, len);
+
+	return skb;
+}
+
+static struct sk_buff *receive_big(struct net_device *dev,
+				   struct receive_queue *rq,
+				   void *buf)
+{
+	struct page *page = buf;
+	struct sk_buff *skb = page_to_skb(rq, page, 0);
+
+	if (unlikely(!skb))
+		goto err;
+
+	return skb;
+
+err:
+	dev->stats.rx_dropped++;
+	give_pages(rq, page);
+	return NULL;
+}
+
+static struct sk_buff *receive_mergeable(struct net_device *dev,
+					 struct receive_queue *rq,
+					 void *buf,
+					 unsigned int len)
+{
+	struct skb_vnet_hdr *hdr = page_address(buf);
+	int num_buf = hdr->mhdr.num_buffers;
+	struct page *page = buf;
+	struct sk_buff *skb = page_to_skb(rq, page, len);
+	int i;
+
+	if (unlikely(!skb))
+		goto err_skb;
 
-	num_buf = hdr->mhdr.num_buffers;
 	while (--num_buf) {
 		i = skb_shinfo(skb)->nr_frags;
 		if (i >= MAX_SKB_FRAGS) {
 			pr_debug("%s: packet too long\n", skb->dev->name);
 			skb->dev->stats.rx_length_errors++;
-			return -EINVAL;
+			goto err_frags;
 		}
 		page = virtqueue_get_buf(rq->vq, &len);
 		if (!page) {
-			pr_debug("%s: rx error: %d buffers missing\n",
-				 skb->dev->name, hdr->mhdr.num_buffers);
-			skb->dev->stats.rx_length_errors++;
-			return -EINVAL;
+			pr_debug("%s: rx error: %d buffers %d missing\n",
+				 dev->name, hdr->mhdr.num_buffers, num_buf);
+			dev->stats.rx_length_errors++;
+			goto err_buf;
 		}
 
 		if (len > PAGE_SIZE)
@@ -323,7 +358,26 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
 
 		--rq->num;
 	}
-	return 0;
+	return skb;
+err_skb:
+	give_pages(rq, page);
+	while (--num_buf) {
+err_frags:
+		buf = virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!buf)) {
+			pr_debug("%s: rx error: %d buffers missing\n",
+				 dev->name, num_buf);
+			dev->stats.rx_length_errors++;
+			break;
+		}
+		page = buf;
+		give_pages(rq, page);
+		--rq->num;
+	}
+err_buf:
+	dev->stats.rx_dropped++;
+	dev_kfree_skb(skb);
+	return NULL;
 }
 
 static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
@@ -332,7 +386,6 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 	struct net_device *dev = vi->dev;
 	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 	struct sk_buff *skb;
-	struct page *page;
 	struct skb_vnet_hdr *hdr;
 
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
@@ -344,25 +397,15 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 			dev_kfree_skb(buf);
 		return;
 	}
+	if (vi->mergeable_rx_bufs)
+		skb = receive_mergeable(dev, rq, buf, len);
+	else if (vi->big_packets)
+		skb = receive_big(dev, rq, buf);
+	else
+		skb = receive_small(buf, len);
 
-	if (!vi->mergeable_rx_bufs && !vi->big_packets) {
-		skb = buf;
-		len -= sizeof(struct virtio_net_hdr);
-		skb_trim(skb, len);
-	} else {
-		page = buf;
-		skb = page_to_skb(rq, page, len);
-		if (unlikely(!skb)) {
-			dev->stats.rx_dropped++;
-			give_pages(rq, page);
-			return;
-		}
-		if (vi->mergeable_rx_bufs)
-			if (receive_mergeable(rq, skb)) {
-				dev_kfree_skb(skb);
-				return;
-			}
-	}
+	if (unlikely(!skb))
+		return;
 
 	hdr = skb_vnet_hdr(skb);
 
@@ -902,7 +945,6 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	struct scatterlist sg;
 	struct virtio_net_ctrl_mq s;
 	struct net_device *dev = vi->dev;
-	int i;
 
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
@@ -916,10 +958,10 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 			 queue_pairs);
 		return -EINVAL;
 	} else {
-		for (i = vi->curr_queue_pairs; i < queue_pairs; i++)
-			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
-				schedule_delayed_work(&vi->refill, 0);
 		vi->curr_queue_pairs = queue_pairs;
+		/* virtnet_open() will refill when device is going to up. */
+		if (dev->flags & IFF_UP)
+			schedule_delayed_work(&vi->refill, 0);
 	}
 
 	return 0;
@@ -1109,6 +1151,7 @@ static int virtnet_cpu_callback(struct notifier_block *nfb,
 	default:
 		break;
 	}
+
 	return NOTIFY_OK;
 }
 
@@ -1285,6 +1328,11 @@ static void virtnet_config_changed(struct virtio_device *vdev)
 
 static void virtnet_free_queues(struct virtnet_info *vi)
 {
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		netif_napi_del(&vi->rq[i].napi);
+
 	kfree(vi->rq);
 	kfree(vi->sq);
 }
@@ -1549,7 +1597,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
@@ -1665,6 +1714,8 @@ static int virtnet_freeze(struct virtio_device *vdev)
 	struct virtnet_info *vi = vdev->priv;
 	int i;
 
+	unregister_hotcpu_notifier(&vi->nb);
+
 	/* Prevent config work handler from accessing the device */
 	mutex_lock(&vi->config_lock);
 	vi->config_enable = false;
@@ -1695,21 +1746,28 @@ static int virtnet_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
-	if (netif_running(vi->dev))
+	if (netif_running(vi->dev)) {
+		for (i = 0; i < vi->curr_queue_pairs; i++)
+			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+				schedule_delayed_work(&vi->refill, 0);
+
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_enable(&vi->rq[i]);
+	}
 
 	netif_device_attach(vi->dev);
 
-	for (i = 0; i < vi->curr_queue_pairs; i++)
-		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
-			schedule_delayed_work(&vi->refill, 0);
-
 	mutex_lock(&vi->config_lock);
 	vi->config_enable = true;
 	mutex_unlock(&vi->config_lock);
 
+	rtnl_lock();
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
+	rtnl_unlock();
+
+	err = register_hotcpu_notifier(&vi->nb);
+	if (err)
+		return err;
 
 	return 0;
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 55a62cae2cb4..d0815855d877 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1741,11 +1741,20 @@ vmxnet3_netpoll(struct net_device *netdev)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
-		vmxnet3_disable_all_intrs(adapter);
-
-	vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
-	vmxnet3_enable_all_intrs(adapter);
+	switch (adapter->intr.type) {
+#ifdef CONFIG_PCI_MSI
+	case VMXNET3_IT_MSIX: {
+		int i;
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			vmxnet3_msix_rx(0, &adapter->rx_queue[i]);
+		break;
+	}
+#endif
+	case VMXNET3_IT_MSI:
+	default:
+		vmxnet3_intr(0, adapter->netdev);
+		break;
+	}
 
 }
 #endif	/* CONFIG_NET_POLL_CONTROLLER */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 054489fdf54a..a1dc186c6f66 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -845,6 +845,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
 
 		neigh_release(n);
 
+		if (reply == NULL)
+			goto out;
+
 		skb_reset_mac_header(reply);
 		__skb_pull(reply, skb_network_offset(reply));
 		reply->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1090,7 +1093,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	iph->daddr	= dst;
 	iph->saddr	= fl4.saddr;
 	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
 	nf_reset(skb);
 
@@ -1311,7 +1314,7 @@ static void vxlan_setup(struct net_device *dev)
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
-	dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+	dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = vxlan_free;
@@ -1451,7 +1454,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 			dev->mtu = lowerdev->mtu - VXLAN_HEADROOM;
 
 		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       VXLAN_HEADROOM;
 	}
 
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 3f0c4f268751..bcfff0d62de4 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -1972,6 +1972,7 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
 	}
 
 	i = port->index;
+	memset(&sync, 0, sizeof(sync));
 	sync.clock_rate = FST_RDL(card, portConfig[i].lineSpeed);
 	/* Lucky card and linux use same encoding here */
 	sync.clock_type = FST_RDB(card, portConfig[i].internalClock) ==
diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c
index 6a24a5a70cc7..4c0a69779b89 100644
--- a/drivers/net/wan/wanxl.c
+++ b/drivers/net/wan/wanxl.c
@@ -355,6 +355,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			ifr->ifr_settings.size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
+		memset(&line, 0, sizeof(line));
 		line.clock_type = get_status(port)->clocking;
 		line.clock_rate = 0;
 		line.loopback = 0;
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 17d7fece35d2..57fc06e0f434 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1764,7 +1764,7 @@ static struct usb_device_id ar5523_id_table[] = {
 	AR5523_DEVICE_UX(0x2001, 0x3a04),	/* Dlink / DWLAG122 */
 	AR5523_DEVICE_UG(0x1690, 0x0712),	/* Gigaset / AR5523 */
 	AR5523_DEVICE_UG(0x1690, 0x0710),	/* Gigaset / SMCWUSBTG */
-	AR5523_DEVICE_UG(0x129b, 0x160c),	/* Gigaset / USB stick 108
+	AR5523_DEVICE_UG(0x129b, 0x160b),	/* Gigaset / USB stick 108
 						   (CyberTAN Technology) */
 	AR5523_DEVICE_UG(0x16ab, 0x7801),	/* Globalsun / AR5523_1 */
 	AR5523_DEVICE_UX(0x16ab, 0x7811),	/* Globalsun / AR5523_2 */
diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c
index 65fe929529a8..3bfd0b88016e 100644
--- a/drivers/net/wireless/ath/ath5k/qcu.c
+++ b/drivers/net/wireless/ath/ath5k/qcu.c
@@ -225,13 +225,7 @@ ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type,
 	} else {
 		switch (queue_type) {
 		case AR5K_TX_QUEUE_DATA:
-			for (queue = AR5K_TX_QUEUE_ID_DATA_MIN;
-				ah->ah_txq[queue].tqi_type !=
-				AR5K_TX_QUEUE_INACTIVE; queue++) {
-
-				if (queue > AR5K_TX_QUEUE_ID_DATA_MAX)
-					return -EINVAL;
-			}
+			queue = queue_info->tqi_subtype;
 			break;
 		case AR5K_TX_QUEUE_UAPSD:
 			queue = AR5K_TX_QUEUE_ID_UAPSD;
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_mac.c b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
index 8d78253c26ce..a366d6b4626f 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
@@ -76,9 +76,16 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 				mask2 |= ATH9K_INT_CST;
 			if (isr2 & AR_ISR_S2_TSFOOR)
 				mask2 |= ATH9K_INT_TSFOOR;
+
+			if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+				REG_WRITE(ah, AR_ISR_S2, isr2);
+				isr &= ~AR_ISR_BCNMISC;
+			}
 		}
 
-		isr = REG_READ(ah, AR_ISR_RAC);
+		if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)
+			isr = REG_READ(ah, AR_ISR_RAC);
+
 		if (isr == 0xffffffff) {
 			*masked = 0;
 			return false;
@@ -97,11 +104,23 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 
 			*masked |= ATH9K_INT_TX;
 
-			s0_s = REG_READ(ah, AR_ISR_S0_S);
+			if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+				s0_s = REG_READ(ah, AR_ISR_S0_S);
+				s1_s = REG_READ(ah, AR_ISR_S1_S);
+			} else {
+				s0_s = REG_READ(ah, AR_ISR_S0);
+				REG_WRITE(ah, AR_ISR_S0, s0_s);
+				s1_s = REG_READ(ah, AR_ISR_S1);
+				REG_WRITE(ah, AR_ISR_S1, s1_s);
+
+				isr &= ~(AR_ISR_TXOK |
+					 AR_ISR_TXDESC |
+					 AR_ISR_TXERR |
+					 AR_ISR_TXEOL);
+			}
+
 			ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXOK);
 			ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXDESC);
-
-			s1_s = REG_READ(ah, AR_ISR_S1_S);
 			ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXERR);
 			ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXEOL);
 		}
@@ -114,13 +133,15 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 		*masked |= mask2;
 	}
 
-	if (AR_SREV_9100(ah))
-		return true;
-
-	if (isr & AR_ISR_GENTMR) {
+	if (!AR_SREV_9100(ah) && (isr & AR_ISR_GENTMR)) {
 		u32 s5_s;
 
-		s5_s = REG_READ(ah, AR_ISR_S5_S);
+		if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+			s5_s = REG_READ(ah, AR_ISR_S5_S);
+		} else {
+			s5_s = REG_READ(ah, AR_ISR_S5);
+		}
+
 		ah->intr_gen_timer_trigger =
 				MS(s5_s, AR_ISR_S5_GENTIMER_TRIG);
 
@@ -133,8 +154,21 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 		if ((s5_s & AR_ISR_S5_TIM_TIMER) &&
 		    !(pCap->hw_caps & ATH9K_HW_CAP_AUTOSLEEP))
 			*masked |= ATH9K_INT_TIM_TIMER;
+
+		if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+			REG_WRITE(ah, AR_ISR_S5, s5_s);
+			isr &= ~AR_ISR_GENTMR;
+		}
 	}
 
+	if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+		REG_WRITE(ah, AR_ISR, isr);
+		REG_READ(ah, AR_ISR);
+	}
+
+	if (AR_SREV_9100(ah))
+		return true;
+
 	if (sync_cause) {
 		ath9k_debug_sync_cause(common, sync_cause);
 		fatal_int =
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 25b8bbbe74fe..f71a9eded5a4 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3937,18 +3937,20 @@ static void ar9003_hw_quick_drop_apply(struct ath_hw *ah, u16 freq)
 	int quick_drop;
 	s32 t[3], f[3] = {5180, 5500, 5785};
 
-	if (!(pBase->miscConfiguration & BIT(1)))
+	if (!(pBase->miscConfiguration & BIT(4)))
 		return;
 
-	if (freq < 4000)
-		quick_drop = eep->modalHeader2G.quick_drop;
-	else {
-		t[0] = eep->base_ext1.quick_drop_low;
-		t[1] = eep->modalHeader5G.quick_drop;
-		t[2] = eep->base_ext1.quick_drop_high;
-		quick_drop = ar9003_hw_power_interpolate(freq, f, t, 3);
+	if (AR_SREV_9300(ah) || AR_SREV_9580(ah) || AR_SREV_9340(ah)) {
+		if (freq < 4000) {
+			quick_drop = eep->modalHeader2G.quick_drop;
+		} else {
+			t[0] = eep->base_ext1.quick_drop_low;
+			t[1] = eep->modalHeader5G.quick_drop;
+			t[2] = eep->base_ext1.quick_drop_high;
+			quick_drop = ar9003_hw_power_interpolate(freq, f, t, 3);
+		}
+		REG_RMW_FIELD(ah, AR_PHY_AGC, AR_PHY_AGC_QUICK_DROP, quick_drop);
 	}
-	REG_RMW_FIELD(ah, AR_PHY_AGC, AR_PHY_AGC_QUICK_DROP, quick_drop);
 }
 
 static void ar9003_hw_txend_to_xpa_off_apply(struct ath_hw *ah, bool is2ghz)
@@ -3988,7 +3990,7 @@ static void ar9003_hw_xlna_bias_strength_apply(struct ath_hw *ah, bool is2ghz)
 	struct ar9300_eeprom *eep = &ah->eeprom.ar9300_eep;
 	u8 bias;
 
-	if (!(eep->baseEepHeader.featureEnable & 0x40))
+	if (!(eep->baseEepHeader.miscConfiguration & 0x40))
 		return;
 
 	if (!AR_SREV_9300(ah))
diff --git a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
index 999ab08c34e6..4ae3cf7283ea 100644
--- a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
@@ -56,7 +56,7 @@ static const u32 ar9462_2p0_baseband_postamble[][5] = {
 	{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e},
 	{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
-	{0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce},
+	{0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5},
 	{0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021},
 	{0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282},
 	{0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27},
@@ -95,7 +95,7 @@ static const u32 ar9462_2p0_baseband_postamble[][5] = {
 	{0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000},
 	{0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c},
-	{0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce},
+	{0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa},
 	{0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550},
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 62f1b7636c92..04b3822ef93a 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -145,21 +145,26 @@ static void ath9k_htc_bssid_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 	struct ath9k_vif_iter_data *iter_data = data;
 	int i;
 
-	for (i = 0; i < ETH_ALEN; i++)
-		iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+	if (iter_data->hw_macaddr != NULL) {
+		for (i = 0; i < ETH_ALEN; i++)
+			iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+	} else {
+		iter_data->hw_macaddr = mac;
+	}
 }
 
-static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
+static void ath9k_htc_set_mac_bssid_mask(struct ath9k_htc_priv *priv,
 				     struct ieee80211_vif *vif)
 {
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	struct ath9k_vif_iter_data iter_data;
 
 	/*
-	 * Use the hardware MAC address as reference, the hardware uses it
-	 * together with the BSSID mask when matching addresses.
+	 * Pick the MAC address of the first interface as the new hardware
+	 * MAC address. The hardware will use it together with the BSSID mask
+	 * when matching addresses.
 	 */
-	iter_data.hw_macaddr = common->macaddr;
+	iter_data.hw_macaddr = NULL;
 	memset(&iter_data.mask, 0xff, ETH_ALEN);
 
 	if (vif)
@@ -171,6 +176,10 @@ static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
 		ath9k_htc_bssid_iter, &iter_data);
 
 	memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
+
+	if (iter_data.hw_macaddr)
+		memcpy(common->macaddr, iter_data.hw_macaddr, ETH_ALEN);
+
 	ath_hw_setbssidmask(common);
 }
 
@@ -1076,7 +1085,7 @@ static int ath9k_htc_add_interface(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ath9k_htc_set_bssid_mask(priv, vif);
+	ath9k_htc_set_mac_bssid_mask(priv, vif);
 
 	priv->vif_slot |= (1 << avp->index);
 	priv->nvifs++;
@@ -1139,7 +1148,7 @@ static void ath9k_htc_remove_interface(struct ieee80211_hw *hw,
 
 	ath9k_htc_set_opmode(priv);
 
-	ath9k_htc_set_bssid_mask(priv, vif);
+	ath9k_htc_set_mac_bssid_mask(priv, vif);
 
 	/*
 	 * Stop ANI only if there are no associated station interfaces.
@@ -1322,21 +1331,22 @@ static void ath9k_htc_sta_rc_update(struct ieee80211_hw *hw,
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	struct ath9k_htc_target_rate trate;
 
+	if (!(changed & IEEE80211_RC_SUPP_RATES_CHANGED))
+		return;
+
 	mutex_lock(&priv->mutex);
 	ath9k_htc_ps_wakeup(priv);
 
-	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
-		memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
-		ath9k_htc_setup_rate(priv, sta, &trate);
-		if (!ath9k_htc_send_rate_cmd(priv, &trate))
-			ath_dbg(common, CONFIG,
-				"Supported rates for sta: %pM updated, rate caps: 0x%X\n",
-				sta->addr, be32_to_cpu(trate.capflags));
-		else
-			ath_dbg(common, CONFIG,
-				"Unable to update supported rates for sta: %pM\n",
-				sta->addr);
-	}
+	memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
+	ath9k_htc_setup_rate(priv, sta, &trate);
+	if (!ath9k_htc_send_rate_cmd(priv, &trate))
+		ath_dbg(common, CONFIG,
+			"Supported rates for sta: %pM updated, rate caps: 0x%X\n",
+			sta->addr, be32_to_cpu(trate.capflags));
+	else
+		ath_dbg(common, CONFIG,
+			"Unable to update supported rates for sta: %pM\n",
+			sta->addr);
 
 	ath9k_htc_ps_restore(priv);
 	mutex_unlock(&priv->mutex);
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index ae3034374bc4..d7d9e311089f 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -215,8 +215,8 @@
 #define AH_WOW_BEACON_MISS		BIT(3)
 
 enum ath_hw_txq_subtype {
-	ATH_TXQ_AC_BE = 0,
-	ATH_TXQ_AC_BK = 1,
+	ATH_TXQ_AC_BK = 0,
+	ATH_TXQ_AC_BE = 1,
 	ATH_TXQ_AC_VI = 2,
 	ATH_TXQ_AC_VO = 3,
 };
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 566109a40fb3..941b08b71308 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -311,14 +311,7 @@ int ath9k_hw_setuptxqueue(struct ath_hw *ah, enum ath9k_tx_queue type,
 		q = ATH9K_NUM_TX_QUEUES - 3;
 		break;
 	case ATH9K_TX_QUEUE_DATA:
-		for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++)
-			if (ah->txq[q].tqi_type ==
-			    ATH9K_TX_QUEUE_INACTIVE)
-				break;
-		if (q == ATH9K_NUM_TX_QUEUES) {
-			ath_err(common, "No available TX queue\n");
-			return -1;
-		}
+		q = qinfo->tqi_subtype;
 		break;
 	default:
 		ath_err(common, "Invalid TX queue type: %u\n", type);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index e33a659e224b..82a1b5b16b62 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -209,6 +209,7 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start)
 	struct ath_hw *ah = sc->sc_ah;
 	struct ath_common *common = ath9k_hw_common(ah);
 	unsigned long flags;
+	int i;
 
 	if (ath_startrecv(sc) != 0) {
 		ath_err(common, "Unable to restart recv logic\n");
@@ -236,6 +237,15 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start)
 		}
 	work:
 		ath_restart_work(sc);
+
+		for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
+			if (!ATH_TXQ_SETUP(sc, i))
+				continue;
+
+			spin_lock_bh(&sc->tx.txq[i].axq_lock);
+			ath_txq_schedule(sc, &sc->tx.txq[i]);
+			spin_unlock_bh(&sc->tx.txq[i].axq_lock);
+		}
 	}
 
 	if ((ah->caps.hw_caps & ATH9K_HW_CAP_ANT_DIV_COMB) && sc->ant_rx != 3)
@@ -543,21 +553,10 @@ chip_reset:
 
 static int ath_reset(struct ath_softc *sc)
 {
-	int i, r;
+	int r;
 
 	ath9k_ps_wakeup(sc);
-
 	r = ath_reset_internal(sc, NULL);
-
-	for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
-		if (!ATH_TXQ_SETUP(sc, i))
-			continue;
-
-		spin_lock_bh(&sc->tx.txq[i].axq_lock);
-		ath_txq_schedule(sc, &sc->tx.txq[i]);
-		spin_unlock_bh(&sc->tx.txq[i].axq_lock);
-	}
-
 	ath9k_ps_restore(sc);
 
 	return r;
@@ -890,8 +889,9 @@ void ath9k_calculate_iter_data(struct ieee80211_hw *hw,
 	struct ath_common *common = ath9k_hw_common(ah);
 
 	/*
-	 * Use the hardware MAC address as reference, the hardware uses it
-	 * together with the BSSID mask when matching addresses.
+	 * Pick the MAC address of the first interface as the new hardware
+	 * MAC address. The hardware will use it together with the BSSID mask
+	 * when matching addresses.
 	 */
 	memset(iter_data, 0, sizeof(*iter_data));
 	memset(&iter_data->mask, 0xff, ETH_ALEN);
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index e752f5d4995d..0c9b2f1c6939 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1255,14 +1255,16 @@ void ath_tx_aggr_sleep(struct ieee80211_sta *sta, struct ath_softc *sc,
 	for (tidno = 0, tid = &an->tid[tidno];
 	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
 
-		if (!tid->sched)
-			continue;
-
 		ac = tid->ac;
 		txq = ac->txq;
 
 		ath_txq_lock(sc, txq);
 
+		if (!tid->sched) {
+			ath_txq_unlock(sc, txq);
+			continue;
+		}
+
 		buffered = !skb_queue_empty(&tid->buf_q);
 
 		tid->sched = false;
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 9dce106cd6d4..95a334f0719c 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -253,6 +253,7 @@ struct ar9170 {
 	atomic_t rx_work_urbs;
 	atomic_t rx_pool_urbs;
 	kernel_ulong_t features;
+	bool usb_ep_cmd_is_bulk;
 
 	/* firmware settings */
 	struct completion fw_load_wait;
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index 307bc0ddff99..83d20c8b2ad7 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd,
 		goto err_free;
 	}
 
-	usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev,
-		AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4,
-		carl9170_usb_cmd_complete, ar, 1);
+	if (ar->usb_ep_cmd_is_bulk)
+		usb_fill_bulk_urb(urb, ar->udev,
+				  usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD),
+				  cmd, cmd->hdr.len + 4,
+				  carl9170_usb_cmd_complete, ar);
+	else
+		usb_fill_int_urb(urb, ar->udev,
+				 usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD),
+				 cmd, cmd->hdr.len + 4,
+				 carl9170_usb_cmd_complete, ar, 1);
 
 	if (free_buf)
 		urb->transfer_flags |= URB_FREE_BUFFER;
@@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw,
 static int carl9170_usb_probe(struct usb_interface *intf,
 			      const struct usb_device_id *id)
 {
+	struct usb_endpoint_descriptor *ep;
 	struct ar9170 *ar;
 	struct usb_device *udev;
-	int err;
+	int i, err;
 
 	err = usb_reset_device(interface_to_usbdev(intf));
 	if (err)
@@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf,
 	ar->intf = intf;
 	ar->features = id->driver_info;
 
+	/* We need to remember the type of endpoint 4 because it differs
+	 * between high- and full-speed configuration. The high-speed
+	 * configuration specifies it as interrupt and the full-speed
+	 * configuration as bulk endpoint. This information is required
+	 * later when sending urbs to that endpoint.
+	 */
+	for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) {
+		ep = &intf->cur_altsetting->endpoint[i].desc;
+
+		if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD &&
+		    usb_endpoint_dir_out(ep) &&
+		    usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK)
+			ar->usb_ep_cmd_is_bulk = true;
+	}
+
 	usb_set_intfdata(intf, ar);
 	SET_IEEE80211_DEV(ar->hw, &intf->dev);
 
diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h
index 7f3d461f7e8d..54376fddfaf9 100644
--- a/drivers/net/wireless/b43/b43.h
+++ b/drivers/net/wireless/b43/b43.h
@@ -731,8 +731,6 @@ enum b43_firmware_file_type {
 struct b43_request_fw_context {
 	/* The device we are requesting the fw for. */
 	struct b43_wldev *dev;
-	/* a completion event structure needed if this call is asynchronous */
-	struct completion fw_load_complete;
 	/* a pointer to the firmware object */
 	const struct firmware *blob;
 	/* The type of firmware to request. */
@@ -809,6 +807,8 @@ enum {
 struct b43_wldev {
 	struct b43_bus_dev *dev;
 	struct b43_wl *wl;
+	/* a completion event structure needed if this call is asynchronous */
+	struct completion fw_load_complete;
 
 	/* The device initialization status.
 	 * Use b43_status() to query. */
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index a95b77ab360e..0b7edd36cfa2 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -2068,6 +2068,7 @@ void b43_do_release_fw(struct b43_firmware_file *fw)
 
 static void b43_release_firmware(struct b43_wldev *dev)
 {
+	complete(&dev->fw_load_complete);
 	b43_do_release_fw(&dev->fw.ucode);
 	b43_do_release_fw(&dev->fw.pcm);
 	b43_do_release_fw(&dev->fw.initvals);
@@ -2093,7 +2094,7 @@ static void b43_fw_cb(const struct firmware *firmware, void *context)
 	struct b43_request_fw_context *ctx = context;
 
 	ctx->blob = firmware;
-	complete(&ctx->fw_load_complete);
+	complete(&ctx->dev->fw_load_complete);
 }
 
 int b43_do_request_fw(struct b43_request_fw_context *ctx,
@@ -2140,7 +2141,7 @@ int b43_do_request_fw(struct b43_request_fw_context *ctx,
 	}
 	if (async) {
 		/* do this part asynchronously */
-		init_completion(&ctx->fw_load_complete);
+		init_completion(&ctx->dev->fw_load_complete);
 		err = request_firmware_nowait(THIS_MODULE, 1, ctx->fwname,
 					      ctx->dev->dev->dev, GFP_KERNEL,
 					      ctx, b43_fw_cb);
@@ -2148,12 +2149,11 @@ int b43_do_request_fw(struct b43_request_fw_context *ctx,
 			pr_err("Unable to load firmware\n");
 			return err;
 		}
-		/* stall here until fw ready */
-		wait_for_completion(&ctx->fw_load_complete);
+		wait_for_completion(&ctx->dev->fw_load_complete);
 		if (ctx->blob)
 			goto fw_ready;
 	/* On some ARM systems, the async request will fail, but the next sync
-	 * request works. For this reason, we dall through here
+	 * request works. For this reason, we fall through here
 	 */
 	}
 	err = request_firmware(&ctx->blob, ctx->fwname,
@@ -2422,6 +2422,7 @@ error:
 
 static int b43_one_core_attach(struct b43_bus_dev *dev, struct b43_wl *wl);
 static void b43_one_core_detach(struct b43_bus_dev *dev);
+static int b43_rng_init(struct b43_wl *wl);
 
 static void b43_request_firmware(struct work_struct *work)
 {
@@ -2473,6 +2474,10 @@ start_ieee80211:
 		goto err_one_core_detach;
 	wl->hw_registred = true;
 	b43_leds_register(wl->current_dev);
+
+	/* Register HW RNG driver */
+	b43_rng_init(wl);
+
 	goto out;
 
 err_one_core_detach:
@@ -4634,9 +4639,6 @@ static void b43_wireless_core_exit(struct b43_wldev *dev)
 	if (!dev || b43_status(dev) != B43_STAT_INITIALIZED)
 		return;
 
-	/* Unregister HW RNG driver */
-	b43_rng_exit(dev->wl);
-
 	b43_set_status(dev, B43_STAT_UNINIT);
 
 	/* Stop the microcode PSM. */
@@ -4779,9 +4781,6 @@ static int b43_wireless_core_init(struct b43_wldev *dev)
 
 	b43_set_status(dev, B43_STAT_INITIALIZED);
 
-	/* Register HW RNG driver */
-	b43_rng_init(dev->wl);
-
 out:
 	return err;
 
@@ -5442,6 +5441,9 @@ static void b43_bcma_remove(struct bcma_device *core)
 
 	b43_one_core_detach(wldev->dev);
 
+	/* Unregister HW RNG driver */
+	b43_rng_exit(wl);
+
 	b43_leds_unregister(wl);
 
 	ieee80211_free_hw(wl->hw);
@@ -5519,6 +5521,9 @@ static void b43_ssb_remove(struct ssb_device *sdev)
 
 	b43_one_core_detach(dev);
 
+	/* Unregister HW RNG driver */
+	b43_rng_exit(wl);
+
 	if (list_empty(&wl->devlist)) {
 		b43_leds_unregister(wl);
 		/* Last core on the chip unregistered.
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 7c970d3ae358..80ecca3e1465 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -5175,22 +5175,22 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev,
 	int ch = new_channel->hw_value;
 
 	u16 old_band_5ghz;
-	u32 tmp32;
+	u16 tmp16;
 
 	old_band_5ghz =
 		b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
 	if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 		b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
 	} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
 		b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 	}
 
 	b43_chantab_phy_upload(dev, e);
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 8cb206a89083..ebcce00ce067 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -810,9 +810,13 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		break;
 	case B43_PHYTYPE_G:
 		status.band = IEEE80211_BAND_2GHZ;
-		/* chanid is the radio channel cookie value as used
-		 * to tune the radio. */
-		status.freq = chanid + 2400;
+		/* Somewhere between 478.104 and 508.1084 firmware for G-PHY
+		 * has been modified to be compatible with N-PHY and others.
+		 */
+		if (dev->fw.rev >= 508)
+			status.freq = ieee80211_channel_to_frequency(chanid, status.band);
+		else
+			status.freq = chanid + 2400;
 		break;
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
@@ -821,10 +825,10 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		 * channel number in b43. */
 		if (chanstat & B43_RX_CHAN_5GHZ) {
 			status.band = IEEE80211_BAND_5GHZ;
-			status.freq = b43_freq_to_channel_5ghz(chanid);
+			status.freq = b43_channel_to_freq_5ghz(chanid);
 		} else {
 			status.band = IEEE80211_BAND_2GHZ;
-			status.freq = b43_freq_to_channel_2ghz(chanid);
+			status.freq = b43_channel_to_freq_2ghz(chanid);
 		}
 		break;
 	default:
diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c
index 572668821862..349c77605231 100644
--- a/drivers/net/wireless/b43legacy/main.c
+++ b/drivers/net/wireless/b43legacy/main.c
@@ -3919,6 +3919,7 @@ static void b43legacy_remove(struct ssb_device *dev)
 	 * as the ieee80211 unreg will destroy the workqueue. */
 	cancel_work_sync(&wldev->restart_work);
 	cancel_work_sync(&wl->firmware_load);
+	complete(&wldev->fw_load_complete);
 
 	B43legacy_WARN_ON(!wl);
 	if (!wldev->fw.ucode)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
index 44fa0cdbf97b..0f6eb2b6d381 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
@@ -575,8 +575,6 @@ static struct sdio_driver brcmf_sdmmc_driver = {
 
 static int brcmf_sdio_pd_probe(struct platform_device *pdev)
 {
-	int ret;
-
 	brcmf_dbg(SDIO, "Enter\n");
 
 	brcmfmac_sdio_pdata = pdev->dev.platform_data;
@@ -584,11 +582,7 @@ static int brcmf_sdio_pd_probe(struct platform_device *pdev)
 	if (brcmfmac_sdio_pdata->power_on)
 		brcmfmac_sdio_pdata->power_on();
 
-	ret = sdio_register_driver(&brcmf_sdmmc_driver);
-	if (ret)
-		brcmf_err("sdio_register_driver failed: %d\n", ret);
-
-	return ret;
+	return 0;
 }
 
 static int brcmf_sdio_pd_remove(struct platform_device *pdev)
@@ -610,6 +604,15 @@ static struct platform_driver brcmf_sdio_pd = {
 	}
 };
 
+void brcmf_sdio_register(void)
+{
+	int ret;
+
+	ret = sdio_register_driver(&brcmf_sdmmc_driver);
+	if (ret)
+		brcmf_err("sdio_register_driver failed: %d\n", ret);
+}
+
 void brcmf_sdio_exit(void)
 {
 	brcmf_dbg(SDIO, "Enter\n");
@@ -620,18 +623,13 @@ void brcmf_sdio_exit(void)
 		sdio_unregister_driver(&brcmf_sdmmc_driver);
 }
 
-void brcmf_sdio_init(void)
+void __init brcmf_sdio_init(void)
 {
 	int ret;
 
 	brcmf_dbg(SDIO, "Enter\n");
 
 	ret = platform_driver_probe(&brcmf_sdio_pd, brcmf_sdio_pd_probe);
-	if (ret == -ENODEV) {
-		brcmf_dbg(SDIO, "No platform data available, registering without.\n");
-		ret = sdio_register_driver(&brcmf_sdmmc_driver);
-	}
-
-	if (ret)
-		brcmf_err("driver registration failed: %d\n", ret);
+	if (ret == -ENODEV)
+		brcmf_dbg(SDIO, "No platform data available.\n");
 }
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
index 080395f49fa5..e715d3396c2c 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
@@ -154,10 +154,11 @@ extern int brcmf_bus_start(struct device *dev);
 #ifdef CONFIG_BRCMFMAC_SDIO
 extern void brcmf_sdio_exit(void);
 extern void brcmf_sdio_init(void);
+extern void brcmf_sdio_register(void);
 #endif
 #ifdef CONFIG_BRCMFMAC_USB
 extern void brcmf_usb_exit(void);
-extern void brcmf_usb_init(void);
+extern void brcmf_usb_register(void);
 #endif
 
 #endif				/* _BRCMF_BUS_H_ */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
index 2c593570497c..95d709959e16 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
@@ -1034,21 +1034,23 @@ u32 brcmf_get_chip_info(struct brcmf_if *ifp)
 	return bus->chip << 4 | bus->chiprev;
 }
 
-static void brcmf_driver_init(struct work_struct *work)
+static void brcmf_driver_register(struct work_struct *work)
 {
-	brcmf_debugfs_init();
-
 #ifdef CONFIG_BRCMFMAC_SDIO
-	brcmf_sdio_init();
+	brcmf_sdio_register();
 #endif
 #ifdef CONFIG_BRCMFMAC_USB
-	brcmf_usb_init();
+	brcmf_usb_register();
 #endif
 }
-static DECLARE_WORK(brcmf_driver_work, brcmf_driver_init);
+static DECLARE_WORK(brcmf_driver_work, brcmf_driver_register);
 
 static int __init brcmfmac_module_init(void)
 {
+	brcmf_debugfs_init();
+#ifdef CONFIG_BRCMFMAC_SDIO
+	brcmf_sdio_init();
+#endif
 	if (!schedule_work(&brcmf_driver_work))
 		return -EBUSY;
 
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
index 01aed7ad6bec..b0ab98b0a226 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
@@ -1532,7 +1532,7 @@ void brcmf_usb_exit(void)
 	brcmf_release_fw(&fw_image_list);
 }
 
-void brcmf_usb_init(void)
+void brcmf_usb_register(void)
 {
 	brcmf_dbg(USB, "Enter\n");
 	INIT_LIST_HEAD(&fw_image_list);
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 3a6544710c8a..8e8543cfe489 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -426,6 +426,12 @@ static int brcms_ops_start(struct ieee80211_hw *hw)
 	bool blocked;
 	int err;
 
+	if (!wl->ucode.bcm43xx_bomminor) {
+		err = brcms_request_fw(wl, wl->wlc->hw->d11core);
+		if (err)
+			return -ENOENT;
+	}
+
 	ieee80211_wake_queues(hw);
 	spin_lock_bh(&wl->lock);
 	blocked = brcms_rfkill_set_hw_state(wl);
@@ -433,14 +439,6 @@ static int brcms_ops_start(struct ieee80211_hw *hw)
 	if (!blocked)
 		wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy);
 
-	if (!wl->ucode.bcm43xx_bomminor) {
-		err = brcms_request_fw(wl, wl->wlc->hw->d11core);
-		if (err) {
-			brcms_remove(wl->wlc->hw->d11core);
-			return -ENOENT;
-		}
-	}
-
 	spin_lock_bh(&wl->lock);
 	/* avoid acknowledging frames before a non-monitor device is added */
 	wl->mute_tx = true;
diff --git a/drivers/net/wireless/iwlegacy/3945.c b/drivers/net/wireless/iwlegacy/3945.c
index dc1e6da9976a..9a5f36e5c864 100644
--- a/drivers/net/wireless/iwlegacy/3945.c
+++ b/drivers/net/wireless/iwlegacy/3945.c
@@ -462,6 +462,8 @@ il3945_is_network_packet(struct il_priv *il, struct ieee80211_hdr *header)
 	}
 }
 
+#define SMALL_PACKET_SIZE 256
+
 static void
 il3945_pass_packet_to_mac80211(struct il_priv *il, struct il_rx_buf *rxb,
 			       struct ieee80211_rx_status *stats)
@@ -470,14 +472,13 @@ il3945_pass_packet_to_mac80211(struct il_priv *il, struct il_rx_buf *rxb,
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)IL_RX_DATA(pkt);
 	struct il3945_rx_frame_hdr *rx_hdr = IL_RX_HDR(pkt);
 	struct il3945_rx_frame_end *rx_end = IL_RX_END(pkt);
-	u16 len = le16_to_cpu(rx_hdr->len);
+	u32 len = le16_to_cpu(rx_hdr->len);
 	struct sk_buff *skb;
 	__le16 fc = hdr->frame_control;
+	u32 fraglen = PAGE_SIZE << il->hw_params.rx_page_order;
 
 	/* We received data from the HW, so stop the watchdog */
-	if (unlikely
-	    (len + IL39_RX_FRAME_SIZE >
-	     PAGE_SIZE << il->hw_params.rx_page_order)) {
+	if (unlikely(len + IL39_RX_FRAME_SIZE > fraglen)) {
 		D_DROP("Corruption detected!\n");
 		return;
 	}
@@ -488,26 +489,32 @@ il3945_pass_packet_to_mac80211(struct il_priv *il, struct il_rx_buf *rxb,
 		return;
 	}
 
-	skb = dev_alloc_skb(128);
+	skb = dev_alloc_skb(SMALL_PACKET_SIZE);
 	if (!skb) {
 		IL_ERR("dev_alloc_skb failed\n");
 		return;
 	}
 
 	if (!il3945_mod_params.sw_crypto)
-		il_set_decrypted_flag(il, (struct ieee80211_hdr *)rxb_addr(rxb),
+		il_set_decrypted_flag(il, (struct ieee80211_hdr *)pkt,
 				      le32_to_cpu(rx_end->status), stats);
 
-	skb_add_rx_frag(skb, 0, rxb->page,
-			(void *)rx_hdr->payload - (void *)pkt, len,
-			len);
-
+	/* If frame is small enough to fit into skb->head, copy it
+	 * and do not consume a full page
+	 */
+	if (len <= SMALL_PACKET_SIZE) {
+		memcpy(skb_put(skb, len), rx_hdr->payload, len);
+	} else {
+		skb_add_rx_frag(skb, 0, rxb->page,
+				(void *)rx_hdr->payload - (void *)pkt, len,
+				fraglen);
+		il->alloc_rxb_page--;
+		rxb->page = NULL;
+	}
 	il_update_stats(il, false, fc, len);
 	memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
 
 	ieee80211_rx(il->hw, skb);
-	il->alloc_rxb_page--;
-	rxb->page = NULL;
 }
 
 #define IL_DELAY_NEXT_SCAN_AFTER_ASSOC (HZ*6)
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index a8eff95ee677..d2586f09f45c 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -574,9 +574,11 @@ il4965_translate_rx_status(struct il_priv *il, u32 decrypt_in)
 	return decrypt_out;
 }
 
+#define SMALL_PACKET_SIZE 256
+
 static void
 il4965_pass_packet_to_mac80211(struct il_priv *il, struct ieee80211_hdr *hdr,
-			       u16 len, u32 ampdu_status, struct il_rx_buf *rxb,
+			       u32 len, u32 ampdu_status, struct il_rx_buf *rxb,
 			       struct ieee80211_rx_status *stats)
 {
 	struct sk_buff *skb;
@@ -593,21 +595,25 @@ il4965_pass_packet_to_mac80211(struct il_priv *il, struct ieee80211_hdr *hdr,
 	    il_set_decrypted_flag(il, hdr, ampdu_status, stats))
 		return;
 
-	skb = dev_alloc_skb(128);
+	skb = dev_alloc_skb(SMALL_PACKET_SIZE);
 	if (!skb) {
 		IL_ERR("dev_alloc_skb failed\n");
 		return;
 	}
 
-	skb_add_rx_frag(skb, 0, rxb->page, (void *)hdr - rxb_addr(rxb), len,
-			len);
+	if (len <= SMALL_PACKET_SIZE) {
+		memcpy(skb_put(skb, len), hdr, len);
+	} else {
+		skb_add_rx_frag(skb, 0, rxb->page, (void *)hdr - rxb_addr(rxb),
+				len, PAGE_SIZE << il->hw_params.rx_page_order);
+		il->alloc_rxb_page--;
+		rxb->page = NULL;
+	}
 
 	il_update_stats(il, false, fc, len);
 	memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
 
 	ieee80211_rx(il->hw, skb);
-	il->alloc_rxb_page--;
-	rxb->page = NULL;
 }
 
 /* Called for N_RX (legacy ABG frames), or
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index e04f3da1ccb3..e9d09f19f856 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -739,6 +739,24 @@ static int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	return ret;
 }
 
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		return false;
+	return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		return false;
+	if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+		return true;
+
+	/* disabled by default */
+	return false;
+}
+
 static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   enum ieee80211_ampdu_mlme_action action,
@@ -760,7 +778,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		if (!iwl_enable_rx_ampdu(priv->cfg))
 			break;
 		IWL_DEBUG_HT(priv, "start Rx\n");
 		ret = iwl_sta_rx_agg_start(priv, sta, tid, *ssn);
@@ -772,7 +790,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 	case IEEE80211_AMPDU_TX_START:
 		if (!priv->trans->ops->txq_enable)
 			break;
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		if (!iwl_enable_tx_ampdu(priv->cfg))
 			break;
 		IWL_DEBUG_HT(priv, "start Tx\n");
 		ret = iwlagn_tx_agg_start(priv, vif, sta, tid, ssn);
diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c
index a8afc7bee545..c2b8e49d00d3 100644
--- a/drivers/net/wireless/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/iwlwifi/dvm/main.c
@@ -252,13 +252,17 @@ static void iwl_bg_bt_runtime_config(struct work_struct *work)
 	struct iwl_priv *priv =
 		container_of(work, struct iwl_priv, bt_runtime_config);
 
+	mutex_lock(&priv->mutex);
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
-		return;
+		goto out;
 
 	/* dont send host command if rf-kill is on */
 	if (!iwl_is_ready_rf(priv))
-		return;
+		goto out;
+
 	iwlagn_send_advance_bt_config(priv);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void iwl_bg_bt_full_concurrency(struct work_struct *work)
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index c3c13ce96eb0..e800002d6158 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -590,6 +590,7 @@ void iwl_deactivate_station(struct iwl_priv *priv, const u8 sta_id,
 			sizeof(priv->tid_data[sta_id][tid]));
 
 	priv->stations[sta_id].used &= ~IWL_STA_DRIVER_ACTIVE;
+	priv->stations[sta_id].used &= ~IWL_STA_UCODE_INPROGRESS;
 
 	priv->num_stations--;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a900aaf47790..2b5dbff9eadb 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -445,27 +445,19 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 	/* Copy MAC header from skb into command buffer */
 	memcpy(tx_cmd->hdr, hdr, hdr_len);
 
+	txq_id = info->hw_queue;
+
 	if (is_agg)
 		txq_id = priv->tid_data[sta_id][tid].agg.txq_id;
 	else if (info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) {
 		/*
-		 * Send this frame after DTIM -- there's a special queue
-		 * reserved for this for contexts that support AP mode.
-		 */
-		txq_id = ctx->mcast_queue;
-
-		/*
 		 * The microcode will clear the more data
 		 * bit in the last frame it transmits.
 		 */
 		hdr->frame_control |=
 			cpu_to_le16(IEEE80211_FCTL_MOREDATA);
-	} else if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
-		txq_id = IWL_AUX_QUEUE;
-	else
-		txq_id = ctx->ac_to_queue[skb_get_queue_mapping(skb)];
+	}
 
-	WARN_ON_ONCE(!is_agg && txq_id != info->hw_queue);
 	WARN_ON_ONCE(is_agg &&
 		     priv->queue_to_mac80211[txq_id] != info->hw_queue);
 
@@ -1330,8 +1322,6 @@ int iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv,
 	struct iwl_compressed_ba_resp *ba_resp = (void *)pkt->data;
 	struct iwl_ht_agg *agg;
 	struct sk_buff_head reclaimed_skbs;
-	struct ieee80211_tx_info *info;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id;
 	int tid;
@@ -1418,22 +1408,28 @@ int iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv,
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(priv->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
 			info = IEEE80211_SKB_CB(skb);
 			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_resp->txed_2_done;
 			info->status.ampdu_len = ba_resp->txed;
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index b5ab8d1bcac0..5282088d6c14 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -268,6 +268,12 @@ const struct iwl_cfg iwl6035_2agn_cfg = {
 	.ht_params = &iwl6000_ht_params,
 };
 
+const struct iwl_cfg iwl6035_2agn_sff_cfg = {
+	.name = "Intel(R) Centrino(R) Ultimate-N 6235 AGN",
+	IWL_DEVICE_6035,
+	.ht_params = &iwl6000_ht_params,
+};
+
 const struct iwl_cfg iwl1030_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 1030 BGN",
 	IWL_DEVICE_6030,
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index dc94d44d95cd..9fd01dc5146b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -125,21 +125,63 @@ static const struct iwl_ht_params iwl7000_ht_params = {
 
 
 const struct iwl_cfg iwl7260_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC7260",
+	.name = "Intel(R) Dual Band Wireless AC 7260",
 	.fw_name_pre = IWL7260_FW_PRE,
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL7260_NVM_VERSION,
 	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
 };
 
-const struct iwl_cfg iwl3160_ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC3160",
+const struct iwl_cfg iwl7260_2n_cfg = {
+	.name = "Intel(R) Dual Band Wireless N 7260",
+	.fw_name_pre = IWL7260_FW_PRE,
+	IWL_DEVICE_7000,
+	.ht_params = &iwl7000_ht_params,
+	.nvm_ver = IWL7260_NVM_VERSION,
+	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl7260_n_cfg = {
+	.name = "Intel(R) Wireless N 7260",
+	.fw_name_pre = IWL7260_FW_PRE,
+	IWL_DEVICE_7000,
+	.ht_params = &iwl7000_ht_params,
+	.nvm_ver = IWL7260_NVM_VERSION,
+	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_2ac_cfg = {
+	.name = "Intel(R) Dual Band Wireless AC 3160",
+	.fw_name_pre = IWL3160_FW_PRE,
+	IWL_DEVICE_7000,
+	.ht_params = &iwl7000_ht_params,
+	.nvm_ver = IWL3160_NVM_VERSION,
+	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_2n_cfg = {
+	.name = "Intel(R) Dual Band Wireless N 3160",
+	.fw_name_pre = IWL3160_FW_PRE,
+	IWL_DEVICE_7000,
+	.ht_params = &iwl7000_ht_params,
+	.nvm_ver = IWL3160_NVM_VERSION,
+	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_n_cfg = {
+	.name = "Intel(R) Wireless N 3160",
 	.fw_name_pre = IWL3160_FW_PRE,
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3160_NVM_VERSION,
 	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+	.host_interrupt_operation_mode = true,
 };
 
 MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h
index c38aa8f77554..8ca006b12a32 100644
--- a/drivers/net/wireless/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/iwlwifi/iwl-config.h
@@ -241,6 +241,8 @@ struct iwl_eeprom_params {
  * @rx_with_siso_diversity: 1x1 device with rx antenna diversity
  * @internal_wimax_coex: internal wifi/wimax combo device
  * @temp_offset_v2: support v2 of temperature offset calibration
+ * @host_interrupt_operation_mode: device needs host interrupt operation
+ *	mode set
  *
  * We enable the driver to be backward compatible wrt. hardware features.
  * API differences in uCode shouldn't be handled here but through TLVs
@@ -273,6 +275,7 @@ struct iwl_cfg {
 	const bool rx_with_siso_diversity;
 	const bool internal_wimax_coex;
 	const bool temp_offset_v2;
+	const bool host_interrupt_operation_mode;
 };
 
 /*
@@ -316,10 +319,15 @@ extern const struct iwl_cfg iwl2000_2bgn_cfg;
 extern const struct iwl_cfg iwl2000_2bgn_d_cfg;
 extern const struct iwl_cfg iwl2030_2bgn_cfg;
 extern const struct iwl_cfg iwl6035_2agn_cfg;
+extern const struct iwl_cfg iwl6035_2agn_sff_cfg;
 extern const struct iwl_cfg iwl105_bgn_cfg;
 extern const struct iwl_cfg iwl105_bgn_d_cfg;
 extern const struct iwl_cfg iwl135_bgn_cfg;
 extern const struct iwl_cfg iwl7260_2ac_cfg;
-extern const struct iwl_cfg iwl3160_ac_cfg;
+extern const struct iwl_cfg iwl7260_2n_cfg;
+extern const struct iwl_cfg iwl7260_n_cfg;
+extern const struct iwl_cfg iwl3160_2ac_cfg;
+extern const struct iwl_cfg iwl3160_2n_cfg;
+extern const struct iwl_cfg iwl3160_n_cfg;
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-csr.h b/drivers/net/wireless/iwlwifi/iwl-csr.h
index 20e845d4da04..bba1af4d406c 100644
--- a/drivers/net/wireless/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/iwlwifi/iwl-csr.h
@@ -463,13 +463,10 @@
  * the CSR_INT_COALESCING is an 8 bit register in 32-usec unit
  *
  * default interrupt coalescing timer is 64 x 32 = 2048 usecs
- * default interrupt coalescing calibration timer is 16 x 32 = 512 usecs
  */
 #define IWL_HOST_INT_TIMEOUT_MAX	(0xFF)
 #define IWL_HOST_INT_TIMEOUT_DEF	(0x40)
 #define IWL_HOST_INT_TIMEOUT_MIN	(0x0)
-#define IWL_HOST_INT_CALIB_TIMEOUT_MAX	(0xFF)
-#define IWL_HOST_INT_CALIB_TIMEOUT_DEF	(0x10)
-#define IWL_HOST_INT_CALIB_TIMEOUT_MIN	(0x0)
+#define IWL_HOST_INT_OPER_MODE		BIT(31)
 
 #endif /* !__iwl_csr_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c
index 40fed1f511e2..96050e6c3d57 100644
--- a/drivers/net/wireless/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/iwlwifi/iwl-drv.c
@@ -1211,7 +1211,7 @@ module_param_named(swcrypto, iwlwifi_mod_params.sw_crypto, int, S_IRUGO);
 MODULE_PARM_DESC(swcrypto, "using crypto in software (default 0 [hardware])");
 module_param_named(11n_disable, iwlwifi_mod_params.disable_11n, uint, S_IRUGO);
 MODULE_PARM_DESC(11n_disable,
-	"disable 11n functionality, bitmap: 1: full, 2: agg TX, 4: agg RX");
+	"disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX");
 module_param_named(amsdu_size_8K, iwlwifi_mod_params.amsdu_size_8K,
 		   int, S_IRUGO);
 MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size (default 0)");
diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h
index d6f6c37c09fd..e99bc55046e5 100644
--- a/drivers/net/wireless/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h
@@ -79,9 +79,12 @@ enum iwl_power_level {
 	IWL_POWER_NUM
 };
 
-#define IWL_DISABLE_HT_ALL	BIT(0)
-#define IWL_DISABLE_HT_TXAGG	BIT(1)
-#define IWL_DISABLE_HT_RXAGG	BIT(2)
+enum iwl_disable_11n {
+	IWL_DISABLE_HT_ALL	 = BIT(0),
+	IWL_DISABLE_HT_TXAGG	 = BIT(1),
+	IWL_DISABLE_HT_RXAGG	 = BIT(2),
+	IWL_ENABLE_HT_TXAGG	 = BIT(3),
+};
 
 /**
  * struct iwl_mod_params
@@ -90,7 +93,7 @@ enum iwl_power_level {
  *
  * @sw_crypto: using hardware encryption, default = 0
  * @disable_11n: disable 11n capabilities, default = 0,
- *	use IWL_DISABLE_HT_* constants
+ *	use IWL_[DIS,EN]ABLE_HT_* constants
  * @amsdu_size_8K: enable 8K amsdu size, default = 0
  * @restart_fw: restart firmware, default = 1
  * @plcp_check: enable plcp health check, default = true
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 6199a0a597a6..a7cf535216c9 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -180,6 +180,11 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 
 	for (ch_idx = 0; ch_idx < IWL_NUM_CHANNELS; ch_idx++) {
 		ch_flags = __le16_to_cpup(nvm_ch_flags + ch_idx);
+
+		if (ch_idx >= NUM_2GHZ_CHANNELS &&
+		    !data->sku_cap_band_52GHz_enable)
+			ch_flags &= ~NVM_CHANNEL_VALID;
+
 		if (!(ch_flags & NVM_CHANNEL_VALID)) {
 			IWL_DEBUG_EEPROM(dev,
 					 "Ch. %d Flags %x [%sGHz] - No traffic\n",
diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h
index 386f2a7c87cb..c26a6dc21eef 100644
--- a/drivers/net/wireless/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/iwlwifi/iwl-prph.h
@@ -260,4 +260,8 @@ static inline unsigned int SCD_QUEUE_STATUS_BITS(unsigned int chnl)
 
 /*********************** END TX SCHEDULER *************************************/
 
+/* Oscillator clock */
+#define OSC_CLK				(0xa04068)
+#define OSC_CLK_FORCE_CONTROL		(0x8)
+
 #endif				/* __iwl_prph_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 7a13790b5bfe..d8df1d9b0de3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -489,6 +489,7 @@ enum iwl_trans_state {
  *	Set during transport allocation.
  * @hw_id_str: a string with info about HW ID. Set during transport allocation.
  * @pm_support: set to true in start_hw if link pm is supported
+ * @ltr_enabled: set to true if the LTR is enabled
  * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
  *	The user should use iwl_trans_{alloc,free}_tx_cmd.
  * @dev_cmd_headroom: room needed for the transport's private use before the
@@ -513,6 +514,7 @@ struct iwl_trans {
 	u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
 
 	bool pm_support;
+	bool ltr_enabled;
 
 	/* The following fields are internal only */
 	struct kmem_cache *dev_cmd_pool;
@@ -605,8 +607,10 @@ static inline int iwl_trans_send_cmd(struct iwl_trans *trans,
 {
 	int ret;
 
-	WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
-		  "%s bad state = %d", __func__, trans->state);
+	if (trans->state != IWL_TRANS_FW_ALIVE) {
+		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		return -EIO;
+	}
 
 	if (!(cmd->flags & CMD_ASYNC))
 		lock_map_acquire_read(&trans->sync_cmd_lockdep_map);
diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
index 810bfa5f6de0..9649f511bd5b 100644
--- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
@@ -523,8 +523,11 @@ void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	mutex_lock(&mvm->mutex);
 
-	/* Rssi update while not associated ?! */
-	if (WARN_ON_ONCE(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT))
+	/*
+	 * Rssi update while not associated - can happen since the statistics
+	 * are handled asynchronously
+	 */
+	if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)
 		goto out_unlock;
 
 	/* No open connection - reports should be disabled */
diff --git a/drivers/net/wireless/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
index 2053dccefcd6..109dc8e437f5 100644
--- a/drivers/net/wireless/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
@@ -119,6 +119,10 @@ static ssize_t iwl_dbgfs_sta_drain_write(struct file *file,
 
 	if (sscanf(buf, "%d %d", &sta_id, &drain) != 2)
 		return -EINVAL;
+	if (sta_id < 0 || sta_id >= IWL_MVM_STATION_COUNT)
+		return -EINVAL;
+	if (drain < 0 || drain > 1)
+		return -EINVAL;
 
 	mutex_lock(&mvm->mutex);
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
index 81fe45f46be7..ac38ecf13c18 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
@@ -67,7 +67,40 @@
 /* Power Management Commands, Responses, Notifications */
 
 /**
- * enum iwl_scan_flags - masks for power table command flags
+ * enum iwl_ltr_config_flags - masks for LTR config command flags
+ * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status
+ * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow
+ *	memory access
+ * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR
+ *	reg change
+ * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from
+ *	D0 to D3
+ * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register
+ * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register
+ * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD
+ */
+enum iwl_ltr_config_flags {
+	LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0),
+	LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1),
+	LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2),
+	LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3),
+	LTR_CFG_FLAG_SW_SET_SHORT = BIT(4),
+	LTR_CFG_FLAG_SW_SET_LONG = BIT(5),
+	LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6),
+};
+
+/**
+ * struct iwl_ltr_config_cmd - configures the LTR
+ * @flags: See %enum iwl_ltr_config_flags
+ */
+struct iwl_ltr_config_cmd {
+	__le32 flags;
+	__le32 static_long;
+	__le32 static_short;
+} __packed;
+
+/**
+ * enum iwl_power_flags - masks for power table command flags
  * @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off
  *		receiver and transmitter. '0' - does not allow.
  * @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index c6384555aab4..4b6730db42a5 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -138,6 +138,7 @@ enum {
 
 	/* Power */
 	POWER_TABLE_CMD = 0x77,
+	LTR_CONFIG = 0xee,
 
 	/* Scanning */
 	SCAN_REQUEST_CMD = 0x80,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index e18c92dd60ec..d250d451fd01 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -443,6 +443,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	if (ret)
 		goto error;
 
+	if (mvm->trans->ltr_enabled) {
+		struct iwl_ltr_config_cmd cmd = {
+			.flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE),
+		};
+
+		WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
+					     sizeof(cmd), &cmd));
+	}
+
 	IWL_DEBUG_INFO(mvm, "RT uCode started.\n");
 
 	return 0;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index f7545e06ce2a..88b9c0964696 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -278,6 +278,24 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 	ieee80211_free_txskb(hw, skb);
 }
 
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		return false;
+	return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		return false;
+	if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+		return true;
+
+	/* enabled by default */
+	return true;
+}
+
 static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    enum ieee80211_ampdu_mlme_action action,
@@ -297,7 +315,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) {
+		if (!iwl_enable_rx_ampdu(mvm->cfg)) {
 			ret = -EINVAL;
 			break;
 		}
@@ -307,7 +325,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 		ret = iwl_mvm_sta_rx_agg(mvm, sta, tid, 0, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) {
+		if (!iwl_enable_tx_ampdu(mvm->cfg)) {
 			ret = -EINVAL;
 			break;
 		}
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index b29c31a41594..649d301cfa2a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -293,6 +293,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = {
 	CMD(BT_PROFILE_NOTIFICATION),
 	CMD(BT_CONFIG),
 	CMD(MCAST_FILTER_CMD),
+	CMD(LTR_CONFIG),
 };
 #undef CMD
 
@@ -424,6 +425,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
  out_unregister:
 	ieee80211_unregister_hw(mvm->hw);
+	iwl_mvm_leds_exit(mvm);
  out_free:
 	iwl_phy_db_free(mvm->phy_db);
 	kfree(mvm->scan_cmd);
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 8e1f6c095a9e..b987dfb879df 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -313,7 +313,8 @@ int iwl_mvm_scan_request(struct iwl_mvm *mvm,
 
 	iwl_mvm_scan_fill_ssids(cmd, req);
 
-	cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL);
+	cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL |
+					   TX_CMD_FLG_BT_DIS);
 	cmd->tx_cmd.sta_id = mvm->aux_sta.sta_id;
 	cmd->tx_cmd.life_time = cpu_to_le32(TX_CMD_LIFE_TIME_INFINITE);
 	cmd->tx_cmd.rate_n_flags =
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index a2e6112e91e9..4ec8385e4307 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -819,16 +819,12 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 	struct iwl_mvm_ba_notif *ba_notif = (void *)pkt->data;
 	struct sk_buff_head reclaimed_skbs;
 	struct iwl_mvm_tid_data *tid_data;
-	struct ieee80211_tx_info *info;
 	struct ieee80211_sta *sta;
 	struct iwl_mvm_sta *mvmsta;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id, tid, freed;
-
 	/* "flow" corresponds to Tx queue */
 	u16 scd_flow = le16_to_cpu(ba_notif->scd_flow);
-
 	/* "ssn" is start of block-ack Tx window, corresponds to index
 	 * (in Tx queue's circular buffer) of first TFD/frame in window */
 	u16 ba_resp_scd_ssn = le16_to_cpu(ba_notif->scd_ssn);
@@ -885,22 +881,26 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
-			info = IEEE80211_SKB_CB(skb);
-			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_notif->txed_2_done;
 			info->status.ampdu_len = ba_notif->txed;
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index 687b34e387ac..0d9e08160fec 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -401,6 +401,8 @@ void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm)
 			mvm->status, table.valid);
 	}
 
+	IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
+
 	trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
 				      table.data1, table.data2, table.data3,
 				      table.blink1, table.blink2, table.ilink1,
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 5283b5552e6f..bb020ad3f76c 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -138,13 +138,16 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 6x00 Series */
 	{IWL_PCI_DEVICE(0x422B, 0x1101, iwl6000_3agn_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1108, iwl6000_3agn_cfg)},
 	{IWL_PCI_DEVICE(0x422B, 0x1121, iwl6000_3agn_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1128, iwl6000_3agn_cfg)},
 	{IWL_PCI_DEVICE(0x422C, 0x1301, iwl6000i_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x422C, 0x1306, iwl6000i_2abg_cfg)},
 	{IWL_PCI_DEVICE(0x422C, 0x1307, iwl6000i_2bg_cfg)},
 	{IWL_PCI_DEVICE(0x422C, 0x1321, iwl6000i_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x422C, 0x1326, iwl6000i_2abg_cfg)},
 	{IWL_PCI_DEVICE(0x4238, 0x1111, iwl6000_3agn_cfg)},
+	{IWL_PCI_DEVICE(0x4238, 0x1118, iwl6000_3agn_cfg)},
 	{IWL_PCI_DEVICE(0x4239, 0x1311, iwl6000i_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x4239, 0x1316, iwl6000i_2abg_cfg)},
 
@@ -152,12 +155,16 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x0082, 0x1301, iwl6005_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x1306, iwl6005_2abg_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x1307, iwl6005_2bg_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1308, iwl6005_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x1321, iwl6005_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x1326, iwl6005_2abg_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1328, iwl6005_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x0085, 0x1311, iwl6005_2agn_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0x1318, iwl6005_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x0085, 0x1316, iwl6005_2abg_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0xC020, iwl6005_2agn_sff_cfg)},
 	{IWL_PCI_DEVICE(0x0085, 0xC220, iwl6005_2agn_sff_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0xC228, iwl6005_2agn_sff_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x4820, iwl6005_2agn_d_cfg)},
 	{IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_2agn_mow1_cfg)},/* low 5GHz active */
 	{IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_2agn_mow2_cfg)},/* high 5GHz active */
@@ -239,8 +246,11 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 6x35 Series */
 	{IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x406A, iwl6035_2agn_sff_cfg)},
 	{IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)},
+	{IWL_PCI_DEVICE(0x088F, 0x426A, iwl6035_2agn_sff_cfg)},
 	{IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x446A, iwl6035_2agn_sff_cfg)},
 	{IWL_PCI_DEVICE(0x088E, 0x4860, iwl6035_2agn_cfg)},
 	{IWL_PCI_DEVICE(0x088F, 0x5260, iwl6035_2agn_cfg)},
 
@@ -257,10 +267,87 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 7000 Series */
 	{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4162, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4270, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4272, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4260, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x426A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4262, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4470, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4472, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4460, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x446A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4462, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4870, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x486E, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4570, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4560, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4370, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4360, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x5070, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4020, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x402A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4220, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4420, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0xC070, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC072, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC170, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC060, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC06A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC160, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC062, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC162, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC262, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC470, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC472, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC460, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC462, iwl7260_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC570, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC560, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC370, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC360, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC020, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC02A, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC220, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC420, iwl7260_2n_cfg)},
+
+/* 3160 Series */
+	{IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0072, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0170, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0172, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0060, iwl3160_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0062, iwl3160_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0270, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0272, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0470, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0472, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0370, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8072, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8170, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8172, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8060, iwl3160_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8062, iwl3160_n_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x8270, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8470, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8570, iwl3160_2ac_cfg)},
 
 	{0}
 };
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index 567e67ad1f61..296026b08a0c 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -489,6 +489,10 @@ static void iwl_pcie_rx_hw_init(struct iwl_trans *trans, struct iwl_rxq *rxq)
 
 	/* Set interrupt coalescing timer to default (2048 usecs) */
 	iwl_write8(trans, CSR_INT_COALESCING, IWL_HOST_INT_TIMEOUT_DEF);
+
+	/* W/A for interrupt coalescing bug in 7260 and 3160 */
+	if (trans->cfg->host_interrupt_operation_mode)
+		iwl_set_bit(trans, CSR_INT_COALESCING, IWL_HOST_INT_OPER_MODE);
 }
 
 int iwl_pcie_rx_init(struct iwl_trans *trans)
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index aeb70e13137a..6a5eb2b29418 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -116,11 +116,13 @@ static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 
 /* PCI registers */
 #define PCI_CFG_RETRY_TIMEOUT	0x041
+#define PCI_EXP_DEVCTL2_LTR_EN	0x0400
 
 static void iwl_pcie_apm_config(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u16 lctl;
+	u16 cap;
 
 	/*
 	 * HW bug W/A for instability in PCIe bus L0S->L1 transition.
@@ -131,16 +133,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans)
 	 *    power savings, even without L1.
 	 */
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
-	if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
-		/* L1-ASPM enabled; disable(!) L0S */
+	if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
 		iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
-		dev_info(trans->dev, "L1 Enabled; Disabling L0S\n");
-	} else {
-		/* L1-ASPM disabled; enable(!) L0S */
+	else
 		iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
-		dev_info(trans->dev, "L1 Disabled; Enabling L0S\n");
-	}
 	trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
+
+	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
+	trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN;
+	dev_info(trans->dev, "L1 %sabled - LTR %sabled\n",
+		 (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis",
+		 trans->ltr_enabled ? "En" : "Dis");
 }
 
 /*
@@ -207,6 +210,22 @@ static int iwl_pcie_apm_init(struct iwl_trans *trans)
 	}
 
 	/*
+	 * Enable the oscillator to count wake up time for L1 exit. This
+	 * consumes slightly more power (100uA) - but allows to be sure
+	 * that we wake up from L1 on time.
+	 *
+	 * This looks weird: read twice the same register, discard the
+	 * value, set a bit, and yet again, read that same register
+	 * just to discard the value. But that's the way the hardware
+	 * seems to like it.
+	 */
+	iwl_read_prph(trans, OSC_CLK);
+	iwl_read_prph(trans, OSC_CLK);
+	iwl_set_bits_prph(trans, OSC_CLK, OSC_CLK_FORCE_CONTROL);
+	iwl_read_prph(trans, OSC_CLK);
+	iwl_read_prph(trans, OSC_CLK);
+
+	/*
 	 * Enable DMA clock and wait for it to stabilize.
 	 *
 	 * Write to "CLK_EN_REG"; "1" bits enable clocks, while "0" bits
@@ -276,9 +295,6 @@ static int iwl_pcie_nic_init(struct iwl_trans *trans)
 	spin_lock_irqsave(&trans_pcie->irq_lock, flags);
 	iwl_pcie_apm_init(trans);
 
-	/* Set interrupt coalescing calibration timer to default (512 usecs) */
-	iwl_write8(trans, CSR_INT_COALESCING, IWL_HOST_INT_CALIB_TIMEOUT_DEF);
-
 	spin_unlock_irqrestore(&trans_pcie->irq_lock, flags);
 
 	iwl_pcie_set_pwr(trans, false);
@@ -326,6 +342,7 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 {
 	int ret;
 	int t = 0;
+	int iter;
 
 	IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n");
 
@@ -334,18 +351,23 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 	if (ret >= 0)
 		return 0;
 
-	/* If HW is not ready, prepare the conditions to check again */
-	iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
-		    CSR_HW_IF_CONFIG_REG_PREPARE);
+	for (iter = 0; iter < 10; iter++) {
+		/* If HW is not ready, prepare the conditions to check again */
+		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+			    CSR_HW_IF_CONFIG_REG_PREPARE);
+
+		do {
+			ret = iwl_pcie_set_hw_ready(trans);
+			if (ret >= 0)
+				return 0;
 
-	do {
-		ret = iwl_pcie_set_hw_ready(trans);
-		if (ret >= 0)
-			return 0;
+			usleep_range(200, 1000);
+			t += 200;
+		} while (t < 150000);
+		msleep(25);
+	}
 
-		usleep_range(200, 1000);
-		t += 200;
-	} while (t < 150000);
+	IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c
index 668dd27616a0..cc6a0a586f0b 100644
--- a/drivers/net/wireless/libertas/debugfs.c
+++ b/drivers/net/wireless/libertas/debugfs.c
@@ -913,7 +913,10 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf,
 	char *p2;
 	struct debug_data *d = f->private_data;
 
-	pdata = kmalloc(cnt, GFP_KERNEL);
+	if (cnt == 0)
+		return 0;
+
+	pdata = kmalloc(cnt + 1, GFP_KERNEL);
 	if (pdata == NULL)
 		return 0;
 
@@ -922,6 +925,7 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf,
 		kfree(pdata);
 		return 0;
 	}
+	pdata[cnt] = '\0';
 
 	p0 = pdata;
 	for (i = 0; i < num_of_items; i++) {
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index 5e0eec4d71c7..5d9a8084665d 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -189,8 +189,7 @@ int mwifiex_cmd_append_11ac_tlv(struct mwifiex_private *priv,
 		vht_cap->header.len  =
 				cpu_to_le16(sizeof(struct ieee80211_vht_cap));
 		memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *)bss_desc->bcn_vht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_vht_cap,
 		       le16_to_cpu(vht_cap->header.len));
 
 		mwifiex_fill_vht_cap_tlv(priv, vht_cap, bss_desc->bss_band);
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index 41e9d25a2d8e..2658c8cda443 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -307,8 +307,7 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv,
 		ht_cap->header.len =
 				cpu_to_le16(sizeof(struct ieee80211_ht_cap));
 		memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *) bss_desc->bcn_ht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_ht_cap,
 		       le16_to_cpu(ht_cap->header.len));
 
 		mwifiex_fill_cap_info(priv, radio_type, ht_cap);
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.c b/drivers/net/wireless/mwifiex/11n_aggr.c
index a78e0651409c..d69d02435b6b 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/mwifiex/11n_aggr.c
@@ -149,7 +149,7 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv,
  */
 int
 mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
-			  struct mwifiex_ra_list_tbl *pra_list, int headroom,
+			  struct mwifiex_ra_list_tbl *pra_list,
 			  int ptrindex, unsigned long ra_list_flags)
 			  __releases(&priv->wmm.ra_list_spinlock)
 {
@@ -159,6 +159,7 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 	int pad = 0, ret;
 	struct mwifiex_tx_param tx_param;
 	struct txpd *ptx_pd = NULL;
+	int headroom = adapter->iface_type == MWIFIEX_USB ? 0 : INTF_HEADER_LEN;
 
 	skb_src = skb_peek(&pra_list->skb_head);
 	if (!skb_src) {
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.h b/drivers/net/wireless/mwifiex/11n_aggr.h
index 900e1c62a0cc..892098d6a696 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.h
+++ b/drivers/net/wireless/mwifiex/11n_aggr.h
@@ -26,7 +26,7 @@
 int mwifiex_11n_deaggregate_pkt(struct mwifiex_private *priv,
 				struct sk_buff *skb);
 int mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
-			      struct mwifiex_ra_list_tbl *ptr, int headroom,
+			      struct mwifiex_ra_list_tbl *ptr,
 			      int ptr_index, unsigned long flags)
 			      __releases(&priv->wmm.ra_list_spinlock);
 
diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c
index 26755d9acb55..7a97f6cba089 100644
--- a/drivers/net/wireless/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/mwifiex/cmdevt.c
@@ -1154,7 +1154,7 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 	uint32_t conditions = le32_to_cpu(phs_cfg->params.hs_config.conditions);
 
 	if (phs_cfg->action == cpu_to_le16(HS_ACTIVATE) &&
-	    adapter->iface_type == MWIFIEX_SDIO) {
+	    adapter->iface_type != MWIFIEX_USB) {
 		mwifiex_hs_activated_event(priv, true);
 		return 0;
 	} else {
@@ -1166,8 +1166,7 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 	}
 	if (conditions != HS_CFG_CANCEL) {
 		adapter->is_hs_configured = true;
-		if (adapter->iface_type == MWIFIEX_USB ||
-		    adapter->iface_type == MWIFIEX_PCIE)
+		if (adapter->iface_type == MWIFIEX_USB)
 			mwifiex_hs_activated_event(priv, true);
 	} else {
 		adapter->is_hs_configured = false;
diff --git a/drivers/net/wireless/mwifiex/fw.h b/drivers/net/wireless/mwifiex/fw.h
index 1f7578d553ec..5400a1e58d79 100644
--- a/drivers/net/wireless/mwifiex/fw.h
+++ b/drivers/net/wireless/mwifiex/fw.h
@@ -228,7 +228,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 
 /* HW_SPEC fw_cap_info */
 
-#define ISSUPP_11ACENABLED(fw_cap_info) (fw_cap_info & (BIT(13)|BIT(14)))
+#define ISSUPP_11ACENABLED(fw_cap_info) (fw_cap_info & (BIT(12)|BIT(13)))
 
 #define GET_VHTCAP_CHWDSET(vht_cap_info)    ((vht_cap_info >> 2) & 0x3)
 #define GET_VHTNSSMCS(mcs_mapset, nss) ((mcs_mapset >> (2 * (nss - 1))) & 0x3)
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index c4a2e775fe1a..83c61964d082 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -270,10 +270,12 @@ process_start:
 		}
 	} while (true);
 
-	if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter))
+	spin_lock_irqsave(&adapter->main_proc_lock, flags);
+	if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter)) {
+		spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
 		goto process_start;
+	}
 
-	spin_lock_irqsave(&adapter->main_proc_lock, flags);
 	adapter->mwifiex_processing = false;
 	spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
 
@@ -499,6 +501,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 
@@ -559,9 +562,8 @@ static void mwifiex_set_multicast_list(struct net_device *dev)
 		mcast_list.mode = MWIFIEX_ALL_MULTI_MODE;
 	} else {
 		mcast_list.mode = MWIFIEX_MULTICAST_MODE;
-		if (netdev_mc_count(dev))
-			mcast_list.num_multicast_addr =
-				mwifiex_copy_mcast_addr(&mcast_list, dev);
+		mcast_list.num_multicast_addr =
+			mwifiex_copy_mcast_addr(&mcast_list, dev);
 	}
 	mwifiex_request_set_multicast_list(priv, &mcast_list);
 }
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 20c9c4c7b0b2..801c709656f9 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1195,6 +1195,12 @@ static int mwifiex_pcie_process_recv_data(struct mwifiex_adapter *adapter)
 		rd_index = card->rxbd_rdptr & reg->rx_mask;
 		skb_data = card->rx_buf_list[rd_index];
 
+		/* If skb allocation was failed earlier for Rx packet,
+		 * rx_buf_list[rd_index] would have been left with a NULL.
+		 */
+		if (!skb_data)
+			return -ENOMEM;
+
 		MWIFIEX_SKB_PACB(skb_data, &buf_pa);
 		pci_unmap_single(card->dev, buf_pa, MWIFIEX_RX_DATA_BUF_SIZE,
 				 PCI_DMA_FROMDEVICE);
@@ -1509,6 +1515,14 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter)
 		if (adapter->ps_state == PS_STATE_SLEEP_CFM) {
 			mwifiex_process_sleep_confirm_resp(adapter, skb->data,
 							   skb->len);
+			mwifiex_pcie_enable_host_int(adapter);
+			if (mwifiex_write_reg(adapter,
+					      PCIE_CPU_INT_EVENT,
+					      CPU_INTR_SLEEP_CFM_DONE)) {
+				dev_warn(adapter->dev,
+					 "Write register failed\n");
+				return -1;
+			}
 			while (reg->sleep_cookie && (count++ < 10) &&
 			       mwifiex_pcie_ok_to_access_hw(adapter))
 				usleep_range(50, 60);
@@ -1979,23 +1993,9 @@ static void mwifiex_interrupt_status(struct mwifiex_adapter *adapter)
 		adapter->int_status |= pcie_ireg;
 		spin_unlock_irqrestore(&adapter->int_lock, flags);
 
-		if (pcie_ireg & HOST_INTR_CMD_DONE) {
-			if ((adapter->ps_state == PS_STATE_SLEEP_CFM) ||
-			    (adapter->ps_state == PS_STATE_SLEEP)) {
-				mwifiex_pcie_enable_host_int(adapter);
-				if (mwifiex_write_reg(adapter,
-						      PCIE_CPU_INT_EVENT,
-						      CPU_INTR_SLEEP_CFM_DONE)
-						      ) {
-					dev_warn(adapter->dev,
-						 "Write register failed\n");
-					return;
-
-				}
-			}
-		} else if (!adapter->pps_uapsd_mode &&
-			   adapter->ps_state == PS_STATE_SLEEP &&
-			   mwifiex_pcie_ok_to_access_hw(adapter)) {
+		if (!adapter->pps_uapsd_mode &&
+		    adapter->ps_state == PS_STATE_SLEEP &&
+		    mwifiex_pcie_ok_to_access_hw(adapter)) {
 				/* Potentially for PCIe we could get other
 				 * interrupts like shared. Don't change power
 				 * state until cookie is set */
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 9cf5d8f07df8..470347a0a729 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -1622,7 +1622,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv,
 		const u8 *ie_buf;
 		size_t ie_len;
 		u16 channel = 0;
-		u64 fw_tsf = 0;
+		__le64 fw_tsf = 0;
 		u16 beacon_size = 0;
 		u32 curr_bcn_bytes;
 		u32 freq;
@@ -1749,7 +1749,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv,
 					      ie_buf, ie_len, rssi, GFP_KERNEL);
 				bss_priv = (struct mwifiex_bss_priv *)bss->priv;
 				bss_priv->band = band;
-				bss_priv->fw_tsf = fw_tsf;
+				bss_priv->fw_tsf = le64_to_cpu(fw_tsf);
 				if (priv->media_connected &&
 				    !memcmp(bssid,
 					    priv->curr_bss_params.bss_descriptor
@@ -2040,12 +2040,12 @@ mwifiex_save_curr_bcn(struct mwifiex_private *priv)
 			 curr_bss->ht_info_offset);
 
 	if (curr_bss->bcn_vht_cap)
-		curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf +
-						curr_bss->vht_cap_offset);
+		curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf +
+						 curr_bss->vht_cap_offset);
 
 	if (curr_bss->bcn_vht_oper)
-		curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf +
-						 curr_bss->vht_info_offset);
+		curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf +
+						  curr_bss->vht_info_offset);
 
 	if (curr_bss->bcn_bss_co_2040)
 		curr_bss->bcn_bss_co_2040 =
diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c
index 139c9581aecc..047a6f348d3d 100644
--- a/drivers/net/wireless/mwifiex/sdio.c
+++ b/drivers/net/wireless/mwifiex/sdio.c
@@ -930,7 +930,10 @@ static int mwifiex_decode_rx_packet(struct mwifiex_adapter *adapter,
 				    struct sk_buff *skb, u32 upld_typ)
 {
 	u8 *cmd_buf;
+	__le16 *curr_ptr = (__le16 *)skb->data;
+	u16 pkt_len = le16_to_cpu(*curr_ptr);
 
+	skb_trim(skb, pkt_len);
 	skb_pull(skb, INTF_HEADER_LEN);
 
 	switch (upld_typ) {
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 1a8a19dbd635..0a9f59c5ab5a 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -104,16 +104,14 @@ int mwifiex_request_set_multicast_list(struct mwifiex_private *priv,
 		} else {
 			priv->curr_pkt_filter &=
 				~HostCmd_ACT_MAC_ALL_MULTICAST_ENABLE;
-			if (mcast_list->num_multicast_addr) {
-				dev_dbg(priv->adapter->dev,
-					"info: Set multicast list=%d\n",
-				       mcast_list->num_multicast_addr);
-				/* Send multicast addresses to firmware */
-				ret = mwifiex_send_cmd_async(priv,
-					HostCmd_CMD_MAC_MULTICAST_ADR,
-					HostCmd_ACT_GEN_SET, 0,
-					mcast_list);
-			}
+			dev_dbg(priv->adapter->dev,
+				"info: Set multicast list=%d\n",
+				mcast_list->num_multicast_addr);
+			/* Send multicast addresses to firmware */
+			ret = mwifiex_send_cmd_async(priv,
+				HostCmd_CMD_MAC_MULTICAST_ADR,
+				HostCmd_ACT_GEN_SET, 0,
+				mcast_list);
 		}
 	}
 	dev_dbg(priv->adapter->dev,
@@ -311,8 +309,8 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss,
 		if (bss_desc && bss_desc->ssid.ssid_len &&
 		    (!mwifiex_ssid_cmp(&priv->curr_bss_params.bss_descriptor.
 				       ssid, &bss_desc->ssid))) {
-			kfree(bss_desc);
-			return 0;
+			ret = 0;
+			goto done;
 		}
 
 		/* Exit Adhoc mode first */
diff --git a/drivers/net/wireless/mwifiex/uap_txrx.c b/drivers/net/wireless/mwifiex/uap_txrx.c
index a018e42d117e..48e67247e8b1 100644
--- a/drivers/net/wireless/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/mwifiex/uap_txrx.c
@@ -34,6 +34,7 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
 	struct mwifiex_txinfo *tx_info;
 	int hdr_chop;
 	struct timeval tv;
+	struct ethhdr *p_ethhdr;
 	u8 rfc1042_eth_hdr[ETH_ALEN] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
 
 	uap_rx_pd = (struct uap_rxpd *)(skb->data);
@@ -48,14 +49,36 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
 	}
 
 	if (!memcmp(&rx_pkt_hdr->rfc1042_hdr,
-		    rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr)))
+		    rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr))) {
+		/* Replace the 803 header and rfc1042 header (llc/snap) with
+		 * an Ethernet II header, keep the src/dst and snap_type
+		 * (ethertype).
+		 *
+		 * The firmware only passes up SNAP frames converting all RX
+		 * data from 802.11 to 802.2/LLC/SNAP frames.
+		 *
+		 * To create the Ethernet II, just move the src, dst address
+		 * right before the snap_type.
+		 */
+		p_ethhdr = (struct ethhdr *)
+			((u8 *)(&rx_pkt_hdr->eth803_hdr)
+			 + sizeof(rx_pkt_hdr->eth803_hdr)
+			 + sizeof(rx_pkt_hdr->rfc1042_hdr)
+			 - sizeof(rx_pkt_hdr->eth803_hdr.h_dest)
+			 - sizeof(rx_pkt_hdr->eth803_hdr.h_source)
+			 - sizeof(rx_pkt_hdr->rfc1042_hdr.snap_type));
+		memcpy(p_ethhdr->h_source, rx_pkt_hdr->eth803_hdr.h_source,
+		       sizeof(p_ethhdr->h_source));
+		memcpy(p_ethhdr->h_dest, rx_pkt_hdr->eth803_hdr.h_dest,
+		       sizeof(p_ethhdr->h_dest));
 		/* Chop off the rxpd + the excess memory from
 		 * 802.2/llc/snap header that was removed.
 		 */
-		hdr_chop = (u8 *)eth_hdr - (u8 *)uap_rx_pd;
-	else
+		hdr_chop = (u8 *)p_ethhdr - (u8 *)uap_rx_pd;
+	} else {
 		/* Chop off the rxpd */
 		hdr_chop = (u8 *)&rx_pkt_hdr->eth803_hdr - (u8 *)uap_rx_pd;
+	}
 
 	/* Chop off the leading header bytes so the it points
 	 * to the start of either the reconstructed EthII frame
diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c
index f90fe21e5bfd..923e348dda70 100644
--- a/drivers/net/wireless/mwifiex/usb.c
+++ b/drivers/net/wireless/mwifiex/usb.c
@@ -446,9 +446,6 @@ static int mwifiex_usb_suspend(struct usb_interface *intf, pm_message_t message)
 	 */
 	adapter->is_suspended = true;
 
-	for (i = 0; i < adapter->priv_num; i++)
-		netif_carrier_off(adapter->priv[i]->netdev);
-
 	if (atomic_read(&card->rx_cmd_urb_pending) && card->rx_cmd.urb)
 		usb_kill_urb(card->rx_cmd.urb);
 
@@ -508,23 +505,12 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 						  MWIFIEX_RX_CMD_BUF_SIZE);
 	}
 
-	for (i = 0; i < adapter->priv_num; i++)
-		if (adapter->priv[i]->media_connected)
-			netif_carrier_on(adapter->priv[i]->netdev);
-
 	/* Disable Host Sleep */
 	if (adapter->hs_activated)
 		mwifiex_cancel_hs(mwifiex_get_priv(adapter,
 						   MWIFIEX_BSS_ROLE_ANY),
 				  MWIFIEX_ASYNC_CMD);
 
-#ifdef CONFIG_PM
-	/* Resume handler may be called due to remote wakeup,
-	 * force to exit suspend anyway
-	 */
-	usb_disable_autosuspend(card->udev);
-#endif /* CONFIG_PM */
-
 	return 0;
 }
 
@@ -583,7 +569,6 @@ static struct usb_driver mwifiex_usb_driver = {
 	.id_table = mwifiex_usb_table,
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
-	.supports_autosuspend = 1,
 };
 
 static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter)
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 4be3d33ceae8..80f72f6b6d56 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -556,7 +556,8 @@ mwifiex_clean_txrx(struct mwifiex_private *priv)
 	mwifiex_wmm_delete_all_ralist(priv);
 	memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
 
-	if (priv->adapter->if_ops.clean_pcie_ring)
+	if (priv->adapter->if_ops.clean_pcie_ring &&
+	    !priv->adapter->surprise_removed)
 		priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
 	spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
 }
@@ -1236,8 +1237,7 @@ mwifiex_dequeue_tx_packet(struct mwifiex_adapter *adapter)
 		if (mwifiex_is_amsdu_allowed(priv, tid) &&
 		    mwifiex_is_11n_aggragation_possible(priv, ptr,
 							adapter->tx_buf_size))
-			mwifiex_11n_aggregate_pkt(priv, ptr, INTF_HEADER_LEN,
-						  ptr_index, flags);
+			mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index, flags);
 			/* ra_list_spinlock has been freed in
 			   mwifiex_11n_aggregate_pkt() */
 		else
diff --git a/drivers/net/wireless/p54/p54usb.c b/drivers/net/wireless/p54/p54usb.c
index b9deef66cf4b..f42dc3ccd496 100644
--- a/drivers/net/wireless/p54/p54usb.c
+++ b/drivers/net/wireless/p54/p54usb.c
@@ -83,6 +83,7 @@ static struct usb_device_id p54u_table[] = {
 	{USB_DEVICE(0x06a9, 0x000e)},	/* Westell 802.11g USB (A90-211WG-01) */
 	{USB_DEVICE(0x06b9, 0x0121)},	/* Thomson SpeedTouch 121g */
 	{USB_DEVICE(0x0707, 0xee13)},   /* SMC 2862W-G version 2 */
+	{USB_DEVICE(0x07aa, 0x0020)},	/* Corega WLUSB2GTST USB */
 	{USB_DEVICE(0x0803, 0x4310)},	/* Zoom 4410a */
 	{USB_DEVICE(0x083a, 0x4521)},   /* Siemens Gigaset USB Adapter 54 version 2 */
 	{USB_DEVICE(0x083a, 0x4531)},	/* T-Com Sinus 154 data II */
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index f95de0d16216..1de59b0f8fa8 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -587,7 +587,7 @@ static void p54_rx_stats(struct p54_common *priv, struct sk_buff *skb)
 	chan = priv->curchan;
 	if (chan) {
 		struct survey_info *survey = &priv->survey[chan->hw_value];
-		survey->noise = clamp_t(s8, priv->noise, -128, 127);
+		survey->noise = clamp(priv->noise, -128, 127);
 		survey->channel_time = priv->survey_raw.active;
 		survey->channel_time_tx = priv->survey_raw.tx;
 		survey->channel_time_busy = priv->survey_raw.tx +
diff --git a/drivers/net/wireless/prism54/islpci_dev.c b/drivers/net/wireless/prism54/islpci_dev.c
index 5970ff6f40cc..d498b02f2d01 100644
--- a/drivers/net/wireless/prism54/islpci_dev.c
+++ b/drivers/net/wireless/prism54/islpci_dev.c
@@ -811,6 +811,10 @@ static const struct net_device_ops islpci_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
+static struct device_type wlan_type = {
+	.name	= "wlan",
+};
+
 struct net_device *
 islpci_setup(struct pci_dev *pdev)
 {
@@ -821,9 +825,8 @@ islpci_setup(struct pci_dev *pdev)
 		return ndev;
 
 	pci_set_drvdata(pdev, ndev);
-#if defined(SET_NETDEV_DEV)
 	SET_NETDEV_DEV(ndev, &pdev->dev);
-#endif
+	SET_NETDEV_DEVTYPE(ndev, &wlan_type);
 
 	/* setup the structure members */
 	ndev->base_addr = pci_resource_start(pdev, 0);
diff --git a/drivers/net/wireless/rt2x00/rt2400pci.c b/drivers/net/wireless/rt2x00/rt2400pci.c
index f7143733d7e9..a3a2dcd27a1e 100644
--- a/drivers/net/wireless/rt2x00/rt2400pci.c
+++ b/drivers/net/wireless/rt2x00/rt2400pci.c
@@ -1261,7 +1261,7 @@ static void rt2400pci_fill_rxdone(struct queue_entry *entry,
 	 */
 	rxdesc->timestamp = ((u64)rx_high << 32) | rx_low;
 	rxdesc->signal = rt2x00_get_field32(word2, RXD_W2_SIGNAL) & ~0x08;
-	rxdesc->rssi = rt2x00_get_field32(word2, RXD_W3_RSSI) -
+	rxdesc->rssi = rt2x00_get_field32(word3, RXD_W3_RSSI) -
 	    entry->queue->rt2x00dev->rssi_offset;
 	rxdesc->size = rt2x00_get_field32(word0, RXD_W0_DATABYTE_COUNT);
 
diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index 77e45b223d15..d582febbfba2 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1684,8 +1684,13 @@ static int rt2500pci_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Detect if this device has an hardware controlled radio.
 	 */
-	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO))
+	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) {
 		__set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags);
+		/*
+		 * On this device RFKILL initialized during probe does not work.
+		 */
+		__set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags);
+	}
 
 	/*
 	 * Check if the BBP tuning should be enabled.
diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h
index a7630d5ec892..a629313dd98a 100644
--- a/drivers/net/wireless/rt2x00/rt2800.h
+++ b/drivers/net/wireless/rt2x00/rt2800.h
@@ -1920,7 +1920,7 @@ struct mac_iveiv_entry {
  * 2 - drop tx power by 12dBm,
  * 3 - increase tx power by 6dBm
  */
-#define BBP1_TX_POWER_CTRL		FIELD8(0x07)
+#define BBP1_TX_POWER_CTRL		FIELD8(0x03)
 #define BBP1_TX_ANTENNA			FIELD8(0x18)
 
 /*
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 7e66a903cfee..12652d204f7e 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -2767,6 +2767,13 @@ static int rt2800_get_gain_calibration_delta(struct rt2x00_dev *rt2x00dev)
 	int i;
 
 	/*
+	 * First check if temperature compensation is supported.
+	 */
+	rt2x00_eeprom_read(rt2x00dev, EEPROM_NIC_CONF1, &eeprom);
+	if (!rt2x00_get_field16(eeprom, EEPROM_NIC_CONF1_EXTERNAL_TX_ALC))
+		return 0;
+
+	/*
 	 * Read TSSI boundaries for temperature compensation from
 	 * the EEPROM.
 	 *
@@ -3393,10 +3400,13 @@ void rt2800_link_tuner(struct rt2x00_dev *rt2x00dev, struct link_qual *qual,
 
 	vgc = rt2800_get_default_vgc(rt2x00dev);
 
-	if (rt2x00_rt(rt2x00dev, RT5592) && qual->rssi > -65)
-		vgc += 0x20;
-	else if (qual->rssi > -80)
-		vgc += 0x10;
+	if (rt2x00_rt(rt2x00dev, RT5592)) {
+		if (qual->rssi > -65)
+			vgc += 0x20;
+	} else {
+		if (qual->rssi > -80)
+			vgc += 0x10;
+	}
 
 	rt2800_set_vgc(rt2x00dev, qual, vgc);
 }
@@ -4041,10 +4051,6 @@ static int rt2800_init_bbp(struct rt2x00_dev *rt2x00dev)
 	u8 reg_id;
 	u8 value;
 
-	if (unlikely(rt2800_wait_bbp_rf_ready(rt2x00dev) ||
-		     rt2800_wait_bbp_ready(rt2x00dev)))
-		return -EACCES;
-
 	if (rt2x00_rt(rt2x00dev, RT5592)) {
 		rt2800_init_bbp_5592(rt2x00dev);
 		return 0;
@@ -5185,20 +5191,23 @@ int rt2800_enable_radio(struct rt2x00_dev *rt2x00dev)
 		     rt2800_init_registers(rt2x00dev)))
 		return -EIO;
 
+	if (unlikely(rt2800_wait_bbp_rf_ready(rt2x00dev)))
+		return -EIO;
+
 	/*
 	 * Send signal to firmware during boot time.
 	 */
 	rt2800_register_write(rt2x00dev, H2M_BBP_AGENT, 0);
 	rt2800_register_write(rt2x00dev, H2M_MAILBOX_CSR, 0);
-	if (rt2x00_is_usb(rt2x00dev)) {
+	if (rt2x00_is_usb(rt2x00dev))
 		rt2800_register_write(rt2x00dev, H2M_INT_SRC, 0);
-		rt2800_mcu_request(rt2x00dev, MCU_BOOT_SIGNAL, 0, 0, 0);
-	}
+	rt2800_mcu_request(rt2x00dev, MCU_BOOT_SIGNAL, 0, 0, 0);
 	msleep(1);
 
-	if (unlikely(rt2800_init_bbp(rt2x00dev)))
+	if (unlikely(rt2800_wait_bbp_ready(rt2x00dev)))
 		return -EIO;
 
+	rt2800_init_bbp(rt2x00dev);
 	rt2800_init_rfcsr(rt2x00dev);
 
 	if (rt2x00_is_usb(rt2x00dev) &&
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index ac854d75bd6c..400b8679796a 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -148,6 +148,8 @@ static bool rt2800usb_txstatus_timeout(struct rt2x00_dev *rt2x00dev)
 	return false;
 }
 
+#define TXSTATUS_READ_INTERVAL 1000000
+
 static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev,
 						 int urb_status, u32 tx_status)
 {
@@ -176,8 +178,9 @@ static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev,
 		queue_work(rt2x00dev->workqueue, &rt2x00dev->txdone_work);
 
 	if (rt2800usb_txstatus_pending(rt2x00dev)) {
-		/* Read register after 250 us */
-		hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 250000),
+		/* Read register after 1 ms */
+		hrtimer_start(&rt2x00dev->txstatus_timer,
+			      ktime_set(0, TXSTATUS_READ_INTERVAL),
 			      HRTIMER_MODE_REL);
 		return false;
 	}
@@ -202,8 +205,9 @@ static void rt2800usb_async_read_tx_status(struct rt2x00_dev *rt2x00dev)
 	if (test_and_set_bit(TX_STATUS_READING, &rt2x00dev->flags))
 		return;
 
-	/* Read TX_STA_FIFO register after 500 us */
-	hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 500000),
+	/* Read TX_STA_FIFO register after 2 ms */
+	hrtimer_start(&rt2x00dev->txstatus_timer,
+		      ktime_set(0, 2*TXSTATUS_READ_INTERVAL),
 		      HRTIMER_MODE_REL);
 }
 
@@ -1087,6 +1091,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	/* Ovislink */
 	{ USB_DEVICE(0x1b75, 0x3071) },
 	{ USB_DEVICE(0x1b75, 0x3072) },
+	{ USB_DEVICE(0x1b75, 0xa200) },
 	/* Para */
 	{ USB_DEVICE(0x20b8, 0x8888) },
 	/* Pegatron */
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index 7510723a8c37..1e716ff0f19e 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -708,6 +708,7 @@ enum rt2x00_capability_flags {
 	REQUIRE_SW_SEQNO,
 	REQUIRE_HT_TX_DESC,
 	REQUIRE_PS_AUTOWAKE,
+	REQUIRE_DELAYED_RFKILL,
 
 	/*
 	 * Capabilities
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 90dc14336980..e22942bc2bb1 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -181,6 +181,7 @@ static void rt2x00lib_autowakeup(struct work_struct *work)
 static void rt2x00lib_bc_buffer_iter(void *data, u8 *mac,
 				     struct ieee80211_vif *vif)
 {
+	struct ieee80211_tx_control control = {};
 	struct rt2x00_dev *rt2x00dev = data;
 	struct sk_buff *skb;
 
@@ -195,7 +196,7 @@ static void rt2x00lib_bc_buffer_iter(void *data, u8 *mac,
 	 */
 	skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
 	while (skb) {
-		rt2x00mac_tx(rt2x00dev->hw, NULL, skb);
+		rt2x00mac_tx(rt2x00dev->hw, &control, skb);
 		skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
 	}
 }
@@ -1127,9 +1128,10 @@ static void rt2x00lib_uninitialize(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/*
-	 * Unregister extra components.
+	 * Stop rfkill polling.
 	 */
-	rt2x00rfkill_unregister(rt2x00dev);
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
 
 	/*
 	 * Allow the HW to uninitialize.
@@ -1167,6 +1169,12 @@ static int rt2x00lib_initialize(struct rt2x00_dev *rt2x00dev)
 
 	set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags);
 
+	/*
+	 * Start rfkill polling.
+	 */
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
+
 	return 0;
 }
 
@@ -1362,7 +1370,12 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 	rt2x00link_register(rt2x00dev);
 	rt2x00leds_register(rt2x00dev);
 	rt2x00debug_register(rt2x00dev);
-	rt2x00rfkill_register(rt2x00dev);
+
+	/*
+	 * Start rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
 
 	return 0;
 
@@ -1378,6 +1391,12 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
 
 	/*
+	 * Stop rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
+
+	/*
 	 * Disable radio.
 	 */
 	rt2x00lib_disable_radio(rt2x00dev);
diff --git a/drivers/net/wireless/rt2x00/rt2x00lib.h b/drivers/net/wireless/rt2x00/rt2x00lib.h
index a0935987fa3a..7f40ab8e1bd8 100644
--- a/drivers/net/wireless/rt2x00/rt2x00lib.h
+++ b/drivers/net/wireless/rt2x00/rt2x00lib.h
@@ -146,7 +146,7 @@ void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length);
  * @local: frame is not from mac80211
  */
 int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
-			       bool local);
+			       struct ieee80211_sta *sta, bool local);
 
 /**
  * rt2x00queue_update_beacon - Send new beacon from mac80211
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index f883802f3505..c03748dafd49 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -90,7 +90,7 @@ static int rt2x00mac_tx_rts_cts(struct rt2x00_dev *rt2x00dev,
 				  frag_skb->data, data_length, tx_info,
 				  (struct ieee80211_rts *)(skb->data));
 
-	retval = rt2x00queue_write_tx_frame(queue, skb, true);
+	retval = rt2x00queue_write_tx_frame(queue, skb, NULL, true);
 	if (retval) {
 		dev_kfree_skb_any(skb);
 		rt2x00_warn(rt2x00dev, "Failed to send RTS/CTS frame\n");
@@ -151,7 +151,7 @@ void rt2x00mac_tx(struct ieee80211_hw *hw,
 			goto exit_fail;
 	}
 
-	if (unlikely(rt2x00queue_write_tx_frame(queue, skb, false)))
+	if (unlikely(rt2x00queue_write_tx_frame(queue, skb, control->sta, false)))
 		goto exit_fail;
 
 	/*
@@ -489,6 +489,8 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	crypto.cipher = rt2x00crypto_key_to_cipher(key);
 	if (crypto.cipher == CIPHER_NONE)
 		return -EOPNOTSUPP;
+	if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev))
+		return -EOPNOTSUPP;
 
 	crypto.cmd = cmd;
 
@@ -623,20 +625,18 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 				      bss_conf->bssid);
 
 	/*
-	 * Update the beacon. This is only required on USB devices. PCI
-	 * devices fetch beacons periodically.
-	 */
-	if (changes & BSS_CHANGED_BEACON && rt2x00_is_usb(rt2x00dev))
-		rt2x00queue_update_beacon(rt2x00dev, vif);
-
-	/*
 	 * Start/stop beaconing.
 	 */
 	if (changes & BSS_CHANGED_BEACON_ENABLED) {
 		if (!bss_conf->enable_beacon && intf->enable_beacon) {
-			rt2x00queue_clear_beacon(rt2x00dev, vif);
 			rt2x00dev->intf_beaconing--;
 			intf->enable_beacon = false;
+			/*
+			 * Clear beacon in the H/W for this vif. This is needed
+			 * to disable beaconing on this particular interface
+			 * and keep it running on other interfaces.
+			 */
+			rt2x00queue_clear_beacon(rt2x00dev, vif);
 
 			if (rt2x00dev->intf_beaconing == 0) {
 				/*
@@ -647,11 +647,15 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 				rt2x00queue_stop_queue(rt2x00dev->bcn);
 				mutex_unlock(&intf->beacon_skb_mutex);
 			}
-
-
 		} else if (bss_conf->enable_beacon && !intf->enable_beacon) {
 			rt2x00dev->intf_beaconing++;
 			intf->enable_beacon = true;
+			/*
+			 * Upload beacon to the H/W. This is only required on
+			 * USB devices. PCI devices fetch beacons periodically.
+			 */
+			if (rt2x00_is_usb(rt2x00dev))
+				rt2x00queue_update_beacon(rt2x00dev, vif);
 
 			if (rt2x00dev->intf_beaconing == 1) {
 				/*
@@ -754,6 +758,9 @@ void rt2x00mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
 	struct rt2x00_dev *rt2x00dev = hw->priv;
 	struct data_queue *queue;
 
+	if (!test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags))
+		return;
+
 	tx_queue_for_each(rt2x00dev, queue)
 		rt2x00queue_flush_queue(queue, drop);
 }
diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c
index d955741e48ff..5be4eee63eb8 100644
--- a/drivers/net/wireless/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/rt2x00/rt2x00queue.c
@@ -160,55 +160,29 @@ void rt2x00queue_align_frame(struct sk_buff *skb)
 	skb_trim(skb, frame_length);
 }
 
-void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int header_length)
+/*
+ * H/W needs L2 padding between the header and the paylod if header size
+ * is not 4 bytes aligned.
+ */
+void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int hdr_len)
 {
-	unsigned int payload_length = skb->len - header_length;
-	unsigned int header_align = ALIGN_SIZE(skb, 0);
-	unsigned int payload_align = ALIGN_SIZE(skb, header_length);
-	unsigned int l2pad = payload_length ? L2PAD_SIZE(header_length) : 0;
+	unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
 
-	/*
-	 * Adjust the header alignment if the payload needs to be moved more
-	 * than the header.
-	 */
-	if (payload_align > header_align)
-		header_align += 4;
-
-	/* There is nothing to do if no alignment is needed */
-	if (!header_align)
+	if (!l2pad)
 		return;
 
-	/* Reserve the amount of space needed in front of the frame */
-	skb_push(skb, header_align);
-
-	/*
-	 * Move the header.
-	 */
-	memmove(skb->data, skb->data + header_align, header_length);
-
-	/* Move the payload, if present and if required */
-	if (payload_length && payload_align)
-		memmove(skb->data + header_length + l2pad,
-			skb->data + header_length + l2pad + payload_align,
-			payload_length);
-
-	/* Trim the skb to the correct size */
-	skb_trim(skb, header_length + l2pad + payload_length);
+	skb_push(skb, l2pad);
+	memmove(skb->data, skb->data + l2pad, hdr_len);
 }
 
-void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length)
+void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int hdr_len)
 {
-	/*
-	 * L2 padding is only present if the skb contains more than just the
-	 * IEEE 802.11 header.
-	 */
-	unsigned int l2pad = (skb->len > header_length) ?
-				L2PAD_SIZE(header_length) : 0;
+	unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
 
 	if (!l2pad)
 		return;
 
-	memmove(skb->data + l2pad, skb->data, header_length);
+	memmove(skb->data + l2pad, skb->data, hdr_len);
 	skb_pull(skb, l2pad);
 }
 
@@ -635,7 +609,7 @@ static void rt2x00queue_bar_check(struct queue_entry *entry)
 }
 
 int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
-			       bool local)
+			       struct ieee80211_sta *sta, bool local)
 {
 	struct ieee80211_tx_info *tx_info;
 	struct queue_entry *entry;
@@ -649,7 +623,7 @@ int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
 	 * after that we are free to use the skb->cb array
 	 * for our information.
 	 */
-	rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, NULL);
+	rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, sta);
 
 	/*
 	 * All information is retrieved from the skb->cb array,
diff --git a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
index e19a20a8e955..ecd1ac424047 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
+++ b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
@@ -15,6 +15,8 @@
 #ifndef RTL8187_H
 #define RTL8187_H
 
+#include <linux/cache.h>
+
 #include "rtl818x.h"
 #include "leds.h"
 
@@ -139,7 +141,10 @@ struct rtl8187_priv {
 	u8 aifsn[4];
 	u8 rfkill_mask;
 	struct {
-		__le64 buf;
+		union {
+			__le64 buf;
+			u8 dummy1[L1_CACHE_BYTES];
+		} ____cacheline_aligned;
 		struct sk_buff_head queue;
 	} b_tx_status; /* This queue is used by both -b and non-b devices */
 	struct mutex io_mutex;
@@ -147,7 +152,8 @@ struct rtl8187_priv {
 		u8 bits8;
 		__le16 bits16;
 		__le32 bits32;
-	} *io_dmabuf;
+		u8 dummy2[L1_CACHE_BYTES];
+	} *io_dmabuf ____cacheline_aligned;
 	bool rfkill_off;
 	u16 seqno;
 };
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index af59dd5718e1..6fc0853fd7f9 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -37,6 +37,7 @@
 
 #include <linux/ip.h>
 #include <linux/module.h>
+#include <linux/udp.h>
 
 /*
  *NOTICE!!!: This file will be very big, we should
@@ -1066,64 +1067,52 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx)
 	if (!ieee80211_is_data(fc))
 		return false;
 
+	ip = (const struct iphdr *)(skb->data + mac_hdr_len +
+				    SNAP_SIZE + PROTOC_TYPE_SIZE);
+	ether_type = be16_to_cpup((__be16 *)
+				  (skb->data + mac_hdr_len + SNAP_SIZE));
 
-	ip = (struct iphdr *)((u8 *) skb->data + mac_hdr_len +
-			      SNAP_SIZE + PROTOC_TYPE_SIZE);
-	ether_type = *(u16 *) ((u8 *) skb->data + mac_hdr_len + SNAP_SIZE);
-	/*	ether_type = ntohs(ether_type); */
-
-	if (ETH_P_IP == ether_type) {
-		if (IPPROTO_UDP == ip->protocol) {
-			struct udphdr *udp = (struct udphdr *)((u8 *) ip +
-							       (ip->ihl << 2));
-			if (((((u8 *) udp)[1] == 68) &&
-			     (((u8 *) udp)[3] == 67)) ||
-			    ((((u8 *) udp)[1] == 67) &&
-			     (((u8 *) udp)[3] == 68))) {
-				/*
-				 * 68 : UDP BOOTP client
-				 * 67 : UDP BOOTP server
-				 */
-				RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV),
-					 DBG_DMESG, "dhcp %s !!\n",
-					 is_tx ? "Tx" : "Rx");
-
-				if (is_tx) {
-					rtlpriv->enter_ps = false;
-					schedule_work(&rtlpriv->
-						      works.lps_change_work);
-					ppsc->last_delaylps_stamp_jiffies =
-					    jiffies;
-				}
+	switch (ether_type) {
+	case ETH_P_IP: {
+		struct udphdr *udp;
+		u16 src;
+		u16 dst;
 
-				return true;
-			}
-		}
-	} else if (ETH_P_ARP == ether_type) {
-		if (is_tx) {
-			rtlpriv->enter_ps = false;
-			schedule_work(&rtlpriv->works.lps_change_work);
-			ppsc->last_delaylps_stamp_jiffies = jiffies;
-		}
+		if (ip->protocol != IPPROTO_UDP)
+			return false;
+		udp = (struct udphdr *)((u8 *)ip + (ip->ihl << 2));
+		src = be16_to_cpu(udp->source);
+		dst = be16_to_cpu(udp->dest);
 
-		return true;
-	} else if (ETH_P_PAE == ether_type) {
+		/* If this case involves port 68 (UDP BOOTP client) connecting
+		 * with port 67 (UDP BOOTP server), then return true so that
+		 * the lowest speed is used.
+		 */
+		if (!((src == 68 && dst == 67) || (src == 67 && dst == 68)))
+			return false;
+
+		RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
+			 "dhcp %s !!\n", is_tx ? "Tx" : "Rx");
+		break;
+	}
+	case ETH_P_ARP:
+		break;
+	case ETH_P_PAE:
 		RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
 			 "802.1X %s EAPOL pkt!!\n", is_tx ? "Tx" : "Rx");
-
-		if (is_tx) {
-			rtlpriv->enter_ps = false;
-			schedule_work(&rtlpriv->works.lps_change_work);
-			ppsc->last_delaylps_stamp_jiffies = jiffies;
-		}
-
-		return true;
-	} else if (ETH_P_IPV6 == ether_type) {
-		/* IPv6 */
-		return true;
+		break;
+	case ETH_P_IPV6:
+		/* TODO: Is this right? */
+		return false;
+	default:
+		return false;
 	}
-
-	return false;
+	if (is_tx) {
+		rtlpriv->enter_ps = false;
+		schedule_work(&rtlpriv->works.lps_change_work);
+		ppsc->last_delaylps_stamp_jiffies = jiffies;
+	}
+	return true;
 }
 
 /*********************************************************
@@ -1438,7 +1427,8 @@ void rtl_watchdog_wq_callback(void *data)
 			/* if we can't recv beacon for 6s, we should
 			 * reconnect this AP
 			 */
-			if (rtlpriv->link_info.roam_times >= 3) {
+			if ((rtlpriv->link_info.roam_times >= 3) &&
+			    !is_zero_ether_addr(rtlpriv->mac80211.bssid)) {
 				RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 					 "AP off, try to reconnect now\n");
 				rtlpriv->link_info.roam_times = 0;
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index ee84844be008..e2301970c85e 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -46,10 +46,20 @@ void rtl_fw_cb(const struct firmware *firmware, void *context)
 			 "Firmware callback routine entered!\n");
 	complete(&rtlpriv->firmware_loading_complete);
 	if (!firmware) {
+		if (rtlpriv->cfg->alt_fw_name) {
+			err = request_firmware(&firmware,
+					       rtlpriv->cfg->alt_fw_name,
+					       rtlpriv->io.dev);
+			pr_info("Loading alternative firmware %s\n",
+				rtlpriv->cfg->alt_fw_name);
+			if (!err)
+				goto found_alt;
+		}
 		pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
 		rtlpriv->max_fw_size = 0;
 		return;
 	}
+found_alt:
 	if (firmware->size > rtlpriv->max_fw_size) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "Firmware is too big!\n");
@@ -184,6 +194,7 @@ static int rtl_op_add_interface(struct ieee80211_hw *hw,
 					rtlpriv->cfg->maps
 					[RTL_IBSS_INT_MASKS]);
 		}
+		mac->link_state = MAC80211_LINKED;
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		RT_TRACE(rtlpriv, COMP_MAC80211, DBG_LOUD,
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index e70b4ffaf97f..ee6a62616c72 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -734,6 +734,8 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 	};
 	int index = rtlpci->rx_ring[rx_queue_idx].idx;
 
+	if (rtlpci->driver_is_goingto_unload)
+		return;
 	/*RX NORMAL PKT */
 	while (count--) {
 		/*rx descriptor */
@@ -1630,6 +1632,7 @@ static void rtl_pci_stop(struct ieee80211_hw *hw)
 	 */
 	set_hal_stop(rtlhal);
 
+	rtlpci->driver_is_goingto_unload = true;
 	rtlpriv->cfg->ops->disable_interrupt(hw);
 	cancel_work_sync(&rtlpriv->works.lps_change_work);
 
@@ -1647,7 +1650,6 @@ static void rtl_pci_stop(struct ieee80211_hw *hw)
 	ppsc->rfchange_inprogress = true;
 	spin_unlock_irqrestore(&rtlpriv->locks.rf_ps_lock, flags);
 
-	rtlpci->driver_is_goingto_unload = true;
 	rtlpriv->cfg->ops->hw_disable(hw);
 	/* some things are not needed if firmware not available */
 	if (!rtlpriv->max_fw_size)
diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c
index 71e917db8338..ace1a087fe8a 100644
--- a/drivers/net/wireless/rtlwifi/ps.c
+++ b/drivers/net/wireless/rtlwifi/ps.c
@@ -48,7 +48,7 @@ bool rtl_ps_enable_nic(struct ieee80211_hw *hw)
 
 	/*<2> Enable Adapter */
 	if (rtlpriv->cfg->ops->hw_init(hw))
-		return 1;
+		return false;
 	RT_CLEAR_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC);
 
 	/*<3> Enable Interrupt */
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c b/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
index 21a5cf060677..a6184b6e1d57 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
@@ -1078,7 +1078,7 @@ static void rtl88e_dm_txpower_tracking_callback_thermalmeter(struct ieee80211_hw
 				rtldm->swing_flag_ofdm = true;
 			}
 
-			if (rtldm->swing_idx_cck != rtldm->swing_idx_cck) {
+			if (rtldm->swing_idx_cck_cur != rtldm->swing_idx_cck) {
 				rtldm->swing_idx_cck_cur = rtldm->swing_idx_cck;
 				rtldm->swing_flag_cck = true;
 			}
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index b68cae3024fc..f923d8c9a296 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -143,6 +143,7 @@ static void _rtl88ee_set_fw_clock_on(struct ieee80211_hw *hw,
 		} else {
 			rtlhal->fw_clk_change_in_progress = false;
 			spin_unlock_bh(&rtlpriv->locks.fw_ps_lock);
+			break;
 		}
 	}
 
@@ -1024,9 +1025,20 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err = 0;
 	u8 tmp_u1b, u1byte;
+	unsigned long flags;
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Rtl8188EE hw init\n");
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	tmp_u1b = rtl_read_byte(rtlpriv, REG_SYS_CLKR+1);
@@ -1042,7 +1054,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl88e_download_fw(hw, false);
@@ -1050,8 +1062,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -1134,10 +1145,12 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	}
 	rtl_write_byte(rtlpriv, REG_NAV_CTRL+2,  ((30000+127)/128));
 	rtl88e_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "end of Rtl8188EE hw init %x\n",
 		 err);
-	return 0;
+	return err;
 }
 
 static enum version_8188e _rtl88ee_read_chip_version(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
index a8871d66d56a..ea4d014a2884 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
@@ -293,7 +293,7 @@ static void _rtl88ee_translate_rx_signal_stuff(struct ieee80211_hw *hw,
 	u8 *psaddr;
 	__le16 fc;
 	u16 type, ufc;
-	bool match_bssid, packet_toself, packet_beacon, addr;
+	bool match_bssid, packet_toself, packet_beacon = false, addr;
 
 	tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift;
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
index d2d57a27a7c1..06cb94cf5085 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
@@ -158,6 +158,42 @@ static const u8 cckswing_table_ch14[CCK_TABLE_SIZE][8] = {
 	{0x09, 0x08, 0x07, 0x04, 0x00, 0x00, 0x00, 0x00}
 };
 
+static u32 power_index_reg[6] = {0xc90, 0xc91, 0xc92, 0xc98, 0xc99, 0xc9a};
+
+void dm_restorepowerindex(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8	index;
+
+	for (index = 0; index < 6; index++)
+		rtl_write_byte(rtlpriv, power_index_reg[index],
+			       rtlpriv->dm.powerindex_backup[index]);
+}
+EXPORT_SYMBOL_GPL(dm_restorepowerindex);
+
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 index;
+
+	for (index = 0; index < 6; index++)
+		rtl_write_byte(rtlpriv, power_index_reg[index], value);
+}
+EXPORT_SYMBOL_GPL(dm_writepowerindex);
+
+void dm_savepowerindex(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 index;
+	u8 tmp;
+
+	for (index = 0; index < 6; index++) {
+		tmp = rtl_read_byte(rtlpriv, power_index_reg[index]);
+		rtlpriv->dm.powerindex_backup[index] = tmp;
+	}
+}
+EXPORT_SYMBOL_GPL(dm_savepowerindex);
+
 static void rtl92c_dm_diginit(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
index 518e208c0180..4f232a063636 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
@@ -91,6 +91,17 @@
 #define TX_POWER_NEAR_FIELD_THRESH_LVL2		74
 #define TX_POWER_NEAR_FIELD_THRESH_LVL1		67
 
+#define DYNAMIC_FUNC_DISABLE			0x0
+#define DYNAMIC_FUNC_DIG			BIT(0)
+#define DYNAMIC_FUNC_HP				BIT(1)
+#define DYNAMIC_FUNC_SS				BIT(2) /*Tx Power Tracking*/
+#define DYNAMIC_FUNC_BT				BIT(3)
+#define DYNAMIC_FUNC_ANT_DIV			BIT(4)
+
+#define	RSSI_CCK				0
+#define	RSSI_OFDM				1
+#define	RSSI_DEFAULT				2
+
 struct swat_t {
 	u8 failure_cnt;
 	u8 try_flag;
@@ -167,5 +178,8 @@ void rtl92c_phy_lc_calibrate(struct ieee80211_hw *hw);
 void rtl92c_phy_iq_calibrate(struct ieee80211_hw *hw, bool recovery);
 void rtl92c_dm_dynamic_txpower(struct ieee80211_hw *hw);
 void rtl92c_dm_bt_coexist(struct ieee80211_hw *hw);
+void dm_savepowerindex(struct ieee80211_hw *hw);
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value);
+void dm_restorepowerindex(struct ieee80211_hw *hw);
 
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
index a82b30a1996c..2eb0b38384dd 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
@@ -937,14 +937,26 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw)
 	bool is92c;
 	int err;
 	u8 tmp_u1b;
+	unsigned long flags;
 
 	rtlpci->being_init_adapter = true;
+
+	/* Since this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl92ce_init_mac(hw);
 	if (!rtstatus) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl92c_download_fw(hw);
@@ -952,7 +964,7 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	rtlhal->last_hmeboxnum = 0;
@@ -1032,6 +1044,8 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
 	}
 	rtl92c_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
 	return err;
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
index 16a0b9e59acf..c16209a336ea 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
@@ -101,6 +101,15 @@ void rtl92cu_dm_dynamic_txpower(struct ieee80211_hw *hw)
 			 "PHY_SetTxPowerLevel8192S() Channel = %d\n",
 			 rtlphy->current_channel);
 		rtl92c_phy_set_txpower_level(hw, rtlphy->current_channel);
+		if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+		    TXHIGHPWRLEVEL_NORMAL)
+			dm_restorepowerindex(hw);
+		else if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+			 TXHIGHPWRLEVEL_LEVEL1)
+			dm_writepowerindex(hw, 0x14);
+		else if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+			 TXHIGHPWRLEVEL_LEVEL2)
+			dm_writepowerindex(hw, 0x10);
 	}
 
 	rtlpriv->dm.last_dtp_lvl = rtlpriv->dm.dynamic_txhighpower_lvl;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
index d947e7d350bb..fafa6bac2a3f 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
@@ -30,3 +30,6 @@
 #include "../rtl8192ce/dm.h"
 
 void rtl92cu_dm_dynamic_txpower(struct ieee80211_hw *hw);
+void dm_savepowerindex(struct ieee80211_hw *hw);
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value);
+void dm_restorepowerindex(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
index 189ba124a8c6..c3f2b55501ae 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
@@ -985,19 +985,30 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	int err = 0;
 	static bool iqk_initialized;
+	unsigned long flags;
+
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
 
 	rtlhal->hw_type = HARDWARE_TYPE_RTL8192CU;
 	err = _rtl92cu_init_mac(hw);
 	if (err) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "init mac failed!\n");
-		return err;
+		goto exit;
 	}
 	err = rtl92c_download_fw(hw);
 	if (err) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 	rtlhal->last_hmeboxnum = 0; /* h2c */
 	_rtl92cu_phy_param_tab_init(hw);
@@ -1034,6 +1045,8 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	_InitPABias(hw);
 	_update_mac_setting(hw);
 	rtl92c_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c b/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
index da4f587199ee..2c68c138912f 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
@@ -778,7 +778,7 @@ static long _rtl92c_signal_scale_mapping(struct ieee80211_hw *hw,
 
 static void _rtl92c_query_rxphystatus(struct ieee80211_hw *hw,
 				      struct rtl_stats *pstats,
-				      struct rx_desc_92c *pdesc,
+				      struct rx_desc_92c *p_desc,
 				      struct rx_fwinfo_92c *p_drvinfo,
 				      bool packet_match_bssid,
 				      bool packet_toself,
@@ -793,11 +793,11 @@ static void _rtl92c_query_rxphystatus(struct ieee80211_hw *hw,
 	u32 rssi, total_rssi = 0;
 	bool in_powersavemode = false;
 	bool is_cck_rate;
+	u8 *pdesc = (u8 *)p_desc;
 
-	is_cck_rate = RX_HAL_IS_CCK_RATE(pdesc);
+	is_cck_rate = RX_HAL_IS_CCK_RATE(p_desc);
 	pstats->packet_matchbssid = packet_match_bssid;
 	pstats->packet_toself = packet_toself;
-	pstats->is_cck = is_cck_rate;
 	pstats->packet_beacon = packet_beacon;
 	pstats->is_cck = is_cck_rate;
 	pstats->RX_SIGQ[0] = -1;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c b/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
index 2119313a737b..b878d56d2f4d 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
@@ -85,17 +85,15 @@ void rtl92cu_phy_rf6052_set_cck_txpower(struct ieee80211_hw *hw,
 	if (mac->act_scanning) {
 		tx_agc[RF90_PATH_A] = 0x3f3f3f3f;
 		tx_agc[RF90_PATH_B] = 0x3f3f3f3f;
-		if (turbo_scanoff) {
-			for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
-				tx_agc[idx1] = ppowerlevel[idx1] |
-				    (ppowerlevel[idx1] << 8) |
-				    (ppowerlevel[idx1] << 16) |
-				    (ppowerlevel[idx1] << 24);
-				if (rtlhal->interface == INTF_USB) {
-					if (tx_agc[idx1] > 0x20 &&
-					    rtlefuse->external_pa)
-						tx_agc[idx1] = 0x20;
-				}
+		for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
+			tx_agc[idx1] = ppowerlevel[idx1] |
+			    (ppowerlevel[idx1] << 8) |
+			    (ppowerlevel[idx1] << 16) |
+			    (ppowerlevel[idx1] << 24);
+			if (rtlhal->interface == INTF_USB) {
+				if (tx_agc[idx1] > 0x20 &&
+				    rtlefuse->external_pa)
+					tx_agc[idx1] = 0x20;
 			}
 		}
 	} else {
@@ -107,7 +105,7 @@ void rtl92cu_phy_rf6052_set_cck_txpower(struct ieee80211_hw *hw,
 			   TXHIGHPWRLEVEL_LEVEL2) {
 			tx_agc[RF90_PATH_A] = 0x00000000;
 			tx_agc[RF90_PATH_B] = 0x00000000;
-		} else{
+		} else {
 			for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
 				tx_agc[idx1] = ppowerlevel[idx1] |
 				    (ppowerlevel[idx1] << 8) |
@@ -373,7 +371,12 @@ static void _rtl92c_write_ofdm_power_reg(struct ieee80211_hw *hw,
 			    regoffset == RTXAGC_B_MCS07_MCS04)
 				regoffset = 0xc98;
 			for (i = 0; i < 3; i++) {
-				writeVal = (writeVal > 6) ? (writeVal - 6) : 0;
+				if (i != 2)
+					writeVal = (writeVal > 8) ?
+						   (writeVal - 8) : 0;
+				else
+					writeVal = (writeVal > 6) ?
+						   (writeVal - 6) : 0;
 				rtl_write_byte(rtlpriv, (u32)(regoffset + i),
 					      (u8)writeVal);
 			}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
index 2bd598526217..e7a2af3ad05a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
@@ -49,6 +49,9 @@ MODULE_AUTHOR("Larry Finger	<Larry.Finger@lwfinger.net>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek 8192C/8188C 802.11n USB wireless");
 MODULE_FIRMWARE("rtlwifi/rtl8192cufw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_A.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_B.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_TMSC.bin");
 
 static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
 {
@@ -68,14 +71,21 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
 			 "Can't alloc buffer for fw\n");
 		return 1;
 	}
-
+	if (IS_VENDOR_UMC_A_CUT(rtlpriv->rtlhal.version) &&
+	    !IS_92C_SERIAL(rtlpriv->rtlhal.version)) {
+		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_A.bin";
+	} else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlpriv->rtlhal.version)) {
+		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_B.bin";
+	} else {
+		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
+	}
+	/* provide name of alternative file */
+	rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin";
 	pr_info("Loading firmware %s\n", rtlpriv->cfg->fw_name);
 	rtlpriv->max_fw_size = 0x4000;
 	err = request_firmware_nowait(THIS_MODULE, 1,
 				      rtlpriv->cfg->fw_name, rtlpriv->io.dev,
 				      GFP_KERNEL, hw, rtl_fw_cb);
-
-
 	return err;
 }
 
@@ -306,6 +316,8 @@ static struct usb_device_id rtl8192c_usb_ids[] = {
 	{RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/
 	{RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
 	{RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
+	{RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */
+	{RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/
 	{RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/
 	{RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/
 	/* HP - Lite-On ,8188CUS Slim Combo */
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
index 763cf1defab5..5c52a8ac314c 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
@@ -303,10 +303,10 @@ out:
 bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
 			   struct rtl_stats *stats,
 			   struct ieee80211_rx_status *rx_status,
-			   u8 *p_desc, struct sk_buff *skb)
+			   u8 *pdesc, struct sk_buff *skb)
 {
 	struct rx_fwinfo_92c *p_drvinfo;
-	struct rx_desc_92c *pdesc = (struct rx_desc_92c *)p_desc;
+	struct rx_desc_92c *p_desc = (struct rx_desc_92c *)pdesc;
 	u32 phystatus = GET_RX_DESC_PHY_STATUS(pdesc);
 
 	stats->length = (u16) GET_RX_DESC_PKT_LEN(pdesc);
@@ -343,12 +343,13 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
 					(bool)GET_RX_DESC_PAGGR(pdesc));
 	rx_status->mactime = GET_RX_DESC_TSFL(pdesc);
 	if (phystatus) {
-		p_drvinfo = (struct rx_fwinfo_92c *)(pdesc + RTL_RX_DESC_SIZE);
-		rtl92c_translate_rx_signal_stuff(hw, skb, stats, pdesc,
+		p_drvinfo = (struct rx_fwinfo_92c *)(skb->data +
+						     stats->rx_bufshift);
+		rtl92c_translate_rx_signal_stuff(hw, skb, stats, p_desc,
 						 p_drvinfo);
 	}
 	/*rx_status->qual = stats->signal; */
-	rx_status->signal = stats->rssi + 10;
+	rx_status->signal = stats->recvsignalpower + 10;
 	/*rx_status->noise = -stats->noise; */
 	return true;
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
index b8ec718a0fab..542394c843e6 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
@@ -525,7 +525,7 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,	struct rtl_stats *stats,
 						   p_drvinfo);
 	}
 	/*rx_status->qual = stats->signal; */
-	rx_status->signal = stats->rssi + 10;
+	rx_status->signal = stats->recvsignalpower + 10;
 	/*rx_status->noise = -stats->noise; */
 	return true;
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
index 4f461786a7eb..c471400fe8f0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
@@ -955,7 +955,7 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 tmp_byte = 0;
-
+	unsigned long flags;
 	bool rtstatus = true;
 	u8 tmp_u1b;
 	int err = false;
@@ -967,6 +967,16 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpci->being_init_adapter = true;
 
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	/* 1. MAC Initialize */
@@ -984,7 +994,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now... "
 			 "Please copy FW into /lib/firmware/rtlwifi\n");
-		return 1;
+		err = 1;
+		goto exit;
 	}
 
 	/* After FW download, we have to reset MAC register */
@@ -997,7 +1008,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
 	if (!rtl92s_phy_mac_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "MAC Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* because last function modify RCR, so we update
@@ -1016,7 +1028,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
 	if (!rtl92s_phy_bb_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, "BB Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */
@@ -1033,7 +1046,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	if (!rtl92s_phy_rf_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "RF Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* After read predefined TXT, we must set BB/MAC/RF
@@ -1122,8 +1136,9 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
 	rtl92s_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
-
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
index 5061f1db3f02..92d38ab3c60e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
@@ -265,7 +265,7 @@ static void _rtl92s_get_txpower_writeval_byregulatory(struct ieee80211_hw *hw,
 				    rtlefuse->pwrgroup_ht40
 				    [RF90_PATH_A][chnl - 1]) {
 					pwrdiff_limit[i] =
-					  rtlefuse->pwrgroup_ht20
+					  rtlefuse->pwrgroup_ht40
 					  [RF90_PATH_A][chnl - 1];
 				}
 			} else {
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index c7095118de6e..c240b7591cf0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -49,6 +49,12 @@ static u8 _rtl92se_map_hwqueue_to_fwqueue(struct sk_buff *skb,	u8 skb_queue)
 	if (ieee80211_is_nullfunc(fc))
 		return QSLT_HIGH;
 
+	/* Kernel commit 1bf4bbb4024dcdab changed EAPOL packets to use
+	 * queue V0 at priority 7; however, the RTL8192SE appears to have
+	 * that queue at priority 6
+	 */
+	if (skb->priority == 7)
+		return QSLT_VO;
 	return skb->priority;
 }
 
@@ -329,7 +335,7 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 	}
 
 	/*rx_status->qual = stats->signal; */
-	rx_status->signal = stats->rssi + 10;
+	rx_status->signal = stats->recvsignalpower + 10;
 	/*rx_status->noise = -stats->noise; */
 
 	return true;
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index c333dfd116b8..99f6bc5fa986 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -880,14 +880,25 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err;
 	u8 tmp_u1b;
+	unsigned long flags;
 
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl8712e_init_mac(hw);
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl8723ae_download_fw(hw);
@@ -895,8 +906,7 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -971,6 +981,8 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
 	}
 	rtl8723ae_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	return err;
 }
diff --git a/drivers/net/wireless/rtlwifi/stats.c b/drivers/net/wireless/rtlwifi/stats.c
index 8ed31744a054..4f083fc1d360 100644
--- a/drivers/net/wireless/rtlwifi/stats.c
+++ b/drivers/net/wireless/rtlwifi/stats.c
@@ -176,6 +176,7 @@ static void rtl_process_pwdb(struct ieee80211_hw *hw, struct rtl_stats *pstatus)
 	struct rtl_sta_info *drv_priv = NULL;
 	struct ieee80211_sta *sta = NULL;
 	long undec_sm_pwdb;
+	long undec_sm_cck;
 
 	rcu_read_lock();
 	if (rtlpriv->mac80211.opmode != NL80211_IFTYPE_STATION)
@@ -185,12 +186,16 @@ static void rtl_process_pwdb(struct ieee80211_hw *hw, struct rtl_stats *pstatus)
 	if (sta) {
 		drv_priv = (struct rtl_sta_info *) sta->drv_priv;
 		undec_sm_pwdb = drv_priv->rssi_stat.undec_sm_pwdb;
+		undec_sm_cck = drv_priv->rssi_stat.undec_sm_cck;
 	} else {
 		undec_sm_pwdb = rtlpriv->dm.undec_sm_pwdb;
+		undec_sm_cck = rtlpriv->dm.undec_sm_cck;
 	}
 
 	if (undec_sm_pwdb < 0)
 		undec_sm_pwdb = pstatus->rx_pwdb_all;
+	if (undec_sm_cck < 0)
+		undec_sm_cck = pstatus->rx_pwdb_all;
 	if (pstatus->rx_pwdb_all > (u32) undec_sm_pwdb) {
 		undec_sm_pwdb = (((undec_sm_pwdb) *
 		      (RX_SMOOTH_FACTOR - 1)) +
@@ -200,6 +205,15 @@ static void rtl_process_pwdb(struct ieee80211_hw *hw, struct rtl_stats *pstatus)
 		undec_sm_pwdb = (((undec_sm_pwdb) * (RX_SMOOTH_FACTOR - 1)) +
 		     (pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
 	}
+	if (pstatus->rx_pwdb_all > (u32) undec_sm_cck) {
+		undec_sm_cck = (((undec_sm_pwdb) *
+		      (RX_SMOOTH_FACTOR - 1)) +
+		     (pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
+		undec_sm_cck = undec_sm_cck + 1;
+	} else {
+		undec_sm_pwdb = (((undec_sm_cck) * (RX_SMOOTH_FACTOR - 1)) +
+		     (pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
+	}
 
 	if (sta) {
 		drv_priv->rssi_stat.undec_sm_pwdb = undec_sm_pwdb;
diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c
index 1feebdc92f41..57b12a5883a0 100644
--- a/drivers/net/wireless/rtlwifi/usb.c
+++ b/drivers/net/wireless/rtlwifi/usb.c
@@ -477,6 +477,8 @@ static void _rtl_usb_rx_process_agg(struct ieee80211_hw *hw,
 			if (unicast)
 				rtlpriv->link_info.num_rx_inperiod++;
 		}
+		/* static bcn for roaming */
+		rtl_beacon_statistic(hw, skb);
 	}
 }
 
@@ -548,7 +550,7 @@ static void _rtl_rx_pre_process(struct ieee80211_hw *hw, struct sk_buff *skb)
 	}
 }
 
-#define __RX_SKB_MAX_QUEUED	32
+#define __RX_SKB_MAX_QUEUED	64
 
 static void _rtl_rx_work(unsigned long param)
 {
diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h
index cc03e7c87cbe..e576a927fde7 100644
--- a/drivers/net/wireless/rtlwifi/wifi.h
+++ b/drivers/net/wireless/rtlwifi/wifi.h
@@ -77,11 +77,7 @@
 #define RTL_SLOT_TIME_9				9
 #define RTL_SLOT_TIME_20			20
 
-/*related with tcp/ip. */
-/*if_ehther.h*/
-#define ETH_P_PAE		0x888E	/*Port Access Entity (IEEE 802.1X) */
-#define ETH_P_IP		0x0800	/*Internet Protocol packet */
-#define ETH_P_ARP		0x0806	/*Address Resolution packet */
+/*related to tcp/ip. */
 #define SNAP_SIZE		6
 #define PROTOC_TYPE_SIZE	2
 
@@ -1039,6 +1035,7 @@ struct rtl_ht_agg {
 
 struct rssi_sta {
 	long undec_sm_pwdb;
+	long undec_sm_cck;
 };
 
 struct rtl_tid_data {
@@ -1329,8 +1326,10 @@ struct fast_ant_training {
 struct rtl_dm {
 	/*PHY status for Dynamic Management */
 	long entry_min_undec_sm_pwdb;
+	long undec_sm_cck;
 	long undec_sm_pwdb;	/*out dm */
 	long entry_max_undec_sm_pwdb;
+	s32 ofdm_pkt_cnt;
 	bool dm_initialgain_enable;
 	bool dynamic_txpower_enable;
 	bool current_turbo_edca;
@@ -1345,6 +1344,7 @@ struct rtl_dm {
 	bool inform_fw_driverctrldm;
 	bool current_mrc_switch;
 	u8 txpowercount;
+	u8 powerindex_backup[6];
 
 	u8 thermalvalue_rxgain;
 	u8 thermalvalue_iqk;
@@ -1356,7 +1356,9 @@ struct rtl_dm {
 	bool done_txpower;
 	u8 dynamic_txhighpower_lvl;	/*Tx high power level */
 	u8 dm_flag;		/*Indicate each dynamic mechanism's status. */
+	u8 dm_flag_tmp;
 	u8 dm_type;
+	u8 dm_rssi_sel;
 	u8 txpower_track_control;
 	bool interrupt_migration;
 	bool disable_tx_int;
@@ -1810,6 +1812,7 @@ struct rtl_hal_cfg {
 	bool write_readback;
 	char *name;
 	char *fw_name;
+	char *alt_fw_name;
 	struct rtl_hal_ops *ops;
 	struct rtl_mod_params *mod_params;
 	struct rtl_hal_usbint_cfg *usb_interface_cfg;
@@ -1954,6 +1957,7 @@ struct dig_t {
 	u8 pre_ccastate;
 	u8 cur_ccasate;
 	u8 large_fa_hit;
+	u8 dig_dynamic_min;
 	u8 forbidden_igi;
 	u8 dig_state;
 	u8 dig_highpwrstate;
@@ -2034,22 +2038,15 @@ struct rtl_priv {
 	struct dig_t dm_digtable;
 	struct ps_t dm_pstable;
 
-	/* section shared by individual drivers */
-	union {
-		struct {	/* data buffer pointer for USB reads */
-			__le32 *usb_data;
-			int usb_data_index;
-			bool initialized;
-		};
-		struct {	/* section for 8723ae */
-			bool reg_init;	/* true if regs saved */
-			u32 reg_874;
-			u32 reg_c70;
-			u32 reg_85c;
-			u32 reg_a74;
-			bool bt_operation_on;
-		};
-	};
+	u32 reg_874;
+	u32 reg_c70;
+	u32 reg_85c;
+	u32 reg_a74;
+	bool reg_init;	/* true if regs saved */
+	bool bt_operation_on;
+	__le32 *usb_data;
+	int usb_data_index;
+	bool initialized;
 	bool enter_ps;	/* true when entering PS */
 	u8 rate_mask[5];
 
@@ -2057,7 +2054,7 @@ struct rtl_priv {
 	   that it points to the data allocated
 	   beyond  this structure like:
 	   rtl_pci_priv or rtl_usb_priv */
-	u8 priv[0];
+	u8 priv[0] __aligned(sizeof(void *));
 };
 
 #define rtl_priv(hw)		(((struct rtl_priv *)(hw)->priv))
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 9d7f1723dd8f..f2faa779e3fe 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -88,6 +88,7 @@ struct xenvif {
 	unsigned long   credit_usec;
 	unsigned long   remaining_credit;
 	struct timer_list credit_timeout;
+	u64 credit_window_start;
 
 	/* Statistics */
 	unsigned long rx_gso_checksum_fixup;
@@ -115,6 +116,7 @@ struct xenvif *xenvif_alloc(struct device *parent,
 int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 		   unsigned long rx_ring_ref, unsigned int evtchn);
 void xenvif_disconnect(struct xenvif *vif);
+void xenvif_free(struct xenvif *vif);
 
 void xenvif_get(struct xenvif *vif);
 void xenvif_put(struct xenvif *vif);
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index d98414168485..540a796593a3 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -275,8 +275,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
 	vif->credit_usec  = 0UL;
 	init_timer(&vif->credit_timeout);
-	/* Initialize 'expires' now: it's used to track the credit window. */
-	vif->credit_timeout.expires = jiffies;
+	vif->credit_window_start = get_jiffies_64();
 
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
@@ -304,6 +303,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	}
 
 	netdev_dbg(dev, "Successfully created xenvif\n");
+
+	__module_get(THIS_MODULE);
+
 	return vif;
 }
 
@@ -363,15 +365,22 @@ void xenvif_disconnect(struct xenvif *vif)
 	if (netif_carrier_ok(vif->dev))
 		xenvif_carrier_off(vif);
 
+	if (vif->irq) {
+		unbind_from_irqhandler(vif->irq, vif);
+		vif->irq = 0;
+	}
+
+	xen_netbk_unmap_frontend_rings(vif);
+}
+
+void xenvif_free(struct xenvif *vif)
+{
 	atomic_dec(&vif->refcnt);
 	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
 
-	if (vif->irq)
-		unbind_from_irqhandler(vif->irq, vif);
-
 	unregister_netdev(vif->dev);
 
-	xen_netbk_unmap_frontend_rings(vif);
-
 	free_netdev(vif->dev);
+
+	module_put(THIS_MODULE);
 }
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 8c20935d72c9..70b830f6c4bf 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -347,13 +347,56 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;
 }
 
+struct xenvif_count_slot_state {
+	unsigned long copy_off;
+	bool head;
+};
+
+unsigned int xenvif_count_frag_slots(struct xenvif *vif,
+				     unsigned long offset, unsigned long size,
+				     struct xenvif_count_slot_state *state)
+{
+	unsigned count = 0;
+
+	offset &= ~PAGE_MASK;
+
+	while (size > 0) {
+		unsigned long bytes;
+
+		bytes = PAGE_SIZE - offset;
+
+		if (bytes > size)
+			bytes = size;
+
+		if (start_new_rx_buffer(state->copy_off, bytes, state->head)) {
+			count++;
+			state->copy_off = 0;
+		}
+
+		if (state->copy_off + bytes > MAX_BUFFER_OFFSET)
+			bytes = MAX_BUFFER_OFFSET - state->copy_off;
+
+		state->copy_off += bytes;
+
+		offset += bytes;
+		size -= bytes;
+
+		if (offset == PAGE_SIZE)
+			offset = 0;
+
+		state->head = false;
+	}
+
+	return count;
+}
+
 /*
  * Figure out how many ring slots we're going to need to send @skb to
  * the guest. This function is essentially a dry run of
@@ -361,48 +404,39 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
  */
 unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
 {
+	struct xenvif_count_slot_state state;
 	unsigned int count;
-	int i, copy_off;
+	unsigned char *data;
+	unsigned i;
 
-	count = DIV_ROUND_UP(skb_headlen(skb), PAGE_SIZE);
+	state.head = true;
+	state.copy_off = 0;
 
-	copy_off = skb_headlen(skb) % PAGE_SIZE;
+	/* Slot for the first (partial) page of data. */
+	count = 1;
 
+	/* Need a slot for the GSO prefix for GSO extra data? */
 	if (skb_shinfo(skb)->gso_size)
 		count++;
 
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
-		unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
-		unsigned long bytes;
-
-		offset &= ~PAGE_MASK;
-
-		while (size > 0) {
-			BUG_ON(offset >= PAGE_SIZE);
-			BUG_ON(copy_off > MAX_BUFFER_OFFSET);
-
-			bytes = PAGE_SIZE - offset;
-
-			if (bytes > size)
-				bytes = size;
+	data = skb->data;
+	while (data < skb_tail_pointer(skb)) {
+		unsigned long offset = offset_in_page(data);
+		unsigned long size = PAGE_SIZE - offset;
 
-			if (start_new_rx_buffer(copy_off, bytes, 0)) {
-				count++;
-				copy_off = 0;
-			}
+		if (data + size > skb_tail_pointer(skb))
+			size = skb_tail_pointer(skb) - data;
 
-			if (copy_off + bytes > MAX_BUFFER_OFFSET)
-				bytes = MAX_BUFFER_OFFSET - copy_off;
+		count += xenvif_count_frag_slots(vif, offset, size, &state);
 
-			copy_off += bytes;
+		data += size;
+	}
 
-			offset += bytes;
-			size -= bytes;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
+		unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
 
-			if (offset == PAGE_SIZE)
-				offset = 0;
-		}
+		count += xenvif_count_frag_slots(vif, offset, size, &state);
 	}
 	return count;
 }
@@ -1389,9 +1423,8 @@ out:
 
 static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 {
-	unsigned long now = jiffies;
-	unsigned long next_credit =
-		vif->credit_timeout.expires +
+	u64 now = get_jiffies_64();
+	u64 next_credit = vif->credit_window_start +
 		msecs_to_jiffies(vif->credit_usec / 1000);
 
 	/* Timer could already be pending in rare cases. */
@@ -1399,8 +1432,8 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 		return true;
 
 	/* Passed the point where we can replenish credit? */
-	if (time_after_eq(now, next_credit)) {
-		vif->credit_timeout.expires = now;
+	if (time_after_eq64(now, next_credit)) {
+		vif->credit_window_start = now;
 		tx_add_credit(vif);
 	}
 
@@ -1412,6 +1445,7 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 			tx_credit_callback;
 		mod_timer(&vif->credit_timeout,
 			  next_credit);
+		vif->credit_window_start = next_credit;
 
 		return true;
 	}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 410018c4c528..8a9e8750703f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -24,6 +24,12 @@
 struct backend_info {
 	struct xenbus_device *dev;
 	struct xenvif *vif;
+
+	/* This is the state that will be reflected in xenstore when any
+	 * active hotplug script completes.
+	 */
+	enum xenbus_state state;
+
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
@@ -33,16 +39,20 @@ static int connect_rings(struct backend_info *);
 static void connect(struct backend_info *);
 static void backend_create_xenvif(struct backend_info *be);
 static void unregister_hotplug_status_watch(struct backend_info *be);
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state);
 
 static int netback_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
+	set_backend_state(be, XenbusStateClosed);
+
 	unregister_hotplug_status_watch(be);
 	if (be->vif) {
 		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
 		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
-		xenvif_disconnect(be->vif);
+		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
 	kfree(be);
@@ -126,6 +136,8 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		goto fail;
 
+	be->state = XenbusStateInitWait;
+
 	/* This kicks hotplug scripts, so do it immediately. */
 	backend_create_xenvif(be);
 
@@ -198,15 +210,113 @@ static void backend_create_xenvif(struct backend_info *be)
 	kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
 }
 
+static void backend_disconnect(struct backend_info *be)
+{
+	if (be->vif)
+		xenvif_disconnect(be->vif);
+}
 
-static void disconnect_backend(struct xenbus_device *dev)
+static void backend_connect(struct backend_info *be)
 {
-	struct backend_info *be = dev_get_drvdata(&dev->dev);
+	if (be->vif)
+		connect(be);
+}
 
-	if (be->vif) {
-		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
-		xenvif_disconnect(be->vif);
-		be->vif = NULL;
+static inline void backend_switch_state(struct backend_info *be,
+					enum xenbus_state state)
+{
+	struct xenbus_device *dev = be->dev;
+
+	pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state));
+	be->state = state;
+
+	/* If we are waiting for a hotplug script then defer the
+	 * actual xenbus state change.
+	 */
+	if (!be->have_hotplug_status_watch)
+		xenbus_switch_state(dev, state);
+}
+
+/* Handle backend state transitions:
+ *
+ * The backend state starts in InitWait and the following transitions are
+ * allowed.
+ *
+ * InitWait -> Connected
+ *
+ *    ^    \         |
+ *    |     \        |
+ *    |      \       |
+ *    |       \      |
+ *    |        \     |
+ *    |         \    |
+ *    |          V   V
+ *
+ *  Closed  <-> Closing
+ *
+ * The state argument specifies the eventual state of the backend and the
+ * function transitions to that state via the shortest path.
+ */
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state)
+{
+	while (be->state != state) {
+		switch (be->state) {
+		case XenbusStateClosed:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+				pr_info("%s: prepare for reconnect\n",
+					be->dev->nodename);
+				backend_switch_state(be, XenbusStateInitWait);
+				break;
+			case XenbusStateClosing:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateInitWait:
+			switch (state) {
+			case XenbusStateConnected:
+				backend_connect(be);
+				backend_switch_state(be, XenbusStateConnected);
+				break;
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateConnected:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_disconnect(be);
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateClosing:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosed);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		default:
+			BUG();
+		}
 	}
 }
 
@@ -218,43 +328,33 @@ static void frontend_changed(struct xenbus_device *dev,
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
-	pr_debug("frontend state %s", xenbus_strstate(frontend_state));
+	pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state));
 
 	be->frontend_state = frontend_state;
 
 	switch (frontend_state) {
 	case XenbusStateInitialising:
-		if (dev->state == XenbusStateClosed) {
-			printk(KERN_INFO "%s: %s: prepare for reconnect\n",
-			       __func__, dev->nodename);
-			xenbus_switch_state(dev, XenbusStateInitWait);
-		}
+		set_backend_state(be, XenbusStateInitWait);
 		break;
 
 	case XenbusStateInitialised:
 		break;
 
 	case XenbusStateConnected:
-		if (dev->state == XenbusStateConnected)
-			break;
-		backend_create_xenvif(be);
-		if (be->vif)
-			connect(be);
+		set_backend_state(be, XenbusStateConnected);
 		break;
 
 	case XenbusStateClosing:
-		if (be->vif)
-			kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
-		disconnect_backend(dev);
-		xenbus_switch_state(dev, XenbusStateClosing);
+		set_backend_state(be, XenbusStateClosing);
 		break;
 
 	case XenbusStateClosed:
-		xenbus_switch_state(dev, XenbusStateClosed);
+		set_backend_state(be, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
 		/* fall through if not online */
 	case XenbusStateUnknown:
+		set_backend_state(be, XenbusStateClosed);
 		device_unregister(&dev->dev);
 		break;
 
@@ -347,7 +447,9 @@ static void hotplug_status_changed(struct xenbus_watch *watch,
 	if (IS_ERR(str))
 		return;
 	if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
-		xenbus_switch_state(be->dev, XenbusStateConnected);
+		/* Complete any pending state change */
+		xenbus_switch_state(be->dev, be->state);
+
 		/* Not interested in this watch anymore. */
 		unregister_hotplug_status_watch(be);
 	}
@@ -377,12 +479,8 @@ static void connect(struct backend_info *be)
 	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
 				   hotplug_status_changed,
 				   "%s/%s", dev->nodename, "hotplug-status");
-	if (err) {
-		/* Switch now, since we can't do a watch. */
-		xenbus_switch_state(dev, XenbusStateConnected);
-	} else {
+	if (!err)
 		be->have_hotplug_status_watch = 1;
-	}
 
 	netif_wake_queue(be->vif->dev);
 }
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 0c01b8e33fe1..a1db958df4a4 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -107,6 +107,7 @@ struct netfront_info {
 	} tx_skbs[NET_TX_RING_SIZE];
 	grant_ref_t gref_tx_head;
 	grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
+	struct page *grant_tx_page[NET_TX_RING_SIZE];
 	unsigned tx_skb_freelist;
 
 	spinlock_t   rx_lock ____cacheline_aligned_in_smp;
@@ -386,6 +387,7 @@ static void xennet_tx_buf_gc(struct net_device *dev)
 			gnttab_release_grant_reference(
 				&np->gref_tx_head, np->grant_tx_ref[id]);
 			np->grant_tx_ref[id] = GRANT_INVALID_REF;
+			np->grant_tx_page[id] = NULL;
 			add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id);
 			dev_kfree_skb_irq(skb);
 		}
@@ -442,6 +444,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
 						mfn, GNTMAP_readonly);
 
+		np->grant_tx_page[id] = virt_to_page(data);
 		tx->gref = np->grant_tx_ref[id] = ref;
 		tx->offset = offset;
 		tx->size = len;
@@ -456,9 +459,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		len = skb_frag_size(frag);
 		offset = frag->page_offset;
 
-		/* Data must not cross a page boundary. */
-		BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
-
 		/* Skip unused frames from start of page */
 		page += offset >> PAGE_SHIFT;
 		offset &= ~PAGE_MASK;
@@ -466,8 +466,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		while (len > 0) {
 			unsigned long bytes;
 
-			BUG_ON(offset >= PAGE_SIZE);
-
 			bytes = PAGE_SIZE - offset;
 			if (bytes > len)
 				bytes = len;
@@ -487,6 +485,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 							np->xbdev->otherend_id,
 							mfn, GNTMAP_readonly);
 
+			np->grant_tx_page[id] = page;
 			tx->gref = np->grant_tx_ref[id] = ref;
 			tx->offset = offset;
 			tx->size = bytes;
@@ -586,6 +585,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	mfn = virt_to_mfn(data);
 	gnttab_grant_foreign_access_ref(
 		ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
+	np->grant_tx_page[id] = virt_to_page(data);
 	tx->gref = np->grant_tx_ref[id] = ref;
 	tx->offset = offset;
 	tx->size = len;
@@ -1115,10 +1115,11 @@ static void xennet_release_tx_bufs(struct netfront_info *np)
 			continue;
 
 		skb = np->tx_skbs[i].skb;
-		gnttab_end_foreign_access_ref(np->grant_tx_ref[i],
-					      GNTMAP_readonly);
-		gnttab_release_grant_reference(&np->gref_tx_head,
-					       np->grant_tx_ref[i]);
+		get_page(np->grant_tx_page[i]);
+		gnttab_end_foreign_access(np->grant_tx_ref[i],
+					  GNTMAP_readonly,
+					  (unsigned long)page_address(np->grant_tx_page[i]));
+		np->grant_tx_page[i] = NULL;
 		np->grant_tx_ref[i] = GRANT_INVALID_REF;
 		add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
 		dev_kfree_skb_irq(skb);
@@ -1127,78 +1128,35 @@ static void xennet_release_tx_bufs(struct netfront_info *np)
 
 static void xennet_release_rx_bufs(struct netfront_info *np)
 {
-	struct mmu_update      *mmu = np->rx_mmu;
-	struct multicall_entry *mcl = np->rx_mcl;
-	struct sk_buff_head free_list;
-	struct sk_buff *skb;
-	unsigned long mfn;
-	int xfer = 0, noxfer = 0, unused = 0;
 	int id, ref;
 
-	dev_warn(&np->netdev->dev, "%s: fix me for copying receiver.\n",
-			 __func__);
-	return;
-
-	skb_queue_head_init(&free_list);
-
 	spin_lock_bh(&np->rx_lock);
 
 	for (id = 0; id < NET_RX_RING_SIZE; id++) {
-		ref = np->grant_rx_ref[id];
-		if (ref == GRANT_INVALID_REF) {
-			unused++;
-			continue;
-		}
+		struct sk_buff *skb;
+		struct page *page;
 
 		skb = np->rx_skbs[id];
-		mfn = gnttab_end_foreign_transfer_ref(ref);
-		gnttab_release_grant_reference(&np->gref_rx_head, ref);
-		np->grant_rx_ref[id] = GRANT_INVALID_REF;
-
-		if (0 == mfn) {
-			skb_shinfo(skb)->nr_frags = 0;
-			dev_kfree_skb(skb);
-			noxfer++;
+		if (!skb)
 			continue;
-		}
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			/* Remap the page. */
-			const struct page *page =
-				skb_frag_page(&skb_shinfo(skb)->frags[0]);
-			unsigned long pfn = page_to_pfn(page);
-			void *vaddr = page_address(page);
 
-			MULTI_update_va_mapping(mcl, (unsigned long)vaddr,
-						mfn_pte(mfn, PAGE_KERNEL),
-						0);
-			mcl++;
-			mmu->ptr = ((u64)mfn << PAGE_SHIFT)
-				| MMU_MACHPHYS_UPDATE;
-			mmu->val = pfn;
-			mmu++;
+		ref = np->grant_rx_ref[id];
+		if (ref == GRANT_INVALID_REF)
+			continue;
 
-			set_phys_to_machine(pfn, mfn);
-		}
-		__skb_queue_tail(&free_list, skb);
-		xfer++;
-	}
+		page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
 
-	dev_info(&np->netdev->dev, "%s: %d xfer, %d noxfer, %d unused\n",
-		 __func__, xfer, noxfer, unused);
+		/* gnttab_end_foreign_access() needs a page ref until
+		 * foreign access is ended (which may be deferred).
+		 */
+		get_page(page);
+		gnttab_end_foreign_access(ref, 0,
+					  (unsigned long)page_address(page));
+		np->grant_rx_ref[id] = GRANT_INVALID_REF;
 
-	if (xfer) {
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			/* Do all the remapping work and M2P updates. */
-			MULTI_mmu_update(mcl, np->rx_mmu, mmu - np->rx_mmu,
-					 NULL, DOMID_SELF);
-			mcl++;
-			HYPERVISOR_multicall(np->rx_mcl, mcl - np->rx_mcl);
-		}
+		kfree_skb(skb);
 	}
 
-	__skb_queue_purge(&free_list);
-
 	spin_unlock_bh(&np->rx_lock);
 }
 
@@ -1333,6 +1291,7 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	for (i = 0; i < NET_RX_RING_SIZE; i++) {
 		np->rx_skbs[i] = NULL;
 		np->grant_rx_ref[i] = GRANT_INVALID_REF;
+		np->grant_tx_page[i] = NULL;
 	}
 
 	/* A grant for every tx ring slot */
diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c
index 3420d833db17..384ab8ca4b37 100644
--- a/drivers/nfc/microread/microread.c
+++ b/drivers/nfc/microread/microread.c
@@ -501,9 +501,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate,
 		targets->sens_res =
 			 be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]);
 		targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK];
-		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
-		       skb->data[MICROREAD_EMCF_A_LEN]);
 		targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN];
+		if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+			r = -EINVAL;
+			goto exit_free;
+		}
+		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
+		       targets->nfcid1_len);
 		break;
 	case MICROREAD_GATE_ID_MREAD_ISO_A_3:
 		targets->supported_protocols =
@@ -511,9 +515,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate,
 		targets->sens_res =
 			 be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]);
 		targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK];
-		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
-		       skb->data[MICROREAD_EMCF_A3_LEN]);
 		targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN];
+		if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+			r = -EINVAL;
+			goto exit_free;
+		}
+		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
+		       targets->nfcid1_len);
 		break;
 	case MICROREAD_GATE_ID_MREAD_ISO_B:
 		targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK;
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c
index 2dacd19e1b8a..b9bf8b551e3c 100644
--- a/drivers/ntb/ntb_hw.c
+++ b/drivers/ntb/ntb_hw.c
@@ -78,6 +78,8 @@ enum {
 	BWD_HW,
 };
 
+static struct dentry *debugfs_dir;
+
 /* Translate memory window 0,1 to BAR 2,4 */
 #define MW_TO_BAR(mw)	(mw * 2 + 2)
 
@@ -531,9 +533,9 @@ static int ntb_xeon_setup(struct ntb_device *ndev)
 	}
 
 	if (val & SNB_PPD_DEV_TYPE)
-		ndev->dev_type = NTB_DEV_DSD;
-	else
 		ndev->dev_type = NTB_DEV_USD;
+	else
+		ndev->dev_type = NTB_DEV_DSD;
 
 	ndev->reg_ofs.pdb = ndev->reg_base + SNB_PDOORBELL_OFFSET;
 	ndev->reg_ofs.pdb_mask = ndev->reg_base + SNB_PDBMSK_OFFSET;
@@ -547,7 +549,7 @@ static int ntb_xeon_setup(struct ntb_device *ndev)
 	if (ndev->conn_type == NTB_CONN_B2B) {
 		ndev->reg_ofs.sdb = ndev->reg_base + SNB_B2B_DOORBELL_OFFSET;
 		ndev->reg_ofs.spad_write = ndev->reg_base + SNB_B2B_SPAD_OFFSET;
-		ndev->limits.max_spads = SNB_MAX_SPADS;
+		ndev->limits.max_spads = SNB_MAX_B2B_SPADS;
 	} else {
 		ndev->reg_ofs.sdb = ndev->reg_base + SNB_SDOORBELL_OFFSET;
 		ndev->reg_ofs.spad_write = ndev->reg_base + SNB_SPAD_OFFSET;
@@ -644,10 +646,16 @@ static int ntb_device_setup(struct ntb_device *ndev)
 		rc = -ENODEV;
 	}
 
+	if (rc)
+		return rc;
+
+	dev_info(&ndev->pdev->dev, "Device Type = %s\n",
+		 ndev->dev_type == NTB_DEV_USD ? "USD/DSP" : "DSD/USP");
+
 	/* Enable Bus Master and Memory Space on the secondary side */
 	writew(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER, ndev->reg_ofs.spci_cmd);
 
-	return rc;
+	return 0;
 }
 
 static void ntb_device_free(struct ntb_device *ndev)
@@ -992,6 +1000,28 @@ static void ntb_free_callbacks(struct ntb_device *ndev)
 	kfree(ndev->db_cb);
 }
 
+static void ntb_setup_debugfs(struct ntb_device *ndev)
+{
+	if (!debugfs_initialized())
+		return;
+
+	if (!debugfs_dir)
+		debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	ndev->debugfs_dir = debugfs_create_dir(pci_name(ndev->pdev),
+					       debugfs_dir);
+}
+
+static void ntb_free_debugfs(struct ntb_device *ndev)
+{
+	debugfs_remove_recursive(ndev->debugfs_dir);
+
+	if (debugfs_dir && simple_empty(debugfs_dir)) {
+		debugfs_remove_recursive(debugfs_dir);
+		debugfs_dir = NULL;
+	}
+}
+
 static int ntb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct ntb_device *ndev;
@@ -1004,6 +1034,7 @@ static int ntb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ndev->pdev = pdev;
 	ndev->link_status = NTB_LINK_DOWN;
 	pci_set_drvdata(pdev, ndev);
+	ntb_setup_debugfs(ndev);
 
 	rc = pci_enable_device(pdev);
 	if (rc)
@@ -1100,6 +1131,7 @@ err2:
 err1:
 	pci_disable_device(pdev);
 err:
+	ntb_free_debugfs(ndev);
 	kfree(ndev);
 
 	dev_err(&pdev->dev, "Error loading %s module\n", KBUILD_MODNAME);
@@ -1129,6 +1161,7 @@ static void ntb_pci_remove(struct pci_dev *pdev)
 	iounmap(ndev->reg_base);
 	pci_release_selected_regions(pdev, NTB_BAR_MASK);
 	pci_disable_device(pdev);
+	ntb_free_debugfs(ndev);
 	kfree(ndev);
 }
 
diff --git a/drivers/ntb/ntb_hw.h b/drivers/ntb/ntb_hw.h
index 3a3038ca83e6..6a4f56f564ee 100644
--- a/drivers/ntb/ntb_hw.h
+++ b/drivers/ntb/ntb_hw.h
@@ -127,6 +127,8 @@ struct ntb_device {
 	unsigned char link_status;
 	struct delayed_work hb_timer;
 	unsigned long last_ts;
+
+	struct dentry *debugfs_dir;
 };
 
 /**
@@ -155,6 +157,20 @@ static inline struct pci_dev *ntb_query_pdev(struct ntb_device *ndev)
 	return ndev->pdev;
 }
 
+/**
+ * ntb_query_debugfs() - return the debugfs pointer
+ * @ndev: pointer to ntb_device instance
+ *
+ * Given the ntb pointer, return the debugfs directory pointer for the NTB
+ * hardware device
+ *
+ * RETURNS: a pointer to the debugfs directory
+ */
+static inline struct dentry *ntb_query_debugfs(struct ntb_device *ndev)
+{
+	return ndev->debugfs_dir;
+}
+
 struct ntb_device *ntb_register_transport(struct pci_dev *pdev,
 					  void *transport);
 void ntb_unregister_transport(struct ntb_device *ndev);
diff --git a/drivers/ntb/ntb_regs.h b/drivers/ntb/ntb_regs.h
index 5bfa8c06c059..96209b4abc22 100644
--- a/drivers/ntb/ntb_regs.h
+++ b/drivers/ntb/ntb_regs.h
@@ -53,8 +53,8 @@
 #define NTB_LINK_WIDTH_MASK	0x03f0
 
 #define SNB_MSIX_CNT		4
-#define SNB_MAX_SPADS		16
-#define SNB_MAX_COMPAT_SPADS	8
+#define SNB_MAX_B2B_SPADS	16
+#define SNB_MAX_COMPAT_SPADS	16
 /* Reserve the uppermost bit for link interrupt */
 #define SNB_MAX_DB_BITS		15
 #define SNB_DB_BITS_PER_VEC	5
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f8d7081ee301..c3089151aa49 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -157,7 +157,6 @@ struct ntb_transport {
 	bool transport_link;
 	struct delayed_work link_work;
 	struct work_struct link_cleanup;
-	struct dentry *debugfs_dir;
 };
 
 enum {
@@ -824,12 +823,12 @@ static void ntb_transport_init_queue(struct ntb_transport *nt,
 	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
 	qp->tx_max_entry = tx_size / qp->tx_max_frame;
 
-	if (nt->debugfs_dir) {
+	if (ntb_query_debugfs(nt->ndev)) {
 		char debugfs_name[4];
 
 		snprintf(debugfs_name, 4, "qp%d", qp_num);
 		qp->debugfs_dir = debugfs_create_dir(debugfs_name,
-						     nt->debugfs_dir);
+						 ntb_query_debugfs(nt->ndev));
 
 		qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
 							qp->debugfs_dir, qp,
@@ -857,11 +856,6 @@ int ntb_transport_init(struct pci_dev *pdev)
 	if (!nt)
 		return -ENOMEM;
 
-	if (debugfs_initialized())
-		nt->debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
-	else
-		nt->debugfs_dir = NULL;
-
 	nt->ndev = ntb_register_transport(pdev, nt);
 	if (!nt->ndev) {
 		rc = -EIO;
@@ -907,7 +901,6 @@ err2:
 err1:
 	ntb_unregister_transport(nt->ndev);
 err:
-	debugfs_remove_recursive(nt->debugfs_dir);
 	kfree(nt);
 	return rc;
 }
@@ -921,16 +914,16 @@ void ntb_transport_free(void *transport)
 	nt->transport_link = NTB_LINK_DOWN;
 
 	/* verify that all the qp's are freed */
-	for (i = 0; i < nt->max_qps; i++)
+	for (i = 0; i < nt->max_qps; i++) {
 		if (!test_bit(i, &nt->qp_bitmap))
 			ntb_transport_free_queue(&nt->qps[i]);
+		debugfs_remove_recursive(nt->qps[i].debugfs_dir);
+	}
 
 	ntb_bus_remove(nt);
 
 	cancel_delayed_work_sync(&nt->link_work);
 
-	debugfs_remove_recursive(nt->debugfs_dir);
-
 	ntb_unregister_event_callback(nt->ndev);
 
 	pdev = ntb_query_pdev(nt->ndev);
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 7c8221d36329..8fb2b5769733 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -69,14 +69,6 @@ static u64 of_bus_default_map(__be32 *addr, const __be32 *range,
 		 (unsigned long long)cp, (unsigned long long)s,
 		 (unsigned long long)da);
 
-	/*
-	 * If the number of address cells is larger than 2 we assume the
-	 * mapping doesn't specify a physical address. Rather, the address
-	 * specifies an identifier that must match exactly.
-	 */
-	if (na > 2 && memcmp(range, addr, na * 4) != 0)
-		return OF_BAD_ADDR;
-
 	if (da < cp || da >= (cp + s))
 		return OF_BAD_ADDR;
 	return da - cp;
@@ -107,11 +99,12 @@ static unsigned int of_bus_default_get_flags(const __be32 *addr)
 static int of_bus_pci_match(struct device_node *np)
 {
 	/*
+ 	 * "pciex" is PCI Express
 	 * "vci" is for the /chaos bridge on 1st-gen PCI powermacs
 	 * "ht" is hypertransport
 	 */
-	return !strcmp(np->type, "pci") || !strcmp(np->type, "vci") ||
-		!strcmp(np->type, "ht");
+	return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex") ||
+		!strcmp(np->type, "vci") || !strcmp(np->type, "ht");
 }
 
 static void of_bus_pci_count_cells(struct device_node *np,
@@ -341,6 +334,21 @@ static struct of_bus *of_match_bus(struct device_node *np)
 	return NULL;
 }
 
+static int of_empty_ranges_quirk(void)
+{
+	if (IS_ENABLED(CONFIG_PPC)) {
+		/* To save cycles, we cache the result */
+		static int quirk_state = -1;
+
+		if (quirk_state < 0)
+			quirk_state =
+				of_machine_is_compatible("Power Macintosh") ||
+				of_machine_is_compatible("MacRISC");
+		return quirk_state;
+	}
+	return false;
+}
+
 static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 			    struct of_bus *pbus, __be32 *addr,
 			    int na, int ns, int pna, const char *rprop)
@@ -366,12 +374,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 	 * This code is only enabled on powerpc. --gcl
 	 */
 	ranges = of_get_property(parent, rprop, &rlen);
-#if !defined(CONFIG_PPC)
-	if (ranges == NULL) {
+	if (ranges == NULL && !of_empty_ranges_quirk()) {
 		pr_err("OF: no ranges; cannot translate\n");
 		return 1;
 	}
-#endif /* !defined(CONFIG_PPC) */
 	if (ranges == NULL || rlen == 0) {
 		offset = of_read_number(addr, na);
 		memset(addr, 0, pna * 4);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index fad95c811bec..191b370b102e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -18,8 +18,10 @@
  *      2 of the License, or (at your option) any later version.
  */
 #include <linux/ctype.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
@@ -231,6 +233,100 @@ const void *of_get_property(const struct device_node *np, const char *name,
 }
 EXPORT_SYMBOL(of_get_property);
 
+/*
+ * arch_match_cpu_phys_id - Match the given logical CPU and physical id
+ *
+ * @cpu: logical cpu index of a core/thread
+ * @phys_id: physical identifier of a core/thread
+ *
+ * CPU logical to physical index mapping is architecture specific.
+ * However this __weak function provides a default match of physical
+ * id to logical cpu index. phys_id provided here is usually values read
+ * from the device tree which must match the hardware internal registers.
+ *
+ * Returns true if the physical identifier and the logical cpu index
+ * correspond to the same core/thread, false otherwise.
+ */
+bool __weak arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return (u32)phys_id == cpu;
+}
+
+/**
+ * Checks if the given "prop_name" property holds the physical id of the
+ * core/thread corresponding to the logical cpu 'cpu'. If 'thread' is not
+ * NULL, local thread number within the core is returned in it.
+ */
+static bool __of_find_n_match_cpu_property(struct device_node *cpun,
+			const char *prop_name, int cpu, unsigned int *thread)
+{
+	const __be32 *cell;
+	int ac, prop_len, tid;
+	u64 hwid;
+
+	ac = of_n_addr_cells(cpun);
+	cell = of_get_property(cpun, prop_name, &prop_len);
+	if (!cell)
+		return false;
+	prop_len /= sizeof(*cell);
+	for (tid = 0; tid < prop_len; tid++) {
+		hwid = of_read_number(cell, ac);
+		if (arch_match_cpu_phys_id(cpu, hwid)) {
+			if (thread)
+				*thread = tid;
+			return true;
+		}
+		cell += ac;
+	}
+	return false;
+}
+
+/**
+ * of_get_cpu_node - Get device node associated with the given logical CPU
+ *
+ * @cpu: CPU number(logical index) for which device node is required
+ * @thread: if not NULL, local thread number within the physical core is
+ *          returned
+ *
+ * The main purpose of this function is to retrieve the device node for the
+ * given logical CPU index. It should be used to initialize the of_node in
+ * cpu device. Once of_node in cpu device is populated, all the further
+ * references can use that instead.
+ *
+ * CPU logical to physical index mapping is architecture specific and is built
+ * before booting secondary cores. This function uses arch_match_cpu_phys_id
+ * which can be overridden by architecture specific implementation.
+ *
+ * Returns a node pointer for the logical cpu if found, else NULL.
+ */
+struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+{
+	struct device_node *cpun, *cpus;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (!cpus) {
+		pr_warn("Missing cpus node, bailing out\n");
+		return NULL;
+	}
+
+	for_each_child_of_node(cpus, cpun) {
+		if (of_node_cmp(cpun->type, "cpu"))
+			continue;
+		/* Check for non-standard "ibm,ppc-interrupt-server#s" property
+		 * for thread ids on PowerPC. If it doesn't exist fallback to
+		 * standard "reg" property.
+		 */
+		if (IS_ENABLED(CONFIG_PPC) &&
+			__of_find_n_match_cpu_property(cpun,
+				"ibm,ppc-interrupt-server#s", cpu, thread))
+			return cpun;
+		if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+			return cpun;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(of_get_cpu_node);
+
 /** Checks if the given "compat" string matches one of the strings in
  * the device's "compatible" property
  */
@@ -964,52 +1060,6 @@ int of_property_read_string(struct device_node *np, const char *propname,
 EXPORT_SYMBOL_GPL(of_property_read_string);
 
 /**
- * of_property_read_string_index - Find and read a string from a multiple
- * strings property.
- * @np:		device node from which the property value is to be read.
- * @propname:	name of the property to be searched.
- * @index:	index of the string in the list of strings
- * @out_string:	pointer to null terminated return string, modified only if
- *		return value is 0.
- *
- * Search for a property in a device tree node and retrieve a null
- * terminated string value (pointer to data, not a copy) in the list of strings
- * contained in that property.
- * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
- * property does not have a value, and -EILSEQ if the string is not
- * null-terminated within the length of the property data.
- *
- * The out_string pointer is modified only if a valid string can be decoded.
- */
-int of_property_read_string_index(struct device_node *np, const char *propname,
-				  int index, const char **output)
-{
-	struct property *prop = of_find_property(np, propname, NULL);
-	int i = 0;
-	size_t l = 0, total = 0;
-	const char *p;
-
-	if (!prop)
-		return -EINVAL;
-	if (!prop->value)
-		return -ENODATA;
-	if (strnlen(prop->value, prop->length) >= prop->length)
-		return -EILSEQ;
-
-	p = prop->value;
-
-	for (i = 0; total < prop->length; total += l, p += l) {
-		l = strlen(p) + 1;
-		if (i++ == index) {
-			*output = p;
-			return 0;
-		}
-	}
-	return -ENODATA;
-}
-EXPORT_SYMBOL_GPL(of_property_read_string_index);
-
-/**
  * of_property_match_string() - Find string in a list and return index
  * @np: pointer to node containing string list property
  * @propname: string list property name
@@ -1035,7 +1085,7 @@ int of_property_match_string(struct device_node *np, const char *propname,
 	end = p + prop->length;
 
 	for (i = 0; p < end; i++, p += l) {
-		l = strlen(p) + 1;
+		l = strnlen(p, end - p) + 1;
 		if (p + l > end)
 			return -EILSEQ;
 		pr_debug("comparing %s with %s\n", string, p);
@@ -1047,39 +1097,41 @@ int of_property_match_string(struct device_node *np, const char *propname,
 EXPORT_SYMBOL_GPL(of_property_match_string);
 
 /**
- * of_property_count_strings - Find and return the number of strings from a
- * multiple strings property.
+ * of_property_read_string_util() - Utility helper for parsing string properties
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
+ * @out_strs:	output array of string pointers.
+ * @sz:		number of array elements to read.
+ * @skip:	Number of strings to skip over at beginning of list.
  *
- * Search for a property in a device tree node and retrieve the number of null
- * terminated string contain in it. Returns the number of strings on
- * success, -EINVAL if the property does not exist, -ENODATA if property
- * does not have a value, and -EILSEQ if the string is not null-terminated
- * within the length of the property data.
+ * Don't call this function directly. It is a utility helper for the
+ * of_property_read_string*() family of functions.
  */
-int of_property_count_strings(struct device_node *np, const char *propname)
+int of_property_read_string_helper(struct device_node *np, const char *propname,
+				   const char **out_strs, size_t sz, int skip)
 {
 	struct property *prop = of_find_property(np, propname, NULL);
-	int i = 0;
-	size_t l = 0, total = 0;
-	const char *p;
+	int l = 0, i = 0;
+	const char *p, *end;
 
 	if (!prop)
 		return -EINVAL;
 	if (!prop->value)
 		return -ENODATA;
-	if (strnlen(prop->value, prop->length) >= prop->length)
-		return -EILSEQ;
-
 	p = prop->value;
+	end = p + prop->length;
 
-	for (i = 0; total < prop->length; total += l, p += l, i++)
-		l = strlen(p) + 1;
-
-	return i;
+	for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) {
+		l = strnlen(p, end - p) + 1;
+		if (p + l > end)
+			return -EILSEQ;
+		if (out_strs && i >= skip)
+			*out_strs++ = p;
+	}
+	i -= skip;
+	return i <= 0 ? -ENODATA : i;
 }
-EXPORT_SYMBOL_GPL(of_property_count_strings);
+EXPORT_SYMBOL_GPL(of_property_read_string_helper);
 
 /**
  * of_parse_phandle - Resolve a phandle property to a device_node pointer
@@ -1730,3 +1782,154 @@ int of_device_is_stdout_path(struct device_node *dn)
 	return of_stdout == dn;
 }
 EXPORT_SYMBOL_GPL(of_device_is_stdout_path);
+
+/**
+ * of_graph_parse_endpoint() - parse common endpoint node properties
+ * @node: pointer to endpoint device_node
+ * @endpoint: pointer to the OF endpoint data structure
+ *
+ * The caller should hold a reference to @node.
+ */
+int of_graph_parse_endpoint(const struct device_node *node,
+			    struct of_endpoint *endpoint)
+{
+	struct device_node *port_node = of_get_parent(node);
+
+	WARN_ONCE(!port_node, "%s(): endpoint %s has no parent node\n",
+		  __func__, node->full_name);
+
+	memset(endpoint, 0, sizeof(*endpoint));
+
+	endpoint->local_node = node;
+	/*
+	 * It doesn't matter whether the two calls below succeed.
+	 * If they don't then the default value 0 is used.
+	 */
+	of_property_read_u32(port_node, "reg", &endpoint->port);
+	of_property_read_u32(node, "reg", &endpoint->id);
+
+	of_node_put(port_node);
+
+	return 0;
+}
+EXPORT_SYMBOL(of_graph_parse_endpoint);
+
+/**
+ * of_graph_get_next_endpoint() - get next endpoint node
+ * @parent: pointer to the parent device node
+ * @prev: previous endpoint node, or NULL to get first
+ *
+ * Return: An 'endpoint' node pointer with refcount incremented. Refcount
+ * of the passed @prev node is not decremented, the caller have to use
+ * of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *prev)
+{
+	struct device_node *endpoint;
+	struct device_node *port;
+
+	if (!parent)
+		return NULL;
+
+	/*
+	 * Start by locating the port node. If no previous endpoint is specified
+	 * search for the first port node, otherwise get the previous endpoint
+	 * parent port node.
+	 */
+	if (!prev) {
+		struct device_node *node;
+
+		node = of_get_child_by_name(parent, "ports");
+		if (node)
+			parent = node;
+
+		port = of_get_child_by_name(parent, "port");
+		of_node_put(node);
+
+		if (!port) {
+			pr_err("%s(): no port node found in %s\n",
+			       __func__, parent->full_name);
+			return NULL;
+		}
+	} else {
+		port = of_get_parent(prev);
+		if (WARN_ONCE(!port, "%s(): endpoint %s has no parent node\n",
+			      __func__, prev->full_name))
+			return NULL;
+
+		/*
+		 * Avoid dropping prev node refcount to 0 when getting the next
+		 * child below.
+		 */
+		of_node_get(prev);
+	}
+
+	while (1) {
+		/*
+		 * Now that we have a port node, get the next endpoint by
+		 * getting the next child. If the previous endpoint is NULL this
+		 * will return the first child.
+		 */
+		endpoint = of_get_next_child(port, prev);
+		if (endpoint) {
+			of_node_put(port);
+			return endpoint;
+		}
+
+		/* No more endpoints under this port, try the next one. */
+		prev = NULL;
+
+		do {
+			port = of_get_next_child(parent, port);
+			if (!port)
+				return NULL;
+		} while (of_node_cmp(port->name, "port"));
+	}
+}
+EXPORT_SYMBOL(of_graph_get_next_endpoint);
+
+/**
+ * of_graph_get_remote_port_parent() - get remote port's parent node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote device node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port_parent(
+			       const struct device_node *node)
+{
+	struct device_node *np;
+	unsigned int depth;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+
+	/* Walk 3 levels up only if there is 'ports' node. */
+	for (depth = 3; depth && np; depth--) {
+		np = of_get_next_parent(np);
+		if (depth == 2 && of_node_cmp(np->name, "ports"))
+			break;
+	}
+	return np;
+}
+EXPORT_SYMBOL(of_graph_get_remote_port_parent);
+
+/**
+ * of_graph_get_remote_port() - get remote port node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote port node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port(const struct device_node *node)
+{
+	struct device_node *np;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+	if (!np)
+		return NULL;
+	return of_get_next_parent(np);
+}
+EXPORT_SYMBOL(of_graph_get_remote_port);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index 0eb5c38b4e07..f5e8dc7a725c 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -126,8 +126,9 @@ static void __init of_selftest_parse_phandle_with_args(void)
 	selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
 }
 
-static void __init of_selftest_property_match_string(void)
+static void __init of_selftest_property_string(void)
 {
+	const char *strings[4];
 	struct device_node *np;
 	int rc;
 
@@ -145,13 +146,66 @@ static void __init of_selftest_property_match_string(void)
 	rc = of_property_match_string(np, "phandle-list-names", "third");
 	selftest(rc == 2, "third expected:0 got:%i\n", rc);
 	rc = of_property_match_string(np, "phandle-list-names", "fourth");
-	selftest(rc == -ENODATA, "unmatched string; rc=%i", rc);
+	selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc);
 	rc = of_property_match_string(np, "missing-property", "blah");
-	selftest(rc == -EINVAL, "missing property; rc=%i", rc);
+	selftest(rc == -EINVAL, "missing property; rc=%i\n", rc);
 	rc = of_property_match_string(np, "empty-property", "blah");
-	selftest(rc == -ENODATA, "empty property; rc=%i", rc);
+	selftest(rc == -ENODATA, "empty property; rc=%i\n", rc);
 	rc = of_property_match_string(np, "unterminated-string", "blah");
-	selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc);
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+
+	/* of_property_count_strings() tests */
+	rc = of_property_count_strings(np, "string-property");
+	selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "phandle-list-names");
+	selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "unterminated-string");
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "unterminated-string-list");
+	selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+
+	/* of_property_read_string_index() tests */
+	rc = of_property_read_string_index(np, "string-property", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "string-property", 1, strings);
+	selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 1, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 2, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "phandle-list-names", 3, strings);
+	selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "unterminated-string", 0, strings);
+	selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */
+	selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[1] = NULL;
+
+	/* of_property_read_string_array() tests */
+	rc = of_property_read_string_array(np, "string-property", strings, 4);
+	selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_read_string_array(np, "phandle-list-names", strings, 4);
+	selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_read_string_array(np, "unterminated-string", strings, 4);
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+	/* -- An incorrectly formed string should cause a failure */
+	rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4);
+	selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+	/* -- parsing the correctly formed strings should still work: */
+	strings[2] = NULL;
+	rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2);
+	selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc);
+	strings[1] = NULL;
+	rc = of_property_read_string_array(np, "phandle-list-names", strings, 1);
+	selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]);
 }
 
 static int __init of_selftest(void)
@@ -167,7 +221,7 @@ static int __init of_selftest(void)
 
 	pr_info("start of selftest - you will see error messages\n");
 	of_selftest_parse_phandle_with_args();
-	of_selftest_property_match_string();
+	of_selftest_property_string();
 	pr_info("end of selftest - %s\n", selftest_passed ? "PASS" : "FAIL");
 	return 0;
 }
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 903e1285fda0..b0a0d5389f41 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2596,8 +2596,6 @@ enum parport_pc_pci_cards {
 	syba_2p_epp,
 	syba_1p_ecp,
 	titan_010l,
-	titan_1284p1,
-	titan_1284p2,
 	avlab_1p,
 	avlab_2p,
 	oxsemi_952,
@@ -2656,8 +2654,6 @@ static struct parport_pc_pci {
 	/* syba_2p_epp AP138B */	{ 2, { { 0, 0x078 }, { 0, 0x178 }, } },
 	/* syba_1p_ecp W83787 */	{ 1, { { 0, 0x078 }, } },
 	/* titan_010l */		{ 1, { { 3, -1 }, } },
-	/* titan_1284p1 */              { 1, { { 0, 1 }, } },
-	/* titan_1284p2 */		{ 2, { { 0, 1 }, { 2, 3 }, } },
 	/* avlab_1p		*/	{ 1, { { 0, 1}, } },
 	/* avlab_2p		*/	{ 2, { { 0, 1}, { 2, 3 },} },
 	/* The Oxford Semi cards are unusual: 954 doesn't support ECP,
@@ -2673,8 +2669,8 @@ static struct parport_pc_pci {
 	/* netmos_9705 */               { 1, { { 0, -1 }, } },
 	/* netmos_9715 */               { 2, { { 0, 1 }, { 2, 3 },} },
 	/* netmos_9755 */               { 2, { { 0, 1 }, { 2, 3 },} },
-	/* netmos_9805 */               { 1, { { 0, -1 }, } },
-	/* netmos_9815 */               { 2, { { 0, -1 }, { 2, -1 }, } },
+	/* netmos_9805 */		{ 1, { { 0, 1 }, } },
+	/* netmos_9815 */		{ 2, { { 0, 1 }, { 2, 3 }, } },
 	/* netmos_9901 */               { 1, { { 0, -1 }, } },
 	/* netmos_9865 */               { 1, { { 0, -1 }, } },
 	/* quatech_sppxp100 */		{ 1, { { 0, 1 }, } },
@@ -2718,8 +2714,6 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, syba_1p_ecp },
 	{ PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_010L,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, titan_010l },
-	{ 0x9710, 0x9805, 0x1000, 0x0010, 0, 0, titan_1284p1 },
-	{ 0x9710, 0x9815, 0x1000, 0x0020, 0, 0, titan_1284p2 },
 	/* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
 	/* AFAVLAB_TK9902 */
 	{ 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p},
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 1cc23661f79b..061da8c3ab4b 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -484,28 +484,29 @@ static inline bool pcie_cap_has_lnkctl(const struct pci_dev *dev)
 {
 	int type = pci_pcie_type(dev);
 
-	return pcie_cap_version(dev) > 1 ||
+	return type == PCI_EXP_TYPE_ENDPOINT ||
+	       type == PCI_EXP_TYPE_LEG_END ||
 	       type == PCI_EXP_TYPE_ROOT_PORT ||
-	       type == PCI_EXP_TYPE_ENDPOINT ||
-	       type == PCI_EXP_TYPE_LEG_END;
+	       type == PCI_EXP_TYPE_UPSTREAM ||
+	       type == PCI_EXP_TYPE_DOWNSTREAM ||
+	       type == PCI_EXP_TYPE_PCI_BRIDGE ||
+	       type == PCI_EXP_TYPE_PCIE_BRIDGE;
 }
 
 static inline bool pcie_cap_has_sltctl(const struct pci_dev *dev)
 {
 	int type = pci_pcie_type(dev);
 
-	return pcie_cap_version(dev) > 1 ||
-	       type == PCI_EXP_TYPE_ROOT_PORT ||
-	       (type == PCI_EXP_TYPE_DOWNSTREAM &&
-		pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT);
+	return (type == PCI_EXP_TYPE_ROOT_PORT ||
+		type == PCI_EXP_TYPE_DOWNSTREAM) &&
+	       pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT;
 }
 
 static inline bool pcie_cap_has_rtctl(const struct pci_dev *dev)
 {
 	int type = pci_pcie_type(dev);
 
-	return pcie_cap_version(dev) > 1 ||
-	       type == PCI_EXP_TYPE_ROOT_PORT ||
+	return type == PCI_EXP_TYPE_ROOT_PORT ||
 	       type == PCI_EXP_TYPE_RC_EC;
 }
 
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 58499277903a..6efc2ec5e4db 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -282,8 +282,8 @@ static int board_added(struct slot *p_slot)
 		return WRONG_BUS_FREQUENCY;
 	}
 
-	bsp = ctrl->pci_dev->bus->cur_bus_speed;
-	msp = ctrl->pci_dev->bus->max_bus_speed;
+	bsp = ctrl->pci_dev->subordinate->cur_bus_speed;
+	msp = ctrl->pci_dev->subordinate->max_bus_speed;
 
 	/* Check if there are other slots or devices on the same bus */
 	if (!list_empty(&ctrl->pci_dev->subordinate->devices))
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 2c1075213bec..402063ff889e 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -530,6 +530,20 @@ out_unroll:
 	return ret;
 }
 
+static int msi_verify_entries(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		if (!dev->no_64bit_msi || !entry->msg.address_hi)
+			continue;
+		dev_err(&dev->dev, "Device has broken 64-bit MSI but arch"
+			" tried to assign one above 4G\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
@@ -583,6 +597,13 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 		return ret;
 	}
 
+	ret = msi_verify_entries(dev);
+	if (ret) {
+		msi_mask_irq(entry, mask, ~mask);
+		free_msi_irqs(dev);
+		return ret;
+	}
+
 	ret = populate_msi_sysfs(dev);
 	if (ret) {
 		msi_mask_irq(entry, mask, ~mask);
@@ -698,6 +719,11 @@ static int msix_capability_init(struct pci_dev *dev,
 	if (ret)
 		goto error;
 
+	/* Check if all MSI entries honor device restrictions */
+	ret = msi_verify_entries(dev);
+	if (ret)
+		goto error;
+
 	/*
 	 * Some devices require MSI-X to be enabled before we can touch the
 	 * MSI-X registers.  We need to mask all the vectors to prevent
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 336b3f94a19a..0eab3a3c51c5 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -47,6 +47,9 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
 	if (event != ACPI_NOTIFY_DEVICE_WAKE || !pci_dev)
 		return;
 
+	if (pci_dev->pme_poll)
+		pci_dev->pme_poll = false;
+
 	if (pci_dev->current_state == PCI_D3cold) {
 		pci_wakeup_event(pci_dev);
 		pm_runtime_resume(&pci_dev->dev);
@@ -57,9 +60,6 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
 	if (pci_dev->pme_support)
 		pci_check_pme_status(pci_dev);
 
-	if (pci_dev->pme_poll)
-		pci_dev->pme_poll = false;
-
 	pci_wakeup_event(pci_dev);
 	pm_runtime_resume(&pci_dev->dev);
 
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 79277fb36c6b..66aabde82727 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/pm_runtime.h>
 #include <linux/suspend.h>
+#include <linux/kexec.h>
 #include "pci.h"
 
 struct pci_dynid {
@@ -388,12 +389,17 @@ static void pci_device_shutdown(struct device *dev)
 	pci_msi_shutdown(pci_dev);
 	pci_msix_shutdown(pci_dev);
 
+#ifdef CONFIG_KEXEC
 	/*
-	 * Turn off Bus Master bit on the device to tell it to not
-	 * continue to do DMA. Don't touch devices in D3cold or unknown states.
+	 * If this is a kexec reboot, turn off Bus Master bit on the
+	 * device to tell it to not continue to do DMA. Don't touch
+	 * devices in D3cold or unknown states.
+	 * If it is not a kexec reboot, firmware will hit the PCI
+	 * devices with big hammer and stop their DMA any way.
 	 */
-	if (pci_dev->current_state <= PCI_D3hot)
+	if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot))
 		pci_clear_master(pci_dev);
+#endif
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5b4a9d9cd200..689f3c87ee5c 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -175,7 +175,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
-	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n",
 		       pci_dev->vendor, pci_dev->device,
 		       pci_dev->subsystem_vendor, pci_dev->subsystem_device,
 		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a899d8bb190d..d6ceb2e45c59 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1119,6 +1119,8 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state);
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
+	u16 cmd;
+	u8 pin;
 
 	err = pci_set_power_state(dev, PCI_D0);
 	if (err < 0 && err != -EIO)
@@ -1128,6 +1130,17 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars)
 		return err;
 	pci_fixup_device(pci_fixup_enable, dev);
 
+	if (dev->msi_enabled || dev->msix_enabled)
+		return 0;
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	if (pin) {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & PCI_COMMAND_INTX_DISABLE)
+			pci_write_config_word(dev, PCI_COMMAND,
+					      cmd & ~PCI_COMMAND_INTX_DISABLE);
+	}
+
 	return 0;
 }
 
@@ -3646,7 +3659,7 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
 	u16 cmd;
 	int rc;
 
-	WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) & (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
+	WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) && (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
 
 	/* ARCH specific VGA enables */
 	rc = pci_set_vga_state_arch(dev, decode, command_bits, flags);
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 696caed5fdf5..ce8acc71f1a8 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -223,7 +223,6 @@ static int pcie_portdrv_probe(struct pci_dev *dev,
 static void pcie_portdrv_remove(struct pci_dev *dev)
 {
 	pcie_port_device_remove(dev);
-	pci_disable_device(dev);
 }
 
 static int error_detected_iter(struct device *device, void *data)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ea37072e8bf2..034a4d2964d6 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -210,14 +210,17 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_SIZEALIGN;
 		if (res->flags & IORESOURCE_IO) {
 			l &= PCI_BASE_ADDRESS_IO_MASK;
+			sz &= PCI_BASE_ADDRESS_IO_MASK;
 			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
 		} else {
 			l &= PCI_BASE_ADDRESS_MEM_MASK;
+			sz &= PCI_BASE_ADDRESS_MEM_MASK;
 			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
 		res->flags |= (l & IORESOURCE_ROM_ENABLE);
 		l &= PCI_ROM_ADDRESS_MASK;
+		sz &= PCI_ROM_ADDRESS_MASK;
 		mask = (u32)PCI_ROM_ADDRESS_MASK;
 	}
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index df4655c5c138..910339c0791f 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -28,6 +28,7 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -291,6 +292,25 @@ static void quirk_citrine(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
 
+/*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
+static void quirk_extend_bar_to_page(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
+			r->end = PAGE_SIZE - 1;
+			r->start = 0;
+			r->flags |= IORESOURCE_UNSET;
+			dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n",
+				 i, r);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page);
+
 /*
  *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
  *  If it's needed, re-allocate the region.
@@ -2930,6 +2950,7 @@ static void disable_igfx_irq(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
 
 /*
  * Some devices may pass our check in pci_intx_mask_supported if
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 9bdaeb8785ce..b32d6c798743 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -2,7 +2,7 @@
 
 ccflags-$(CONFIG_DEBUG_PINCTRL)	+= -DDEBUG
 
-obj-$(CONFIG_PINCTRL)		+= core.o
+obj-$(CONFIG_PINCTRL)		+= core.o pinctrl-utils.o
 obj-$(CONFIG_PINMUX)		+= pinmux.o
 obj-$(CONFIG_PINCONF)		+= pinconf.o
 ifeq ($(CONFIG_OF),y)
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 5327f35d9b5c..bb7ee9cb00b1 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -807,7 +807,9 @@ static struct pinctrl *create_pinctrl(struct device *dev)
 	kref_init(&p->users);
 
 	/* Add the pinctrl handle to the global list */
+	mutex_lock(&pinctrl_list_mutex);
 	list_add_tail(&p->node, &pinctrl_list);
+	mutex_unlock(&pinctrl_list_mutex);
 
 	return p;
 }
diff --git a/drivers/pinctrl/mvebu/pinctrl-dove.c b/drivers/pinctrl/mvebu/pinctrl-dove.c
index 428ea96a94d3..e29e6d831aeb 100644
--- a/drivers/pinctrl/mvebu/pinctrl-dove.c
+++ b/drivers/pinctrl/mvebu/pinctrl-dove.c
@@ -323,7 +323,7 @@ static int dove_twsi_ctrl_set(struct mvebu_mpp_ctrl *ctrl,
 	unsigned long gcfg2 = readl(DOVE_GLOBAL_CONFIG_2);
 
 	gcfg1 &= ~DOVE_TWSI_ENABLE_OPTION1;
-	gcfg2 &= ~(DOVE_TWSI_ENABLE_OPTION2 | DOVE_TWSI_ENABLE_OPTION2);
+	gcfg2 &= ~(DOVE_TWSI_ENABLE_OPTION2 | DOVE_TWSI_ENABLE_OPTION3);
 
 	switch (config) {
 	case 1:
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 2ad5a8d337b5..872e74a23788 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -21,8 +21,10 @@
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinconf.h>
 #include <linux/pinctrl/pinconf-generic.h>
+#include <linux/of.h>
 #include "core.h"
 #include "pinconf.h"
+#include "pinctrl-utils.h"
 
 #ifdef CONFIG_DEBUG_FS
 
@@ -37,14 +39,19 @@ struct pin_config_item {
 static struct pin_config_item conf_items[] = {
 	PCONFDUMP(PIN_CONFIG_BIAS_DISABLE, "input bias disabled", NULL),
 	PCONFDUMP(PIN_CONFIG_BIAS_HIGH_IMPEDANCE, "input bias high impedance", NULL),
+	PCONFDUMP(PIN_CONFIG_BIAS_BUS_HOLD, "input bias bus hold", NULL),
 	PCONFDUMP(PIN_CONFIG_BIAS_PULL_UP, "input bias pull up", NULL),
 	PCONFDUMP(PIN_CONFIG_BIAS_PULL_DOWN, "input bias pull down", NULL),
+	PCONFDUMP(PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
+				"input bias pull to pin specific state", NULL),
 	PCONFDUMP(PIN_CONFIG_DRIVE_PUSH_PULL, "output drive push pull", NULL),
 	PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_DRAIN, "output drive open drain", NULL),
 	PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_SOURCE, "output drive open source", NULL),
+	PCONFDUMP(PIN_CONFIG_DRIVE_STRENGTH, "output drive strength", "mA"),
+	PCONFDUMP(PIN_CONFIG_INPUT_ENABLE, "input enabled", NULL),
 	PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_ENABLE, "input schmitt enabled", NULL),
 	PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT, "input schmitt trigger", NULL),
-	PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "time units"),
+	PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "usec"),
 	PCONFDUMP(PIN_CONFIG_POWER_SOURCE, "pin power source", "selector"),
 	PCONFDUMP(PIN_CONFIG_SLEW_RATE, "slew rate", NULL),
 	PCONFDUMP(PIN_CONFIG_LOW_POWER_MODE, "pin low power", "mode"),
@@ -135,3 +142,198 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 }
 EXPORT_SYMBOL_GPL(pinconf_generic_dump_config);
 #endif
+
+#ifdef CONFIG_OF
+struct pinconf_generic_dt_params {
+	const char * const property;
+	enum pin_config_param param;
+	u32 default_value;
+};
+
+static struct pinconf_generic_dt_params dt_params[] = {
+	{ "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 },
+	{ "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 },
+	{ "bias-bus-hold", PIN_CONFIG_BIAS_BUS_HOLD, 0 },
+	{ "bias-pull-up", PIN_CONFIG_BIAS_PULL_UP, 1 },
+	{ "bias-pull-down", PIN_CONFIG_BIAS_PULL_DOWN, 1 },
+	{ "bias-pull-pin-default", PIN_CONFIG_BIAS_PULL_PIN_DEFAULT, 1 },
+	{ "drive-push-pull", PIN_CONFIG_DRIVE_PUSH_PULL, 0 },
+	{ "drive-open-drain", PIN_CONFIG_DRIVE_OPEN_DRAIN, 0 },
+	{ "drive-open-source", PIN_CONFIG_DRIVE_OPEN_SOURCE, 0 },
+	{ "drive-strength", PIN_CONFIG_DRIVE_STRENGTH, 0 },
+	{ "input-enable", PIN_CONFIG_INPUT_ENABLE, 1 },
+	{ "input-disable", PIN_CONFIG_INPUT_ENABLE, 0 },
+	{ "input-schmitt-enable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 1 },
+	{ "input-schmitt-disable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 0 },
+	{ "input-debounce", PIN_CONFIG_INPUT_DEBOUNCE, 0 },
+	{ "low-power-enable", PIN_CONFIG_LOW_POWER_MODE, 1 },
+	{ "low-power-disable", PIN_CONFIG_LOW_POWER_MODE, 0 },
+	{ "output-low", PIN_CONFIG_OUTPUT, 0, },
+	{ "output-high", PIN_CONFIG_OUTPUT, 1, },
+	{ "slew-rate", PIN_CONFIG_SLEW_RATE, 0},
+};
+
+/**
+ * pinconf_generic_parse_dt_config()
+ * parse the config properties into generic pinconfig values.
+ * @np: node containing the pinconfig properties
+ * @configs: array with nconfigs entries containing the generic pinconf values
+ * @nconfigs: umber of configurations
+ */
+int pinconf_generic_parse_dt_config(struct device_node *np,
+				    unsigned long **configs,
+				    unsigned int *nconfigs)
+{
+	unsigned long *cfg;
+	unsigned int ncfg = 0;
+	int ret;
+	int i;
+	u32 val;
+
+	if (!np)
+		return -EINVAL;
+
+	/* allocate a temporary array big enough to hold one of each option */
+	cfg = kzalloc(sizeof(*cfg) * ARRAY_SIZE(dt_params), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
+		struct pinconf_generic_dt_params *par = &dt_params[i];
+		ret = of_property_read_u32(np, par->property, &val);
+
+		/* property not found */
+		if (ret == -EINVAL)
+			continue;
+
+		/* use default value, when no value is specified */
+		if (ret)
+			val = par->default_value;
+
+		pr_debug("found %s with value %u\n", par->property, val);
+		cfg[ncfg] = pinconf_to_config_packed(par->param, val);
+		ncfg++;
+	}
+
+	ret = 0;
+
+	/* no configs found at all */
+	if (ncfg == 0) {
+		*configs = NULL;
+		*nconfigs = 0;
+		goto out;
+	}
+
+	/*
+	 * Now limit the number of configs to the real number of
+	 * found properties.
+	 */
+	*configs = kzalloc(ncfg * sizeof(unsigned long), GFP_KERNEL);
+	if (!*configs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memcpy(*configs, cfg, ncfg * sizeof(unsigned long));
+	*nconfigs = ncfg;
+
+out:
+	kfree(cfg);
+	return ret;
+}
+
+int pinconf_generic_dt_subnode_to_map_new(struct pinctrl_dev *pctldev,
+		struct device_node *np, struct pinctrl_map **map,
+		unsigned *reserved_maps, unsigned *num_maps,
+		enum pinctrl_map_type type)
+{
+	int ret;
+	const char *function;
+	struct device *dev = pctldev->dev;
+	unsigned long *configs = NULL;
+	unsigned num_configs = 0;
+	unsigned reserve;
+	struct property *prop;
+	const char *group;
+
+	ret = of_property_read_string(np, "function", &function);
+	if (ret < 0) {
+		/* EINVAL=missing, which is fine since it's optional */
+		if (ret != -EINVAL)
+			dev_err(dev, "could not parse property function\n");
+		function = NULL;
+	}
+
+	ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+	if (ret < 0) {
+		dev_err(dev, "could not parse node property\n");
+		return ret;
+	}
+
+	reserve = 0;
+	if (function != NULL)
+		reserve++;
+	if (num_configs)
+		reserve++;
+	ret = of_property_count_strings(np, "pins");
+	if (ret < 0) {
+		dev_err(dev, "could not parse property pins\n");
+		goto exit;
+	}
+	reserve *= ret;
+
+	ret = pinctrl_utils_reserve_map(pctldev, map, reserved_maps,
+			num_maps, reserve);
+	if (ret < 0)
+		goto exit;
+
+	of_property_for_each_string(np, "pins", prop, group) {
+		if (function) {
+			ret = pinctrl_utils_add_map_mux(pctldev, map,
+					reserved_maps, num_maps, group,
+					function);
+			if (ret < 0)
+				goto exit;
+		}
+
+		if (num_configs) {
+			ret = pinctrl_utils_add_map_configs(pctldev, map,
+					reserved_maps, num_maps, group, configs,
+					num_configs, type);
+			if (ret < 0)
+				goto exit;
+		}
+	}
+	ret = 0;
+
+exit:
+	kfree(configs);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pinconf_generic_dt_subnode_to_map_new);
+
+int pinconf_generic_dt_node_to_map_new(struct pinctrl_dev *pctldev,
+		struct device_node *np_config, struct pinctrl_map **map,
+		unsigned *num_maps, enum pinctrl_map_type type)
+{
+	unsigned reserved_maps;
+	struct device_node *np;
+	int ret;
+
+	reserved_maps = 0;
+	*map = NULL;
+	*num_maps = 0;
+
+	for_each_child_of_node(np_config, np) {
+		ret = pinconf_generic_dt_subnode_to_map_new(pctldev, np, map,
+					&reserved_maps, num_maps, type);
+		if (ret < 0) {
+			pinctrl_utils_dt_free_map(pctldev, *map, *num_maps);
+			return ret;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pinconf_generic_dt_node_to_map_new);
+
+#endif
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 694c3ace4520..596a2522a6b1 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -35,7 +35,9 @@ int pinconf_check_ops(struct pinctrl_dev *pctldev)
 		return -EINVAL;
 	}
 	/* We have to be able to config the pins in SOME way */
-	if (!ops->pin_config_set && !ops->pin_config_group_set) {
+	if (!ops->pin_config_set && !ops->pin_config_group_set
+		&& !ops->pin_config_set_bulk
+		&& !ops->pin_config_group_set_bulk) {
 		dev_err(pctldev->dev,
 			"pinconf has to be able to set a pins config\n");
 		return -EINVAL;
@@ -75,98 +77,6 @@ int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
 	return ops->pin_config_get(pctldev, pin, config);
 }
 
-/**
- * pin_config_get() - get the configuration of a single pin parameter
- * @dev_name: name of the pin controller device for this pin
- * @name: name of the pin to get the config for
- * @config: the config pointed to by this argument will be filled in with the
- *	current pin state, it can be used directly by drivers as a numeral, or
- *	it can be dereferenced to any struct.
- */
-int pin_config_get(const char *dev_name, const char *name,
-			  unsigned long *config)
-{
-	struct pinctrl_dev *pctldev;
-	int pin;
-
-	pctldev = get_pinctrl_dev_from_devname(dev_name);
-	if (!pctldev) {
-		pin = -EINVAL;
-		return pin;
-	}
-
-	mutex_lock(&pctldev->mutex);
-
-	pin = pin_get_from_name(pctldev, name);
-	if (pin < 0)
-		goto unlock;
-
-	pin = pin_config_get_for_pin(pctldev, pin, config);
-
-unlock:
-	mutex_unlock(&pctldev->mutex);
-	return pin;
-}
-EXPORT_SYMBOL(pin_config_get);
-
-static int pin_config_set_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
-			   unsigned long config)
-{
-	const struct pinconf_ops *ops = pctldev->desc->confops;
-	int ret;
-
-	if (!ops || !ops->pin_config_set) {
-		dev_err(pctldev->dev, "cannot configure pin, missing "
-			"config function in driver\n");
-		return -EINVAL;
-	}
-
-	ret = ops->pin_config_set(pctldev, pin, config);
-	if (ret) {
-		dev_err(pctldev->dev,
-			"unable to set pin configuration on pin %d\n", pin);
-		return ret;
-	}
-
-	return 0;
-}
-
-/**
- * pin_config_set() - set the configuration of a single pin parameter
- * @dev_name: name of pin controller device for this pin
- * @name: name of the pin to set the config for
- * @config: the config in this argument will contain the desired pin state, it
- *	can be used directly by drivers as a numeral, or it can be dereferenced
- *	to any struct.
- */
-int pin_config_set(const char *dev_name, const char *name,
-		   unsigned long config)
-{
-	struct pinctrl_dev *pctldev;
-	int pin, ret;
-
-	pctldev = get_pinctrl_dev_from_devname(dev_name);
-	if (!pctldev) {
-		ret = -EINVAL;
-		return ret;
-	}
-
-	mutex_lock(&pctldev->mutex);
-
-	pin = pin_get_from_name(pctldev, name);
-	if (pin < 0) {
-		ret = pin;
-		goto unlock;
-	}
-
-	ret = pin_config_set_for_pin(pctldev, pin, config);
-
-unlock:
-	mutex_unlock(&pctldev->mutex);
-	return ret;
-}
-EXPORT_SYMBOL(pin_config_set);
-
 int pin_config_group_get(const char *dev_name, const char *pin_group,
 			 unsigned long *config)
 {
@@ -204,88 +114,6 @@ unlock:
 	mutex_unlock(&pctldev->mutex);
 	return ret;
 }
-EXPORT_SYMBOL(pin_config_group_get);
-
-int pin_config_group_set(const char *dev_name, const char *pin_group,
-			 unsigned long config)
-{
-	struct pinctrl_dev *pctldev;
-	const struct pinconf_ops *ops;
-	const struct pinctrl_ops *pctlops;
-	int selector;
-	const unsigned *pins;
-	unsigned num_pins;
-	int ret;
-	int i;
-
-	pctldev = get_pinctrl_dev_from_devname(dev_name);
-	if (!pctldev) {
-		ret = -EINVAL;
-		return ret;
-	}
-
-	mutex_lock(&pctldev->mutex);
-
-	ops = pctldev->desc->confops;
-	pctlops = pctldev->desc->pctlops;
-
-	if (!ops || (!ops->pin_config_group_set && !ops->pin_config_set)) {
-		dev_err(pctldev->dev, "cannot configure pin group, missing "
-			"config function in driver\n");
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	selector = pinctrl_get_group_selector(pctldev, pin_group);
-	if (selector < 0) {
-		ret = selector;
-		goto unlock;
-	}
-
-	ret = pctlops->get_group_pins(pctldev, selector, &pins, &num_pins);
-	if (ret) {
-		dev_err(pctldev->dev, "cannot configure pin group, error "
-			"getting pins\n");
-		goto unlock;
-	}
-
-	/*
-	 * If the pin controller supports handling entire groups we use that
-	 * capability.
-	 */
-	if (ops->pin_config_group_set) {
-		ret = ops->pin_config_group_set(pctldev, selector, config);
-		/*
-		 * If the pin controller prefer that a certain group be handled
-		 * pin-by-pin as well, it returns -EAGAIN.
-		 */
-		if (ret != -EAGAIN)
-			goto unlock;
-	}
-
-	/*
-	 * If the controller cannot handle entire groups, we configure each pin
-	 * individually.
-	 */
-	if (!ops->pin_config_set) {
-		ret = 0;
-		goto unlock;
-	}
-
-	for (i = 0; i < num_pins; i++) {
-		ret = ops->pin_config_set(pctldev, pins[i], config);
-		if (ret < 0)
-			goto unlock;
-	}
-
-	ret = 0;
-
-unlock:
-	mutex_unlock(&pctldev->mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL(pin_config_group_set);
 
 int pinconf_map_to_setting(struct pinctrl_map const *map,
 			  struct pinctrl_setting *setting)
@@ -332,7 +160,7 @@ int pinconf_apply_setting(struct pinctrl_setting const *setting)
 {
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinconf_ops *ops = pctldev->desc->confops;
-	int i, ret;
+	int ret, i;
 
 	if (!ops) {
 		dev_err(pctldev->dev, "missing confops\n");
@@ -341,39 +169,66 @@ int pinconf_apply_setting(struct pinctrl_setting const *setting)
 
 	switch (setting->type) {
 	case PIN_MAP_TYPE_CONFIGS_PIN:
-		if (!ops->pin_config_set) {
+		if (!ops->pin_config_set && !ops->pin_config_set_bulk) {
 			dev_err(pctldev->dev, "missing pin_config_set op\n");
 			return -EINVAL;
 		}
-		for (i = 0; i < setting->data.configs.num_configs; i++) {
-			ret = ops->pin_config_set(pctldev,
+		if (ops->pin_config_set_bulk) {
+			ret = ops->pin_config_set_bulk(pctldev,
 					setting->data.configs.group_or_pin,
-					setting->data.configs.configs[i]);
+					setting->data.configs.configs,
+					setting->data.configs.num_configs);
 			if (ret < 0) {
 				dev_err(pctldev->dev,
-					"pin_config_set op failed for pin %d config %08lx\n",
-					setting->data.configs.group_or_pin,
-					setting->data.configs.configs[i]);
+					"pin_config_set_bulk op failed for pin %d\n",
+					setting->data.configs.group_or_pin);
 				return ret;
 			}
+		} else if (ops->pin_config_set) {
+			for (i = 0; i < setting->data.configs.num_configs; i++) {
+				ret = ops->pin_config_set(pctldev,
+							  setting->data.configs.group_or_pin,
+							  setting->data.configs.configs[i]);
+				if (ret < 0) {
+					dev_err(pctldev->dev,
+						"pin_config_set op failed for pin %d config %08lx\n",
+						setting->data.configs.group_or_pin,
+						setting->data.configs.configs[i]);
+					return ret;
+				}
+			}
 		}
 		break;
 	case PIN_MAP_TYPE_CONFIGS_GROUP:
-		if (!ops->pin_config_group_set) {
+		if (!ops->pin_config_group_set &&
+		    !ops->pin_config_group_set_bulk) {
 			dev_err(pctldev->dev,
 				"missing pin_config_group_set op\n");
 			return -EINVAL;
 		}
-		for (i = 0; i < setting->data.configs.num_configs; i++) {
-			ret = ops->pin_config_group_set(pctldev,
+		if (ops->pin_config_group_set_bulk) {
+			ret = ops->pin_config_group_set_bulk(pctldev,
 					setting->data.configs.group_or_pin,
-					setting->data.configs.configs[i]);
+					setting->data.configs.configs,
+					setting->data.configs.num_configs);
 			if (ret < 0) {
 				dev_err(pctldev->dev,
-					"pin_config_group_set op failed for group %d config %08lx\n",
+					"pin_config_group_set_bulk op failed for group %d\n",
+					setting->data.configs.group_or_pin);
+				return ret;
+			}
+		} else if (ops->pin_config_group_set) {
+			for (i = 0; i < setting->data.configs.num_configs; i++) {
+				ret = ops->pin_config_group_set(pctldev,
 					setting->data.configs.group_or_pin,
 					setting->data.configs.configs[i]);
-				return ret;
+				if (ret < 0) {
+					dev_err(pctldev->dev,
+						"pin_config_group_set op failed for group %d config %08lx\n",
+						setting->data.configs.group_or_pin,
+						setting->data.configs.configs[i]);
+					return ret;
+				}
 			}
 		}
 		break;
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index 92c7267244d2..a4a5417e1413 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -123,3 +123,9 @@ static inline void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 	return;
 }
 #endif
+
+#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
+int pinconf_generic_parse_dt_config(struct device_node *np,
+				    unsigned long **configs,
+				    unsigned int *nconfigs);
+#endif
diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c
index b7d8c890514c..876d7cc4d8a7 100644
--- a/drivers/pinctrl/pinctrl-sunxi.c
+++ b/drivers/pinctrl/pinctrl-sunxi.c
@@ -1754,12 +1754,6 @@ static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset)
 	return val;
 }
 
-static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip,
-					unsigned offset, int value)
-{
-	return pinctrl_gpio_direction_output(chip->base + offset);
-}
-
 static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
 				unsigned offset, int value)
 {
@@ -1770,6 +1764,13 @@ static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
 	writel((value & DATA_PINS_MASK) << index, pctl->membase + reg);
 }
 
+static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip,
+					unsigned offset, int value)
+{
+	sunxi_pinctrl_gpio_set(chip, offset, value);
+	return pinctrl_gpio_direction_output(chip->base + offset);
+}
+
 static int sunxi_pinctrl_gpio_of_xlate(struct gpio_chip *gc,
 				const struct of_phandle_args *gpiospec,
 				u32 *flags)
diff --git a/drivers/pinctrl/pinctrl-utils.c b/drivers/pinctrl/pinctrl-utils.c
new file mode 100644
index 000000000000..48277e025f84
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-utils.c
@@ -0,0 +1,141 @@
+/*
+ * Utils functions to implement the pincontrol driver.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include "core.h"
+#include "pinctrl-utils.h"
+
+int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, unsigned reserve)
+{
+	unsigned old_num = *reserved_maps;
+	unsigned new_num = *num_maps + reserve;
+	struct pinctrl_map *new_map;
+
+	if (old_num >= new_num)
+		return 0;
+
+	new_map = krealloc(*map, sizeof(*new_map) * new_num, GFP_KERNEL);
+	if (!new_map) {
+		dev_err(pctldev->dev, "krealloc(map) failed\n");
+		return -ENOMEM;
+	}
+
+	memset(new_map + old_num, 0, (new_num - old_num) * sizeof(*new_map));
+
+	*map = new_map;
+	*reserved_maps = new_num;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_reserve_map);
+
+int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, const char *group,
+		const char *function)
+{
+	if (WARN_ON(*num_maps == *reserved_maps))
+		return -ENOSPC;
+
+	(*map)[*num_maps].type = PIN_MAP_TYPE_MUX_GROUP;
+	(*map)[*num_maps].data.mux.group = group;
+	(*map)[*num_maps].data.mux.function = function;
+	(*num_maps)++;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_mux);
+
+int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, const char *group,
+		unsigned long *configs, unsigned num_configs,
+		enum pinctrl_map_type type)
+{
+	unsigned long *dup_configs;
+
+	if (WARN_ON(*num_maps == *reserved_maps))
+		return -ENOSPC;
+
+	dup_configs = kmemdup(configs, num_configs * sizeof(*dup_configs),
+			      GFP_KERNEL);
+	if (!dup_configs) {
+		dev_err(pctldev->dev, "kmemdup(configs) failed\n");
+		return -ENOMEM;
+	}
+
+	(*map)[*num_maps].type = type;
+	(*map)[*num_maps].data.configs.group_or_pin = group;
+	(*map)[*num_maps].data.configs.configs = dup_configs;
+	(*map)[*num_maps].data.configs.num_configs = num_configs;
+	(*num_maps)++;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_configs);
+
+int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
+		unsigned long **configs, unsigned *num_configs,
+		unsigned long config)
+{
+	unsigned old_num = *num_configs;
+	unsigned new_num = old_num + 1;
+	unsigned long *new_configs;
+
+	new_configs = krealloc(*configs, sizeof(*new_configs) * new_num,
+			       GFP_KERNEL);
+	if (!new_configs) {
+		dev_err(pctldev->dev, "krealloc(configs) failed\n");
+		return -ENOMEM;
+	}
+
+	new_configs[old_num] = config;
+
+	*configs = new_configs;
+	*num_configs = new_num;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_config);
+
+void pinctrl_utils_dt_free_map(struct pinctrl_dev *pctldev,
+	      struct pinctrl_map *map, unsigned num_maps)
+{
+	int i;
+
+	for (i = 0; i < num_maps; i++) {
+		switch (map[i].type) {
+		case PIN_MAP_TYPE_CONFIGS_GROUP:
+		case PIN_MAP_TYPE_CONFIGS_PIN:
+			kfree(map[i].data.configs.configs);
+			break;
+		default:
+			break;
+		}
+	}
+	kfree(map);
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_dt_free_map);
diff --git a/drivers/pinctrl/pinctrl-utils.h b/drivers/pinctrl/pinctrl-utils.h
new file mode 100644
index 000000000000..d0ffe1ce200f
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-utils.h
@@ -0,0 +1,43 @@
+/*
+ * Utils functions to implement the pincontrol driver.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+#ifndef __PINCTRL_UTILS_H__
+#define __PINCTRL_UTILS_H__
+
+int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, unsigned reserve);
+int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, const char *group,
+		const char *function);
+int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps, const char *group,
+		unsigned long *configs, unsigned num_configs,
+		enum pinctrl_map_type type);
+int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
+		unsigned long **configs, unsigned *num_configs,
+		unsigned long config);
+void pinctrl_utils_dt_free_map(struct pinctrl_dev *pctldev,
+		struct pinctrl_map *map, unsigned num_maps);
+
+#endif /* __PINCTRL_UTILS_H__ */
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index 70d986e04afb..8b54b5da00c0 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -276,7 +276,20 @@ static int wmt_pctl_dt_node_to_map_pull(struct wmt_pinctrl_data *data,
 	if (!configs)
 		return -ENOMEM;
 
-	configs[0] = pull;
+	switch (pull) {
+	case 0:
+		configs[0] = PIN_CONFIG_BIAS_DISABLE;
+		break;
+	case 1:
+		configs[0] = PIN_CONFIG_BIAS_PULL_DOWN;
+		break;
+	case 2:
+		configs[0] = PIN_CONFIG_BIAS_PULL_UP;
+		break;
+	default:
+		configs[0] = PIN_CONFIG_BIAS_DISABLE;
+		dev_err(data->dev, "invalid pull state %d - disabling\n", pull);
+	}
 
 	map->type = PIN_MAP_TYPE_CONFIGS_PIN;
 	map->data.configs.group_or_pin = data->groups[group];
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index c9076bdaf2c1..59a8d325a697 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -572,6 +572,17 @@ static const struct dmi_system_id video_vendor_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"),
 		},
 	},
+	{
+		/*
+		 * Note no video_set_backlight_video_vendor, we must use the
+		 * acer interface, as there is no native backlight interface.
+		 */
+		.ident = "Acer KAV80",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index fa9a2171cc13..b264d8fe1908 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context)
 		const struct key_entry *key;
 		int reported_key;
 		u16 *buffer_entry = (u16 *)obj->buffer.pointer;
+		int buffer_size = obj->buffer.length/2;
 
-		if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
+		if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) {
 			pr_info("Received unknown WMI event (0x%x)\n",
 				buffer_entry[1]);
 			kfree(obj);
 			return;
 		}
 
-		if (dell_new_hk_type || buffer_entry[1] == 0x0)
+		if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0))
 			reported_key = (int)buffer_entry[2];
-		else
+		else if (buffer_size >= 2)
 			reported_key = (int)buffer_entry[1] & 0xffff;
+		else {
+			pr_info("Received unknown WMI event\n");
+			kfree(obj);
+			return;
+		}
 
 		key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
 							reported_key);
diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
index a8e43cf70fac..0ed96df20162 100644
--- a/drivers/platform/x86/hp_accel.c
+++ b/drivers/platform/x86/hp_accel.c
@@ -77,6 +77,7 @@ static inline void delayed_sysfs_set(struct led_classdev *led_cdev,
 static struct acpi_device_id lis3lv02d_device_ids[] = {
 	{"HPQ0004", 0}, /* HP Mobile Data Protection System PNP */
 	{"HPQ6000", 0}, /* HP Mobile Data Protection System PNP */
+	{"HPQ6007", 0}, /* HP Mobile Data Protection System PNP */
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, lis3lv02d_device_ids);
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 9847ab163829..a8b7466196ee 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -183,9 +183,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	struct resource r;
 	int i, flags;
 
-	if (acpi_dev_resource_memory(res, &r)
-	    || acpi_dev_resource_io(res, &r)
-	    || acpi_dev_resource_address_space(res, &r)
+	if (acpi_dev_resource_address_space(res, &r)
 	    || acpi_dev_resource_ext_address_space(res, &r)) {
 		pnp_add_resource(dev, &r);
 		return AE_OK;
@@ -217,6 +215,17 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	}
 
 	switch (res->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		if (acpi_dev_resource_memory(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
+	case ACPI_RESOURCE_TYPE_IO:
+	case ACPI_RESOURCE_TYPE_FIXED_IO:
+		if (acpi_dev_resource_io(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
 	case ACPI_RESOURCE_TYPE_DMA:
 		dma = &res->data.dma;
 		if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index c7ff6d67f158..0fbac861080d 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -148,7 +148,7 @@ static void max17040_get_online(struct i2c_client *client)
 {
 	struct max17040_chip *chip = i2c_get_clientdata(client);
 
-	if (chip->pdata->battery_online)
+	if (chip->pdata && chip->pdata->battery_online)
 		chip->online = chip->pdata->battery_online();
 	else
 		chip->online = 1;
@@ -158,7 +158,8 @@ static void max17040_get_status(struct i2c_client *client)
 {
 	struct max17040_chip *chip = i2c_get_clientdata(client);
 
-	if (!chip->pdata->charger_online || !chip->pdata->charger_enable) {
+	if (!chip->pdata || !chip->pdata->charger_online
+			|| !chip->pdata->charger_enable) {
 		chip->status = POWER_SUPPLY_STATUS_UNKNOWN;
 		return;
 	}
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 349e9ae8090a..ee039dcead04 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -32,7 +32,8 @@ config POWER_RESET_RESTART
 	  user presses a key. u-boot then boots into Linux.
 
 config POWER_RESET_VEXPRESS
-	bool
+	bool "ARM Versatile Express power-off and reset driver"
+	depends on ARM || ARM64
 	depends on POWER_RESET
 	help
 	  Power off and reset support for the ARM Ltd. Versatile
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index b4b0d83f9ef6..7061ac0ad428 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -678,6 +678,7 @@ struct tsi721_bdma_chan {
 	struct list_head	free_list;
 	dma_cookie_t		completed_cookie;
 	struct tasklet_struct	tasklet;
+	bool			active;
 };
 
 #endif /* CONFIG_RAPIDIO_DMA_ENGINE */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 502663f5f7c6..47257b6eea84 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -206,8 +206,8 @@ void tsi721_bdma_handler(struct tsi721_bdma_chan *bdma_chan)
 {
 	/* Disable BDMA channel interrupts */
 	iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
-	tasklet_schedule(&bdma_chan->tasklet);
+	if (bdma_chan->active)
+		tasklet_schedule(&bdma_chan->tasklet);
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 			"desc %p not ACKed\n", tx_desc);
 	}
 
+	if (ret == NULL) {
+		dev_dbg(bdma_chan->dchan.device->dev,
+			"%s: unable to obtain tx descriptor\n", __func__);
+		goto err_out;
+	}
+
 	i = bdma_chan->wr_count_next % bdma_chan->bd_num;
 	if (i == bdma_chan->bd_num - 1) {
 		i = 0;
@@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 	tx_desc->txd.phys = bdma_chan->bd_phys +
 				i * sizeof(struct tsi721_dma_desc);
 	tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i];
-
+err_out:
 	spin_unlock_bh(&bdma_chan->lock);
 
 	return ret;
@@ -562,7 +568,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 	}
 #endif /* CONFIG_PCI_MSI */
 
-	tasklet_enable(&bdma_chan->tasklet);
+	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
 	return bdma_chan->bd_num - 1;
@@ -576,9 +582,7 @@ err_out:
 static void tsi721_free_chan_resources(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
 	struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
 	LIST_HEAD(list);
 
 	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +593,25 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan)
 	BUG_ON(!list_empty(&bdma_chan->active_list));
 	BUG_ON(!list_empty(&bdma_chan->queue));
 
-	tasklet_disable(&bdma_chan->tasklet);
+	tsi721_bdma_interrupt_enable(bdma_chan, 0);
+	bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+	if (priv->flags & TSI721_USING_MSIX) {
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+					   bdma_chan->id].vector);
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+					   bdma_chan->id].vector);
+	} else
+#endif
+	synchronize_irq(priv->pdev->irq);
+
+	tasklet_kill(&bdma_chan->tasklet);
 
 	spin_lock_bh(&bdma_chan->lock);
 	list_splice_init(&bdma_chan->free_list, &list);
 	spin_unlock_bh(&bdma_chan->lock);
 
-	tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
 #ifdef CONFIG_PCI_MSI
 	if (priv->flags & TSI721_USING_MSIX) {
 		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +805,7 @@ int tsi721_register_dma(struct tsi721_device *priv)
 		bdma_chan->dchan.cookie = 1;
 		bdma_chan->dchan.chan_id = i;
 		bdma_chan->id = i;
+		bdma_chan->active = false;
 
 		spin_lock_init(&bdma_chan->lock);
 
@@ -799,7 +815,6 @@ int tsi721_register_dma(struct tsi721_device *priv)
 
 		tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
 			     (unsigned long)bdma_chan);
-		tasklet_disable(&bdma_chan->tasklet);
 		list_add_tail(&bdma_chan->dchan.device_node,
 			      &mport->dma.channels);
 	}
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 81d8681c3195..b1b35f38d11d 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -141,8 +141,6 @@ static struct regulator_ops arizona_ldo1_ops = {
 	.map_voltage = regulator_map_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_bypass = regulator_get_bypass_regmap,
-	.set_bypass = regulator_set_bypass_regmap,
 };
 
 static const struct regulator_desc arizona_ldo1 = {
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 815d6df8bd5f..874dd261b248 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -919,6 +919,8 @@ static int machine_constraints_voltage(struct regulator_dev *rdev,
 	return 0;
 }
 
+static int _regulator_do_enable(struct regulator_dev *rdev);
+
 /**
  * set_machine_constraints - sets regulator constraints
  * @rdev: regulator source
@@ -975,10 +977,9 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 	/* If the constraints say the regulator should be on at this point
 	 * and we have control then make sure it is enabled.
 	 */
-	if ((rdev->constraints->always_on || rdev->constraints->boot_on) &&
-	    ops->enable) {
-		ret = ops->enable(rdev);
-		if (ret < 0) {
+	if (rdev->constraints->always_on || rdev->constraints->boot_on) {
+		ret = _regulator_do_enable(rdev);
+		if (ret < 0 && ret != -EINVAL) {
 			rdev_err(rdev, "failed to enable\n");
 			goto out;
 		}
@@ -1711,8 +1712,6 @@ static int _regulator_do_disable(struct regulator_dev *rdev)
 
 	trace_regulator_disable_complete(rdev_get_name(rdev));
 
-	_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
-			     NULL);
 	return 0;
 }
 
@@ -1736,6 +1735,8 @@ static int _regulator_disable(struct regulator_dev *rdev)
 				rdev_err(rdev, "failed to disable\n");
 				return ret;
 			}
+			_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
+					NULL);
 		}
 
 		rdev->use_count = 0;
@@ -1788,20 +1789,16 @@ static int _regulator_force_disable(struct regulator_dev *rdev)
 {
 	int ret = 0;
 
-	/* force disable */
-	if (rdev->desc->ops->disable) {
-		/* ah well, who wants to live forever... */
-		ret = rdev->desc->ops->disable(rdev);
-		if (ret < 0) {
-			rdev_err(rdev, "failed to force disable\n");
-			return ret;
-		}
-		/* notify other consumers that power has been forced off */
-		_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
-			REGULATOR_EVENT_DISABLE, NULL);
+	ret = _regulator_do_disable(rdev);
+	if (ret < 0) {
+		rdev_err(rdev, "failed to force disable\n");
+		return ret;
 	}
 
-	return ret;
+	_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+			REGULATOR_EVENT_DISABLE, NULL);
+
+	return 0;
 }
 
 /**
@@ -1890,8 +1887,9 @@ int regulator_disable_deferred(struct regulator *regulator, int ms)
 	rdev->deferred_disables++;
 	mutex_unlock(&rdev->mutex);
 
-	ret = schedule_delayed_work(&rdev->disable_work,
-				    msecs_to_jiffies(ms));
+	ret = queue_delayed_work(system_power_efficient_wq,
+				 &rdev->disable_work,
+				 msecs_to_jiffies(ms));
 	if (ret < 0)
 		return ret;
 	else
@@ -3787,23 +3785,18 @@ int regulator_suspend_finish(void)
 
 	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(rdev, &regulator_list, list) {
-		struct regulator_ops *ops = rdev->desc->ops;
-
 		mutex_lock(&rdev->mutex);
-		if ((rdev->use_count > 0  || rdev->constraints->always_on) &&
-				ops->enable) {
-			error = ops->enable(rdev);
+		if (rdev->use_count > 0  || rdev->constraints->always_on) {
+			error = _regulator_do_enable(rdev);
 			if (error)
 				ret = error;
 		} else {
 			if (!has_full_constraints)
 				goto unlock;
-			if (!ops->disable)
-				goto unlock;
 			if (!_regulator_is_enabled(rdev))
 				goto unlock;
 
-			error = ops->disable(rdev);
+			error = _regulator_do_disable(rdev);
 			if (error)
 				ret = error;
 		}
@@ -3993,7 +3986,7 @@ static int __init regulator_init_complete(void)
 		ops = rdev->desc->ops;
 		c = rdev->constraints;
 
-		if (!ops->disable || (c && c->always_on))
+		if (c && c->always_on)
 			continue;
 
 		mutex_lock(&rdev->mutex);
@@ -4014,7 +4007,7 @@ static int __init regulator_init_complete(void)
 			/* We log since this may kill the system if it
 			 * goes wrong. */
 			rdev_info(rdev, "disabling\n");
-			ret = ops->disable(rdev);
+			ret = _regulator_do_disable(rdev);
 			if (ret != 0) {
 				rdev_err(rdev, "couldn't disable: %d\n", ret);
 			}
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index f296f3f7db9b..e51cc5fec98a 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -49,6 +49,7 @@ struct at91_rtc_config {
 
 static const struct at91_rtc_config *at91_rtc_config;
 static DECLARE_COMPLETION(at91_rtc_updated);
+static DECLARE_COMPLETION(at91_rtc_upd_rdy);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;
@@ -162,6 +163,8 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
+	wait_for_completion(&at91_rtc_upd_rdy);
+
 	/* Stop Time/Calendar from counting */
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
@@ -184,7 +187,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 
 	/* Restart Time/Calendar */
 	cr = at91_rtc_read(AT91_RTC_CR);
+	at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
 	at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM));
+	at91_rtc_write_ier(AT91_RTC_SECEV);
 
 	return 0;
 }
@@ -221,6 +226,8 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	at91_alarm_year = tm.tm_year;
 
+	tm.tm_mon = alrm->time.tm_mon;
+	tm.tm_mday = alrm->time.tm_mday;
 	tm.tm_hour = alrm->time.tm_hour;
 	tm.tm_min = alrm->time.tm_min;
 	tm.tm_sec = alrm->time.tm_sec;
@@ -289,8 +296,10 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
-		if (rtsr & AT91_RTC_SECEV)
-			events |= (RTC_UF | RTC_IRQF);
+		if (rtsr & AT91_RTC_SECEV) {
+			complete(&at91_rtc_upd_rdy);
+			at91_rtc_write_idr(AT91_RTC_SECEV);
+		}
 		if (rtsr & AT91_RTC_ACKUPD)
 			complete(&at91_rtc_updated);
 
@@ -413,6 +422,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	}
 	platform_set_drvdata(pdev, rtc);
 
+	/* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy
+	 * completion.
+	 */
+	at91_rtc_write_ier(AT91_RTC_SECEV);
+
 	dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n");
 	return 0;
 
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index f1cb706445c7..6ae046bdb263 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -34,11 +34,11 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
-#include <linux/mod_devicetable.h>
 #include <linux/log2.h>
 #include <linux/pm.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/dmi.h>
 
 /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
 #include <asm-generic/rtc.h>
@@ -377,6 +377,51 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
+/*
+ * Do not disable RTC alarm on shutdown - workaround for b0rked BIOSes.
+ */
+static bool alarm_disable_quirk;
+
+static int __init set_alarm_disable_quirk(const struct dmi_system_id *id)
+{
+	alarm_disable_quirk = true;
+	pr_info("rtc-cmos: BIOS has alarm-disable quirk. ");
+	pr_info("RTC alarms disabled\n");
+	return 0;
+}
+
+static const struct dmi_system_id rtc_quirks[] __initconst = {
+	/* https://bugzilla.novell.com/show_bug.cgi?id=805740 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "IBM Truman",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "4852570"),
+		},
+	},
+	/* https://bugzilla.novell.com/show_bug.cgi?id=812592 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Gigabyte GA-990XA-UD3",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"Gigabyte Technology Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA-990XA-UD3"),
+		},
+	},
+	/* http://permalink.gmane.org/gmane.linux.kernel/1604474 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Toshiba Satellite L300",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L300"),
+		},
+	},
+	{}
+};
+
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -385,6 +430,9 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	if (!is_valid_irq(cmos->irq))
 		return -EINVAL;
 
+	if (alarm_disable_quirk)
+		return 0;
+
 	spin_lock_irqsave(&rtc_lock, flags);
 
 	if (enabled)
@@ -1163,6 +1211,8 @@ static int __init cmos_init(void)
 			platform_driver_registered = true;
 	}
 
+	dmi_check_system(rtc_quirks);
+
 	if (retval == 0)
 		return 0;
 
diff --git a/drivers/rtc/rtc-max8907.c b/drivers/rtc/rtc-max8907.c
index 86afb797125d..5d0ce597ba83 100644
--- a/drivers/rtc/rtc-max8907.c
+++ b/drivers/rtc/rtc-max8907.c
@@ -51,7 +51,7 @@ static irqreturn_t max8907_irq_handler(int irq, void *data)
 {
 	struct max8907_rtc *rtc = data;
 
-	regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x7f, 0);
+	regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0);
 
 	rtc_update_irq(rtc->rtc_dev, 1, RTC_IRQF | RTC_AF);
 
@@ -64,7 +64,7 @@ static void regs_to_tm(u8 *regs, struct rtc_time *tm)
 		bcd2bin(regs[RTC_YEAR1]) - 1900;
 	tm->tm_mon = bcd2bin(regs[RTC_MONTH] & 0x1f) - 1;
 	tm->tm_mday = bcd2bin(regs[RTC_DATE] & 0x3f);
-	tm->tm_wday = (regs[RTC_WEEKDAY] & 0x07) - 1;
+	tm->tm_wday = (regs[RTC_WEEKDAY] & 0x07);
 	if (regs[RTC_HOUR] & HOUR_12) {
 		tm->tm_hour = bcd2bin(regs[RTC_HOUR] & 0x01f);
 		if (tm->tm_hour == 12)
@@ -88,7 +88,7 @@ static void tm_to_regs(struct rtc_time *tm, u8 *regs)
 	regs[RTC_YEAR1] = bin2bcd(low);
 	regs[RTC_MONTH] = bin2bcd(tm->tm_mon + 1);
 	regs[RTC_DATE] = bin2bcd(tm->tm_mday);
-	regs[RTC_WEEKDAY] = tm->tm_wday + 1;
+	regs[RTC_WEEKDAY] = tm->tm_wday;
 	regs[RTC_HOUR] = bin2bcd(tm->tm_hour);
 	regs[RTC_MIN] = bin2bcd(tm->tm_min);
 	regs[RTC_SEC] = bin2bcd(tm->tm_sec);
@@ -153,7 +153,7 @@ static int max8907_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	tm_to_regs(&alrm->time, regs);
 
 	/* Disable alarm while we update the target time */
-	ret = regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x7f, 0);
+	ret = regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0);
 	if (ret < 0)
 		return ret;
 
@@ -163,8 +163,7 @@ static int max8907_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 		return ret;
 
 	if (alrm->enabled)
-		ret = regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL,
-					 0x7f, 0x7f);
+		ret = regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x77);
 
 	return ret;
 }
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d72a9216ee2e..e91ec8cd9b09 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2879,12 +2879,12 @@ static int dasd_alloc_queue(struct dasd_block *block)
 
 	elevator_exit(block->request_queue->elevator);
 	block->request_queue->elevator = NULL;
+	mutex_lock(&block->request_queue->sysfs_lock);
 	rc = elevator_init(block->request_queue, "deadline");
-	if (rc) {
+	if (rc)
 		blk_cleanup_queue(block->request_queue);
-		return rc;
-	}
-	return 0;
+	mutex_unlock(&block->request_queue->sysfs_lock);
+	return rc;
 }
 
 /*
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index eb5d22795c47..bb86494e2b7b 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -922,7 +922,7 @@ static int __init con3215_init(void)
 		raw3215_freelist = req;
 	}
 
-	cdev = ccw_device_probe_console();
+	cdev = ccw_device_probe_console(&raw3215_ccw_driver);
 	if (IS_ERR(cdev))
 		return -ENODEV;
 
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 699fd3e363df..bb6b0df50b33 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -576,7 +576,6 @@ static struct console con3270 = {
 static int __init
 con3270_init(void)
 {
-	struct ccw_device *cdev;
 	struct raw3270 *rp;
 	void *cbuf;
 	int i;
@@ -591,10 +590,7 @@ con3270_init(void)
 		cpcmd("TERM AUTOCR OFF", NULL, 0, NULL);
 	}
 
-	cdev = ccw_device_probe_console();
-	if (IS_ERR(cdev))
-		return -ENODEV;
-	rp = raw3270_setup_console(cdev);
+	rp = raw3270_setup_console();
 	if (IS_ERR(rp))
 		return PTR_ERR(rp);
 
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 24a08e8f19e1..651d1f5da7c4 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -776,16 +776,24 @@ raw3270_setup_device(struct ccw_device *cdev, struct raw3270 *rp, char *ascebc)
 }
 
 #ifdef CONFIG_TN3270_CONSOLE
+/* Tentative definition - see below for actual definition. */
+static struct ccw_driver raw3270_ccw_driver;
+
 /*
  * Setup 3270 device configured as console.
  */
-struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev)
+struct raw3270 __init *raw3270_setup_console(void)
 {
+	struct ccw_device *cdev;
 	unsigned long flags;
 	struct raw3270 *rp;
 	char *ascebc;
 	int rc;
 
+	cdev = ccw_device_probe_console(&raw3270_ccw_driver);
+	if (IS_ERR(cdev))
+		return ERR_CAST(cdev);
+
 	rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA);
 	ascebc = kzalloc(256, GFP_KERNEL);
 	rc = raw3270_setup_device(cdev, rp, ascebc);
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 7b73ff8c1bd7..359276a88396 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -190,7 +190,7 @@ raw3270_put_view(struct raw3270_view *view)
 		wake_up(&raw3270_wait_queue);
 }
 
-struct raw3270 *raw3270_setup_console(struct ccw_device *cdev);
+struct raw3270 *raw3270_setup_console(void);
 void raw3270_wait_cons_dev(struct raw3270 *);
 
 /* Notifier for device addition/removal */
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index cee69dac3e18..4dd71ca0269c 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -942,7 +942,7 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty)
 		return rc;
 	}
 
-	tp->screen = tty3270_alloc_screen(tp->view.cols, tp->view.rows);
+	tp->screen = tty3270_alloc_screen(tp->view.rows, tp->view.cols);
 	if (IS_ERR(tp->screen)) {
 		rc = PTR_ERR(tp->screen);
 		raw3270_put_view(&tp->view);
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 8ea7d9b2c671..815e290a1afb 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -500,18 +500,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 
 static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 {
-	do {
+	static int ntsm_unsupported;
+
+	while (true) {
 		memset(sei, 0, sizeof(*sei));
 		sei->request.length = 0x0010;
 		sei->request.code = 0x000e;
-		sei->ntsm = ntsm;
+		if (!ntsm_unsupported)
+			sei->ntsm = ntsm;
 
 		if (chsc(sei))
 			break;
 
 		if (sei->response.code != 0x0001) {
-			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
-				      sei->response.code);
+			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n",
+				      sei->response.code, sei->ntsm);
+
+			if (sei->response.code == 3 && sei->ntsm) {
+				/* Fallback for old firmware. */
+				ntsm_unsupported = 1;
+				continue;
+			}
 			break;
 		}
 
@@ -527,7 +536,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 			CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt);
 			break;
 		}
-	} while (sei->u.nt0_area.flags & 0x80);
+
+		if (!(sei->u.nt0_area.flags & 0x80))
+			break;
+	}
 }
 
 /*
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 1ab5f6c36d9b..8d04a9a88cc4 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1610,7 +1610,7 @@ out_unlock:
 	return rc;
 }
 
-struct ccw_device *ccw_device_probe_console(void)
+struct ccw_device *ccw_device_probe_console(struct ccw_driver *drv)
 {
 	struct io_subchannel_private *io_priv;
 	struct ccw_device *cdev;
@@ -1632,6 +1632,7 @@ struct ccw_device *ccw_device_probe_console(void)
 		kfree(io_priv);
 		return cdev;
 	}
+	cdev->drv = drv;
 	set_io_private(sch, io_priv);
 	ret = ccw_device_console_enable(cdev, sch);
 	if (ret) {
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 6cd0fc1b203a..e06cb8f8d0c2 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4448,7 +4448,7 @@ int qeth_snmp_command(struct qeth_card *card, char __user *udata)
 	struct qeth_cmd_buffer *iob;
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_snmp_ureq *ureq;
-	int req_len;
+	unsigned int req_len;
 	struct qeth_arp_query_info qinfo = {0, };
 	int rc = 0;
 
@@ -4464,6 +4464,10 @@ int qeth_snmp_command(struct qeth_card *card, char __user *udata)
 	/* skip 4 bytes (data_len struct member) to get req_len */
 	if (copy_from_user(&req_len, udata + sizeof(int), sizeof(int)))
 		return -EFAULT;
+	if (req_len > (QETH_BUFSIZE - IPA_PDU_HEADER_SIZE -
+		       sizeof(struct qeth_ipacmd_hdr) -
+		       sizeof(struct qeth_ipacmd_setadpparms_hdr)))
+		return -EINVAL;
 	ureq = memdup_user(udata, req_len + sizeof(struct qeth_snmp_ureq_hdr));
 	if (IS_ERR(ureq)) {
 		QETH_CARD_TEXT(card, 2, "snmpnome");
diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c
index 160e7510aca6..0787b9756165 100644
--- a/drivers/sbus/char/bbc_envctrl.c
+++ b/drivers/sbus/char/bbc_envctrl.c
@@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!tp)
 		return;
 
+	INIT_LIST_HEAD(&tp->bp_list);
+	INIT_LIST_HEAD(&tp->glob_list);
+
 	tp->client = bbc_i2c_attach(bp, op);
 	if (!tp->client) {
 		kfree(tp);
@@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!fp)
 		return;
 
+	INIT_LIST_HEAD(&fp->bp_list);
+	INIT_LIST_HEAD(&fp->glob_list);
+
 	fp->client = bbc_i2c_attach(bp, op);
 	if (!fp->client) {
 		kfree(fp);
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index c1441ed282eb..e0e6cd605cca 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -301,13 +301,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index
 	if (!bp)
 		return NULL;
 
+	INIT_LIST_HEAD(&bp->temps);
+	INIT_LIST_HEAD(&bp->fans);
+
 	bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs");
 	if (!bp->i2c_control_regs)
 		goto fail;
 
-	bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
-	if (!bp->i2c_bussel_reg)
-		goto fail;
+	if (op->num_resources == 2) {
+		bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
+		if (!bp->i2c_bussel_reg)
+			goto fail;
+	}
 
 	bp->waiting = 0;
 	init_waitqueue_head(&bp->wq);
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 5e1e12c0cf42..0a7325361d29 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -2025,7 +2025,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= twa_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index c845bdbeb6c0..4de346017e9f 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1600,7 +1600,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= twl_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 56662ae03dea..430ee3774c3b 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -2277,7 +2277,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,	
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= tw_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 1ef041bc60c8..ee6caddd978c 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -510,7 +510,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 		goto cleanup;
 	}
 
-	if (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr))) {
+	if ((fibsize < (sizeof(struct user_aac_srb) - sizeof(struct user_sgentry))) ||
+	    (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr)))) {
 		rcode = -EINVAL;
 		goto cleanup;
 	}
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 408a42ef787a..4921ed19a027 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -771,6 +771,8 @@ static long aac_compat_do_ioctl(struct aac_dev *dev, unsigned cmd, unsigned long
 static int aac_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	struct aac_dev *dev = (struct aac_dev *)sdev->host->hostdata;
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
 	return aac_compat_do_ioctl(dev, cmd, (unsigned long)arg);
 }
 
@@ -1079,6 +1081,7 @@ static struct scsi_host_template aac_driver_template = {
 #endif
 	.use_clustering			= ENABLE_CLUSTERING,
 	.emulated			= 1,
+	.no_write_same			= 1,
 };
 
 static void __aac_shutdown(struct aac_dev * aac)
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 33c52bc2c7b4..1822cb9ec623 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -137,6 +137,7 @@ static struct scsi_host_template arcmsr_scsi_host_template = {
 	.cmd_per_lun		= ARCMSR_MAX_CMD_PERLUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= arcmsr_host_attrs,
+	.no_write_same		= 1,
 };
 static struct pci_device_id arcmsr_device_id_table[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110)},
@@ -2500,16 +2501,15 @@ static int arcmsr_polling_ccbdone(struct AdapterControlBlock *acb,
 static int arcmsr_iop_confirm(struct AdapterControlBlock *acb)
 {
 	uint32_t cdb_phyaddr, cdb_phyaddr_hi32;
-	dma_addr_t dma_coherent_handle;
+
 	/*
 	********************************************************************
 	** here we need to tell iop 331 our freeccb.HighPart
 	** if freeccb.HighPart is not zero
 	********************************************************************
 	*/
-	dma_coherent_handle = acb->dma_coherent_handle;
-	cdb_phyaddr = (uint32_t)(dma_coherent_handle);
-	cdb_phyaddr_hi32 = (uint32_t)((cdb_phyaddr >> 16) >> 16);
+	cdb_phyaddr = lower_32_bits(acb->dma_coherent_handle);
+	cdb_phyaddr_hi32 = upper_32_bits(acb->dma_coherent_handle);
 	acb->cdb_phyaddr_hi32 = cdb_phyaddr_hi32;
 	/*
 	***********************************************************************
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 245a9595a93a..ef0a78b0d730 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -812,17 +812,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba,
 
 	if (ip_action == IP_ACTION_ADD) {
 		memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value,
-		       ip_param->len);
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		if (subnet_param)
 			memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-			       subnet_param->value, subnet_param->len);
+			       subnet_param->value,
+			       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	} else {
 		memcpy(req->ip_params.ip_record.ip_addr.addr,
-		       if_info->ip_addr.addr, ip_param->len);
+		       if_info->ip_addr.addr,
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-		       if_info->ip_addr.subnet_mask, ip_param->len);
+		       if_info->ip_addr.subnet_mask,
+		       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	}
 
 	rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
@@ -850,7 +853,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr,
 	req->action = gtway_action;
 	req->ip_addr.ip_type = BE2_IPV4;
 
-	memcpy(req->ip_addr.addr, gt_addr, param_len);
+	memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr));
 
 	return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
 }
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index a449706c6bc0..6c6c7c35ca10 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -299,6 +299,7 @@ wwn_t bfa_fcs_lport_get_rport(struct bfa_fcs_lport_s *port, wwn_t wwn,
 struct bfa_fcs_lport_s *bfa_fcs_lookup_port(struct bfa_fcs_s *fcs,
 					    u16 vf_id, wwn_t lpwwn);
 
+void bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port, char *symname);
 void bfa_fcs_lport_get_info(struct bfa_fcs_lport_s *port,
 			    struct bfa_lport_info_s *port_info);
 void bfa_fcs_lport_get_attr(struct bfa_fcs_lport_s *port,
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index 1224d0462a49..2826961c3806 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -1097,6 +1097,17 @@ bfa_fcs_lport_init(struct bfa_fcs_lport_s *lport,
 	bfa_sm_send_event(lport, BFA_FCS_PORT_SM_CREATE);
 }
 
+void
+bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port,
+				char *symname)
+{
+	strcpy(port->port_cfg.sym_name.symname, symname);
+
+	if (bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
+		bfa_fcs_lport_ns_util_send_rspn_id(
+			BFA_FCS_GET_NS_FROM_PORT(port), NULL);
+}
+
 /*
  *  fcs_lport_api
  */
@@ -4950,9 +4961,6 @@ bfa_fcs_lport_ns_util_send_rspn_id(void *cbarg, struct bfa_fcxp_s *fcxp_alloced)
 	u8 *psymbl = &symbl[0];
 	int len;
 
-	if (!bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
-		return;
-
 	/* Avoid sending RSPN in the following states. */
 	if (bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_offline) ||
 	    bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_plogi_sending) ||
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 23a90e7b7107..a119421cb324 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -72,7 +72,7 @@ struct bfa_sge_s {
 } while (0)
 
 #define bfa_swap_words(_x)  (	\
-	((_x) << 32) | ((_x) >> 32))
+	((u64)(_x) << 32) | ((u64)(_x) >> 32))
 
 #ifdef __BIG_ENDIAN
 #define bfa_sge_to_be(_x)
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index a5f7690e819e..ae2564d3123b 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -1824,7 +1824,7 @@ out:
 static u32 *
 bfad_load_fwimg(struct pci_dev *pdev)
 {
-	if (pdev->device == BFA_PCI_DEVICE_ID_CT2) {
+	if (bfa_asic_id_ct2(pdev->device)) {
 		if (bfi_image_ct2_size == 0)
 			bfad_read_firmware(pdev, &bfi_image_ct2,
 				&bfi_image_ct2_size, BFAD_FW_FILE_CT2);
@@ -1834,12 +1834,14 @@ bfad_load_fwimg(struct pci_dev *pdev)
 			bfad_read_firmware(pdev, &bfi_image_ct,
 				&bfi_image_ct_size, BFAD_FW_FILE_CT);
 		return bfi_image_ct;
-	} else {
+	} else if (bfa_asic_id_cb(pdev->device)) {
 		if (bfi_image_cb_size == 0)
 			bfad_read_firmware(pdev, &bfi_image_cb,
 				&bfi_image_cb_size, BFAD_FW_FILE_CB);
 		return bfi_image_cb;
 	}
+
+	return NULL;
 }
 
 static void
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index 72f5dc32cc12..58eeca2bbb4b 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -610,11 +610,8 @@ bfad_im_vport_set_symbolic_name(struct fc_vport *fc_vport)
 		return;
 
 	spin_lock_irqsave(&bfad->bfad_lock, flags);
-	if (strlen(sym_name) > 0) {
-		strcpy(fcs_vport->lport.port_cfg.sym_name.symname, sym_name);
-		bfa_fcs_lport_ns_util_send_rspn_id(
-			BFA_FCS_GET_NS_FROM_PORT((&fcs_vport->lport)), NULL);
-	}
+	if (strlen(sym_name) > 0)
+		bfa_fcs_lport_set_symname(&fcs_vport->lport, sym_name);
 	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
 }
 
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 69ac55495c1d..aad5535db782 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -411,6 +411,7 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct fc_frame_header *fh;
 	struct fcoe_rcv_info *fr;
 	struct fcoe_percpu_s *bg;
+	struct sk_buff *tmp_skb;
 	unsigned short oxid;
 
 	interface = container_of(ptype, struct bnx2fc_interface,
@@ -423,6 +424,12 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto err;
 	}
 
+	tmp_skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!tmp_skb)
+		goto err;
+
+	skb = tmp_skb;
+
 	if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) {
 		printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n");
 		goto err;
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 34552bf1c023..55548dc5cec3 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -530,7 +530,7 @@ static int esp_need_to_nego_sync(struct esp_target_data *tp)
 static int esp_alloc_lun_tag(struct esp_cmd_entry *ent,
 			     struct esp_lun_data *lp)
 {
-	if (!ent->tag[0]) {
+	if (!ent->orig_tag[0]) {
 		/* Non-tagged, slot already taken?  */
 		if (lp->non_tagged_cmd)
 			return -EBUSY;
@@ -564,9 +564,9 @@ static int esp_alloc_lun_tag(struct esp_cmd_entry *ent,
 			return -EBUSY;
 	}
 
-	BUG_ON(lp->tagged_cmds[ent->tag[1]]);
+	BUG_ON(lp->tagged_cmds[ent->orig_tag[1]]);
 
-	lp->tagged_cmds[ent->tag[1]] = ent;
+	lp->tagged_cmds[ent->orig_tag[1]] = ent;
 	lp->num_tagged++;
 
 	return 0;
@@ -575,9 +575,9 @@ static int esp_alloc_lun_tag(struct esp_cmd_entry *ent,
 static void esp_free_lun_tag(struct esp_cmd_entry *ent,
 			     struct esp_lun_data *lp)
 {
-	if (ent->tag[0]) {
-		BUG_ON(lp->tagged_cmds[ent->tag[1]] != ent);
-		lp->tagged_cmds[ent->tag[1]] = NULL;
+	if (ent->orig_tag[0]) {
+		BUG_ON(lp->tagged_cmds[ent->orig_tag[1]] != ent);
+		lp->tagged_cmds[ent->orig_tag[1]] = NULL;
 		lp->num_tagged--;
 	} else {
 		BUG_ON(lp->non_tagged_cmd != ent);
@@ -667,6 +667,8 @@ static struct esp_cmd_entry *find_and_prep_issuable_command(struct esp *esp)
 			ent->tag[0] = 0;
 			ent->tag[1] = 0;
 		}
+		ent->orig_tag[0] = ent->tag[0];
+		ent->orig_tag[1] = ent->tag[1];
 
 		if (esp_alloc_lun_tag(ent, lp) < 0)
 			continue;
diff --git a/drivers/scsi/esp_scsi.h b/drivers/scsi/esp_scsi.h
index 28e22acf87ea..cd68805e8d78 100644
--- a/drivers/scsi/esp_scsi.h
+++ b/drivers/scsi/esp_scsi.h
@@ -271,6 +271,7 @@ struct esp_cmd_entry {
 #define ESP_CMD_FLAG_AUTOSENSE	0x04 /* Doing automatic REQUEST_SENSE */
 
 	u8			tag[2];
+	u8			orig_tag[2];
 
 	u8			status;
 	u8			message;
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 6d55b4e7e792..aec3d4da276f 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -4686,6 +4686,7 @@ static struct scsi_host_template gdth_template = {
         .cmd_per_lun            = GDTH_MAXC_P_L,
         .unchecked_isa_dma      = 1,
         .use_clustering         = ENABLE_CLUSTERING,
+	.no_write_same		= 1,
 };
 
 #ifdef CONFIG_ISA
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index df0c3c71ea43..3cafe0d784b8 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -388,6 +388,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
 	shost->ordered_tag = sht->ordered_tag;
+	shost->no_write_same = sht->no_write_same;
 
 	if (sht->supported_mode == MODE_UNKNOWN)
 		/* means we didn't set it ... default to INITIATOR */
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 7f4f790a3d71..62ed744bbe06 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -538,6 +538,7 @@ static struct scsi_host_template hpsa_driver_template = {
 	.sdev_attrs = hpsa_sdev_attrs,
 	.shost_attrs = hpsa_shost_attrs,
 	.max_sectors = 8192,
+	.no_write_same = 1,
 };
 
 
@@ -1205,8 +1206,8 @@ static void complete_scsi_command(struct CommandList *cp)
 	scsi_set_resid(cmd, ei->ResidualCnt);
 
 	if (ei->CommandStatus == 0) {
-		cmd->scsi_done(cmd);
 		cmd_free(h, cp);
+		cmd->scsi_done(cmd);
 		return;
 	}
 
@@ -1265,7 +1266,7 @@ static void complete_scsi_command(struct CommandList *cp)
 					"has check condition: aborted command: "
 					"ASC: 0x%x, ASCQ: 0x%x\n",
 					cp, asc, ascq);
-				cmd->result = DID_SOFT_ERROR << 16;
+				cmd->result |= DID_SOFT_ERROR << 16;
 				break;
 			}
 			/* Must be some other type of check condition */
@@ -1379,8 +1380,8 @@ static void complete_scsi_command(struct CommandList *cp)
 		dev_warn(&h->pdev->dev, "cp %p returned unknown status %x\n",
 				cp, ei->CommandStatus);
 	}
-	cmd->scsi_done(cmd);
 	cmd_free(h, cp);
+	cmd->scsi_done(cmd);
 }
 
 static void hpsa_pci_unmap(struct pci_dev *pdev,
@@ -3117,7 +3118,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		}
 		if (ioc->Request.Type.Direction == XFER_WRITE) {
 			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
-				status = -ENOMEM;
+				status = -EFAULT;
 				goto cleanup1;
 			}
 		} else
@@ -4904,7 +4905,7 @@ reinit_after_soft_reset:
 	hpsa_hba_inquiry(h);
 	hpsa_register_scsi(h);	/* hook ourselves into SCSI subsystem */
 	start_controller_lockup_detector(h);
-	return 1;
+	return 0;
 
 clean4:
 	hpsa_free_sg_chain_blocks(h);
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index d0fa4b6c551f..c62b3e5d44bd 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -185,6 +185,11 @@ static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue)
 	if (crq->valid & 0x80) {
 		if (++queue->cur == queue->size)
 			queue->cur = 0;
+
+		/* Ensure the read of the valid bit occurs before reading any
+		 * other bits of the CRQ entry
+		 */
+		rmb();
 	} else
 		crq = NULL;
 	spin_unlock_irqrestore(&queue->lock, flags);
@@ -203,6 +208,11 @@ static int ibmvscsi_send_crq(struct ibmvscsi_host_data *hostdata,
 {
 	struct vio_dev *vdev = to_vio_dev(hostdata->dev);
 
+	/*
+	 * Ensure the command buffer is flushed to memory before handing it
+	 * over to the VIOS to prevent it from fetching any stale data.
+	 */
+	mb();
 	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
 }
 
@@ -794,7 +804,8 @@ static void purge_requests(struct ibmvscsi_host_data *hostdata, int error_code)
 				       evt->hostdata->dev);
 			if (evt->cmnd_done)
 				evt->cmnd_done(evt->cmnd);
-		} else if (evt->done)
+		} else if (evt->done && evt->crq.format != VIOSRP_MAD_FORMAT &&
+			   evt->iu.srp.login_req.opcode != SRP_LOGIN_REQ)
 			evt->done(evt);
 		free_event_struct(&evt->hostdata->pool, evt);
 		spin_lock_irqsave(hostdata->host->host_lock, flags);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 6c4cedb44c07..0ff37a5e286c 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6267,7 +6267,8 @@ static struct scsi_host_template driver_template = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = ipr_ioa_attrs,
 	.sdev_attrs = ipr_dev_attrs,
-	.proc_name = IPR_NAME
+	.proc_name = IPR_NAME,
+	.no_write_same = 1,
 };
 
 /**
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 8d5ea8a1e5a6..52a216f21ae5 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -374,6 +374,7 @@ static struct scsi_host_template ips_driver_template = {
 	.sg_tablesize		= IPS_MAX_SG,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
+	.no_write_same		= 1,
 };
 
 
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 4911310a38f5..22a9bb1abae1 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -311,9 +311,8 @@ static inline struct Scsi_Host *to_shost(struct isci_host *ihost)
 }
 
 #define for_each_isci_host(id, ihost, pdev) \
-	for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \
-	     id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \
-	     ihost = to_pci_info(pdev)->hosts[++id])
+	for (id = 0; id < SCI_MAX_CONTROLLERS && \
+	     (ihost = to_pci_info(pdev)->hosts[id]); id++)
 
 static inline void wait_for_start(struct isci_host *ihost)
 {
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index cd962da4a57a..5017bde3b366 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -615,13 +615,6 @@ static void sci_apc_agent_link_up(struct isci_host *ihost,
 					  SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION);
 	} else {
 		/* the phy is already the part of the port */
-		u32 port_state = iport->sm.current_state_id;
-
-		/* if the PORT'S state is resetting then the link up is from
-		 * port hard reset in this case, we need to tell the port
-		 * that link up is recieved
-		 */
-		BUG_ON(port_state != SCI_PORT_RESETTING);
 		port_agent->phy_ready_mask |= 1 << phy_index;
 		sci_port_link_up(iport, iphy);
 	}
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 0d30ca849e8f..5d6fda72d659 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -801,7 +801,7 @@ int isci_task_I_T_nexus_reset(struct domain_device *dev)
 		/* XXX: need to cleanup any ireqs targeting this
 		 * domain_device
 		 */
-		ret = TMF_RESP_FUNC_COMPLETE;
+		ret = -ENODEV;
 		goto out;
 	}
 
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 5de946984500..f91d41788ce4 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -717,11 +717,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 			return NULL;
 		}
 
+		if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) {
+			iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN);
+			return NULL;
+		}
+
 		task = conn->login_task;
 	} else {
 		if (session->state != ISCSI_STATE_LOGGED_IN)
 			return NULL;
 
+		if (data_size != 0) {
+			iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode);
+			return NULL;
+		}
+
 		BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE);
 		BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED);
 
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 161c98efade9..d2895836f9fa 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -211,7 +211,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		qc->tf.nsect = 0;
 	}
 
-	ata_tf_to_fis(&qc->tf, 1, 0, (u8*)&task->ata_task.fis);
+	ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, (u8 *)&task->ata_task.fis);
 	task->uldd_task = qc;
 	if (ata_is_atapi(qc->tf.protocol)) {
 		memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len);
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 846f475f62c1..60cf7b1f5423 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -4244,6 +4244,7 @@ static struct scsi_host_template megaraid_template = {
 	.eh_device_reset_handler	= megaraid_reset,
 	.eh_bus_reset_handler		= megaraid_reset,
 	.eh_host_reset_handler		= megaraid_reset,
+	.no_write_same			= 1,
 };
 
 static int
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index e6a1e0b38a19..3316d8031e82 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -367,6 +367,7 @@ static struct scsi_host_template megaraid_template_g = {
 	.eh_host_reset_handler		= megaraid_reset_handler,
 	.change_queue_depth		= megaraid_change_queue_depth,
 	.use_clustering			= ENABLE_CLUSTERING,
+	.no_write_same			= 1,
 	.sdev_attrs			= megaraid_sdev_attrs,
 	.shost_attrs			= megaraid_shost_attrs,
 };
diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c
index 25506c777381..9bec1717047e 100644
--- a/drivers/scsi/megaraid/megaraid_mm.c
+++ b/drivers/scsi/megaraid/megaraid_mm.c
@@ -486,6 +486,8 @@ mimd_to_kioc(mimd_t __user *umimd, mraid_mmadp_t *adp, uioc_t *kioc)
 
 	pthru32->dataxferaddr	= kioc->buf_paddr;
 	if (kioc->data_dir & UIOC_WR) {
+		if (pthru32->dataxferlen > kioc->xferlen)
+			return -EINVAL;
 		if (copy_from_user(kioc->buf_vaddr, kioc->user_data,
 						pthru32->dataxferlen)) {
 			return (-EFAULT);
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 684cc343cf09..b52121358385 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1295,7 +1295,6 @@ struct megasas_instance {
 	u32 *reply_queue;
 	dma_addr_t reply_queue_h;
 
-	unsigned long base_addr;
 	struct megasas_register_set __iomem *reg_set;
 
 	struct megasas_pd_list          pd_list[MEGASAS_MAX_PD];
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9b60dc129a53..78b4fe845245 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -933,7 +933,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 	abort_fr->abort_mfi_phys_addr_hi = 0;
 
 	cmd->sync_cmd = 1;
-	cmd->cmd_status = 0xFF;
+	cmd->cmd_status = ENODATA;
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
@@ -2099,6 +2099,7 @@ static struct scsi_host_template megasas_template = {
 	.bios_param = megasas_bios_param,
 	.use_clustering = ENABLE_CLUSTERING,
 	.change_queue_depth = megasas_change_queue_depth,
+	.no_write_same = 1,
 };
 
 /**
@@ -3460,6 +3461,7 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	u32 max_sectors_1;
 	u32 max_sectors_2;
 	u32 tmp_sectors, msix_enable;
+	resource_size_t base_addr;
 	struct megasas_register_set __iomem *reg_set;
 	struct megasas_ctrl_info *ctrl_info;
 	unsigned long bar_list;
@@ -3468,14 +3470,14 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	/* Find first memory bar */
 	bar_list = pci_select_bars(instance->pdev, IORESOURCE_MEM);
 	instance->bar = find_first_bit(&bar_list, sizeof(unsigned long));
-	instance->base_addr = pci_resource_start(instance->pdev, instance->bar);
 	if (pci_request_selected_regions(instance->pdev, instance->bar,
 					 "megasas: LSI")) {
 		printk(KERN_DEBUG "megasas: IO memory region busy!\n");
 		return -EBUSY;
 	}
 
-	instance->reg_set = ioremap_nocache(instance->base_addr, 8192);
+	base_addr = pci_resource_start(instance->pdev, instance->bar);
+	instance->reg_set = ioremap_nocache(base_addr, 8192);
 
 	if (!instance->reg_set) {
 		printk(KERN_DEBUG "megasas: Failed to map IO mem\n");
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 8dbe500c935d..fe76185cd79a 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -8174,7 +8174,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	mpt2sas_base_free_resources(ioc);
 	pci_save_state(pdev);
-	pci_disable_device(pdev);
 	pci_set_power_state(pdev, device_state);
 	return 0;
 }
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 8e1b73775065..bfb72ec277c7 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4314,6 +4314,7 @@ static struct scsi_host_template pmcraid_host_template = {
 	.this_id = -1,
 	.sg_tablesize = PMCRAID_MAX_IOADLS,
 	.max_sectors = PMCRAID_IOA_MAX_SECTORS,
+	.no_write_same = 1,
 	.cmd_per_lun = PMCRAID_MAX_CMD_PER_LUN,
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = pmcraid_host_attrs,
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index c32efc753229..799c266b0bb5 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2980,8 +2980,7 @@ struct qla_hw_data {
 				IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
 				IS_QLA82XX(ha) || IS_QLA83XX(ha))
 #define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
-#define IS_NOPOLLING_TYPE(ha)	((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
-			IS_QLA83XX(ha)) && (ha)->flags.msix_enabled)
+#define IS_NOPOLLING_TYPE(ha)	(IS_QLA81XX(ha) && (ha)->flags.msix_enabled)
 #define IS_FAC_REQUIRED(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_NOCACHE_VPD_TYPE(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_ALOGIO_CAPABLE(ha)	(IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index ad72c1d85111..66c495d21016 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2553,7 +2553,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    ha->flags.enable_64bit_addressing ? "enable" :
 	    "disable");
 	ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp);
-	if (!ret) {
+	if (ret) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0031,
 		    "Failed to allocate memory for adapter, aborting.\n");
 
@@ -3458,10 +3458,10 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	else {
 		qla2x00_set_reserved_loop_ids(ha);
 		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
-		    "loop_id_map=%p. \n", ha->loop_id_map);
+		    "loop_id_map=%p.\n", ha->loop_id_map);
 	}
 
-	return 1;
+	return 0;
 
 fail_async_pd:
 	dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index fcdc22306cab..e6884940d107 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1514,12 +1514,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha,
 static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
 	uint32_t req_cnt)
 {
-	struct qla_hw_data *ha = vha->hw;
-	device_reg_t __iomem *reg = ha->iobase;
 	uint32_t cnt;
 
 	if (vha->req->cnt < (req_cnt + 2)) {
-		cnt = (uint16_t)RD_REG_DWORD(&reg->isp24.req_q_out);
+		cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out);
 
 		ql_dbg(ql_dbg_tgt, vha, 0xe00a,
 		    "Request ring circled: cnt=%d, vha->->ring_index=%d, "
@@ -3339,7 +3337,8 @@ restart:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
 		    "SRR cmd %p (se_cmd %p, tag %d, op %x), "
 		    "sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
-		    se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset);
+		    se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+		    cmd->sg_cnt, cmd->offset);
 
 		qlt_handle_srr(vha, sctio, imm);
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 66b0b26a1381..cfd49eca67aa 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -762,7 +762,16 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess)
 	pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id);
 
 	node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id);
-	WARN_ON(node && (node != se_nacl));
+	if (WARN_ON(node && (node != se_nacl))) {
+		/*
+		 * The nacl no longer matches what we think it should be.
+		 * Most likely a new dynamic acl has been added while
+		 * someone dropped the hardware lock.  It clearly is a
+		 * bug elsewhere, but this bit can't make things worse.
+		 */
+		btree_insert32(&lport->lport_fcport_map, nacl->nport_id,
+			       node, GFP_ATOMIC);
+	}
 
 	pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n",
 	    se_nacl, nacl->nport_wwnn, nacl->nport_id);
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f43de1e56420..3668b1b23b5a 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1689,8 +1689,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost)
 	 * is no point trying to lock the door of an off-line device.
 	 */
 	shost_for_each_device(sdev, shost) {
-		if (scsi_device_online(sdev) && sdev->locked)
+		if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) {
 			scsi_eh_lock_door(sdev);
+			sdev->was_reset = 0;
+		}
 	}
 
 	/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 86d522004a20..e5953c8018c5 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -815,6 +815,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			scsi_next_command(cmd);
 			return;
 		}
+	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+		/*
+		 * Certain non BLOCK_PC requests are commands that don't
+		 * actually transfer anything (FLUSH), so cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets the error explicitly for the problem case.
+		 */
+		error = __scsi_error_from_host_byte(cmd, result);
 	}
 
 	/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c
index fe30ea94ffe6..109802f776ed 100644
--- a/drivers/scsi/scsi_netlink.c
+++ b/drivers/scsi/scsi_netlink.c
@@ -77,7 +77,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb)
 			goto next_msg;
 		}
 
-		if (!capable(CAP_SYS_ADMIN)) {
+		if (!netlink_capable(skb, CAP_SYS_ADMIN)) {
 			err = -EPERM;
 			goto next_msg;
 		}
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 3e58b2245f1f..859240408f9e 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -320,6 +320,7 @@ static void scsi_target_destroy(struct scsi_target *starget)
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
 	unsigned long flags;
 
+	starget->state = STARGET_DEL;
 	transport_destroy_device(dev);
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (shost->hostt->target_destroy)
@@ -371,6 +372,37 @@ static struct scsi_target *__scsi_find_target(struct device *parent,
 }
 
 /**
+ * scsi_target_reap_ref_release - remove target from visibility
+ * @kref: the reap_ref in the target being released
+ *
+ * Called on last put of reap_ref, which is the indication that no device
+ * under this target is visible anymore, so render the target invisible in
+ * sysfs.  Note: we have to be in user context here because the target reaps
+ * should be done in places where the scsi device visibility is being removed.
+ */
+static void scsi_target_reap_ref_release(struct kref *kref)
+{
+	struct scsi_target *starget
+		= container_of(kref, struct scsi_target, reap_ref);
+
+	/*
+	 * if we get here and the target is still in the CREATED state that
+	 * means it was allocated but never made visible (because a scan
+	 * turned up no LUNs), so don't call device_del() on it.
+	 */
+	if (starget->state != STARGET_CREATED) {
+		transport_remove_device(&starget->dev);
+		device_del(&starget->dev);
+	}
+	scsi_target_destroy(starget);
+}
+
+static void scsi_target_reap_ref_put(struct scsi_target *starget)
+{
+	kref_put(&starget->reap_ref, scsi_target_reap_ref_release);
+}
+
+/**
  * scsi_alloc_target - allocate a new or find an existing target
  * @parent:	parent of the target (need not be a scsi host)
  * @channel:	target channel number (zero if no channels)
@@ -392,7 +424,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 		+ shost->transportt->target_size;
 	struct scsi_target *starget;
 	struct scsi_target *found_target;
-	int error;
+	int error, ref_got;
 
 	starget = kzalloc(size, GFP_KERNEL);
 	if (!starget) {
@@ -401,7 +433,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	}
 	dev = &starget->dev;
 	device_initialize(dev);
-	starget->reap_ref = 1;
+	kref_init(&starget->reap_ref);
 	dev->parent = get_device(parent);
 	dev_set_name(dev, "target%d:%d:%d", shost->host_no, channel, id);
 	dev->bus = &scsi_bus_type;
@@ -441,29 +473,36 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	return starget;
 
  found:
-	found_target->reap_ref++;
+	/*
+	 * release routine already fired if kref is zero, so if we can still
+	 * take the reference, the target must be alive.  If we can't, it must
+	 * be dying and we need to wait for a new target
+	 */
+	ref_got = kref_get_unless_zero(&found_target->reap_ref);
+
 	spin_unlock_irqrestore(shost->host_lock, flags);
-	if (found_target->state != STARGET_DEL) {
+	if (ref_got) {
 		put_device(dev);
 		return found_target;
 	}
-	/* Unfortunately, we found a dying target; need to
-	 * wait until it's dead before we can get a new one */
+	/*
+	 * Unfortunately, we found a dying target; need to wait until it's
+	 * dead before we can get a new one.  There is an anomaly here.  We
+	 * *should* call scsi_target_reap() to balance the kref_get() of the
+	 * reap_ref above.  However, since the target being released, it's
+	 * already invisible and the reap_ref is irrelevant.  If we call
+	 * scsi_target_reap() we might spuriously do another device_del() on
+	 * an already invisible target.
+	 */
 	put_device(&found_target->dev);
-	flush_scheduled_work();
+	/*
+	 * length of time is irrelevant here, we just want to yield the CPU
+	 * for a tick to avoid busy waiting for the target to die.
+	 */
+	msleep(1);
 	goto retry;
 }
 
-static void scsi_target_reap_usercontext(struct work_struct *work)
-{
-	struct scsi_target *starget =
-		container_of(work, struct scsi_target, ew.work);
-
-	transport_remove_device(&starget->dev);
-	device_del(&starget->dev);
-	scsi_target_destroy(starget);
-}
-
 /**
  * scsi_target_reap - check to see if target is in use and destroy if not
  * @starget: target to be checked
@@ -474,28 +513,13 @@ static void scsi_target_reap_usercontext(struct work_struct *work)
  */
 void scsi_target_reap(struct scsi_target *starget)
 {
-	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
-	unsigned long flags;
-	enum scsi_target_state state;
-	int empty = 0;
-
-	spin_lock_irqsave(shost->host_lock, flags);
-	state = starget->state;
-	if (--starget->reap_ref == 0 && list_empty(&starget->devices)) {
-		empty = 1;
-		starget->state = STARGET_DEL;
-	}
-	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	if (!empty)
-		return;
-
-	BUG_ON(state == STARGET_DEL);
-	if (state == STARGET_CREATED)
-		scsi_target_destroy(starget);
-	else
-		execute_in_process_context(scsi_target_reap_usercontext,
-					   &starget->ew);
+	/*
+	 * serious problem if this triggers: STARGET_DEL is only set in the if
+	 * the reap_ref drops to zero, so we're trying to do another final put
+	 * on an already released kref
+	 */
+	BUG_ON(starget->state == STARGET_DEL);
+	scsi_target_reap_ref_put(starget);
 }
 
 /**
@@ -1527,6 +1551,10 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel,
 	}
 	mutex_unlock(&shost->scan_mutex);
 	scsi_autopm_put_target(starget);
+	/*
+	 * paired with scsi_alloc_target().  Target will be destroyed unless
+	 * scsi_probe_and_add_lun made an underlying device visible
+	 */
 	scsi_target_reap(starget);
 	put_device(&starget->dev);
 
@@ -1607,8 +1635,10 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel,
 
  out_reap:
 	scsi_autopm_put_target(starget);
-	/* now determine if the target has any children at all
-	 * and if not, nuke it */
+	/*
+	 * paired with scsi_alloc_target(): determine if the target has
+	 * any children at all and if not, nuke it
+	 */
 	scsi_target_reap(starget);
 
 	put_device(&starget->dev);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 931a7d954203..9e2dd478dd15 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -332,17 +332,14 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 {
 	struct scsi_device *sdev;
 	struct device *parent;
-	struct scsi_target *starget;
 	struct list_head *this, *tmp;
 	unsigned long flags;
 
 	sdev = container_of(work, struct scsi_device, ew.work);
 
 	parent = sdev->sdev_gendev.parent;
-	starget = to_scsi_target(parent);
 
 	spin_lock_irqsave(sdev->host->host_lock, flags);
-	starget->reap_ref++;
 	list_del(&sdev->siblings);
 	list_del(&sdev->same_target_siblings);
 	list_del(&sdev->starved_entry);
@@ -362,8 +359,6 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	/* NULL queue means the device can't be used */
 	sdev->request_queue = NULL;
 
-	scsi_target_reap(scsi_target(sdev));
-
 	kfree(sdev->inquiry);
 	kfree(sdev);
 
@@ -978,6 +973,13 @@ void __scsi_remove_device(struct scsi_device *sdev)
 		sdev->host->hostt->slave_destroy(sdev);
 	transport_destroy_device(dev);
 
+	/*
+	 * Paired with the kref_get() in scsi_sysfs_initialize().  We have
+	 * remoed sysfs visibility from the device, so make the target
+	 * invisible if this was the last device underneath it.
+	 */
+	scsi_target_reap(scsi_target(sdev));
+
 	put_device(dev);
 }
 
@@ -1040,7 +1042,7 @@ void scsi_remove_target(struct device *dev)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			/* assuming new targets arrive at the end */
-			starget->reap_ref++;
+			kref_get(&starget->reap_ref);
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			if (last)
 				scsi_target_reap(last);
@@ -1124,6 +1126,12 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	list_add_tail(&sdev->same_target_siblings, &starget->devices);
 	list_add_tail(&sdev->siblings, &shost->__devices);
 	spin_unlock_irqrestore(shost->host_lock, flags);
+	/*
+	 * device can now only be removed via __scsi_remove_device() so hold
+	 * the target.  Target will be held in CREATED state until something
+	 * beneath it becomes visible (in which case it moves to RUNNING)
+	 */
+	kref_get(&starget->reap_ref);
 }
 
 int scsi_is_sdev_device(const struct device *dev)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c39863441337..26b543bc4f53 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2627,14 +2627,23 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
 {
 	struct scsi_device *sdev = sdkp->device;
 
+	if (sdev->host->no_write_same) {
+		sdev->no_write_same = 1;
+
+		return;
+	}
+
 	if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) {
+		/* too large values might cause issues with arcmsr */
+		int vpd_buf_len = 64;
+
 		sdev->no_report_opcodes = 1;
 
 		/* Disable WRITE SAME if REPORT SUPPORTED OPERATION
 		 * CODES is unsupported and the device has an ATA
 		 * Information VPD page (SAT).
 		 */
-		if (!scsi_get_vpd_page(sdev, 0x89, buffer, SD_BUF_SIZE))
+		if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len))
 			sdev->no_write_same = 1;
 	}
 
@@ -2843,6 +2852,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 		gd->events |= DISK_EVENT_MEDIA_CHANGE;
 	}
 
+	blk_pm_runtime_init(sdp->request_queue, dev);
 	add_disk(gd);
 	if (sdkp->capacity)
 		sd_dif_config_host(sdkp);
@@ -2851,7 +2861,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 
 	sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
 		  sdp->removable ? "removable " : "");
-	blk_pm_runtime_init(sdp->request_queue, dev);
 	scsi_autopm_put_device(sdp);
 	put_device(&sdkp->dev);
 }
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 16a3a0cc9672..87ca72d36d5b 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -33,6 +33,7 @@
 #include <linux/device.h>
 #include <linux/hyperv.h>
 #include <linux/mempool.h>
+#include <linux/blkdev.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -803,6 +804,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 		case ATA_12:
 			set_host_byte(scmnd, DID_PASSTHROUGH);
 			break;
+		/*
+		 * On Some Windows hosts TEST_UNIT_READY command can return
+		 * SRB_STATUS_ERROR, let the upper level code deal with it
+		 * based on the sense information.
+		 */
+		case TEST_UNIT_READY:
+			break;
 		default:
 			set_host_byte(scmnd, DID_TARGET_FAILURE);
 		}
@@ -1189,6 +1197,9 @@ static void storvsc_device_destroy(struct scsi_device *sdevice)
 {
 	struct stor_mem_pools *memp = sdevice->hostdata;
 
+	if (!memp)
+		return;
+
 	mempool_destroy(memp->request_mempool);
 	kmem_cache_destroy(memp->request_pool);
 	kfree(memp);
@@ -1282,6 +1293,16 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
 	return SUCCESS;
 }
 
+/*
+ * The host guarantees to respond to each command, although I/O latencies might
+ * be unbounded on Azure.  Reset the timer unconditionally to give the host a
+ * chance to perform EH.
+ */
+static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
+{
+	return BLK_EH_RESET_TIMER;
+}
+
 static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)
 {
 	bool allowed = true;
@@ -1441,6 +1462,7 @@ static struct scsi_host_template scsi_driver = {
 	.bios_param =		storvsc_get_chs,
 	.queuecommand =		storvsc_queuecommand,
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
+	.eh_timed_out =		storvsc_eh_timed_out,
 	.slave_alloc =		storvsc_device_alloc,
 	.slave_destroy =	storvsc_device_destroy,
 	.slave_configure =	storvsc_device_configure,
@@ -1454,6 +1476,7 @@ static struct scsi_host_template scsi_driver = {
 	.use_clustering =	DISABLE_CLUSTERING,
 	/* Make sure we dont get a sg segment crosses a page boundary */
 	.dma_boundary =		PAGE_SIZE-1,
+	.no_write_same =	1,
 };
 
 enum {
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index d92fe4037e94..6b349e301869 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3000,7 +3000,11 @@ sym_dequeue_from_squeue(struct sym_hcb *np, int i, int target, int lun, int task
 		if ((target == -1 || cp->target == target) &&
 		    (lun    == -1 || cp->lun    == lun)    &&
 		    (task   == -1 || cp->tag    == task)) {
+#ifdef SYM_OPT_HANDLE_DEVICE_QUEUEING
 			sym_set_cam_status(cp->cmd, DID_SOFT_ERROR);
+#else
+			sym_set_cam_status(cp->cmd, DID_REQUEUE);
+#endif
 			sym_remque(&cp->link_ccbq);
 			sym_insque_tail(&cp->link_ccbq, &np->comp_ccbq);
 		}
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 74b88efde6ad..11f5326f449f 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -270,6 +270,16 @@ static void virtscsi_req_done(struct virtqueue *vq)
 	virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd);
 };
 
+static void virtscsi_poll_requests(struct virtio_scsi *vscsi)
+{
+	int i, num_vqs;
+
+	num_vqs = vscsi->num_queues;
+	for (i = 0; i < num_vqs; i++)
+		virtscsi_vq_done(vscsi, &vscsi->req_vqs[i],
+				 virtscsi_complete_cmd);
+}
+
 static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_cmd *cmd = buf;
@@ -288,6 +298,8 @@ static void virtscsi_ctrl_done(struct virtqueue *vq)
 	virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free);
 };
 
+static void virtscsi_handle_event(struct work_struct *work);
+
 static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 			       struct virtio_scsi_event_node *event_node)
 {
@@ -295,6 +307,7 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 	struct scatterlist sg;
 	unsigned long flags;
 
+	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
@@ -412,7 +425,6 @@ static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_event_node *event_node = buf;
 
-	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	schedule_work(&event_node->work);
 }
 
@@ -602,6 +614,18 @@ static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 	    cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED)
 		ret = SUCCESS;
 
+	/*
+	 * The spec guarantees that all requests related to the TMF have
+	 * been completed, but the callback might not have run yet if
+	 * we're using independent interrupts (e.g. MSI).  Poll the
+	 * virtqueues once.
+	 *
+	 * In the abort case, sc->scsi_done will do nothing, because
+	 * the block layer must have detected a timeout and as a result
+	 * REQ_ATOM_COMPLETE has been set.
+	 */
+	virtscsi_poll_requests(vscsi);
+
 out:
 	mempool_free(cmd, virtscsi_cmd_pool);
 	return ret;
@@ -751,8 +775,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
 
 		vscsi->affinity_hint_set = true;
 	} else {
-		for (i = 0; i < vscsi->num_queues; i++)
+		for (i = 0; i < vscsi->num_queues; i++) {
+			if (!vscsi->req_vqs[i].vq)
+				continue;
+
 			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
+		}
 
 		vscsi->affinity_hint_set = false;
 	}
@@ -957,6 +985,10 @@ static void virtscsi_remove(struct virtio_device *vdev)
 #ifdef CONFIG_PM
 static int virtscsi_freeze(struct virtio_device *vdev)
 {
+	struct Scsi_Host *sh = virtio_scsi_host(vdev);
+	struct virtio_scsi *vscsi = shost_priv(sh);
+
+	unregister_hotcpu_notifier(&vscsi->nb);
 	virtscsi_remove_vqs(vdev);
 	return 0;
 }
@@ -965,8 +997,17 @@ static int virtscsi_restore(struct virtio_device *vdev)
 {
 	struct Scsi_Host *sh = virtio_scsi_host(vdev);
 	struct virtio_scsi *vscsi = shost_priv(sh);
+	int err;
+
+	err = virtscsi_init(vdev, vscsi);
+	if (err)
+		return err;
+
+	err = register_hotcpu_notifier(&vscsi->nb);
+	if (err)
+		vdev->config->del_vqs(vdev);
 
-	return virtscsi_init(vdev, vscsi);
+	return err;
 }
 #endif
 
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index e504b7636058..23f1ba6e9ccf 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -132,9 +132,9 @@ static int ath79_spi_setup_cs(struct spi_device *spi)
 
 		flags = GPIOF_DIR_OUT;
 		if (spi->mode & SPI_CS_HIGH)
-			flags |= GPIOF_INIT_HIGH;
-		else
 			flags |= GPIOF_INIT_LOW;
+		else
+			flags |= GPIOF_INIT_HIGH;
 
 		status = gpio_request_one(cdata->gpio, flags,
 					  dev_name(&spi->dev));
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index a4ec5f4ec817..cd716f4cd37f 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -180,8 +180,6 @@ static int bcm63xx_txrx_bufs(struct spi_device *spi, struct spi_transfer *first,
 			       transfer_list);
 	}
 
-	len -= prepend_len;
-
 	init_completion(&bs->done);
 
 	/* Fill in the Message control register */
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index b9f0192758d6..0791c92e8c50 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,7 +89,13 @@ err_exit:
 
 static void mid_spi_dma_exit(struct dw_spi *dws)
 {
+	if (!dws->dma_inited)
+		return;
+
+	dmaengine_terminate_all(dws->txchan);
 	dma_release_channel(dws->txchan);
+
+	dmaengine_terminate_all(dws->rxchan);
 	dma_release_channel(dws->rxchan);
 }
 
@@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	txconf.dst_addr = dws->dma_addr;
 	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
 	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	txconf.dst_addr_width = dws->dma_width;
 	txconf.device_fc = false;
 
 	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
@@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	rxconf.src_addr = dws->dma_addr;
 	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
 	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	rxconf.src_addr_width = dws->dma_width;
 	rxconf.device_fc = false;
 
 	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index c1abc06899e7..137a4deba5a3 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -394,9 +394,6 @@ static void pump_transfers(unsigned long data)
 	chip = dws->cur_chip;
 	spi = message->spi;
 
-	if (unlikely(!chip->clk_div))
-		chip->clk_div = dws->max_freq / chip->speed_hz;
-
 	if (message->state == ERROR_STATE) {
 		message->status = -EIO;
 		goto early_exit;
@@ -438,7 +435,7 @@ static void pump_transfers(unsigned long data)
 	if (transfer->speed_hz) {
 		speed = chip->speed_hz;
 
-		if (transfer->speed_hz != speed) {
+		if ((transfer->speed_hz != speed) || (!chip->clk_div)) {
 			speed = transfer->speed_hz;
 			if (speed > dws->max_freq) {
 				printk(KERN_ERR "MRST SPI0: unsupported"
@@ -677,7 +674,6 @@ static int dw_spi_setup(struct spi_device *spi)
 		dev_err(&spi->dev, "No max speed HZ parameter\n");
 		return -EINVAL;
 	}
-	chip->speed_hz = spi->max_speed_hz;
 
 	chip->tmode = 0; /* Tx & Rx */
 	/* Default SPI mode is SCPOL = 0, SCPH = 0 */
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 86d2158946bb..798729eb6689 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -136,6 +136,7 @@ struct omap2_mcspi_cs {
 	void __iomem		*base;
 	unsigned long		phys;
 	int			word_len;
+	u16			mode;
 	struct list_head	node;
 	/* Context save and restore shadow register */
 	u32			chconf0;
@@ -801,6 +802,8 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 
 	mcspi_write_chconf0(spi, l);
 
+	cs->mode = spi->mode;
+
 	dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n",
 			OMAP2_MCSPI_MAX_FREQ >> div,
 			(spi->mode & SPI_CPHA) ? "trailing" : "leading",
@@ -871,6 +874,7 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 			return -ENOMEM;
 		cs->base = mcspi->base + spi->chip_select * 0x14;
 		cs->phys = mcspi->phys + spi->chip_select * 0x14;
+		cs->mode = 0;
 		cs->chconf0 = 0;
 		spi->controller_state = cs;
 		/* Link this to context save list */
@@ -1043,6 +1047,16 @@ static void omap2_mcspi_work(struct omap2_mcspi *mcspi, struct spi_message *m)
 			mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
 	}
 
+	/*
+	 * The slave driver could have changed spi->mode in which case
+	 * it will be different from cs->mode (the current hardware setup).
+	 * If so, set par_override (even though its not a parity issue) so
+	 * omap2_mcspi_setup_transfer will be called to configure the hardware
+	 * with the correct mode on the first iteration of the loop below.
+	 */
+	if (spi->mode != cs->mode)
+		par_override = 1;
+
 	omap2_mcspi_set_enable(spi, 0);
 
 	m->status = status;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 66a5f82cf138..183aa80c9017 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -403,8 +403,6 @@ static int orion_spi_probe(struct platform_device *pdev)
 	struct resource *r;
 	unsigned long tclk_hz;
 	int status = 0;
-	const u32 *iprop;
-	int size;
 
 	master = spi_alloc_master(&pdev->dev, sizeof *spi);
 	if (master == NULL) {
@@ -415,10 +413,10 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (pdev->id != -1)
 		master->bus_num = pdev->id;
 	if (pdev->dev.of_node) {
-		iprop = of_get_property(pdev->dev.of_node, "cell-index",
-					&size);
-		if (iprop && size == sizeof(*iprop))
-			master->bus_num = *iprop;
+		u32 cell_index;
+		if (!of_property_read_u32(pdev->dev.of_node, "cell-index",
+					  &cell_index))
+			master->bus_num = cell_index;
 	}
 
 	/* we support only mode 0, and no options */
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 371cc66f1a0e..5266c89fc989 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1080,7 +1080,7 @@ err_rxdesc:
 		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
 err_tx_sgmap:
 	dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl,
-		     pl022->sgt_tx.nents, DMA_FROM_DEVICE);
+		     pl022->sgt_rx.nents, DMA_FROM_DEVICE);
 err_rx_sgmap:
 	sg_free_table(&pl022->sgt_tx);
 err_alloc_tx_sg:
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 48b396fced0a..d26a2d195d21 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1324,7 +1324,9 @@ static int pxa2xx_spi_suspend(struct device *dev)
 	if (status != 0)
 		return status;
 	write_SSCR0(0, drv_data->ioaddr);
-	clk_disable_unprepare(ssp->clk);
+
+	if (!pm_runtime_suspended(dev))
+		clk_disable_unprepare(ssp->clk);
 
 	return 0;
 }
@@ -1338,7 +1340,8 @@ static int pxa2xx_spi_resume(struct device *dev)
 	pxa2xx_spi_dma_resume(drv_data);
 
 	/* Enable the SSP clock */
-	clk_prepare_enable(ssp->clk);
+	if (!pm_runtime_suspended(dev))
+		clk_prepare_enable(ssp->clk);
 
 	/* Start the queue running */
 	status = spi_master_resume(drv_data->master);
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index 1567ac296b39..0fce5fc9923b 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -2902,7 +2902,7 @@ static int binder_node_release(struct binder_node *node, int refs)
 		refs++;
 
 		if (!ref->death)
-			goto out;
+			continue;
 
 		death++;
 
@@ -2915,7 +2915,6 @@ static int binder_node_release(struct binder_node *node, int refs)
 			BUG();
 	}
 
-out:
 	binder_debug(BINDER_DEBUG_DEAD_BINDER,
 		     "node %d now dead, refs %d, death %d\n",
 		     node->debug_id, refs, death);
diff --git a/drivers/staging/bcm/Bcmchar.c b/drivers/staging/bcm/Bcmchar.c
index 35641e529396..8fa64d964b16 100644
--- a/drivers/staging/bcm/Bcmchar.c
+++ b/drivers/staging/bcm/Bcmchar.c
@@ -1960,6 +1960,7 @@ cntrlEnd:
 
 		BCM_DEBUG_PRINT(Adapter, DBG_TYPE_OTHERS, OSAL_DBG, DBG_LVL_ALL, "Called IOCTL_BCM_GET_DEVICE_DRIVER_INFO\n");
 
+		memset(&DevInfo, 0, sizeof(DevInfo));
 		DevInfo.MaxRDMBufferSize = BUFFER_4K;
 		DevInfo.u32DSDStartOffset = EEPROM_CALPARAM_START;
 		DevInfo.u32RxAlignmentCorrection = 0;
diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c
index 76dec96aeb2a..e54031c558e8 100644
--- a/drivers/staging/comedi/drivers/8255_pci.c
+++ b/drivers/staging/comedi/drivers/8255_pci.c
@@ -59,6 +59,7 @@ Configuration Options: not applicable, uses PCI auto config
 #include "../comedidev.h"
 
 #include "8255.h"
+#include "mite.h"
 
 enum pci_8255_boardid {
 	BOARD_ADLINK_PCI7224,
@@ -66,7 +67,8 @@ enum pci_8255_boardid {
 	BOARD_ADLINK_PCI7296,
 	BOARD_CB_PCIDIO24,
 	BOARD_CB_PCIDIO24H,
-	BOARD_CB_PCIDIO48H,
+	BOARD_CB_PCIDIO48H_OLD,
+	BOARD_CB_PCIDIO48H_NEW,
 	BOARD_CB_PCIDIO96H,
 	BOARD_NI_PCIDIO96,
 	BOARD_NI_PCIDIO96B,
@@ -81,6 +83,7 @@ struct pci_8255_boardinfo {
 	const char *name;
 	int dio_badr;
 	int n_8255;
+	unsigned int has_mite:1;
 };
 
 static const struct pci_8255_boardinfo pci_8255_boards[] = {
@@ -109,11 +112,16 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = {
 		.dio_badr	= 2,
 		.n_8255		= 1,
 	},
-	[BOARD_CB_PCIDIO48H] = {
+	[BOARD_CB_PCIDIO48H_OLD] = {
 		.name		= "cb_pci-dio48h",
 		.dio_badr	= 1,
 		.n_8255		= 2,
 	},
+	[BOARD_CB_PCIDIO48H_NEW] = {
+		.name		= "cb_pci-dio48h",
+		.dio_badr	= 2,
+		.n_8255		= 2,
+	},
 	[BOARD_CB_PCIDIO96H] = {
 		.name		= "cb_pci-dio96h",
 		.dio_badr	= 2,
@@ -123,36 +131,43 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = {
 		.name		= "ni_pci-dio-96",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCIDIO96B] = {
 		.name		= "ni_pci-dio-96b",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PXI6508] = {
 		.name		= "ni_pxi-6508",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503] = {
 		.name		= "ni_pci-6503",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503B] = {
 		.name		= "ni_pci-6503b",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503X] = {
 		.name		= "ni_pci-6503x",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PXI_6503] = {
 		.name		= "ni_pxi-6503",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 };
 
@@ -160,6 +175,25 @@ struct pci_8255_private {
 	void __iomem *mmio_base;
 };
 
+static int pci_8255_mite_init(struct pci_dev *pcidev)
+{
+	void __iomem *mite_base;
+	u32 main_phys_addr;
+
+	/* ioremap the MITE registers (BAR 0) temporarily */
+	mite_base = pci_ioremap_bar(pcidev, 0);
+	if (!mite_base)
+		return -ENOMEM;
+
+	/* set data window to main registers (BAR 1) */
+	main_phys_addr = pci_resource_start(pcidev, 1);
+	writel(main_phys_addr | WENAB, mite_base + MITE_IODWBSR);
+
+	/* finished with MITE registers */
+	iounmap(mite_base);
+	return 0;
+}
+
 static int pci_8255_mmio(int dir, int port, int data, unsigned long iobase)
 {
 	void __iomem *mmio_base = (void __iomem *)iobase;
@@ -199,6 +233,12 @@ static int pci_8255_auto_attach(struct comedi_device *dev,
 	if (ret)
 		return ret;
 
+	if (board->has_mite) {
+		ret = pci_8255_mite_init(pcidev);
+		if (ret)
+			return ret;
+	}
+
 	is_mmio = (pci_resource_flags(pcidev, board->dio_badr) &
 		   IORESOURCE_MEM) != 0;
 	if (is_mmio) {
@@ -270,7 +310,10 @@ static DEFINE_PCI_DEVICE_TABLE(pci_8255_pci_table) = {
 	{ PCI_VDEVICE(ADLINK, 0x7296), BOARD_ADLINK_PCI7296 },
 	{ PCI_VDEVICE(CB, 0x0028), BOARD_CB_PCIDIO24 },
 	{ PCI_VDEVICE(CB, 0x0014), BOARD_CB_PCIDIO24H },
-	{ PCI_VDEVICE(CB, 0x000b), BOARD_CB_PCIDIO48H },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, 0x0000, 0x0000),
+	  .driver_data = BOARD_CB_PCIDIO48H_OLD },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, PCI_VENDOR_ID_CB, 0x000b),
+	  .driver_data = BOARD_CB_PCIDIO48H_NEW },
 	{ PCI_VDEVICE(CB, 0x0017), BOARD_CB_PCIDIO96H },
 	{ PCI_VDEVICE(NI, 0x0160), BOARD_NI_PCIDIO96 },
 	{ PCI_VDEVICE(NI, 0x1630), BOARD_NI_PCIDIO96B },
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 3d4878facc26..d919a9863e01 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -332,8 +332,8 @@ static int apci1032_auto_attach(struct comedi_device *dev,
 	s = &dev->subdevices[1];
 	if (dev->irq) {
 		dev->read_subdev = s;
-		s->type		= COMEDI_SUBD_DI | SDF_CMD_READ;
-		s->subdev_flags	= SDF_READABLE;
+		s->type		= COMEDI_SUBD_DI;
+		s->subdev_flags	= SDF_READABLE | SDF_CMD_READ;
 		s->n_chan	= 1;
 		s->maxdata	= 1;
 		s->range_table	= &range_digital;
diff --git a/drivers/staging/comedi/drivers/adl_pci9111.c b/drivers/staging/comedi/drivers/adl_pci9111.c
index 6247fdcedcbf..71043a1c8500 100644
--- a/drivers/staging/comedi/drivers/adl_pci9111.c
+++ b/drivers/staging/comedi/drivers/adl_pci9111.c
@@ -873,7 +873,7 @@ static int pci9111_auto_attach(struct comedi_device *dev,
 	pci9111_reset(dev);
 
 	if (pcidev->irq > 0) {
-		ret = request_irq(dev->irq, pci9111_interrupt,
+		ret = request_irq(pcidev->irq, pci9111_interrupt,
 				  IRQF_SHARED, dev->board_name, dev);
 		if (ret)
 			return ret;
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index f847bbc175e7..acb66a9513cf 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -489,6 +489,7 @@ static int pci171x_insn_write_ao(struct comedi_device *dev,
 				 struct comedi_insn *insn, unsigned int *data)
 {
 	struct pci1710_private *devpriv = dev->private;
+	unsigned int val;
 	int n, chan, range, ofs;
 
 	chan = CR_CHAN(insn->chanspec);
@@ -504,11 +505,14 @@ static int pci171x_insn_write_ao(struct comedi_device *dev,
 		outw(devpriv->da_ranges, dev->iobase + PCI171x_DAREF);
 		ofs = PCI171x_DA1;
 	}
+	val = devpriv->ao_data[chan];
 
-	for (n = 0; n < insn->n; n++)
-		outw(data[n], dev->iobase + ofs);
+	for (n = 0; n < insn->n; n++) {
+		val = data[n];
+		outw(val, dev->iobase + ofs);
+	}
 
-	devpriv->ao_data[chan] = data[n];
+	devpriv->ao_data[chan] = val;
 
 	return n;
 
@@ -678,6 +682,7 @@ static int pci1720_insn_write_ao(struct comedi_device *dev,
 				 struct comedi_insn *insn, unsigned int *data)
 {
 	struct pci1710_private *devpriv = dev->private;
+	unsigned int val;
 	int n, rangereg, chan;
 
 	chan = CR_CHAN(insn->chanspec);
@@ -687,13 +692,15 @@ static int pci1720_insn_write_ao(struct comedi_device *dev,
 		outb(rangereg, dev->iobase + PCI1720_RANGE);
 		devpriv->da_ranges = rangereg;
 	}
+	val = devpriv->ao_data[chan];
 
 	for (n = 0; n < insn->n; n++) {
-		outw(data[n], dev->iobase + PCI1720_DA0 + (chan << 1));
+		val = data[n];
+		outw(val, dev->iobase + PCI1720_DA0 + (chan << 1));
 		outb(0, dev->iobase + PCI1720_SYNCOUT);	/*  update outputs */
 	}
 
-	devpriv->ao_data[chan] = data[n];
+	devpriv->ao_data[chan] = val;
 
 	return n;
 }
diff --git a/drivers/staging/comedi/drivers/amplc_pc263.c b/drivers/staging/comedi/drivers/amplc_pc263.c
index 94a752d852bb..0d88e6227761 100644
--- a/drivers/staging/comedi/drivers/amplc_pc263.c
+++ b/drivers/staging/comedi/drivers/amplc_pc263.c
@@ -72,6 +72,9 @@ static int pc263_do_insn_bits(struct comedi_device *dev,
 		outb(s->state & 0xFF, dev->iobase);
 		outb(s->state >> 8, dev->iobase + 1);
 	}
+
+	data[1] = s->state;
+
 	return insn->n;
 }
 
diff --git a/drivers/staging/comedi/drivers/amplc_pci263.c b/drivers/staging/comedi/drivers/amplc_pci263.c
index 8b57533bf406..9c53199a419b 100644
--- a/drivers/staging/comedi/drivers/amplc_pci263.c
+++ b/drivers/staging/comedi/drivers/amplc_pci263.c
@@ -59,6 +59,9 @@ static int pci263_do_insn_bits(struct comedi_device *dev,
 		outb(s->state & 0xFF, dev->iobase);
 		outb(s->state >> 8, dev->iobase + 1);
 	}
+
+	data[1] = s->state;
+
 	return insn->n;
 }
 
diff --git a/drivers/staging/comedi/drivers/ni_65xx.c b/drivers/staging/comedi/drivers/ni_65xx.c
index 3f71f0f54d3c..05eb6fefb745 100644
--- a/drivers/staging/comedi/drivers/ni_65xx.c
+++ b/drivers/staging/comedi/drivers/ni_65xx.c
@@ -383,28 +383,23 @@ static int ni_65xx_dio_insn_bits(struct comedi_device *dev,
 {
 	const struct ni_65xx_board *board = comedi_board(dev);
 	struct ni_65xx_private *devpriv = dev->private;
-	unsigned base_bitfield_channel;
-	const unsigned max_ports_per_bitfield = 5;
+	int base_bitfield_channel;
 	unsigned read_bits = 0;
-	unsigned j;
+	int last_port_offset = ni_65xx_port_by_channel(s->n_chan - 1);
+	int port_offset;
 
 	base_bitfield_channel = CR_CHAN(insn->chanspec);
-	for (j = 0; j < max_ports_per_bitfield; ++j) {
-		const unsigned port_offset =
-			ni_65xx_port_by_channel(base_bitfield_channel) + j;
-		const unsigned port =
-			sprivate(s)->base_port + port_offset;
-		unsigned base_port_channel;
+	for (port_offset = ni_65xx_port_by_channel(base_bitfield_channel);
+	     port_offset <= last_port_offset; port_offset++) {
+		unsigned port = sprivate(s)->base_port + port_offset;
+		int base_port_channel = port_offset * ni_65xx_channels_per_port;
 		unsigned port_mask, port_data, port_read_bits;
-		int bitshift;
-		if (port >= ni_65xx_total_num_ports(board))
+		int bitshift = base_port_channel - base_bitfield_channel;
+
+		if (bitshift >= 32)
 			break;
-		base_port_channel = port_offset * ni_65xx_channels_per_port;
 		port_mask = data[0];
 		port_data = data[1];
-		bitshift = base_port_channel - base_bitfield_channel;
-		if (bitshift >= 32 || bitshift <= -32)
-			break;
 		if (bitshift > 0) {
 			port_mask >>= bitshift;
 			port_data >>= bitshift;
diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c
index d067ef70e194..5e80d428e544 100644
--- a/drivers/staging/comedi/drivers/ni_daq_700.c
+++ b/drivers/staging/comedi/drivers/ni_daq_700.c
@@ -127,6 +127,8 @@ static int daq700_ai_rinsn(struct comedi_device *dev,
 	/* write channel to multiplexer */
 	/* set mask scan bit high to disable scanning */
 	outb(chan | 0x80, dev->iobase + CMD_R1);
+	/* mux needs 2us to really settle [Fred Brooks]. */
+	udelay(2);
 
 	/* convert n samples */
 	for (n = 0; n < insn->n; n++) {
diff --git a/drivers/staging/comedi/drivers/pcmuio.c b/drivers/staging/comedi/drivers/pcmuio.c
index 0c98e26bbba1..b5ed093e59c3 100644
--- a/drivers/staging/comedi/drivers/pcmuio.c
+++ b/drivers/staging/comedi/drivers/pcmuio.c
@@ -935,12 +935,13 @@ static void pcmuio_detach(struct comedi_device *dev)
 	struct pcmuio_private *devpriv = dev->private;
 	int i;
 
-	for (i = 0; i < MAX_ASICS; ++i) {
-		if (devpriv->asics[i].irq)
-			free_irq(devpriv->asics[i].irq, dev);
-	}
-	if (devpriv && devpriv->sprivs)
+	if (devpriv) {
+		for (i = 0; i < MAX_ASICS; ++i) {
+			if (devpriv->asics[i].irq)
+				free_irq(devpriv->asics[i].irq, dev);
+		}
 		kfree(devpriv->sprivs);
+	}
 	comedi_legacy_detach(dev);
 }
 
diff --git a/drivers/staging/comedi/drivers/ssv_dnp.c b/drivers/staging/comedi/drivers/ssv_dnp.c
index a76df092a57b..8c84dc0cfe07 100644
--- a/drivers/staging/comedi/drivers/ssv_dnp.c
+++ b/drivers/staging/comedi/drivers/ssv_dnp.c
@@ -87,11 +87,11 @@ static int dnp_dio_insn_bits(struct comedi_device *dev,
 
 	/* on return, data[1] contains the value of the digital input lines. */
 	outb(PADR, CSCIR);
-	data[0] = inb(CSCDR);
+	data[1] = inb(CSCDR);
 	outb(PBDR, CSCIR);
-	data[0] += inb(CSCDR) << 8;
+	data[1] += inb(CSCDR) << 8;
 	outb(PCDR, CSCIR);
-	data[0] += ((inb(CSCDR) & 0xF0) << 12);
+	data[1] += ((inb(CSCDR) & 0xF0) << 12);
 
 	return insn->n;
 
diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c
index 8dc97b36e05a..b0cb2de93050 100644
--- a/drivers/staging/iio/adc/ad799x_core.c
+++ b/drivers/staging/iio/adc/ad799x_core.c
@@ -644,7 +644,8 @@ static int ad799x_probe(struct i2c_client *client,
 	return 0;
 
 error_free_irq:
-	free_irq(client->irq, indio_dev);
+	if (client->irq > 0)
+		free_irq(client->irq, indio_dev);
 error_cleanup_ring:
 	ad799x_ring_cleanup(indio_dev);
 error_disable_reg:
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 6330af656a0f..bc23d66a7a1e 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -115,6 +115,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.channel = 0,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
 		.address = AD5933_REG_TEMP_DATA,
+		.scan_index = -1,
 		.scan_type = {
 			.sign = 's',
 			.realbits = 14,
@@ -124,9 +125,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "real_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
-		BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "real",
 		.address = AD5933_REG_REAL_DATA,
 		.scan_index = 0,
 		.scan_type = {
@@ -138,9 +137,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "imag_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
-		BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "imag",
 		.address = AD5933_REG_IMAG_DATA,
 		.scan_index = 1,
 		.scan_type = {
@@ -746,14 +743,14 @@ static int ad5933_probe(struct i2c_client *client,
 	indio_dev->name = id->name;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = ad5933_channels;
-	indio_dev->num_channels = 1; /* only register temp0_input */
+	indio_dev->num_channels = ARRAY_SIZE(ad5933_channels);
 
 	ret = ad5933_register_ring_funcs_and_init(indio_dev);
 	if (ret)
 		goto error_disable_reg;
 
-	/* skip temp0_input, register in0_(real|imag)_raw */
-	ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2);
+	ret = iio_buffer_register(indio_dev, ad5933_channels,
+		ARRAY_SIZE(ad5933_channels));
 	if (ret)
 		goto error_unreg_ring;
 
diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index c99f890cc6c6..64c73adfa3b0 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -672,9 +672,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev)
 	chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
 			chip->tsl2x7x_settings.prox_pulse_count;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
-	chip->tsl2x7x_settings.prox_thres_low;
+			(chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
-			chip->tsl2x7x_settings.prox_thres_high;
+			(chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
 
 	/* and make sure we're not already on */
 	if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h
index 07318203a836..e8c98cf57070 100644
--- a/drivers/staging/iio/meter/ade7758.h
+++ b/drivers/staging/iio/meter/ade7758.h
@@ -119,7 +119,6 @@ struct ade7758_state {
 	u8			*tx;
 	u8			*rx;
 	struct mutex		buf_lock;
-	const struct iio_chan_spec *ade7758_ring_channels;
 	struct spi_transfer	ring_xfer[4];
 	struct spi_message	ring_msg;
 	/*
diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c
index 8f5bcfab3563..75d9fe6a1bc1 100644
--- a/drivers/staging/iio/meter/ade7758_core.c
+++ b/drivers/staging/iio/meter/ade7758_core.c
@@ -648,9 +648,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE),
 		.scan_index = 0,
 		.scan_type = {
@@ -662,9 +659,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT),
 		.scan_index = 1,
 		.scan_type = {
@@ -676,9 +670,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR),
 		.scan_index = 2,
 		.scan_type = {
@@ -690,9 +682,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR),
 		.scan_index = 3,
 		.scan_type = {
@@ -704,9 +694,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR),
 		.scan_index = 4,
 		.scan_type = {
@@ -718,9 +706,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE),
 		.scan_index = 5,
 		.scan_type = {
@@ -732,9 +717,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT),
 		.scan_index = 6,
 		.scan_type = {
@@ -746,9 +728,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR),
 		.scan_index = 7,
 		.scan_type = {
@@ -760,9 +740,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR),
 		.scan_index = 8,
 		.scan_type = {
@@ -774,9 +752,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR),
 		.scan_index = 9,
 		.scan_type = {
@@ -788,9 +764,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE),
 		.scan_index = 10,
 		.scan_type = {
@@ -802,9 +775,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT),
 		.scan_index = 11,
 		.scan_type = {
@@ -816,9 +786,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR),
 		.scan_index = 12,
 		.scan_type = {
@@ -830,9 +798,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR),
 		.scan_index = 13,
 		.scan_type = {
@@ -844,9 +810,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR),
 		.scan_index = 14,
 		.scan_type = {
@@ -890,13 +854,14 @@ static int ade7758_probe(struct spi_device *spi)
 		goto error_free_rx;
 	}
 	st->us = spi;
-	st->ade7758_ring_channels = &ade7758_channels[0];
 	mutex_init(&st->buf_lock);
 
 	indio_dev->name = spi->dev.driver->name;
 	indio_dev->dev.parent = &spi->dev;
 	indio_dev->info = &ade7758_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = ade7758_channels;
+	indio_dev->num_channels = ARRAY_SIZE(ade7758_channels);
 
 	ret = ade7758_configure_ring(indio_dev);
 	if (ret)
diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c
index b29e2d5d9937..6a0ef97e9146 100644
--- a/drivers/staging/iio/meter/ade7758_ring.c
+++ b/drivers/staging/iio/meter/ade7758_ring.c
@@ -89,11 +89,10 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p)
  **/
 static int ade7758_ring_preenable(struct iio_dev *indio_dev)
 {
-	struct ade7758_state *st = iio_priv(indio_dev);
 	unsigned channel;
 	int ret;
 
-	if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
+	if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
 		return -EINVAL;
 
 	ret = iio_sw_buffer_preenable(indio_dev);
@@ -104,7 +103,7 @@ static int ade7758_ring_preenable(struct iio_dev *indio_dev)
 				 indio_dev->masklength);
 
 	ade7758_write_waveform_type(&indio_dev->dev,
-		st->ade7758_ring_channels[channel].address);
+		indio_dev->channels[channel].address);
 
 	return 0;
 }
diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c
index 7a94ddd42f59..8c4f2896cd0d 100644
--- a/drivers/staging/iio/meter/ade7758_trigger.c
+++ b/drivers/staging/iio/meter/ade7758_trigger.c
@@ -85,7 +85,7 @@ int ade7758_probe_trigger(struct iio_dev *indio_dev)
 	ret = iio_trigger_register(st->trig);
 
 	/* select default trigger */
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 	if (ret)
 		goto error_free_irq;
 
diff --git a/drivers/staging/media/lirc/lirc_zilog.c b/drivers/staging/media/lirc/lirc_zilog.c
index 11d5338b4f2f..0feeaadf29dc 100644
--- a/drivers/staging/media/lirc/lirc_zilog.c
+++ b/drivers/staging/media/lirc/lirc_zilog.c
@@ -61,6 +61,9 @@
 #include <media/lirc_dev.h>
 #include <media/lirc.h>
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct IR;
 
 struct IR_rx {
@@ -941,7 +944,14 @@ static ssize_t read(struct file *filep, char *outbuf, size_t n, loff_t *ppos)
 			schedule();
 			set_current_state(TASK_INTERRUPTIBLE);
 		} else {
-			unsigned char buf[rbuf->chunk_size];
+			unsigned char buf[MAX_XFER_SIZE];
+
+			if (rbuf->chunk_size > sizeof(buf)) {
+				zilog_error("chunk_size is too big (%d)!\n",
+					    rbuf->chunk_size);
+				ret = -EINVAL;
+				break;
+			}
 			m = lirc_buffer_read(rbuf, buf);
 			if (m == rbuf->chunk_size) {
 				ret = copy_to_user((void *)outbuf+written, buf,
diff --git a/drivers/staging/ozwpan/ozcdev.c b/drivers/staging/ozwpan/ozcdev.c
index 27d06666c81a..224ccff75d4f 100644
--- a/drivers/staging/ozwpan/ozcdev.c
+++ b/drivers/staging/ozwpan/ozcdev.c
@@ -153,6 +153,9 @@ static ssize_t oz_cdev_write(struct file *filp, const char __user *buf,
 	struct oz_app_hdr *app_hdr;
 	struct oz_serial_ctx *ctx;
 
+	if (count > sizeof(ei->data) - sizeof(*elt) - sizeof(*app_hdr))
+		return -EINVAL;
+
 	spin_lock_bh(&g_cdev.lock);
 	pd = g_cdev.active_pd;
 	if (pd)
diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c
index 23ec684b60e1..274c359279ef 100644
--- a/drivers/staging/rtl8712/rtl871x_recv.c
+++ b/drivers/staging/rtl8712/rtl871x_recv.c
@@ -254,7 +254,7 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter,
 	struct sta_info *psta;
 	struct	sta_priv *pstapriv;
 	union recv_frame *prtnframe;
-	u16 ether_type = 0;
+	u16 ether_type;
 
 	pstapriv = &adapter->stapriv;
 	ptr = get_recvframe_data(precv_frame);
@@ -263,15 +263,14 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter,
 	psta = r8712_get_stainfo(pstapriv, psta_addr);
 	auth_alg = adapter->securitypriv.AuthAlgrthm;
 	if (auth_alg == 2) {
+		/* get ether_type */
+		ptr = ptr + pfhdr->attrib.hdrlen + LLC_HEADER_SIZE;
+		memcpy(&ether_type, ptr, 2);
+		ether_type = ntohs((unsigned short)ether_type);
+
 		if ((psta != NULL) && (psta->ieee8021x_blocked)) {
 			/* blocked
 			 * only accept EAPOL frame */
-			prtnframe = precv_frame;
-			/*get ether_type */
-			ptr = ptr + pfhdr->attrib.hdrlen +
-			      pfhdr->attrib.iv_len + LLC_HEADER_SIZE;
-			memcpy(&ether_type, ptr, 2);
-			ether_type = ntohs((unsigned short)ether_type);
 			if (ether_type == 0x888e)
 				prtnframe = precv_frame;
 			else {
diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c
index c812d6c7dc31..e3a005da776b 100644
--- a/drivers/staging/rtl8712/usb_intf.c
+++ b/drivers/staging/rtl8712/usb_intf.c
@@ -358,6 +358,10 @@ static u8 key_2char2num(u8 hch, u8 lch)
 	return (hex_to_bin(hch) << 4) | hex_to_bin(lch);
 }
 
+static const struct device_type wlan_type = {
+	.name = "wlan",
+};
+
 /*
  * drv_init() - a device potentially for us
  *
@@ -393,6 +397,7 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf,
 	padapter->pusb_intf = pusb_intf;
 	usb_set_intfdata(pusb_intf, pnetdev);
 	SET_NETDEV_DEV(pnetdev, &pusb_intf->dev);
+	pnetdev->dev.type = &wlan_type;
 	/* step 2. */
 	padapter->dvobj_init = &r8712_usb_dvobj_init;
 	padapter->dvobj_deinit = &r8712_usb_dvobj_deinit;
diff --git a/drivers/staging/sb105x/sb_pci_mp.c b/drivers/staging/sb105x/sb_pci_mp.c
index cd94f6c27723..b90e96b7ca01 100644
--- a/drivers/staging/sb105x/sb_pci_mp.c
+++ b/drivers/staging/sb105x/sb_pci_mp.c
@@ -1063,7 +1063,7 @@ static int mp_wait_modem_status(struct sb_uart_state *state, unsigned long arg)
 
 static int mp_get_count(struct sb_uart_state *state, struct serial_icounter_struct *icnt)
 {
-	struct serial_icounter_struct icount;
+	struct serial_icounter_struct icount = {};
 	struct sb_uart_icount cnow;
 	struct sb_uart_port *port = state->port;
 
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 8a6e5ea476e1..380d9d707109 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -725,7 +725,7 @@ static int qt_startup(struct usb_serial *serial)
 		goto startup_error;
 	}
 
-	switch (serial->dev->descriptor.idProduct) {
+	switch (le16_to_cpu(serial->dev->descriptor.idProduct)) {
 	case QUATECH_DSU100:
 	case QUATECH_QSU100:
 	case QUATECH_ESU100A:
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 6c7b55c2947d..e70a48e3b376 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -2219,6 +2219,7 @@ static void __exit speakup_exit(void)
 	unregister_keyboard_notifier(&keyboard_notifier_block);
 	unregister_vt_notifier(&vt_notifier_block);
 	speakup_unregister_devsynth();
+	speakup_cancel_paste();
 	del_timer(&cursor_timer);
 	kthread_stop(speakup_task);
 	speakup_task = NULL;
diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c
index f0fb00392d6b..b9359753784e 100644
--- a/drivers/staging/speakup/selection.c
+++ b/drivers/staging/speakup/selection.c
@@ -4,6 +4,9 @@
 #include <linux/sched.h>
 #include <linux/device.h> /* for dev_warn */
 #include <linux/selection.h>
+#include <linux/workqueue.h>
+#include <linux/tty.h>
+#include <asm/cmpxchg.h>
 
 #include "speakup.h"
 
@@ -121,31 +124,60 @@ int speakup_set_selection(struct tty_struct *tty)
 	return 0;
 }
 
-/* TODO: move to some helper thread, probably.  That'd fix having to check for
- * in_atomic().  */
-int speakup_paste_selection(struct tty_struct *tty)
+struct speakup_paste_work {
+	struct work_struct work;
+	struct tty_struct *tty;
+};
+
+static void __speakup_paste_selection(struct work_struct *work)
 {
+	struct speakup_paste_work *spw =
+		container_of(work, struct speakup_paste_work, work);
+	struct tty_struct *tty = xchg(&spw->tty, NULL);
 	struct vc_data *vc = (struct vc_data *) tty->driver_data;
 	int pasted = 0, count;
+	struct tty_ldisc *ld;
 	DECLARE_WAITQUEUE(wait, current);
+
+	ld = tty_ldisc_ref_wait(tty);
+
+	/* FIXME: this is completely unsafe */
 	add_wait_queue(&vc->paste_wait, &wait);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (test_bit(TTY_THROTTLED, &tty->flags)) {
-			if (in_atomic())
-				/* if we are in an interrupt handler, abort */
-				break;
 			schedule();
 			continue;
 		}
 		count = sel_buffer_lth - pasted;
 		count = min_t(int, count, tty->receive_room);
-		tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
-			NULL, count);
+		ld->ops->receive_buf(tty, sel_buffer + pasted, NULL, count);
 		pasted += count;
 	}
 	remove_wait_queue(&vc->paste_wait, &wait);
 	current->state = TASK_RUNNING;
+
+	tty_ldisc_deref(ld);
+	tty_kref_put(tty);
+}
+
+static struct speakup_paste_work speakup_paste_work = {
+	.work = __WORK_INITIALIZER(speakup_paste_work.work,
+				   __speakup_paste_selection)
+};
+
+int speakup_paste_selection(struct tty_struct *tty)
+{
+	if (cmpxchg(&speakup_paste_work.tty, NULL, tty) != NULL)
+		return -EBUSY;
+
+	tty_kref_get(tty);
+	schedule_work_on(WORK_CPU_UNBOUND, &speakup_paste_work.work);
 	return 0;
 }
 
+void speakup_cancel_paste(void)
+{
+	cancel_work_sync(&speakup_paste_work.work);
+	tty_kref_put(speakup_paste_work.tty);
+}
diff --git a/drivers/staging/speakup/speakup.h b/drivers/staging/speakup/speakup.h
index 0126f714821a..74fe72429b2d 100644
--- a/drivers/staging/speakup/speakup.h
+++ b/drivers/staging/speakup/speakup.h
@@ -77,6 +77,7 @@ extern void synth_buffer_clear(void);
 extern void speakup_clear_selection(void);
 extern int speakup_set_selection(struct tty_struct *tty);
 extern int speakup_paste_selection(struct tty_struct *tty);
+extern void speakup_cancel_paste(void);
 extern void speakup_register_devsynth(void);
 extern void speakup_unregister_devsynth(void);
 extern void synth_write(const char *buf, size_t count);
diff --git a/drivers/staging/tidspbridge/Kconfig b/drivers/staging/tidspbridge/Kconfig
index 60848f198b48..f7deabcf8355 100644
--- a/drivers/staging/tidspbridge/Kconfig
+++ b/drivers/staging/tidspbridge/Kconfig
@@ -4,7 +4,7 @@
 
 menuconfig TIDSPBRIDGE
 	tristate "DSP Bridge driver"
-	depends on ARCH_OMAP3 && !ARCH_MULTIPLATFORM
+	depends on ARCH_OMAP3 && !ARCH_MULTIPLATFORM && BROKEN
 	select OMAP_MBOX_FWK
 	help
 	  DSP/BIOS Bridge is designed for platforms that contain a GPP and
diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c
index 2f084e181d39..a1aca4416ca7 100644
--- a/drivers/staging/tidspbridge/core/dsp-clock.c
+++ b/drivers/staging/tidspbridge/core/dsp-clock.c
@@ -226,7 +226,7 @@ int dsp_clk_enable(enum dsp_clk_id clk_id)
 	case GPT_CLK:
 		status = omap_dm_timer_start(timer[clk_id - 1]);
 		break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
 	case MCBSP_CLK:
 		omap_mcbsp_request(MCBSP_ID(clk_id));
 		omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC);
@@ -302,7 +302,7 @@ int dsp_clk_disable(enum dsp_clk_id clk_id)
 	case GPT_CLK:
 		status = omap_dm_timer_stop(timer[clk_id - 1]);
 		break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
 	case MCBSP_CLK:
 		omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PRCM_SRC);
 		omap_mcbsp_free(MCBSP_ID(clk_id));
diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c
index f983915168b7..3496a77612ba 100644
--- a/drivers/staging/vt6655/bssdb.c
+++ b/drivers/staging/vt6655/bssdb.c
@@ -1026,7 +1026,7 @@ start:
 		pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1));
 	}
 
-	{
+	if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) {
 		pDevice->byReAssocCount++;
 		if ((pDevice->byReAssocCount > 10) && (pDevice->bLinkPass != true)) {  //10 sec timeout
 			printk("Re-association timeout!!!\n");
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 08b250f01dae..d170b6f9db7c 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -2434,6 +2434,7 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 	int             handled = 0;
 	unsigned char byData = 0;
 	int             ii = 0;
+	unsigned long flags;
 //    unsigned char byRSSI;
 
 	MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr);
@@ -2459,7 +2460,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 
 	handled = 1;
 	MACvIntDisable(pDevice->PortOffset);
-	spin_lock_irq(&pDevice->lock);
+
+	spin_lock_irqsave(&pDevice->lock, flags);
 
 	//Make sure current page is 0
 	VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel);
@@ -2700,7 +2702,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 		MACvSelectPage1(pDevice->PortOffset);
 	}
 
-	spin_unlock_irq(&pDevice->lock);
+	spin_unlock_irqrestore(&pDevice->lock, flags);
+
 	MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE);
 
 	return IRQ_RETVAL(handled);
diff --git a/drivers/staging/vt6656/baseband.c b/drivers/staging/vt6656/baseband.c
index 33fa76759bf1..55185336afe2 100644
--- a/drivers/staging/vt6656/baseband.c
+++ b/drivers/staging/vt6656/baseband.c
@@ -941,6 +941,7 @@ int BBbVT3184Init(struct vnt_private *pDevice)
     u8 *                   pbyAgc;
     u16                    wLengthAgc;
     u8                    abyArray[256];
+	u8 data;
 
     ntStatus = CONTROLnsRequestIn(pDevice,
                                   MESSAGE_TYPE_READ,
@@ -1106,6 +1107,16 @@ else {
     ControlvWriteByte(pDevice,MESSAGE_REQUEST_BBREG,0x0D,0x01);
 
     RFbRFTableDownload(pDevice);
+
+	/* Fix for TX USB resets from vendors driver */
+	CONTROLnsRequestIn(pDevice, MESSAGE_TYPE_READ, USB_REG4,
+		MESSAGE_REQUEST_MEM, sizeof(data), &data);
+
+	data |= 0x2;
+
+	CONTROLnsRequestOut(pDevice, MESSAGE_TYPE_WRITE, USB_REG4,
+		MESSAGE_REQUEST_MEM, sizeof(data), &data);
+
     return true;//ntStatus;
 }
 
@@ -1455,7 +1466,6 @@ void BBvUpdatePreEDThreshold(struct vnt_private *pDevice, int bScanning)
 
             if( bScanning )
             {   // need Max sensitivity //RSSI -69, -70,....
-                if(pDevice->byBBPreEDIndex == 0) break;
                 pDevice->byBBPreEDIndex = 0;
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x30); //CR206(0xCE)
@@ -1598,7 +1608,6 @@ void BBvUpdatePreEDThreshold(struct vnt_private *pDevice, int bScanning)
 
             if( bScanning )
             {   // need Max sensitivity  //RSSI -69, -70, ...
-                if(pDevice->byBBPreEDIndex == 0) break;
                 pDevice->byBBPreEDIndex = 0;
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x24); //CR206(0xCE)
@@ -1750,7 +1759,6 @@ void BBvUpdatePreEDThreshold(struct vnt_private *pDevice, int bScanning)
         case RF_VT3342A0: //RobertYu:20060627, testing table
             if( bScanning )
             {   // need Max sensitivity  //RSSI -67, -68, ...
-                if(pDevice->byBBPreEDIndex == 0) break;
                 pDevice->byBBPreEDIndex = 0;
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
                 ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x38); //CR206(0xCE)
diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c
index 24291aee58b5..0beb246af4ad 100644
--- a/drivers/staging/vt6656/card.c
+++ b/drivers/staging/vt6656/card.c
@@ -761,7 +761,7 @@ u64 CARDqGetNextTBTT(u64 qwTSF, u16 wBeaconInterval)
 
     uBeaconInterval = wBeaconInterval * 1024;
     // Next TBTT = ((local_current_TSF / beacon_interval) + 1 ) * beacon_interval
-	uLowNextTBTT = ((qwTSF & 0xffffffffU) >> 10) << 10;
+	uLowNextTBTT = ((qwTSF & 0xffffffffULL) >> 10) << 10;
 	uLowRemain = (uLowNextTBTT) % uBeaconInterval;
 	uHighRemain = ((0x80000000 % uBeaconInterval) * 2 * (u32)(qwTSF >> 32))
 		% uBeaconInterval;
diff --git a/drivers/staging/vt6656/iwctl.c b/drivers/staging/vt6656/iwctl.c
index d0cf7d8a20e5..8872e0f84f40 100644
--- a/drivers/staging/vt6656/iwctl.c
+++ b/drivers/staging/vt6656/iwctl.c
@@ -1634,6 +1634,9 @@ int iwctl_siwencodeext(struct net_device *dev, struct iw_request_info *info,
 	if (pMgmt == NULL)
 		return -EFAULT;
 
+	if (!(pDevice->flags & DEVICE_FLAGS_OPENED))
+		return -ENODEV;
+
 	buf = kzalloc(sizeof(struct viawget_wpa_param), GFP_KERNEL);
 	if (buf == NULL)
 		return -ENOMEM;
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 3a3fdc58b6da..06b966cf5bdd 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -1099,6 +1099,8 @@ static int device_close(struct net_device *dev)
     memset(pMgmt->abyCurrBSSID, 0, 6);
     pMgmt->eCurrState = WMAC_STATE_IDLE;
 
+	pDevice->flags &= ~DEVICE_FLAGS_OPENED;
+
     device_free_tx_bufs(pDevice);
     device_free_rx_bufs(pDevice);
     device_free_int_bufs(pDevice);
@@ -1110,7 +1112,6 @@ static int device_close(struct net_device *dev)
     usb_free_urb(pDevice->pInterruptURB);
 
     BSSvClearNodeDBTable(pDevice, 0);
-    pDevice->flags &=(~DEVICE_FLAGS_OPENED);
 
     DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "device_close2 \n");
 
diff --git a/drivers/staging/vt6656/rndis.h b/drivers/staging/vt6656/rndis.h
index 5e073062017a..5cf5e732a36f 100644
--- a/drivers/staging/vt6656/rndis.h
+++ b/drivers/staging/vt6656/rndis.h
@@ -66,6 +66,8 @@
 
 #define VIAUSB20_PACKET_HEADER          0x04
 
+#define USB_REG4	0x604
+
 typedef struct _CMD_MESSAGE
 {
     u8        byData[256];
diff --git a/drivers/staging/wlags49_h2/wl_priv.c b/drivers/staging/wlags49_h2/wl_priv.c
index c97e0e154d28..7e10dcdc3090 100644
--- a/drivers/staging/wlags49_h2/wl_priv.c
+++ b/drivers/staging/wlags49_h2/wl_priv.c
@@ -570,6 +570,7 @@ int wvlan_uil_put_info(struct uilreq *urq, struct wl_private *lp)
 	ltv_t                   *pLtv;
 	bool_t                  ltvAllocated = FALSE;
 	ENCSTRCT                sEncryption;
+	size_t			len;
 
 #ifdef USE_WDS
 	hcf_16                  hcfPort  = HCF_PORT_0;
@@ -686,7 +687,8 @@ int wvlan_uil_put_info(struct uilreq *urq, struct wl_private *lp)
 					break;
 				case CFG_CNF_OWN_NAME:
 					memset(lp->StationName, 0, sizeof(lp->StationName));
-					memcpy((void *)lp->StationName, (void *)&pLtv->u.u8[2], (size_t)pLtv->u.u16[0]);
+					len = min_t(size_t, pLtv->u.u16[0], sizeof(lp->StationName));
+					strlcpy(lp->StationName, &pLtv->u.u8[2], len);
 					pLtv->u.u16[0] = CNV_INT_TO_LITTLE(pLtv->u.u16[0]);
 					break;
 				case CFG_CNF_LOAD_BALANCING:
@@ -1783,6 +1785,7 @@ int wvlan_set_station_nickname(struct net_device *dev,
 {
 	struct wl_private *lp = wl_priv(dev);
 	unsigned long flags;
+	size_t len;
 	int         ret = 0;
 	/*------------------------------------------------------------------------*/
 
@@ -1793,8 +1796,8 @@ int wvlan_set_station_nickname(struct net_device *dev,
 	wl_lock(lp, &flags);
 
 	memset(lp->StationName, 0, sizeof(lp->StationName));
-
-	memcpy(lp->StationName, extra, wrqu->data.length);
+	len = min_t(size_t, wrqu->data.length, sizeof(lp->StationName));
+	strlcpy(lp->StationName, extra, len);
 
 	/* Commit the adapter parameters */
 	wl_apply(lp);
diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
index f82f7e69c8a5..288f58252a18 100644
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ b/drivers/staging/zsmalloc/zsmalloc-main.c
@@ -430,7 +430,12 @@ static struct page *get_next_page(struct page *page)
 	return next;
 }
 
-/* Encode <page, obj_idx> as a single handle value */
+/*
+ * Encode <page, obj_idx> as a single handle value.
+ * On hardware platforms with physical memory starting at 0x0 the pfn
+ * could be 0 so we ensure that the handle will never be 0 by adjusting the
+ * encoded obj_idx value before encoding.
+ */
 static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
 {
 	unsigned long handle;
@@ -441,17 +446,21 @@ static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
 	}
 
 	handle = page_to_pfn(page) << OBJ_INDEX_BITS;
-	handle |= (obj_idx & OBJ_INDEX_MASK);
+	handle |= ((obj_idx + 1) & OBJ_INDEX_MASK);
 
 	return (void *)handle;
 }
 
-/* Decode <page, obj_idx> pair from the given object handle */
+/*
+ * Decode <page, obj_idx> pair from the given object handle. We adjust the
+ * decoded obj_idx back to its original value since it was adjusted in
+ * obj_location_to_handle().
+ */
 static void obj_handle_to_location(unsigned long handle, struct page **page,
 				unsigned long *obj_idx)
 {
 	*page = pfn_to_page(handle >> OBJ_INDEX_BITS);
-	*obj_idx = handle & OBJ_INDEX_MASK;
+	*obj_idx = (handle & OBJ_INDEX_MASK) - 1;
 }
 
 static unsigned long obj_idx_to_offset(struct page *page,
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 4c1b8dbdcb36..651b5768862f 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -54,7 +54,7 @@
 static LIST_HEAD(g_tiqn_list);
 static LIST_HEAD(g_np_list);
 static DEFINE_SPINLOCK(tiqn_lock);
-static DEFINE_SPINLOCK(np_lock);
+static DEFINE_MUTEX(np_lock);
 
 static struct idr tiqn_idr;
 struct idr sess_idr;
@@ -303,6 +303,9 @@ bool iscsit_check_np_match(
 	return false;
 }
 
+/*
+ * Called with mutex np_lock held
+ */
 static struct iscsi_np *iscsit_get_np(
 	struct __kernel_sockaddr_storage *sockaddr,
 	int network_transport)
@@ -310,11 +313,10 @@ static struct iscsi_np *iscsit_get_np(
 	struct iscsi_np *np;
 	bool match;
 
-	spin_lock_bh(&np_lock);
 	list_for_each_entry(np, &g_np_list, np_list) {
-		spin_lock(&np->np_thread_lock);
+		spin_lock_bh(&np->np_thread_lock);
 		if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) {
-			spin_unlock(&np->np_thread_lock);
+			spin_unlock_bh(&np->np_thread_lock);
 			continue;
 		}
 
@@ -326,13 +328,11 @@ static struct iscsi_np *iscsit_get_np(
 			 * while iscsi_tpg_add_network_portal() is called.
 			 */
 			np->np_exports++;
-			spin_unlock(&np->np_thread_lock);
-			spin_unlock_bh(&np_lock);
+			spin_unlock_bh(&np->np_thread_lock);
 			return np;
 		}
-		spin_unlock(&np->np_thread_lock);
+		spin_unlock_bh(&np->np_thread_lock);
 	}
-	spin_unlock_bh(&np_lock);
 
 	return NULL;
 }
@@ -346,16 +346,22 @@ struct iscsi_np *iscsit_add_np(
 	struct sockaddr_in6 *sock_in6;
 	struct iscsi_np *np;
 	int ret;
+
+	mutex_lock(&np_lock);
+
 	/*
 	 * Locate the existing struct iscsi_np if already active..
 	 */
 	np = iscsit_get_np(sockaddr, network_transport);
-	if (np)
+	if (np) {
+		mutex_unlock(&np_lock);
 		return np;
+	}
 
 	np = kzalloc(sizeof(struct iscsi_np), GFP_KERNEL);
 	if (!np) {
 		pr_err("Unable to allocate memory for struct iscsi_np\n");
+		mutex_unlock(&np_lock);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -378,6 +384,7 @@ struct iscsi_np *iscsit_add_np(
 	ret = iscsi_target_setup_login_socket(np, sockaddr);
 	if (ret != 0) {
 		kfree(np);
+		mutex_unlock(&np_lock);
 		return ERR_PTR(ret);
 	}
 
@@ -386,6 +393,7 @@ struct iscsi_np *iscsit_add_np(
 		pr_err("Unable to create kthread: iscsi_np\n");
 		ret = PTR_ERR(np->np_thread);
 		kfree(np);
+		mutex_unlock(&np_lock);
 		return ERR_PTR(ret);
 	}
 	/*
@@ -396,10 +404,10 @@ struct iscsi_np *iscsit_add_np(
 	 * point because iscsi_np has not been added to g_np_list yet.
 	 */
 	np->np_exports = 1;
+	np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 
-	spin_lock_bh(&np_lock);
 	list_add_tail(&np->np_list, &g_np_list);
-	spin_unlock_bh(&np_lock);
+	mutex_unlock(&np_lock);
 
 	pr_debug("CORE[0] - Added Network Portal: %s:%hu on %s\n",
 		np->np_ip, np->np_port, np->np_transport->name);
@@ -452,6 +460,7 @@ int iscsit_del_np(struct iscsi_np *np)
 	spin_lock_bh(&np->np_thread_lock);
 	np->np_exports--;
 	if (np->np_exports) {
+		np->enabled = true;
 		spin_unlock_bh(&np->np_thread_lock);
 		return 0;
 	}
@@ -469,9 +478,9 @@ int iscsit_del_np(struct iscsi_np *np)
 
 	np->np_transport->iscsit_free_np(np);
 
-	spin_lock_bh(&np_lock);
+	mutex_lock(&np_lock);
 	list_del(&np->np_list);
-	spin_unlock_bh(&np_lock);
+	mutex_unlock(&np_lock);
 
 	pr_debug("CORE[0] - Removed Network Portal: %s:%hu on %s\n",
 		np->np_ip, np->np_port, np->np_transport->name);
@@ -838,24 +847,22 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	if (((hdr->flags & ISCSI_FLAG_CMD_READ) ||
 	     (hdr->flags & ISCSI_FLAG_CMD_WRITE)) && !hdr->data_length) {
 		/*
-		 * Vmware ESX v3.0 uses a modified Cisco Initiator (v3.4.2)
-		 * that adds support for RESERVE/RELEASE.  There is a bug
-		 * add with this new functionality that sets R/W bits when
-		 * neither CDB carries any READ or WRITE datapayloads.
+		 * From RFC-3720 Section 10.3.1:
+		 *
+		 * "Either or both of R and W MAY be 1 when either the
+		 *  Expected Data Transfer Length and/or Bidirectional Read
+		 *  Expected Data Transfer Length are 0"
+		 *
+		 * For this case, go ahead and clear the unnecssary bits
+		 * to avoid any confusion with ->data_direction.
 		 */
-		if ((hdr->cdb[0] == 0x16) || (hdr->cdb[0] == 0x17)) {
-			hdr->flags &= ~ISCSI_FLAG_CMD_READ;
-			hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
-			goto done;
-		}
+		hdr->flags &= ~ISCSI_FLAG_CMD_READ;
+		hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
 
-		pr_err("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
+		pr_warn("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
 			" set when Expected Data Transfer Length is 0 for"
-			" CDB: 0x%02x. Bad iSCSI Initiator.\n", hdr->cdb[0]);
-		return iscsit_add_reject_cmd(cmd,
-					     ISCSI_REASON_BOOKMARK_INVALID, buf);
+			" CDB: 0x%02x, Fixing up flags\n", hdr->cdb[0]);
 	}
-done:
 
 	if (!(hdr->flags & ISCSI_FLAG_CMD_READ) &&
 	    !(hdr->flags & ISCSI_FLAG_CMD_WRITE) && (hdr->data_length != 0)) {
@@ -1306,7 +1313,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 	if (cmd->data_direction != DMA_TO_DEVICE) {
 		pr_err("Command ITT: 0x%08x received DataOUT for a"
 			" NON-WRITE command.\n", cmd->init_task_tag);
-		return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf);
+		return iscsit_dump_data_payload(conn, payload_length, 1);
 	}
 	se_cmd = &cmd->se_cmd;
 	iscsit_mod_dataout_timer(cmd);
@@ -2448,6 +2455,7 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 {
 	struct iscsi_cmd *cmd;
 	struct iscsi_conn *conn_p;
+	bool found = false;
 
 	/*
 	 * Only send a Asynchronous Message on connections whos network
@@ -2456,11 +2464,12 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 	list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) {
 		if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) {
 			iscsit_inc_conn_usage_count(conn_p);
+			found = true;
 			break;
 		}
 	}
 
-	if (!conn_p)
+	if (!found)
 		return;
 
 	cmd = iscsit_allocate_cmd(conn_p, GFP_ATOMIC);
@@ -3647,7 +3656,7 @@ iscsit_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state
 		break;
 	case ISTATE_REMOVE:
 		spin_lock_bh(&conn->cmd_lock);
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_cmd(cmd, false);
@@ -4093,7 +4102,7 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn)
 	spin_lock_bh(&conn->cmd_lock);
 	list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_increment_maxcmdsn(cmd, sess);
@@ -4138,7 +4147,9 @@ int iscsit_close_connection(
 	iscsit_stop_timers_for_cmds(conn);
 	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
-	iscsit_free_queue_reqs_for_conn(conn);
+
+	if (conn->conn_transport->iscsit_wait_conn)
+		conn->conn_transport->iscsit_wait_conn(conn);
 
 	/*
 	 * During Connection recovery drop unacknowledged out of order
@@ -4156,6 +4167,7 @@ int iscsit_close_connection(
 		iscsit_clear_ooo_cmdsns_for_conn(conn);
 		iscsit_release_commands_from_conn(conn);
 	}
+	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
 	 * Handle decrementing session or connection usage count if
@@ -4441,6 +4453,7 @@ static void iscsit_logout_post_handler_diffcid(
 {
 	struct iscsi_conn *l_conn;
 	struct iscsi_session *sess = conn->sess;
+	bool conn_found = false;
 
 	if (!sess)
 		return;
@@ -4449,12 +4462,13 @@ static void iscsit_logout_post_handler_diffcid(
 	list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) {
 		if (l_conn->cid == cid) {
 			iscsit_inc_conn_usage_count(l_conn);
+			conn_found = true;
 			break;
 		}
 	}
 	spin_unlock_bh(&sess->conn_lock);
 
-	if (!l_conn)
+	if (!conn_found)
 		return;
 
 	if (l_conn->sock)
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index cee17543278c..3c9a8dfd1c2e 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -148,6 +148,7 @@ static int chap_server_compute_md5(
 	unsigned char client_digest[MD5_SIGNATURE_SIZE];
 	unsigned char server_digest[MD5_SIGNATURE_SIZE];
 	unsigned char chap_n[MAX_CHAP_N_SIZE], chap_r[MAX_RESPONSE_LENGTH];
+	size_t compare_len;
 	struct iscsi_chap *chap = conn->auth_protocol;
 	struct crypto_hash *tfm;
 	struct hash_desc desc;
@@ -186,7 +187,9 @@ static int chap_server_compute_md5(
 		goto out;
 	}
 
-	if (memcmp(chap_n, auth->userid, strlen(auth->userid)) != 0) {
+	/* Include the terminating NULL in the compare */
+	compare_len = strlen(auth->userid) + 1;
+	if (strncmp(chap_n, auth->userid, compare_len) != 0) {
 		pr_err("CHAP_N values do not match!\n");
 		goto out;
 	}
@@ -313,6 +316,16 @@ static int chap_server_compute_md5(
 		goto out;
 	}
 	/*
+	 * During mutual authentication, the CHAP_C generated by the
+	 * initiator must not match the original CHAP_C generated by
+	 * the target.
+	 */
+	if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+		pr_err("initiator CHAP_C matches target CHAP_C, failing"
+		       " login attempt\n");
+		goto out;
+	}
+	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
 	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 421344da8b51..c45b3365d63d 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1650,6 +1650,11 @@ static int lio_queue_status(struct se_cmd *se_cmd)
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
 
 	cmd->i_state = ISTATE_SEND_STATUS;
+
+	if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
+		iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
+		return 0;
+	}
 	cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
 
 	return 0;
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 8907dcdc0db9..e117870eb445 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -760,6 +760,7 @@ struct iscsi_np {
 	int			np_ip_proto;
 	int			np_sock_type;
 	enum np_thread_state_table np_thread_state;
+	bool                    enabled;
 	enum iscsi_timer_flags_table np_login_timer_flags;
 	u32			np_exports;
 	enum np_flags_table	np_flags;
diff --git a/drivers/target/iscsi/iscsi_target_device.c b/drivers/target/iscsi/iscsi_target_device.c
index 1b74033510a0..4edcc47c0634 100644
--- a/drivers/target/iscsi/iscsi_target_device.c
+++ b/drivers/target/iscsi/iscsi_target_device.c
@@ -60,11 +60,7 @@ void iscsit_increment_maxcmdsn(struct iscsi_cmd *cmd, struct iscsi_session *sess
 
 	cmd->maxcmdsn_inc = 1;
 
-	if (!mutex_trylock(&sess->cmdsn_mutex)) {
-		sess->max_cmd_sn += 1;
-		pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
-		return;
-	}
+	mutex_lock(&sess->cmdsn_mutex);
 	sess->max_cmd_sn += 1;
 	pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
 	mutex_unlock(&sess->cmdsn_mutex);
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 45a5afd5ea13..0d2d013076c4 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -140,7 +140,7 @@ void iscsit_free_connection_recovery_entires(struct iscsi_session *sess)
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -162,7 +162,7 @@ void iscsit_free_connection_recovery_entires(struct iscsi_session *sess)
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -218,7 +218,7 @@ int iscsit_remove_cmd_from_connection_recovery(
 	}
 	cr = cmd->cr;
 
-	list_del(&cmd->i_conn_node);
+	list_del_init(&cmd->i_conn_node);
 	return --cr->cmd_count;
 }
 
@@ -299,7 +299,7 @@ int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *conn)
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN))
 			continue;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 
 		spin_unlock_bh(&conn->cmd_lock);
 		iscsit_free_cmd(cmd, true);
@@ -337,7 +337,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 	/*
 	 * Only perform connection recovery on ISCSI_OP_SCSI_CMD or
 	 * ISCSI_OP_NOOP_OUT opcodes.  For all other opcodes call
-	 * list_del(&cmd->i_conn_node); to release the command to the
+	 * list_del_init(&cmd->i_conn_node); to release the command to the
 	 * session pool and remove it from the connection's list.
 	 *
 	 * Also stop the DataOUT timer, which will be restarted after
@@ -353,7 +353,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 				" CID: %hu\n", cmd->iscsi_opcode,
 				cmd->init_task_tag, cmd->cmd_sn, conn->cid);
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -373,7 +373,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 		 */
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd &&
 		     iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) {
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -395,7 +395,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 
 		cmd->sess = conn->sess;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_all_datain_reqs(cmd);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index bc788c52b6cc..e14e105acff8 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -250,6 +250,28 @@ static void iscsi_login_set_conn_values(
 	mutex_unlock(&auth_id_lock);
 }
 
+static __printf(2, 3) int iscsi_change_param_sprintf(
+	struct iscsi_conn *conn,
+	const char *fmt, ...)
+{
+	va_list args;
+	unsigned char buf[64];
+
+	memset(buf, 0, sizeof buf);
+
+	va_start(args, fmt);
+	vsnprintf(buf, sizeof buf, fmt, args);
+	va_end(args);
+
+	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
+		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		return -1;
+	}
+
+	return 0;
+}
+
 /*
  *	This is the leading connection of a new session,
  *	or session reinstatement.
@@ -339,7 +361,6 @@ static int iscsi_login_zero_tsih_s2(
 {
 	struct iscsi_node_attrib *na;
 	struct iscsi_session *sess = conn->sess;
-	unsigned char buf[32];
 	bool iser = false;
 
 	sess->tpg = conn->tpg;
@@ -380,26 +401,16 @@ static int iscsi_login_zero_tsih_s2(
 	 *
 	 * In our case, we have already located the struct iscsi_tiqn at this point.
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
 		return -1;
-	}
 
 	/*
 	 * Workaround for Initiators that have broken connection recovery logic.
 	 *
 	 * "We would really like to get rid of this." Linux-iSCSI.org team
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "ErrorRecoveryLevel=%d", na->default_erl);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "ErrorRecoveryLevel=%d", na->default_erl))
 		return -1;
-	}
 
 	if (iscsi_login_disable_FIM_keys(conn->param_list, conn) < 0)
 		return -1;
@@ -411,12 +422,9 @@ static int iscsi_login_zero_tsih_s2(
 		unsigned long mrdsl, off;
 		int rc;
 
-		sprintf(buf, "RDMAExtensions=Yes");
-		if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		if (iscsi_change_param_sprintf(conn, "RDMAExtensions=Yes"))
 			return -1;
-		}
+
 		/*
 		 * Make MaxRecvDataSegmentLength PAGE_SIZE aligned for
 		 * Immediate Data + Unsolicitied Data-OUT if necessary..
@@ -446,12 +454,8 @@ static int iscsi_login_zero_tsih_s2(
 		pr_warn("Aligning ISER MaxRecvDataSegmentLength: %lu down"
 			" to PAGE_SIZE\n", mrdsl);
 
-		sprintf(buf, "MaxRecvDataSegmentLength=%lu\n", mrdsl);
-		if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		if (iscsi_change_param_sprintf(conn, "MaxRecvDataSegmentLength=%lu\n", mrdsl))
 			return -1;
-		}
 	}
 
 	return 0;
@@ -593,13 +597,8 @@ static int iscsi_login_non_zero_tsih_s2(
 	 *
 	 * In our case, we have already located the struct iscsi_tiqn at this point.
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
 		return -1;
-	}
 
 	return iscsi_login_disable_FIM_keys(conn->param_list, conn);
 }
@@ -984,6 +983,7 @@ int iscsi_target_setup_login_socket(
 	}
 
 	np->np_transport = t;
+	np->enabled = true;
 	return 0;
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index cd5018ff9cd7..72d9dec991c0 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -90,7 +90,7 @@ int extract_param(
 	if (len < 0)
 		return -1;
 
-	if (len > max_length) {
+	if (len >= max_length) {
 		pr_err("Length of input: %d exceeds max_length:"
 			" %d\n", len, max_length);
 		return -1;
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e38222191a33..30be6c9bdbc6 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -603,7 +603,7 @@ int iscsi_copy_param_list(
 	param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL);
 	if (!param_list) {
 		pr_err("Unable to allocate memory for struct iscsi_param_list.\n");
-		goto err_out;
+		return -1;
 	}
 	INIT_LIST_HEAD(&param_list->param_list);
 	INIT_LIST_HEAD(&param_list->extra_response_list);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 439260b7d87f..75a4e83842c2 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -138,7 +138,7 @@ struct iscsi_portal_group *iscsit_get_tpg_from_np(
 	list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
 
 		spin_lock(&tpg->tpg_state_lock);
-		if (tpg->tpg_state == TPG_STATE_FREE) {
+		if (tpg->tpg_state != TPG_STATE_ACTIVE) {
 			spin_unlock(&tpg->tpg_state_lock);
 			continue;
 		}
@@ -175,13 +175,16 @@ void iscsit_put_tpg(struct iscsi_portal_group *tpg)
 
 static void iscsit_clear_tpg_np_login_thread(
 	struct iscsi_tpg_np *tpg_np,
-	struct iscsi_portal_group *tpg)
+	struct iscsi_portal_group *tpg,
+	bool shutdown)
 {
 	if (!tpg_np->tpg_np) {
 		pr_err("struct iscsi_tpg_np->tpg_np is NULL!\n");
 		return;
 	}
 
+	if (shutdown)
+		tpg_np->tpg_np->enabled = false;
 	iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg);
 }
 
@@ -197,7 +200,7 @@ void iscsit_clear_tpg_np_login_threads(
 			continue;
 		}
 		spin_unlock(&tpg->tpg_np_lock);
-		iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+		iscsit_clear_tpg_np_login_thread(tpg_np, tpg, false);
 		spin_lock(&tpg->tpg_np_lock);
 	}
 	spin_unlock(&tpg->tpg_np_lock);
@@ -520,7 +523,7 @@ static int iscsit_tpg_release_np(
 	struct iscsi_portal_group *tpg,
 	struct iscsi_np *np)
 {
-	iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+	iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true);
 
 	pr_debug("CORE[%s] - Removed Network Portal: %s:%hu,%hu on %s\n",
 		tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt,
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 96e7fdbba9fc..c9790f6fdd89 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -734,7 +734,7 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 		 * Fallthrough
 		 */
 	case ISCSI_OP_SCSI_TMFUNC:
-		rc = transport_generic_free_cmd(&cmd->se_cmd, 1);
+		rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
 		if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
 			__iscsit_free_cmd(cmd, true, shutdown);
 			target_put_sess_cmd(se_cmd->se_sess, se_cmd);
@@ -750,7 +750,7 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 			se_cmd = &cmd->se_cmd;
 			__iscsit_free_cmd(cmd, true, shutdown);
 
-			rc = transport_generic_free_cmd(&cmd->se_cmd, 1);
+			rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
 			if (!rc && shutdown && se_cmd->se_sess) {
 				__iscsit_free_cmd(cmd, true, shutdown);
 				target_put_sess_cmd(se_cmd->se_sess, se_cmd);
@@ -1288,6 +1288,8 @@ int iscsit_tx_login_rsp(struct iscsi_conn *conn, u8 status_class, u8 status_deta
 	login->login_failed = 1;
 	iscsit_collect_login_stats(conn, status_class, status_detail);
 
+	memset(&login->rsp[0], 0, ISCSI_HDR_LEN);
+
 	hdr	= (struct iscsi_login_rsp *)&login->rsp[0];
 	hdr->opcode		= ISCSI_OP_LOGIN_RSP;
 	hdr->status_class	= status_class;
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index f608fbc14a27..df58a67f81e0 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -409,7 +409,16 @@ static inline int core_alua_state_standby(
 	case REPORT_LUNS:
 	case RECEIVE_DIAGNOSTIC:
 	case SEND_DIAGNOSTIC:
+	case READ_CAPACITY:
 		return 0;
+	case SERVICE_ACTION_IN:
+		switch (cdb[1] & 0x1f) {
+		case SAI_READ_CAPACITY_16:
+			return 0;
+		default:
+			*alua_ascq = ASCQ_04H_ALUA_TG_PT_STANDBY;
+			return 1;
+		}
 	case MAINTENANCE_IN:
 		switch (cdb[1] & 0x1f) {
 		case MI_REPORT_TARGET_PGS:
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 4a8bd36d3958..8cda4080b597 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2034,6 +2034,11 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 			" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
 		return -EINVAL;
 	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("Unable to set alua_access_state while device is"
+		       " not configured\n");
+		return -ENODEV;
+	}
 
 	ret = strict_strtoul(page, 0, &tmp);
 	if (ret < 0) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 4630481b6043..2be407e22eb4 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -614,6 +614,7 @@ void core_dev_unexport(
 	dev->export_count--;
 	spin_unlock(&hba->device_lock);
 
+	lun->lun_sep = NULL;
 	lun->lun_se_dev = NULL;
 }
 
@@ -796,10 +797,10 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 		pr_err("emulate_write_cache not supported for pSCSI\n");
 		return -EINVAL;
 	}
-	if (dev->transport->get_write_cache) {
-		pr_warn("emulate_write_cache cannot be changed when underlying"
-			" HW reports WriteCacheEnabled, ignoring request\n");
-		return 0;
+	if (flag &&
+	    dev->transport->get_write_cache) {
+		pr_err("emulate_write_cache not supported for this device\n");
+		return -EINVAL;
 	}
 
 	dev->dev_attrib.emulate_write_cache = flag;
@@ -1078,6 +1079,11 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 	dev->dev_attrib.block_size = block_size;
 	pr_debug("dev[%p]: SE Device block_size changed to %u\n",
 			dev, block_size);
+
+	if (dev->dev_attrib.max_bytes_per_io)
+		dev->dev_attrib.hw_max_sectors =
+			dev->dev_attrib.max_bytes_per_io / block_size;
+
 	return 0;
 }
 
@@ -1287,7 +1293,8 @@ int core_dev_add_initiator_node_lun_acl(
 	 * Check to see if there are any existing persistent reservation APTPL
 	 * pre-registrations that need to be enabled for this LUN ACL..
 	 */
-	core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl);
+	core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl,
+					    lacl->mapped_lun);
 	return 0;
 }
 
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index b11890d85120..3b2879316b87 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -66,9 +66,8 @@ static int fd_attach_hba(struct se_hba *hba, u32 host_id)
 	pr_debug("CORE_HBA[%d] - TCM FILEIO HBA Driver %s on Generic"
 		" Target Core Stack %s\n", hba->hba_id, FD_VERSION,
 		TARGET_CORE_MOD_VERSION);
-	pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic"
-		" MaxSectors: %u\n",
-		hba->hba_id, fd_host->fd_host_id, FD_MAX_SECTORS);
+	pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic\n",
+		hba->hba_id, fd_host->fd_host_id);
 
 	return 0;
 }
@@ -220,7 +219,8 @@ static int fd_configure_device(struct se_device *dev)
 	}
 
 	dev->dev_attrib.hw_block_size = fd_dev->fd_block_size;
-	dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS;
+	dev->dev_attrib.max_bytes_per_io = FD_MAX_BYTES;
+	dev->dev_attrib.hw_max_sectors = FD_MAX_BYTES / fd_dev->fd_block_size;
 	dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
 
 	if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 37ffc5bd2399..d7772c167685 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -7,7 +7,10 @@
 #define FD_DEVICE_QUEUE_DEPTH	32
 #define FD_MAX_DEVICE_QUEUE_DEPTH 128
 #define FD_BLOCKSIZE		512
-#define FD_MAX_SECTORS		2048
+/*
+ * Limited by the number of iovecs (2048) per vfs_[writev,readv] call
+ */
+#define FD_MAX_BYTES		8388608
 
 #define RRF_EMULATE_CDB		0x01
 #define RRF_GOT_LBA		0x02
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 04a74938bb43..27ec6e4d1c7c 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -945,10 +945,10 @@ int core_scsi3_check_aptpl_registration(
 	struct se_device *dev,
 	struct se_portal_group *tpg,
 	struct se_lun *lun,
-	struct se_lun_acl *lun_acl)
+	struct se_node_acl *nacl,
+	u32 mapped_lun)
 {
-	struct se_node_acl *nacl = lun_acl->se_lun_nacl;
-	struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun];
+	struct se_dev_entry *deve = nacl->device_list[mapped_lun];
 
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return 0;
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index b4a004247ab2..ea9220de1dff 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -55,7 +55,7 @@ extern int core_scsi3_alloc_aptpl_registration(
 			unsigned char *, u16, u32, int, int, u8);
 extern int core_scsi3_check_aptpl_registration(struct se_device *,
 			struct se_portal_group *, struct se_lun *,
-			struct se_lun_acl *);
+			struct se_node_acl *, u32);
 extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *,
 					     struct se_node_acl *);
 extern void core_scsi3_free_all_registrations(struct se_device *);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index e992b27aa090..3250ba2594e0 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -134,10 +134,10 @@ static int pscsi_pmode_enable_hba(struct se_hba *hba, unsigned long mode_flag)
 	 * pSCSI Host ID and enable for phba mode
 	 */
 	sh = scsi_host_lookup(phv->phv_host_id);
-	if (IS_ERR(sh)) {
+	if (!sh) {
 		pr_err("pSCSI: Unable to locate SCSI Host for"
 			" phv_host_id: %d\n", phv->phv_host_id);
-		return PTR_ERR(sh);
+		return -EINVAL;
 	}
 
 	phv->phv_lld_host = sh;
@@ -515,10 +515,10 @@ static int pscsi_configure_device(struct se_device *dev)
 			sh = phv->phv_lld_host;
 		} else {
 			sh = scsi_host_lookup(pdv->pdv_host_id);
-			if (IS_ERR(sh)) {
+			if (!sh) {
 				pr_err("pSCSI: Unable to locate"
 					" pdv_host_id: %d\n", pdv->pdv_host_id);
-				return PTR_ERR(sh);
+				return -EINVAL;
 			}
 		}
 	} else {
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 0921a64b5550..5c3b6778c22a 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -174,7 +174,7 @@ static int rd_build_device_space(struct rd_dev *rd_dev)
 						- 1;
 
 		for (j = 0; j < sg_per_table; j++) {
-			pg = alloc_pages(GFP_KERNEL, 0);
+			pg = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
 			if (!pg) {
 				pr_err("Unable to allocate scatterlist"
 					" pages for struct rd_dev_sg_table\n");
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index bbc5b0ee2bdc..0ef75fb0ecba 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -63,7 +63,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8);
 	return 0;
 }
 
@@ -101,7 +101,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 32);
 	return 0;
 }
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 9fabbf7214cd..34254b2ec466 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -628,6 +628,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 	unsigned char buf[SE_INQUIRY_BUF];
 	sense_reason_t ret;
 	int p;
+	int len = 0;
 
 	memset(buf, 0, SE_INQUIRY_BUF);
 
@@ -645,6 +646,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		}
 
 		ret = spc_emulate_inquiry_std(cmd, buf);
+		len = buf[4] + 5;
 		goto out;
 	}
 
@@ -652,6 +654,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		if (cdb[2] == evpd_handlers[p].page) {
 			buf[1] = cdb[2];
 			ret = evpd_handlers[p].emulate(cmd, buf);
+			len = get_unaligned_be16(&buf[2]) + 4;
 			goto out;
 		}
 	}
@@ -667,7 +670,7 @@ out:
 	}
 
 	if (!ret)
-		target_complete_cmd(cmd, GOOD);
+		target_complete_cmd_with_length(cmd, GOOD, len);
 	return ret;
 }
 
@@ -985,7 +988,7 @@ set_length:
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, length);
 	return 0;
 }
 
@@ -1162,7 +1165,7 @@ done:
 	buf[3] = (lun_count & 0xff);
 	transport_kunmap_data_sg(cmd);
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
 	return 0;
 }
 EXPORT_SYMBOL(spc_emulate_report_luns);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index aac9d2727e3c..8572207e3d4d 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -40,6 +40,7 @@
 #include <target/target_core_fabric.h>
 
 #include "target_core_internal.h"
+#include "target_core_pr.h"
 
 extern struct se_device *g_lun0_dev;
 
@@ -165,6 +166,13 @@ void core_tpg_add_node_to_devs(
 
 		core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun,
 				lun_access, acl, tpg);
+		/*
+		 * Check to see if there are any existing persistent reservation
+		 * APTPL pre-registrations that need to be enabled for this dynamic
+		 * LUN ACL now..
+		 */
+		core_scsi3_check_aptpl_registration(dev, tpg, lun, acl,
+						    lun->unpacked_lun);
 		spin_lock(&tpg->tpg_lun_lock);
 	}
 	spin_unlock(&tpg->tpg_lun_lock);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 21e315874a54..dcc5daa0ff1c 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -488,7 +488,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists)
 
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return 1;
 	}
 
@@ -617,7 +617,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	if (cmd->transport_state & CMD_T_ABORTED &&
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	} else if (cmd->transport_state & CMD_T_FAILED) {
 		INIT_WORK(&cmd->work, target_complete_failure_work);
@@ -633,6 +633,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
+void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
+{
+	if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
+		if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+			cmd->residual_count += cmd->data_length - length;
+		} else {
+			cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
+			cmd->residual_count = cmd->data_length - length;
+		}
+
+		cmd->data_length = length;
+	}
+
+	target_complete_cmd(cmd, scsi_status);
+}
+EXPORT_SYMBOL(target_complete_cmd_with_length);
+
 static void target_add_to_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -1688,7 +1705,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 			cmd->se_tfo->get_task_tag(cmd));
 
 		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	}
 
@@ -1771,8 +1788,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
 
 	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
 		ret = cmd->se_tfo->queue_status(cmd);
-		if (ret)
-			goto out;
+		goto out;
 	}
 
 	switch (cmd->data_direction) {
@@ -2112,7 +2128,7 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 	 * and let it call back once the write buffers are ready.
 	 */
 	target_add_to_state_list(cmd);
-	if (cmd->data_direction != DMA_TO_DEVICE) {
+	if (cmd->data_direction != DMA_TO_DEVICE || cmd->data_length == 0) {
 		target_execute_cmd(cmd);
 		return 0;
 	}
@@ -2877,6 +2893,12 @@ static void target_tmr_work(struct work_struct *work)
 int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd->transport_state |= CMD_T_ACTIVE;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index 4859505ae2ed..639fdb395fb7 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -68,6 +68,7 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport)
 
 	if (tport) {
 		tport->tpg = tpg;
+		tpg->tport = tport;
 		return tport;
 	}
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 5e3c02554d99..e92e1dcb6e3f 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -17,8 +17,30 @@ if THERMAL
 
 config THERMAL_HWMON
 	bool
+	prompt "Expose thermal sensors as hwmon device"
 	depends on HWMON=y || HWMON=THERMAL
 	default y
+	help
+	  In case a sensor is registered with the thermal
+	  framework, this option will also register it
+	  as a hwmon. The sensor will then have the common
+	  hwmon sysfs interface.
+
+	  Say 'Y' here if you want all thermal sensors to
+	  have hwmon sysfs interface too.
+
+config THERMAL_OF
+	bool
+	prompt "APIs to parse thermal data out of device tree"
+	depends on OF
+	default y
+	help
+	  This options provides helpers to add the support to
+	  read and parse thermal data definitions out of the
+	  device tree blob.
+
+	  Say 'Y' here if you need to build thermal infrastructure
+	  based on device tree.
 
 choice
 	prompt "Default Thermal governor"
@@ -69,6 +91,7 @@ config THERMAL_GOV_USER_SPACE
 config CPU_THERMAL
 	bool "generic cpu cooling support"
 	depends on CPU_FREQ
+	depends on THERMAL_OF
 	select CPU_FREQ_TABLE
 	help
 	  This implements the generic cpu cooling mechanism through frequency
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c054d410ac3f..71f8eef49c1c 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -5,6 +5,10 @@
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
 thermal_sys-y			+= thermal_core.o
 
+# interface to/from other layers providing sensors
+thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
+thermal_sys-$(CONFIG_THERMAL_OF)		+= of-thermal.o
+
 # governors
 thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
 thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index c94bf2e5de62..4246262c4bd2 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -167,13 +167,20 @@ static int get_property(unsigned int cpu, unsigned long input,
 			continue;
 
 		/* get the frequency order */
-		if (freq != CPUFREQ_ENTRY_INVALID && descend != -1)
+		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
 			descend = !!(freq > table[i].frequency);
 
 		freq = table[i].frequency;
 		max_level++;
 	}
 
+	/* No valid cpu frequency entry */
+	if (max_level == 0)
+		return -EINVAL;
+
+	/* max_level is an index, not a counter */
+	max_level--;
+
 	/* get max level */
 	if (property == GET_MAXL) {
 		*output = (unsigned int)max_level;
@@ -181,7 +188,7 @@ static int get_property(unsigned int cpu, unsigned long input,
 	}
 
 	if (property == GET_FREQ)
-		level = descend ? input : (max_level - input - 1);
+		level = descend ? input : (max_level - input);
 
 	for (i = 0, j = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
 		/* ignore invalid entry */
@@ -197,7 +204,7 @@ static int get_property(unsigned int cpu, unsigned long input,
 
 		if (property == GET_LEVEL && (unsigned int)input == freq) {
 			/* get level by frequency */
-			*output = descend ? j : (max_level - j - 1);
+			*output = descend ? j : (max_level - j);
 			return 0;
 		}
 		if (property == GET_FREQ && level == j) {
@@ -322,6 +329,8 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 
 	if (cpumask_test_cpu(policy->cpu, &notify_device->allowed_cpus))
 		max_freq = notify_device->cpufreq_val;
+	else
+		return 0;
 
 	/* Never exceed user_policy.max */
 	if (max_freq > policy->user_policy.max)
@@ -415,18 +424,21 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
 };
 
 /**
- * cpufreq_cooling_register - function to create cpufreq cooling device.
+ * __cpufreq_cooling_register - helper function to create cpufreq cooling device
+ * @np: a valid struct device_node to the cooling device device tree node
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
- * cooling devices.
+ * cooling devices. It also gives the opportunity to link the cooling device
+ * with a device tree node, in order to bind it via the thermal DT code.
  *
  * Return: a valid struct thermal_cooling_device pointer on success,
  * on failure, it returns a corresponding ERR_PTR().
  */
-struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+static struct thermal_cooling_device *
+__cpufreq_cooling_register(struct device_node *np,
+			   const struct cpumask *clip_cpus)
 {
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev = NULL;
@@ -465,12 +477,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
 		 cpufreq_dev->id);
 
-	cool_dev = thermal_cooling_device_register(dev_name, cpufreq_dev,
-						   &cpufreq_cooling_ops);
-	if (!cool_dev) {
+	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
+						      &cpufreq_cooling_ops);
+	if (IS_ERR(cool_dev)) {
 		release_idr(&cpufreq_idr, cpufreq_dev->id);
 		kfree(cpufreq_dev);
-		return ERR_PTR(-EINVAL);
+		return cool_dev;
 	}
 	cpufreq_dev->cool_dev = cool_dev;
 	cpufreq_dev->cpufreq_state = 0;
@@ -486,9 +498,50 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
 
 	return cool_dev;
 }
+
+/**
+ * cpufreq_cooling_register - function to create cpufreq cooling device.
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ *
+ * This interface function registers the cpufreq cooling device with the name
+ * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
+ * cooling devices.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+cpufreq_cooling_register(const struct cpumask *clip_cpus)
+{
+	return __cpufreq_cooling_register(NULL, clip_cpus);
+}
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
 /**
+ * of_cpufreq_cooling_register - function to create cpufreq cooling device.
+ * @np: a valid struct device_node to the cooling device device tree node
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ *
+ * This interface function registers the cpufreq cooling device with the name
+ * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
+ * cooling devices. Using this API, the cpufreq cooling device will be
+ * linked to the device tree node provided.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+			    const struct cpumask *clip_cpus)
+{
+	if (!np)
+		return ERR_PTR(-EINVAL);
+
+	return __cpufreq_cooling_register(np, clip_cpus);
+}
+EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
+
+/**
  * cpufreq_cooling_unregister - function to remove cpufreq cooling device.
  * @cdev: thermal cooling device pointer.
  *
@@ -496,8 +549,12 @@ EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
  */
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
-	struct cpufreq_cooling_device *cpufreq_dev = cdev->devdata;
+	struct cpufreq_cooling_device *cpufreq_dev;
+
+	if (!cdev)
+		return;
 
+	cpufreq_dev = cdev->devdata;
 	mutex_lock(&cooling_cpufreq_lock);
 	cpufreq_dev_count--;
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
new file mode 100644
index 000000000000..4b2b999b7611
--- /dev/null
+++ b/drivers/thermal/of-thermal.c
@@ -0,0 +1,850 @@
+/*
+ *  of-thermal.c - Generic Thermal Management device tree support.
+ *
+ *  Copyright (C) 2013 Texas Instruments
+ *  Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/string.h>
+
+#include "thermal_core.h"
+
+/***   Private data structures to represent thermal device tree data ***/
+
+/**
+ * struct __thermal_trip - representation of a point in temperature domain
+ * @np: pointer to struct device_node that this trip point was created from
+ * @temperature: temperature value in miliCelsius
+ * @hysteresis: relative hysteresis in miliCelsius
+ * @type: trip point type
+ */
+
+struct __thermal_trip {
+	struct device_node *np;
+	unsigned long int temperature;
+	unsigned long int hysteresis;
+	enum thermal_trip_type type;
+};
+
+/**
+ * struct __thermal_bind_param - a match between trip and cooling device
+ * @cooling_device: a pointer to identify the referred cooling device
+ * @trip_id: the trip point index
+ * @usage: the percentage (from 0 to 100) of cooling contribution
+ * @min: minimum cooling state used at this trip point
+ * @max: maximum cooling state used at this trip point
+ */
+
+struct __thermal_bind_params {
+	struct device_node *cooling_device;
+	unsigned int trip_id;
+	unsigned int usage;
+	unsigned long min;
+	unsigned long max;
+};
+
+/**
+ * struct __thermal_zone - internal representation of a thermal zone
+ * @mode: current thermal zone device mode (enabled/disabled)
+ * @passive_delay: polling interval while passive cooling is activated
+ * @polling_delay: zone polling interval
+ * @ntrips: number of trip points
+ * @trips: an array of trip points (0..ntrips - 1)
+ * @num_tbps: number of thermal bind params
+ * @tbps: an array of thermal bind params (0..num_tbps - 1)
+ * @sensor_data: sensor private data used while reading temperature and trend
+ * @get_temp: sensor callback to read temperature
+ * @get_trend: sensor callback to read temperature trend
+ */
+
+struct __thermal_zone {
+	enum thermal_device_mode mode;
+	int passive_delay;
+	int polling_delay;
+
+	/* trip data */
+	int ntrips;
+	struct __thermal_trip *trips;
+
+	/* cooling binding data */
+	int num_tbps;
+	struct __thermal_bind_params *tbps;
+
+	/* sensor interface */
+	void *sensor_data;
+	int (*get_temp)(void *, long *);
+	int (*get_trend)(void *, long *);
+};
+
+/***   DT thermal zone device callbacks   ***/
+
+static int of_thermal_get_temp(struct thermal_zone_device *tz,
+			       unsigned long *temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data->get_temp)
+		return -EINVAL;
+
+	return data->get_temp(data->sensor_data, temp);
+}
+
+static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
+				enum thermal_trend *trend)
+{
+	struct __thermal_zone *data = tz->devdata;
+	long dev_trend;
+	int r;
+
+	if (!data->get_trend)
+		return -EINVAL;
+
+	r = data->get_trend(data->sensor_data, &dev_trend);
+	if (r)
+		return r;
+
+	/* TODO: These intervals might have some thresholds, but in core code */
+	if (dev_trend > 0)
+		*trend = THERMAL_TREND_RAISING;
+	else if (dev_trend < 0)
+		*trend = THERMAL_TREND_DROPPING;
+	else
+		*trend = THERMAL_TREND_STABLE;
+
+	return 0;
+}
+
+static int of_thermal_bind(struct thermal_zone_device *thermal,
+			   struct thermal_cooling_device *cdev)
+{
+	struct __thermal_zone *data = thermal->devdata;
+	int i;
+
+	if (!data || IS_ERR(data))
+		return -ENODEV;
+
+	/* find where to bind */
+	for (i = 0; i < data->num_tbps; i++) {
+		struct __thermal_bind_params *tbp = data->tbps + i;
+
+		if (tbp->cooling_device == cdev->np) {
+			int ret;
+
+			ret = thermal_zone_bind_cooling_device(thermal,
+						tbp->trip_id, cdev,
+						tbp->max,
+						tbp->min);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int of_thermal_unbind(struct thermal_zone_device *thermal,
+			     struct thermal_cooling_device *cdev)
+{
+	struct __thermal_zone *data = thermal->devdata;
+	int i;
+
+	if (!data || IS_ERR(data))
+		return -ENODEV;
+
+	/* find where to unbind */
+	for (i = 0; i < data->num_tbps; i++) {
+		struct __thermal_bind_params *tbp = data->tbps + i;
+
+		if (tbp->cooling_device == cdev->np) {
+			int ret;
+
+			ret = thermal_zone_unbind_cooling_device(thermal,
+						tbp->trip_id, cdev);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int of_thermal_get_mode(struct thermal_zone_device *tz,
+			       enum thermal_device_mode *mode)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	*mode = data->mode;
+
+	return 0;
+}
+
+static int of_thermal_set_mode(struct thermal_zone_device *tz,
+			       enum thermal_device_mode mode)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	mutex_lock(&tz->lock);
+
+	if (mode == THERMAL_DEVICE_ENABLED)
+		tz->polling_delay = data->polling_delay;
+	else
+		tz->polling_delay = 0;
+
+	mutex_unlock(&tz->lock);
+
+	data->mode = mode;
+	thermal_zone_device_update(tz);
+
+	return 0;
+}
+
+static int of_thermal_get_trip_type(struct thermal_zone_device *tz, int trip,
+				    enum thermal_trip_type *type)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (trip >= data->ntrips || trip < 0)
+		return -EDOM;
+
+	*type = data->trips[trip].type;
+
+	return 0;
+}
+
+static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip,
+				    unsigned long *temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (trip >= data->ntrips || trip < 0)
+		return -EDOM;
+
+	*temp = data->trips[trip].temperature;
+
+	return 0;
+}
+
+static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip,
+				    unsigned long temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (trip >= data->ntrips || trip < 0)
+		return -EDOM;
+
+	/* thermal framework should take care of data->mask & (1 << trip) */
+	data->trips[trip].temperature = temp;
+
+	return 0;
+}
+
+static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip,
+				    unsigned long *hyst)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (trip >= data->ntrips || trip < 0)
+		return -EDOM;
+
+	*hyst = data->trips[trip].hysteresis;
+
+	return 0;
+}
+
+static int of_thermal_set_trip_hyst(struct thermal_zone_device *tz, int trip,
+				    unsigned long hyst)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (trip >= data->ntrips || trip < 0)
+		return -EDOM;
+
+	/* thermal framework should take care of data->mask & (1 << trip) */
+	data->trips[trip].hysteresis = hyst;
+
+	return 0;
+}
+
+static int of_thermal_get_crit_temp(struct thermal_zone_device *tz,
+				    unsigned long *temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+	int i;
+
+	for (i = 0; i < data->ntrips; i++)
+		if (data->trips[i].type == THERMAL_TRIP_CRITICAL) {
+			*temp = data->trips[i].temperature;
+			return 0;
+		}
+
+	return -EINVAL;
+}
+
+static struct thermal_zone_device_ops of_thermal_ops = {
+	.get_mode = of_thermal_get_mode,
+	.set_mode = of_thermal_set_mode,
+
+	.get_trip_type = of_thermal_get_trip_type,
+	.get_trip_temp = of_thermal_get_trip_temp,
+	.set_trip_temp = of_thermal_set_trip_temp,
+	.get_trip_hyst = of_thermal_get_trip_hyst,
+	.set_trip_hyst = of_thermal_set_trip_hyst,
+	.get_crit_temp = of_thermal_get_crit_temp,
+
+	.bind = of_thermal_bind,
+	.unbind = of_thermal_unbind,
+};
+
+/***   sensor API   ***/
+
+static struct thermal_zone_device *
+thermal_zone_of_add_sensor(struct device_node *zone,
+			   struct device_node *sensor, void *data,
+			   int (*get_temp)(void *, long *),
+			   int (*get_trend)(void *, long *))
+{
+	struct thermal_zone_device *tzd;
+	struct __thermal_zone *tz;
+
+	tzd = thermal_zone_get_zone_by_name(zone->name);
+	if (IS_ERR(tzd))
+		return ERR_PTR(-EPROBE_DEFER);
+
+	tz = tzd->devdata;
+
+	mutex_lock(&tzd->lock);
+	tz->get_temp = get_temp;
+	tz->get_trend = get_trend;
+	tz->sensor_data = data;
+
+	tzd->ops->get_temp = of_thermal_get_temp;
+	tzd->ops->get_trend = of_thermal_get_trend;
+	mutex_unlock(&tzd->lock);
+
+	return tzd;
+}
+
+/**
+ * thermal_zone_of_sensor_register - registers a sensor to a DT thermal zone
+ * @dev: a valid struct device pointer of a sensor device. Must contain
+ *       a valid .of_node, for the sensor node.
+ * @sensor_id: a sensor identifier, in case the sensor IP has more
+ *             than one sensors
+ * @data: a private pointer (owned by the caller) that will be passed
+ *        back, when a temperature reading is needed.
+ * @get_temp: a pointer to a function that reads the sensor temperature.
+ * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ *
+ * This function will search the list of thermal zones described in device
+ * tree and look for the zone that refer to the sensor device pointed by
+ * @dev->of_node as temperature providers. For the zone pointing to the
+ * sensor node, the sensor will be added to the DT thermal zone device.
+ *
+ * The thermal zone temperature is provided by the @get_temp function
+ * pointer. When called, it will have the private pointer @data back.
+ *
+ * The thermal zone temperature trend is provided by the @get_trend function
+ * pointer. When called, it will have the private pointer @data back.
+ *
+ * TODO:
+ * 01 - This function must enqueue the new sensor instead of using
+ * it as the only source of temperature values.
+ *
+ * 02 - There must be a way to match the sensor with all thermal zones
+ * that refer to it.
+ *
+ * Return: On success returns a valid struct thermal_zone_device,
+ * otherwise, it returns a corresponding ERR_PTR(). Caller must
+ * check the return value with help of IS_ERR() helper.
+ */
+struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
+				void *data, int (*get_temp)(void *, long *),
+				int (*get_trend)(void *, long *))
+{
+	struct device_node *np, *child, *sensor_np;
+
+	np = of_find_node_by_name(NULL, "thermal-zones");
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	if (!dev || !dev->of_node)
+		return ERR_PTR(-EINVAL);
+
+	sensor_np = dev->of_node;
+
+	for_each_child_of_node(np, child) {
+		struct of_phandle_args sensor_specs;
+		int ret, id;
+
+		/* For now, thermal framework supports only 1 sensor per zone */
+		ret = of_parse_phandle_with_args(child, "thermal-sensors",
+						 "#thermal-sensor-cells",
+						 0, &sensor_specs);
+		if (ret)
+			continue;
+
+		if (sensor_specs.args_count >= 1) {
+			id = sensor_specs.args[0];
+			WARN(sensor_specs.args_count > 1,
+			     "%s: too many cells in sensor specifier %d\n",
+			     sensor_specs.np->name, sensor_specs.args_count);
+		} else {
+			id = 0;
+		}
+
+		if (sensor_specs.np == sensor_np && id == sensor_id) {
+			of_node_put(np);
+			return thermal_zone_of_add_sensor(child, sensor_np,
+							  data,
+							  get_temp,
+							  get_trend);
+		}
+	}
+	of_node_put(np);
+
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_register);
+
+/**
+ * thermal_zone_of_sensor_unregister - unregisters a sensor from a DT thermal zone
+ * @dev: a valid struct device pointer of a sensor device. Must contain
+ *       a valid .of_node, for the sensor node.
+ * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
+ *
+ * This function removes the sensor callbacks and private data from the
+ * thermal zone device registered with thermal_zone_of_sensor_register()
+ * API. It will also silent the zone by remove the .get_temp() and .get_trend()
+ * thermal zone device callbacks.
+ *
+ * TODO: When the support to several sensors per zone is added, this
+ * function must search the sensor list based on @dev parameter.
+ *
+ */
+void thermal_zone_of_sensor_unregister(struct device *dev,
+				       struct thermal_zone_device *tzd)
+{
+	struct __thermal_zone *tz;
+
+	if (!dev || !tzd || !tzd->devdata)
+		return;
+
+	tz = tzd->devdata;
+
+	/* no __thermal_zone, nothing to be done */
+	if (!tz)
+		return;
+
+	mutex_lock(&tzd->lock);
+	tzd->ops->get_temp = NULL;
+	tzd->ops->get_trend = NULL;
+
+	tz->get_temp = NULL;
+	tz->get_trend = NULL;
+	tz->sensor_data = NULL;
+	mutex_unlock(&tzd->lock);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
+
+/***   functions parsing device tree nodes   ***/
+
+/**
+ * thermal_of_populate_bind_params - parse and fill cooling map data
+ * @np: DT node containing a cooling-map node
+ * @__tbp: data structure to be filled with cooling map info
+ * @trips: array of thermal zone trip points
+ * @ntrips: number of trip points inside trips.
+ *
+ * This function parses a cooling-map type of node represented by
+ * @np parameter and fills the read data into @__tbp data structure.
+ * It needs the already parsed array of trip points of the thermal zone
+ * in consideration.
+ *
+ * Return: 0 on success, proper error code otherwise
+ */
+static int thermal_of_populate_bind_params(struct device_node *np,
+					   struct __thermal_bind_params *__tbp,
+					   struct __thermal_trip *trips,
+					   int ntrips)
+{
+	struct of_phandle_args cooling_spec;
+	struct device_node *trip;
+	int ret, i;
+	u32 prop;
+
+	/* Default weight. Usage is optional */
+	__tbp->usage = 0;
+	ret = of_property_read_u32(np, "contribution", &prop);
+	if (ret == 0)
+		__tbp->usage = prop;
+
+	trip = of_parse_phandle(np, "trip", 0);
+	if (!trip) {
+		pr_err("missing trip property\n");
+		return -ENODEV;
+	}
+
+	/* match using device_node */
+	for (i = 0; i < ntrips; i++)
+		if (trip == trips[i].np) {
+			__tbp->trip_id = i;
+			break;
+		}
+
+	if (i == ntrips) {
+		ret = -ENODEV;
+		goto end;
+	}
+
+	ret = of_parse_phandle_with_args(np, "cooling-device", "#cooling-cells",
+					 0, &cooling_spec);
+	if (ret < 0) {
+		pr_err("missing cooling_device property\n");
+		goto end;
+	}
+	__tbp->cooling_device = cooling_spec.np;
+	if (cooling_spec.args_count >= 2) { /* at least min and max */
+		__tbp->min = cooling_spec.args[0];
+		__tbp->max = cooling_spec.args[1];
+	} else {
+		pr_err("wrong reference to cooling device, missing limits\n");
+	}
+
+end:
+	of_node_put(trip);
+
+	return ret;
+}
+
+/**
+ * It maps 'enum thermal_trip_type' found in include/linux/thermal.h
+ * into the device tree binding of 'trip', property type.
+ */
+static const char * const trip_types[] = {
+	[THERMAL_TRIP_ACTIVE]	= "active",
+	[THERMAL_TRIP_PASSIVE]	= "passive",
+	[THERMAL_TRIP_HOT]	= "hot",
+	[THERMAL_TRIP_CRITICAL]	= "critical",
+};
+
+/**
+ * thermal_of_get_trip_type - Get phy mode for given device_node
+ * @np:	Pointer to the given device_node
+ * @type: Pointer to resulting trip type
+ *
+ * The function gets trip type string from property 'type',
+ * and store its index in trip_types table in @type,
+ *
+ * Return: 0 on success, or errno in error case.
+ */
+static int thermal_of_get_trip_type(struct device_node *np,
+				    enum thermal_trip_type *type)
+{
+	const char *t;
+	int err, i;
+
+	err = of_property_read_string(np, "type", &t);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(trip_types); i++)
+		if (!strcasecmp(t, trip_types[i])) {
+			*type = i;
+			return 0;
+		}
+
+	return -ENODEV;
+}
+
+/**
+ * thermal_of_populate_trip - parse and fill one trip point data
+ * @np: DT node containing a trip point node
+ * @trip: trip point data structure to be filled up
+ *
+ * This function parses a trip point type of node represented by
+ * @np parameter and fills the read data into @trip data structure.
+ *
+ * Return: 0 on success, proper error code otherwise
+ */
+static int thermal_of_populate_trip(struct device_node *np,
+				    struct __thermal_trip *trip)
+{
+	int prop;
+	int ret;
+
+	ret = of_property_read_u32(np, "temperature", &prop);
+	if (ret < 0) {
+		pr_err("missing temperature property\n");
+		return ret;
+	}
+	trip->temperature = prop;
+
+	ret = of_property_read_u32(np, "hysteresis", &prop);
+	if (ret < 0) {
+		pr_err("missing hysteresis property\n");
+		return ret;
+	}
+	trip->hysteresis = prop;
+
+	ret = thermal_of_get_trip_type(np, &trip->type);
+	if (ret < 0) {
+		pr_err("wrong trip type property\n");
+		return ret;
+	}
+
+	/* Required for cooling map matching */
+	trip->np = np;
+
+	return 0;
+}
+
+/**
+ * thermal_of_build_thermal_zone - parse and fill one thermal zone data
+ * @np: DT node containing a thermal zone node
+ *
+ * This function parses a thermal zone type of node represented by
+ * @np parameter and fills the read data into a __thermal_zone data structure
+ * and return this pointer.
+ *
+ * TODO: Missing properties to parse: thermal-sensor-names and coefficients
+ *
+ * Return: On success returns a valid struct __thermal_zone,
+ * otherwise, it returns a corresponding ERR_PTR(). Caller must
+ * check the return value with help of IS_ERR() helper.
+ */
+static struct __thermal_zone *
+thermal_of_build_thermal_zone(struct device_node *np)
+{
+	struct device_node *child = NULL, *gchild;
+	struct __thermal_zone *tz;
+	int ret, i;
+	u32 prop;
+
+	if (!np) {
+		pr_err("no thermal zone np\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	tz = kzalloc(sizeof(*tz), GFP_KERNEL);
+	if (!tz)
+		return ERR_PTR(-ENOMEM);
+
+	ret = of_property_read_u32(np, "polling-delay-passive", &prop);
+	if (ret < 0) {
+		pr_err("missing polling-delay-passive property\n");
+		goto free_tz;
+	}
+	tz->passive_delay = prop;
+
+	ret = of_property_read_u32(np, "polling-delay", &prop);
+	if (ret < 0) {
+		pr_err("missing polling-delay property\n");
+		goto free_tz;
+	}
+	tz->polling_delay = prop;
+
+	/* trips */
+	child = of_get_child_by_name(np, "trips");
+
+	/* No trips provided */
+	if (!child)
+		goto finish;
+
+	tz->ntrips = of_get_child_count(child);
+	if (tz->ntrips == 0) /* must have at least one child */
+		goto finish;
+
+	tz->trips = kzalloc(tz->ntrips * sizeof(*tz->trips), GFP_KERNEL);
+	if (!tz->trips) {
+		ret = -ENOMEM;
+		goto free_tz;
+	}
+
+	i = 0;
+	for_each_child_of_node(child, gchild) {
+		ret = thermal_of_populate_trip(gchild, &tz->trips[i++]);
+		if (ret)
+			goto free_trips;
+	}
+
+	of_node_put(child);
+
+	/* cooling-maps */
+	child = of_get_child_by_name(np, "cooling-maps");
+
+	/* cooling-maps not provided */
+	if (!child)
+		goto finish;
+
+	tz->num_tbps = of_get_child_count(child);
+	if (tz->num_tbps == 0)
+		goto finish;
+
+	tz->tbps = kzalloc(tz->num_tbps * sizeof(*tz->tbps), GFP_KERNEL);
+	if (!tz->tbps) {
+		ret = -ENOMEM;
+		goto free_trips;
+	}
+
+	i = 0;
+	for_each_child_of_node(child, gchild) {
+		ret = thermal_of_populate_bind_params(gchild, &tz->tbps[i++],
+						      tz->trips, tz->ntrips);
+		if (ret)
+			goto free_tbps;
+	}
+
+finish:
+	of_node_put(child);
+	tz->mode = THERMAL_DEVICE_DISABLED;
+
+	return tz;
+
+free_tbps:
+	kfree(tz->tbps);
+free_trips:
+	kfree(tz->trips);
+free_tz:
+	kfree(tz);
+	of_node_put(child);
+
+	return ERR_PTR(ret);
+}
+
+static inline void of_thermal_free_zone(struct __thermal_zone *tz)
+{
+	kfree(tz->tbps);
+	kfree(tz->trips);
+	kfree(tz);
+}
+
+/**
+ * of_parse_thermal_zones - parse device tree thermal data
+ *
+ * Initialization function that can be called by machine initialization
+ * code to parse thermal data and populate the thermal framework
+ * with hardware thermal zones info. This function only parses thermal zones.
+ * Cooling devices and sensor devices nodes are supposed to be parsed
+ * by their respective drivers.
+ *
+ * Return: 0 on success, proper error code otherwise
+ *
+ */
+int __init of_parse_thermal_zones(void)
+{
+	struct device_node *np, *child;
+	struct __thermal_zone *tz;
+	struct thermal_zone_device_ops *ops;
+
+	np = of_find_node_by_name(NULL, "thermal-zones");
+	if (!np) {
+		pr_debug("unable to find thermal zones\n");
+		return 0; /* Run successfully on systems without thermal DT */
+	}
+
+	for_each_child_of_node(np, child) {
+		struct thermal_zone_device *zone;
+		struct thermal_zone_params *tzp;
+
+		tz = thermal_of_build_thermal_zone(child);
+		if (IS_ERR(tz)) {
+			pr_err("failed to build thermal zone %s: %ld\n",
+			       child->name,
+			       PTR_ERR(tz));
+			continue;
+		}
+
+		ops = kmemdup(&of_thermal_ops, sizeof(*ops), GFP_KERNEL);
+		if (!ops)
+			goto exit_free;
+
+		tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
+		if (!tzp) {
+			kfree(ops);
+			goto exit_free;
+		}
+
+		/* No hwmon because there might be hwmon drivers registering */
+		tzp->no_hwmon = true;
+
+		zone = thermal_zone_device_register(child->name, tz->ntrips,
+						    0, tz,
+						    ops, tzp,
+						    tz->passive_delay,
+						    tz->polling_delay);
+		if (IS_ERR(zone)) {
+			pr_err("Failed to build %s zone %ld\n", child->name,
+			       PTR_ERR(zone));
+			kfree(tzp);
+			kfree(ops);
+			of_thermal_free_zone(tz);
+			/* attempting to build remaining zones still */
+		}
+	}
+
+	return 0;
+
+exit_free:
+	of_thermal_free_zone(tz);
+
+	/* no memory available, so free what we have built */
+	of_thermal_destroy_zones();
+
+	return -ENOMEM;
+}
+
+/**
+ * of_thermal_destroy_zones - remove all zones parsed and allocated resources
+ *
+ * Finds all zones parsed and added to the thermal framework and remove them
+ * from the system, together with their resources.
+ *
+ */
+void of_thermal_destroy_zones(void)
+{
+	struct device_node *np, *child;
+
+	np = of_find_node_by_name(NULL, "thermal-zones");
+	if (!np) {
+		pr_err("unable to find thermal zones\n");
+		return;
+	}
+
+	for_each_child_of_node(np, child) {
+		struct thermal_zone_device *zone;
+
+		zone = thermal_zone_get_zone_by_name(child->name);
+		if (IS_ERR(zone))
+			continue;
+
+		thermal_zone_device_unregister(zone);
+		kfree(zone->tzp);
+		kfree(zone->ops);
+		of_thermal_free_zone(zone->devdata);
+	}
+}
diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c
index 4d4ddae1a991..c83a3097ef90 100644
--- a/drivers/thermal/step_wise.c
+++ b/drivers/thermal/step_wise.c
@@ -53,6 +53,7 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 	unsigned long cur_state;
 
 	cdev->ops->get_cur_state(cdev, &cur_state);
+	dev_dbg(&cdev->device, "cur_state=%ld\n", cur_state);
 
 	switch (trend) {
 	case THERMAL_TREND_RAISING:
@@ -124,6 +125,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 	if (tz->temperature >= trip_temp)
 		throttle = true;
 
+	dev_dbg(&tz->device, "Trip%d[type=%d,temp=%ld]:trend=%d,throttle=%d\n",
+				trip, trip_type, trip_temp, trend, throttle);
+
 	mutex_lock(&tz->lock);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
@@ -132,6 +136,8 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 
 		old_target = instance->target;
 		instance->target = get_target_state(instance, trend, throttle);
+		dev_dbg(&instance->cdev->device, "old_target=%d, target=%d\n",
+					old_target, (int)instance->target);
 
 		/* Activate a passive thermal instance */
 		if (old_target == THERMAL_NO_TARGET &&
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index d755440791b7..edc0cb88f1d0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -33,10 +33,13 @@
 #include <linux/idr.h>
 #include <linux/thermal.h>
 #include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/of.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 
 #include "thermal_core.h"
+#include "thermal_hwmon.h"
 
 MODULE_AUTHOR("Zhang Rui");
 MODULE_DESCRIPTION("Generic thermal management sysfs support");
@@ -53,10 +56,15 @@ static LIST_HEAD(thermal_governor_list);
 static DEFINE_MUTEX(thermal_list_lock);
 static DEFINE_MUTEX(thermal_governor_lock);
 
+static struct thermal_governor *def_governor;
+
 static struct thermal_governor *__find_governor(const char *name)
 {
 	struct thermal_governor *pos;
 
+	if (!name || !name[0])
+		return def_governor;
+
 	list_for_each_entry(pos, &thermal_governor_list, governor_list)
 		if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
 			return pos;
@@ -79,17 +87,23 @@ int thermal_register_governor(struct thermal_governor *governor)
 	if (__find_governor(governor->name) == NULL) {
 		err = 0;
 		list_add(&governor->governor_list, &thermal_governor_list);
+		if (!def_governor && !strncmp(governor->name,
+			DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
+			def_governor = governor;
 	}
 
 	mutex_lock(&thermal_list_lock);
 
 	list_for_each_entry(pos, &thermal_tz_list, node) {
+		/*
+		 * only thermal zones with specified tz->tzp->governor_name
+		 * may run with tz->govenor unset
+		 */
 		if (pos->governor)
 			continue;
-		if (pos->tzp)
-			name = pos->tzp->governor_name;
-		else
-			name = DEFAULT_THERMAL_GOVERNOR;
+
+		name = pos->tzp->governor_name;
+
 		if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
 			pos->governor = governor;
 	}
@@ -235,10 +249,11 @@ static void bind_cdev(struct thermal_cooling_device *cdev)
 		if (!pos->tzp && !pos->ops->bind)
 			continue;
 
-		if (!pos->tzp && pos->ops->bind) {
+		if (pos->ops->bind) {
 			ret = pos->ops->bind(pos, cdev);
 			if (ret)
 				print_bind_err_msg(pos, cdev, ret);
+			continue;
 		}
 
 		tzp = pos->tzp;
@@ -269,8 +284,8 @@ static void bind_tz(struct thermal_zone_device *tz)
 
 	mutex_lock(&thermal_list_lock);
 
-	/* If there is no platform data, try to use ops->bind */
-	if (!tzp && tz->ops->bind) {
+	/* If there is ops->bind, try to use ops->bind */
+	if (tz->ops->bind) {
 		list_for_each_entry(pos, &thermal_cdev_list, node) {
 			ret = tz->ops->bind(tz, pos);
 			if (ret)
@@ -326,8 +341,8 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz)
 static void handle_non_critical_trips(struct thermal_zone_device *tz,
 			int trip, enum thermal_trip_type trip_type)
 {
-	if (tz->governor)
-		tz->governor->throttle(tz, trip);
+	tz->governor ? tz->governor->throttle(tz, trip) :
+		       def_governor->throttle(tz, trip);
 }
 
 static void handle_critical_trips(struct thermal_zone_device *tz,
@@ -388,7 +403,7 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp)
 	enum thermal_trip_type type;
 #endif
 
-	if (!tz || IS_ERR(tz))
+	if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
 		goto exit;
 
 	mutex_lock(&tz->lock);
@@ -435,12 +450,18 @@ static void update_temperature(struct thermal_zone_device *tz)
 	tz->last_temperature = tz->temperature;
 	tz->temperature = temp;
 	mutex_unlock(&tz->lock);
+
+	dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n",
+				tz->last_temperature, tz->temperature);
 }
 
 void thermal_zone_device_update(struct thermal_zone_device *tz)
 {
 	int count;
 
+	if (!tz->ops->get_temp)
+		return;
+
 	update_temperature(tz);
 
 	for (count = 0; count < tz->trips; count++)
@@ -756,6 +777,9 @@ emul_temp_store(struct device *dev, struct device_attribute *attr,
 		ret = tz->ops->set_emul_temp(tz, temperature);
 	}
 
+	if (!ret)
+		thermal_zone_device_update(tz);
+
 	return ret ? ret : count;
 }
 static DEVICE_ATTR(emul_temp, S_IWUSR, NULL, emul_temp_store);
@@ -854,260 +878,6 @@ thermal_cooling_device_trip_point_show(struct device *dev,
 
 /* Device management */
 
-#if defined(CONFIG_THERMAL_HWMON)
-
-/* hwmon sys I/F */
-#include <linux/hwmon.h>
-
-/* thermal zone devices with the same type share one hwmon device */
-struct thermal_hwmon_device {
-	char type[THERMAL_NAME_LENGTH];
-	struct device *device;
-	int count;
-	struct list_head tz_list;
-	struct list_head node;
-};
-
-struct thermal_hwmon_attr {
-	struct device_attribute attr;
-	char name[16];
-};
-
-/* one temperature input for each thermal zone */
-struct thermal_hwmon_temp {
-	struct list_head hwmon_node;
-	struct thermal_zone_device *tz;
-	struct thermal_hwmon_attr temp_input;	/* hwmon sys attr */
-	struct thermal_hwmon_attr temp_crit;	/* hwmon sys attr */
-};
-
-static LIST_HEAD(thermal_hwmon_list);
-
-static ssize_t
-name_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", hwmon->type);
-}
-static DEVICE_ATTR(name, 0444, name_show, NULL);
-
-static ssize_t
-temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	long temperature;
-	int ret;
-	struct thermal_hwmon_attr *hwmon_attr
-			= container_of(attr, struct thermal_hwmon_attr, attr);
-	struct thermal_hwmon_temp *temp
-			= container_of(hwmon_attr, struct thermal_hwmon_temp,
-				       temp_input);
-	struct thermal_zone_device *tz = temp->tz;
-
-	ret = thermal_zone_get_temp(tz, &temperature);
-
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%ld\n", temperature);
-}
-
-static ssize_t
-temp_crit_show(struct device *dev, struct device_attribute *attr,
-		char *buf)
-{
-	struct thermal_hwmon_attr *hwmon_attr
-			= container_of(attr, struct thermal_hwmon_attr, attr);
-	struct thermal_hwmon_temp *temp
-			= container_of(hwmon_attr, struct thermal_hwmon_temp,
-				       temp_crit);
-	struct thermal_zone_device *tz = temp->tz;
-	long temperature;
-	int ret;
-
-	ret = tz->ops->get_trip_temp(tz, 0, &temperature);
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%ld\n", temperature);
-}
-
-
-static struct thermal_hwmon_device *
-thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
-{
-	struct thermal_hwmon_device *hwmon;
-
-	mutex_lock(&thermal_list_lock);
-	list_for_each_entry(hwmon, &thermal_hwmon_list, node)
-		if (!strcmp(hwmon->type, tz->type)) {
-			mutex_unlock(&thermal_list_lock);
-			return hwmon;
-		}
-	mutex_unlock(&thermal_list_lock);
-
-	return NULL;
-}
-
-/* Find the temperature input matching a given thermal zone */
-static struct thermal_hwmon_temp *
-thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
-			  const struct thermal_zone_device *tz)
-{
-	struct thermal_hwmon_temp *temp;
-
-	mutex_lock(&thermal_list_lock);
-	list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
-		if (temp->tz == tz) {
-			mutex_unlock(&thermal_list_lock);
-			return temp;
-		}
-	mutex_unlock(&thermal_list_lock);
-
-	return NULL;
-}
-
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-	struct thermal_hwmon_device *hwmon;
-	struct thermal_hwmon_temp *temp;
-	int new_hwmon_device = 1;
-	int result;
-
-	hwmon = thermal_hwmon_lookup_by_type(tz);
-	if (hwmon) {
-		new_hwmon_device = 0;
-		goto register_sys_interface;
-	}
-
-	hwmon = kzalloc(sizeof(struct thermal_hwmon_device), GFP_KERNEL);
-	if (!hwmon)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&hwmon->tz_list);
-	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
-	hwmon->device = hwmon_device_register(NULL);
-	if (IS_ERR(hwmon->device)) {
-		result = PTR_ERR(hwmon->device);
-		goto free_mem;
-	}
-	dev_set_drvdata(hwmon->device, hwmon);
-	result = device_create_file(hwmon->device, &dev_attr_name);
-	if (result)
-		goto free_mem;
-
- register_sys_interface:
-	temp = kzalloc(sizeof(struct thermal_hwmon_temp), GFP_KERNEL);
-	if (!temp) {
-		result = -ENOMEM;
-		goto unregister_name;
-	}
-
-	temp->tz = tz;
-	hwmon->count++;
-
-	snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
-		 "temp%d_input", hwmon->count);
-	temp->temp_input.attr.attr.name = temp->temp_input.name;
-	temp->temp_input.attr.attr.mode = 0444;
-	temp->temp_input.attr.show = temp_input_show;
-	sysfs_attr_init(&temp->temp_input.attr.attr);
-	result = device_create_file(hwmon->device, &temp->temp_input.attr);
-	if (result)
-		goto free_temp_mem;
-
-	if (tz->ops->get_crit_temp) {
-		unsigned long temperature;
-		if (!tz->ops->get_crit_temp(tz, &temperature)) {
-			snprintf(temp->temp_crit.name,
-				 sizeof(temp->temp_crit.name),
-				"temp%d_crit", hwmon->count);
-			temp->temp_crit.attr.attr.name = temp->temp_crit.name;
-			temp->temp_crit.attr.attr.mode = 0444;
-			temp->temp_crit.attr.show = temp_crit_show;
-			sysfs_attr_init(&temp->temp_crit.attr.attr);
-			result = device_create_file(hwmon->device,
-						    &temp->temp_crit.attr);
-			if (result)
-				goto unregister_input;
-		}
-	}
-
-	mutex_lock(&thermal_list_lock);
-	if (new_hwmon_device)
-		list_add_tail(&hwmon->node, &thermal_hwmon_list);
-	list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
-	mutex_unlock(&thermal_list_lock);
-
-	return 0;
-
- unregister_input:
-	device_remove_file(hwmon->device, &temp->temp_input.attr);
- free_temp_mem:
-	kfree(temp);
- unregister_name:
-	if (new_hwmon_device) {
-		device_remove_file(hwmon->device, &dev_attr_name);
-		hwmon_device_unregister(hwmon->device);
-	}
- free_mem:
-	if (new_hwmon_device)
-		kfree(hwmon);
-
-	return result;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-	struct thermal_hwmon_device *hwmon;
-	struct thermal_hwmon_temp *temp;
-
-	hwmon = thermal_hwmon_lookup_by_type(tz);
-	if (unlikely(!hwmon)) {
-		/* Should never happen... */
-		dev_dbg(&tz->device, "hwmon device lookup failed!\n");
-		return;
-	}
-
-	temp = thermal_hwmon_lookup_temp(hwmon, tz);
-	if (unlikely(!temp)) {
-		/* Should never happen... */
-		dev_dbg(&tz->device, "temperature input lookup failed!\n");
-		return;
-	}
-
-	device_remove_file(hwmon->device, &temp->temp_input.attr);
-	if (tz->ops->get_crit_temp)
-		device_remove_file(hwmon->device, &temp->temp_crit.attr);
-
-	mutex_lock(&thermal_list_lock);
-	list_del(&temp->hwmon_node);
-	kfree(temp);
-	if (!list_empty(&hwmon->tz_list)) {
-		mutex_unlock(&thermal_list_lock);
-		return;
-	}
-	list_del(&hwmon->node);
-	mutex_unlock(&thermal_list_lock);
-
-	device_remove_file(hwmon->device, &dev_attr_name);
-	hwmon_device_unregister(hwmon->device);
-	kfree(hwmon);
-}
-#else
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-	return 0;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-}
-#endif
-
 /**
  * thermal_zone_bind_cooling_device() - bind a cooling device to a thermal zone
  * @tz:		pointer to struct thermal_zone_device
@@ -1287,7 +1057,8 @@ static struct class thermal_class = {
 };
 
 /**
- * thermal_cooling_device_register() - register a new thermal cooling device
+ * __thermal_cooling_device_register() - register a new thermal cooling device
+ * @np:		a pointer to a device tree node.
  * @type:	the thermal cooling device type.
  * @devdata:	device private data.
  * @ops:		standard thermal cooling devices callbacks.
@@ -1295,13 +1066,16 @@ static struct class thermal_class = {
  * This interface function adds a new thermal cooling device (fan/processor/...)
  * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
  * to all the thermal zone devices registered at the same time.
+ * It also gives the opportunity to link the cooling device to a device tree
+ * node, so that it can be bound to a thermal zone created out of device tree.
  *
  * Return: a pointer to the created struct thermal_cooling_device or an
  * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
  */
-struct thermal_cooling_device *
-thermal_cooling_device_register(char *type, void *devdata,
-				const struct thermal_cooling_device_ops *ops)
+static struct thermal_cooling_device *
+__thermal_cooling_device_register(struct device_node *np,
+				  char *type, void *devdata,
+				  const struct thermal_cooling_device_ops *ops)
 {
 	struct thermal_cooling_device *cdev;
 	int result;
@@ -1326,8 +1100,9 @@ thermal_cooling_device_register(char *type, void *devdata,
 	strlcpy(cdev->type, type ? : "", sizeof(cdev->type));
 	mutex_init(&cdev->lock);
 	INIT_LIST_HEAD(&cdev->thermal_instances);
+	cdev->np = np;
 	cdev->ops = ops;
-	cdev->updated = true;
+	cdev->updated = false;
 	cdev->device.class = &thermal_class;
 	cdev->devdata = devdata;
 	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -1368,9 +1143,53 @@ unregister:
 	device_unregister(&cdev->device);
 	return ERR_PTR(result);
 }
+
+/**
+ * thermal_cooling_device_register() - register a new thermal cooling device
+ * @type:	the thermal cooling device type.
+ * @devdata:	device private data.
+ * @ops:		standard thermal cooling devices callbacks.
+ *
+ * This interface function adds a new thermal cooling device (fan/processor/...)
+ * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+ * to all the thermal zone devices registered at the same time.
+ *
+ * Return: a pointer to the created struct thermal_cooling_device or an
+ * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
+ */
+struct thermal_cooling_device *
+thermal_cooling_device_register(char *type, void *devdata,
+				const struct thermal_cooling_device_ops *ops)
+{
+	return __thermal_cooling_device_register(NULL, type, devdata, ops);
+}
 EXPORT_SYMBOL_GPL(thermal_cooling_device_register);
 
 /**
+ * thermal_of_cooling_device_register() - register an OF thermal cooling device
+ * @np:		a pointer to a device tree node.
+ * @type:	the thermal cooling device type.
+ * @devdata:	device private data.
+ * @ops:		standard thermal cooling devices callbacks.
+ *
+ * This function will register a cooling device with device tree node reference.
+ * This interface function adds a new thermal cooling device (fan/processor/...)
+ * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+ * to all the thermal zone devices registered at the same time.
+ *
+ * Return: a pointer to the created struct thermal_cooling_device or an
+ * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
+ */
+struct thermal_cooling_device *
+thermal_of_cooling_device_register(struct device_node *np,
+				   char *type, void *devdata,
+				   const struct thermal_cooling_device_ops *ops)
+{
+	return __thermal_cooling_device_register(np, type, devdata, ops);
+}
+EXPORT_SYMBOL_GPL(thermal_of_cooling_device_register);
+
+/**
  * thermal_cooling_device_unregister - removes the registered thermal cooling device
  * @cdev:	the thermal cooling device to remove.
  *
@@ -1442,6 +1261,8 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev)
 	mutex_lock(&cdev->lock);
 	/* Make sure cdev enters the deepest cooling state */
 	list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) {
+		dev_dbg(&cdev->device, "zone%d->target=%lu\n",
+				instance->tz->id, instance->target);
 		if (instance->target == THERMAL_NO_TARGET)
 			continue;
 		if (instance->target > target)
@@ -1450,6 +1271,7 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev)
 	mutex_unlock(&cdev->lock);
 	cdev->ops->set_cur_state(cdev, target);
 	cdev->updated = true;
+	dev_dbg(&cdev->device, "set to state %lu\n", target);
 }
 EXPORT_SYMBOL(thermal_cdev_update);
 
@@ -1605,7 +1427,7 @@ static void remove_trip_attrs(struct thermal_zone_device *tz)
  */
 struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int trips, int mask, void *devdata,
-	const struct thermal_zone_device_ops *ops,
+	struct thermal_zone_device_ops *ops,
 	const struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 {
@@ -1621,7 +1443,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips)
 		return ERR_PTR(-EINVAL);
 
-	if (!ops || !ops->get_temp)
+	if (!ops)
 		return ERR_PTR(-EINVAL);
 
 	if (trips > 0 && !ops->get_trip_type)
@@ -1706,13 +1528,15 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	if (tz->tzp)
 		tz->governor = __find_governor(tz->tzp->governor_name);
 	else
-		tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+		tz->governor = def_governor;
 
 	mutex_unlock(&thermal_governor_lock);
 
-	result = thermal_add_hwmon_sysfs(tz);
-	if (result)
-		goto unregister;
+	if (!tz->tzp || !tz->tzp->no_hwmon) {
+		result = thermal_add_hwmon_sysfs(tz);
+		if (result)
+			goto unregister;
+	}
 
 	mutex_lock(&thermal_list_lock);
 	list_add_tail(&tz->node, &thermal_tz_list);
@@ -1723,6 +1547,9 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 
 	INIT_DELAYED_WORK(&(tz->poll_queue), thermal_zone_device_check);
 
+	if (!tz->ops->get_temp)
+		thermal_zone_device_set_polling(tz, 0);
+
 	thermal_zone_device_update(tz);
 
 	if (!result)
@@ -1980,8 +1807,14 @@ static int __init thermal_init(void)
 	if (result)
 		goto unregister_class;
 
+	result = of_parse_thermal_zones();
+	if (result)
+		goto exit_netlink;
+
 	return 0;
 
+exit_netlink:
+	genetlink_exit();
 unregister_governors:
 	thermal_unregister_governors();
 unregister_class:
@@ -1997,6 +1830,7 @@ error:
 
 static void __exit thermal_exit(void)
 {
+	of_thermal_destroy_zones();
 	genetlink_exit();
 	class_unregister(&thermal_class);
 	thermal_unregister_governors();
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 7cf2f6626251..3db339fb636f 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -77,4 +77,13 @@ static inline int thermal_gov_user_space_register(void) { return 0; }
 static inline void thermal_gov_user_space_unregister(void) {}
 #endif /* CONFIG_THERMAL_GOV_USER_SPACE */
 
+/* device tree support */
+#ifdef CONFIG_THERMAL_OF
+int of_parse_thermal_zones(void);
+void of_thermal_destroy_zones(void);
+#else
+static inline int of_parse_thermal_zones(void) { return 0; }
+static inline void of_thermal_destroy_zones(void) { }
+#endif
+
 #endif /* __THERMAL_CORE_H__ */
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
new file mode 100644
index 000000000000..fdb07199d9c2
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.c
@@ -0,0 +1,269 @@
+/*
+ *  thermal_hwmon.c - Generic Thermal Management hwmon support.
+ *
+ *  Code based on Intel thermal_core.c. Copyrights of the original code:
+ *  Copyright (C) 2008 Intel Corp
+ *  Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ *  Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ *  Copyright (C) 2013 Texas Instruments
+ *  Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/hwmon.h>
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include "thermal_hwmon.h"
+
+/* hwmon sys I/F */
+/* thermal zone devices with the same type share one hwmon device */
+struct thermal_hwmon_device {
+	char type[THERMAL_NAME_LENGTH];
+	struct device *device;
+	int count;
+	struct list_head tz_list;
+	struct list_head node;
+};
+
+struct thermal_hwmon_attr {
+	struct device_attribute attr;
+	char name[16];
+};
+
+/* one temperature input for each thermal zone */
+struct thermal_hwmon_temp {
+	struct list_head hwmon_node;
+	struct thermal_zone_device *tz;
+	struct thermal_hwmon_attr temp_input;	/* hwmon sys attr */
+	struct thermal_hwmon_attr temp_crit;	/* hwmon sys attr */
+};
+
+static LIST_HEAD(thermal_hwmon_list);
+
+static DEFINE_MUTEX(thermal_hwmon_list_lock);
+
+static ssize_t
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
+	return sprintf(buf, "%s\n", hwmon->type);
+}
+static DEVICE_ATTR(name, 0444, name_show, NULL);
+
+static ssize_t
+temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	long temperature;
+	int ret;
+	struct thermal_hwmon_attr *hwmon_attr
+			= container_of(attr, struct thermal_hwmon_attr, attr);
+	struct thermal_hwmon_temp *temp
+			= container_of(hwmon_attr, struct thermal_hwmon_temp,
+				       temp_input);
+	struct thermal_zone_device *tz = temp->tz;
+
+	ret = thermal_zone_get_temp(tz, &temperature);
+
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%ld\n", temperature);
+}
+
+static ssize_t
+temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct thermal_hwmon_attr *hwmon_attr
+			= container_of(attr, struct thermal_hwmon_attr, attr);
+	struct thermal_hwmon_temp *temp
+			= container_of(hwmon_attr, struct thermal_hwmon_temp,
+				       temp_crit);
+	struct thermal_zone_device *tz = temp->tz;
+	long temperature;
+	int ret;
+
+	ret = tz->ops->get_trip_temp(tz, 0, &temperature);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%ld\n", temperature);
+}
+
+
+static struct thermal_hwmon_device *
+thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
+{
+	struct thermal_hwmon_device *hwmon;
+
+	mutex_lock(&thermal_hwmon_list_lock);
+	list_for_each_entry(hwmon, &thermal_hwmon_list, node)
+		if (!strcmp(hwmon->type, tz->type)) {
+			mutex_unlock(&thermal_hwmon_list_lock);
+			return hwmon;
+		}
+	mutex_unlock(&thermal_hwmon_list_lock);
+
+	return NULL;
+}
+
+/* Find the temperature input matching a given thermal zone */
+static struct thermal_hwmon_temp *
+thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
+			  const struct thermal_zone_device *tz)
+{
+	struct thermal_hwmon_temp *temp;
+
+	mutex_lock(&thermal_hwmon_list_lock);
+	list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
+		if (temp->tz == tz) {
+			mutex_unlock(&thermal_hwmon_list_lock);
+			return temp;
+		}
+	mutex_unlock(&thermal_hwmon_list_lock);
+
+	return NULL;
+}
+
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+	struct thermal_hwmon_device *hwmon;
+	struct thermal_hwmon_temp *temp;
+	int new_hwmon_device = 1;
+	int result;
+
+	hwmon = thermal_hwmon_lookup_by_type(tz);
+	if (hwmon) {
+		new_hwmon_device = 0;
+		goto register_sys_interface;
+	}
+
+	hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&hwmon->tz_list);
+	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
+	hwmon->device = hwmon_device_register(NULL);
+	if (IS_ERR(hwmon->device)) {
+		result = PTR_ERR(hwmon->device);
+		goto free_mem;
+	}
+	dev_set_drvdata(hwmon->device, hwmon);
+	result = device_create_file(hwmon->device, &dev_attr_name);
+	if (result)
+		goto free_mem;
+
+ register_sys_interface:
+	temp = kzalloc(sizeof(*temp), GFP_KERNEL);
+	if (!temp) {
+		result = -ENOMEM;
+		goto unregister_name;
+	}
+
+	temp->tz = tz;
+	hwmon->count++;
+
+	snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
+		 "temp%d_input", hwmon->count);
+	temp->temp_input.attr.attr.name = temp->temp_input.name;
+	temp->temp_input.attr.attr.mode = 0444;
+	temp->temp_input.attr.show = temp_input_show;
+	sysfs_attr_init(&temp->temp_input.attr.attr);
+	result = device_create_file(hwmon->device, &temp->temp_input.attr);
+	if (result)
+		goto free_temp_mem;
+
+	if (tz->ops->get_crit_temp) {
+		unsigned long temperature;
+		if (!tz->ops->get_crit_temp(tz, &temperature)) {
+			snprintf(temp->temp_crit.name,
+				 sizeof(temp->temp_crit.name),
+				"temp%d_crit", hwmon->count);
+			temp->temp_crit.attr.attr.name = temp->temp_crit.name;
+			temp->temp_crit.attr.attr.mode = 0444;
+			temp->temp_crit.attr.show = temp_crit_show;
+			sysfs_attr_init(&temp->temp_crit.attr.attr);
+			result = device_create_file(hwmon->device,
+						    &temp->temp_crit.attr);
+			if (result)
+				goto unregister_input;
+		}
+	}
+
+	mutex_lock(&thermal_hwmon_list_lock);
+	if (new_hwmon_device)
+		list_add_tail(&hwmon->node, &thermal_hwmon_list);
+	list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
+	mutex_unlock(&thermal_hwmon_list_lock);
+
+	return 0;
+
+ unregister_input:
+	device_remove_file(hwmon->device, &temp->temp_input.attr);
+ free_temp_mem:
+	kfree(temp);
+ unregister_name:
+	if (new_hwmon_device) {
+		device_remove_file(hwmon->device, &dev_attr_name);
+		hwmon_device_unregister(hwmon->device);
+	}
+ free_mem:
+	if (new_hwmon_device)
+		kfree(hwmon);
+
+	return result;
+}
+
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+	struct thermal_hwmon_device *hwmon;
+	struct thermal_hwmon_temp *temp;
+
+	hwmon = thermal_hwmon_lookup_by_type(tz);
+	if (unlikely(!hwmon)) {
+		/* Should never happen... */
+		dev_dbg(&tz->device, "hwmon device lookup failed!\n");
+		return;
+	}
+
+	temp = thermal_hwmon_lookup_temp(hwmon, tz);
+	if (unlikely(!temp)) {
+		/* Should never happen... */
+		dev_dbg(&tz->device, "temperature input lookup failed!\n");
+		return;
+	}
+
+	device_remove_file(hwmon->device, &temp->temp_input.attr);
+	if (tz->ops->get_crit_temp)
+		device_remove_file(hwmon->device, &temp->temp_crit.attr);
+
+	mutex_lock(&thermal_hwmon_list_lock);
+	list_del(&temp->hwmon_node);
+	kfree(temp);
+	if (!list_empty(&hwmon->tz_list)) {
+		mutex_unlock(&thermal_hwmon_list_lock);
+		return;
+	}
+	list_del(&hwmon->node);
+	mutex_unlock(&thermal_hwmon_list_lock);
+
+	device_remove_file(hwmon->device, &dev_attr_name);
+	hwmon_device_unregister(hwmon->device);
+	kfree(hwmon);
+}
diff --git a/drivers/thermal/thermal_hwmon.h b/drivers/thermal/thermal_hwmon.h
new file mode 100644
index 000000000000..c798fdb2ae43
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.h
@@ -0,0 +1,49 @@
+/*
+ *  thermal_hwmon.h - Generic Thermal Management hwmon support.
+ *
+ *  Code based on Intel thermal_core.c. Copyrights of the original code:
+ *  Copyright (C) 2008 Intel Corp
+ *  Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ *  Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ *  Copyright (C) 2013 Texas Instruments
+ *  Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef __THERMAL_HWMON_H__
+#define __THERMAL_HWMON_H__
+
+#include <linux/thermal.h>
+
+#ifdef CONFIG_THERMAL_HWMON
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz);
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz);
+#else
+static int
+thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+	return 0;
+}
+
+static void
+thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+}
+#endif
+
+#endif /* __THERMAL_HWMON_H__ */
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index eb255e807c06..f179033eaa3e 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/major.h>
+#include <linux/atomic.h>
 #include <linux/sysrq.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
@@ -70,6 +71,9 @@ static struct task_struct *hvc_task;
 /* Picks up late kicks after list walk but before schedule() */
 static int hvc_kicked;
 
+/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
+static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
+
 static int hvc_init(void);
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -186,7 +190,7 @@ static struct tty_driver *hvc_console_device(struct console *c, int *index)
 	return hvc_driver;
 }
 
-static int __init hvc_console_setup(struct console *co, char *options)
+static int hvc_console_setup(struct console *co, char *options)
 {	
 	if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES)
 		return -ENODEV;
@@ -842,7 +846,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	int i;
 
 	/* We wait until a driver actually comes along */
-	if (!hvc_driver) {
+	if (atomic_inc_not_zero(&hvc_needs_init)) {
 		int err = hvc_init();
 		if (err)
 			return ERR_PTR(err);
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 682210d778bd..4fc32c8091e9 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -636,6 +636,7 @@ struct console xenboot_console = {
 	.name		= "xenboot",
 	.write		= xenboot_write_console,
 	.flags		= CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME,
+	.index		= -1,
 };
 #endif	/* CONFIG_EARLY_PRINTK */
 
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 642239015b46..3ee7217e25b2 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1089,6 +1089,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, u8 *data, int clen)
 {
 	unsigned int addr = 0;
 	unsigned int modem = 0;
+	unsigned int brk = 0;
 	struct gsm_dlci *dlci;
 	int len = clen;
 	u8 *dp = data;
@@ -1115,6 +1116,16 @@ static void gsm_control_modem(struct gsm_mux *gsm, u8 *data, int clen)
 		if (len == 0)
 			return;
 	}
+	len--;
+	if (len > 0) {
+		while (gsm_read_ea(&brk, *dp++) == 0) {
+			len--;
+			if (len == 0)
+				return;
+		}
+		modem <<= 7;
+		modem |= (brk & 0x7f);
+	}
 	tty = tty_port_tty_get(&dlci->port);
 	gsm_process_modem(tty, dlci, modem, clen);
 	if (tty) {
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 6c7fe90ad72d..6cfe4019abc6 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2066,8 +2066,12 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 			if (tty->ops->flush_chars)
 				tty->ops->flush_chars(tty);
 		} else {
+			struct n_tty_data *ldata = tty->disc_data;
+
 			while (nr > 0) {
+				mutex_lock(&ldata->output_lock);
 				c = tty->ops->write(tty, b, nr);
+				mutex_unlock(&ldata->output_lock);
 				if (c < 0) {
 					retval = c;
 					goto break_out;
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 86c00b1c5583..d8c06a3d391e 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -555,7 +555,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 	 */
 	if ((p->port.type == PORT_XR17V35X) ||
 	   (p->port.type == PORT_XR17D15X)) {
-		serial_out(p, UART_EXAR_SLEEP, 0xff);
+		serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0);
 		return;
 	}
 
@@ -1520,7 +1520,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 			status = serial8250_rx_chars(up, status);
 	}
 	serial8250_modem_status(up);
-	if (status & UART_LSR_THRE)
+	if (!up->dma && (status & UART_LSR_THRE))
 		serial8250_tx_chars(up);
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -2670,6 +2670,10 @@ static void serial8250_config_port(struct uart_port *port, int flags)
 	if (port->type == PORT_16550A && port->iotype == UPIO_AU)
 		up->bugs |= UART_BUG_NOMSR;
 
+	/* HW bugs may trigger IRQ while IIR == NO_INT */
+	if (port->type == PORT_TEGRA)
+		up->bugs |= UART_BUG_NOMSR;
+
 	if (port->type != PORT_UNKNOWN && flags & UART_CONFIG_IRQ)
 		autoconfig_irq(up);
 
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index 7046769608d4..148ffe4c232f 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -20,12 +20,15 @@ static void __dma_tx_complete(void *param)
 	struct uart_8250_port	*p = param;
 	struct uart_8250_dma	*dma = p->dma;
 	struct circ_buf		*xmit = &p->port.state->xmit;
-
-	dma->tx_running = 0;
+	unsigned long	flags;
 
 	dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 
+	spin_lock_irqsave(&p->port.lock, flags);
+
+	dma->tx_running = 0;
+
 	xmit->tail += dma->tx_size;
 	xmit->tail &= UART_XMIT_SIZE - 1;
 	p->port.icount.tx += dma->tx_size;
@@ -35,6 +38,8 @@ static void __dma_tx_complete(void *param)
 
 	if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port))
 		serial8250_tx_dma(p);
+
+	spin_unlock_irqrestore(&p->port.lock, flags);
 }
 
 static void __dma_rx_complete(void *param)
@@ -187,21 +192,28 @@ int serial8250_request_dma(struct uart_8250_port *p)
 
 	dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size,
 					&dma->rx_addr, GFP_KERNEL);
-	if (!dma->rx_buf) {
-		dma_release_channel(dma->rxchan);
-		dma_release_channel(dma->txchan);
-		return -ENOMEM;
-	}
+	if (!dma->rx_buf)
+		goto err;
 
 	/* TX buffer */
 	dma->tx_addr = dma_map_single(dma->txchan->device->dev,
 					p->port.state->xmit.buf,
 					UART_XMIT_SIZE,
 					DMA_TO_DEVICE);
+	if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) {
+		dma_free_coherent(dma->rxchan->device->dev, dma->rx_size,
+				  dma->rx_buf, dma->rx_addr);
+		goto err;
+	}
 
 	dev_dbg_ratelimited(p->port.dev, "got both dma channels\n");
 
 	return 0;
+err:
+	dma_release_channel(dma->rxchan);
+	dma_release_channel(dma->txchan);
+
+	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(serial8250_request_dma);
 
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index d07b6af3a937..345b5ddcb1a0 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -54,58 +54,100 @@
 
 
 struct dw8250_data {
-	int		last_lcr;
+	int		last_mcr;
 	int		line;
 	struct clk	*clk;
 };
 
+static inline int dw8250_modify_msr(struct uart_port *p, int offset, int value)
+{
+	struct dw8250_data *d = p->private_data;
+
+	/* If reading MSR, report CTS asserted when auto-CTS/RTS enabled */
+	if (offset == UART_MSR && d->last_mcr & UART_MCR_AFE) {
+		value |= UART_MSR_CTS;
+		value &= ~UART_MSR_DCTS;
+	}
+
+	return value;
+}
+
+static void dw8250_force_idle(struct uart_port *p)
+{
+	serial8250_clear_and_reinit_fifos(container_of
+					  (p, struct uart_8250_port, port));
+	(void)p->serial_in(p, UART_RX);
+}
+
 static void dw8250_serial_out(struct uart_port *p, int offset, int value)
 {
 	struct dw8250_data *d = p->private_data;
 
-	if (offset == UART_LCR)
-		d->last_lcr = value;
+	if (offset == UART_MCR)
+		d->last_mcr = value;
+
+	writeb(value, p->membase + (offset << p->regshift));
 
-	offset <<= p->regshift;
-	writeb(value, p->membase + offset);
+	/* Make sure LCR write wasn't ignored */
+	if (offset == UART_LCR) {
+		int tries = 1000;
+		while (tries--) {
+			unsigned int lcr = p->serial_in(p, UART_LCR);
+			if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
+				return;
+			dw8250_force_idle(p);
+			writeb(value, p->membase + (UART_LCR << p->regshift));
+		}
+		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+	}
 }
 
 static unsigned int dw8250_serial_in(struct uart_port *p, int offset)
 {
-	offset <<= p->regshift;
+	unsigned int value = readb(p->membase + (offset << p->regshift));
 
-	return readb(p->membase + offset);
+	return dw8250_modify_msr(p, offset, value);
 }
 
 static void dw8250_serial_out32(struct uart_port *p, int offset, int value)
 {
 	struct dw8250_data *d = p->private_data;
 
-	if (offset == UART_LCR)
-		d->last_lcr = value;
+	if (offset == UART_MCR)
+		d->last_mcr = value;
 
-	offset <<= p->regshift;
-	writel(value, p->membase + offset);
+	writel(value, p->membase + (offset << p->regshift));
+
+	/* Make sure LCR write wasn't ignored */
+	if (offset == UART_LCR) {
+		int tries = 1000;
+		while (tries--) {
+			unsigned int lcr = p->serial_in(p, UART_LCR);
+			if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
+				return;
+			dw8250_force_idle(p);
+			writel(value, p->membase + (UART_LCR << p->regshift));
+		}
+		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+	}
 }
 
 static unsigned int dw8250_serial_in32(struct uart_port *p, int offset)
 {
-	offset <<= p->regshift;
+	unsigned int value = readl(p->membase + (offset << p->regshift));
 
-	return readl(p->membase + offset);
+	return dw8250_modify_msr(p, offset, value);
 }
 
 static int dw8250_handle_irq(struct uart_port *p)
 {
-	struct dw8250_data *d = p->private_data;
 	unsigned int iir = p->serial_in(p, UART_IIR);
 
 	if (serial8250_handle_irq(p, iir)) {
 		return 1;
 	} else if ((iir & UART_IIR_BUSY) == UART_IIR_BUSY) {
-		/* Clear the USR and write the LCR again. */
+		/* Clear the USR */
 		(void)p->serial_in(p, DW_UART_USR);
-		p->serial_out(p, UART_LCR, d->last_lcr);
 
 		return 1;
 	}
@@ -369,6 +411,8 @@ MODULE_DEVICE_TABLE(of, dw8250_of_match);
 static const struct acpi_device_id dw8250_acpi_match[] = {
 	{ "INT33C4", 0 },
 	{ "INT33C5", 0 },
+	{ "INT3434", 0 },
+	{ "INT3435", 0 },
 	{ "80860F0A", 0 },
 	{ },
 };
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 721904f8efa9..4858b8a99d3b 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -35,18 +35,8 @@
 #include <linux/serial_8250.h>
 #include <asm/io.h>
 #include <asm/serial.h>
-#ifdef CONFIG_FIX_EARLYCON_MEM
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#endif
 
-struct early_serial8250_device {
-	struct uart_port port;
-	char options[16];		/* e.g., 115200n8 */
-	unsigned int baud;
-};
-
-static struct early_serial8250_device early_device;
+static struct earlycon_device *early_device;
 
 unsigned int __weak __init serial8250_early_in(struct uart_port *port, int offset)
 {
@@ -100,7 +90,7 @@ static void __init serial_putc(struct uart_port *port, int c)
 static void __init early_serial8250_write(struct console *console,
 					const char *s, unsigned int count)
 {
-	struct uart_port *port = &early_device.port;
+	struct uart_port *port = &early_device->port;
 	unsigned int ier;
 
 	/* Save the IER and disable interrupts */
@@ -129,7 +119,7 @@ static unsigned int __init probe_baud(struct uart_port *port)
 	return (port->uartclk / 16) / quot;
 }
 
-static void __init init_port(struct early_serial8250_device *device)
+static void __init init_port(struct earlycon_device *device)
 {
 	struct uart_port *port = &device->port;
 	unsigned int divisor;
@@ -148,127 +138,45 @@ static void __init init_port(struct early_serial8250_device *device)
 	serial8250_early_out(port, UART_LCR, c & ~UART_LCR_DLAB);
 }
 
-static int __init parse_options(struct early_serial8250_device *device,
-								char *options)
+static int __init early_serial8250_setup(struct earlycon_device *device,
+					 const char *options)
 {
-	struct uart_port *port = &device->port;
-	int mmio, mmio32, length;
-
-	if (!options)
-		return -ENODEV;
-
-	port->uartclk = BASE_BAUD * 16;
-
-	mmio = !strncmp(options, "mmio,", 5);
-	mmio32 = !strncmp(options, "mmio32,", 7);
-	if (mmio || mmio32) {
-		port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
-		port->mapbase = simple_strtoul(options + (mmio ? 5 : 7),
-					       &options, 0);
-		if (mmio32)
-			port->regshift = 2;
-#ifdef CONFIG_FIX_EARLYCON_MEM
-		set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
-					port->mapbase & PAGE_MASK);
-		port->membase =
-			(void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
-		port->membase += port->mapbase & ~PAGE_MASK;
-#else
-		port->membase = ioremap_nocache(port->mapbase, 64);
-		if (!port->membase) {
-			printk(KERN_ERR "%s: Couldn't ioremap 0x%llx\n",
-				__func__,
-			       (unsigned long long) port->mapbase);
-			return -ENOMEM;
-		}
-#endif
-	} else if (!strncmp(options, "io,", 3)) {
-		port->iotype = UPIO_PORT;
-		port->iobase = simple_strtoul(options + 3, &options, 0);
-		mmio = 0;
-	} else
-		return -EINVAL;
+	if (!(device->port.membase || device->port.iobase))
+		return 0;
 
-	options = strchr(options, ',');
-	if (options) {
-		options++;
-		device->baud = simple_strtoul(options, NULL, 0);
-		length = min(strcspn(options, " "), sizeof(device->options));
-		strlcpy(device->options, options, length);
-	} else {
-		device->baud = probe_baud(port);
+	if (!device->baud) {
+		device->baud = probe_baud(&device->port);
 		snprintf(device->options, sizeof(device->options), "%u",
-			device->baud);
+			 device->baud);
 	}
 
-	if (mmio || mmio32)
-		printk(KERN_INFO
-		       "Early serial console at MMIO%s 0x%llx (options '%s')\n",
-			mmio32 ? "32" : "",
-			(unsigned long long)port->mapbase,
-			device->options);
-	else
-		printk(KERN_INFO
-		      "Early serial console at I/O port 0x%lx (options '%s')\n",
-			port->iobase,
-			device->options);
-
-	return 0;
-}
-
-static struct console early_serial8250_console __initdata = {
-	.name	= "uart",
-	.write	= early_serial8250_write,
-	.flags	= CON_PRINTBUFFER | CON_BOOT,
-	.index	= -1,
-};
-
-static int __init early_serial8250_setup(char *options)
-{
-	struct early_serial8250_device *device = &early_device;
-	int err;
-
-	if (device->port.membase || device->port.iobase)
-		return 0;
-
-	err = parse_options(device, options);
-	if (err < 0)
-		return err;
-
 	init_port(device);
+
+	early_device = device;
+	device->con->write = early_serial8250_write;
 	return 0;
 }
+EARLYCON_DECLARE(uart8250, early_serial8250_setup);
+EARLYCON_DECLARE(uart, early_serial8250_setup);
 
 int __init setup_early_serial8250_console(char *cmdline)
 {
-	char *options;
-	int err;
+	char match[] = "uart8250";
 
-	options = strstr(cmdline, "uart8250,");
-	if (!options) {
-		options = strstr(cmdline, "uart,");
-		if (!options)
-			return 0;
-	}
-
-	options = strchr(cmdline, ',') + 1;
-	err = early_serial8250_setup(options);
-	if (err < 0)
-		return err;
-
-	register_console(&early_serial8250_console);
+	if (cmdline && cmdline[4] == ',')
+		match[4] = '\0';
 
-	return 0;
+	return setup_earlycon(cmdline, match, early_serial8250_setup);
 }
 
 int serial8250_find_port_for_earlycon(void)
 {
-	struct early_serial8250_device *device = &early_device;
-	struct uart_port *port = &device->port;
+	struct earlycon_device *device = early_device;
+	struct uart_port *port = device ? &device->port : NULL;
 	int line;
 	int ret;
 
-	if (!device->port.membase && !device->port.iobase)
+	if (!port || (!port->membase && !port->iobase))
 		return -ENODEV;
 
 	line = serial8250_find_port(port);
@@ -283,5 +191,3 @@ int serial8250_find_port_for_earlycon(void)
 
 	return ret;
 }
-
-early_param("earlycon", setup_early_serial8250_console);
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index c52948b368d8..8d3c0b5e2878 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1260,10 +1260,10 @@ static int pci_quatech_init(struct pci_dev *dev)
 		unsigned long base = pci_resource_start(dev, 0);
 		if (base) {
 			u32 tmp;
-			outl(inl(base + 0x38), base + 0x38);
+			outl(inl(base + 0x38) | 0x00002000, base + 0x38);
 			tmp = inl(base + 0x3c);
 			outl(tmp | 0x01000000, base + 0x3c);
-			outl(tmp, base + 0x3c);
+			outl(tmp &= ~0x01000000, base + 0x3c);
 		}
 	}
 	return 0;
@@ -1545,6 +1545,7 @@ pci_wch_ch353_setup(struct serial_private *priv,
 #define PCI_DEVICE_ID_TITAN_800E	0xA014
 #define PCI_DEVICE_ID_TITAN_200EI	0xA016
 #define PCI_DEVICE_ID_TITAN_200EISI	0xA017
+#define PCI_DEVICE_ID_TITAN_200V3	0xA306
 #define PCI_DEVICE_ID_TITAN_400V3	0xA310
 #define PCI_DEVICE_ID_TITAN_410V3	0xA312
 #define PCI_DEVICE_ID_TITAN_800V3	0xA314
@@ -4139,6 +4140,9 @@ static struct pci_device_id serial_pci_tbl[] = {
 	{	PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_200EISI,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_oxsemi_2_4000000 },
+	{	PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_200V3,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_bt_2_921600 },
 	{	PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_400V3,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_b0_4_921600 },
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index 80fe91e64a52..902c4bf15f0b 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -62,6 +62,7 @@ config SERIAL_8250_CONSOLE
 	bool "Console on 8250/16550 and compatible serial port"
 	depends on SERIAL_8250=y
 	select SERIAL_CORE_CONSOLE
+	select SERIAL_EARLYCON
 	---help---
 	  If you say Y here, it will be possible to use a serial port as the
 	  system console (the system console is the device which receives all
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 7e7006fd404e..1ad9aadc0055 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -7,6 +7,13 @@ if TTY
 menu "Serial drivers"
 	depends on HAS_IOMEM && GENERIC_HARDIRQS
 
+config SERIAL_EARLYCON
+	bool
+	help
+	  Support for early consoles with the earlycon parameter. This enables
+	  the console before standard serial driver is probed. The console is
+	  enabled when early_param is processed.
+
 source "drivers/tty/serial/8250/Kconfig"
 
 comment "Non-8250 serial port support"
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index eedfec40e3dd..e51c680d6044 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -5,6 +5,8 @@
 obj-$(CONFIG_SERIAL_CORE) += serial_core.o
 obj-$(CONFIG_SERIAL_21285) += 21285.o
 
+obj-$(CONFIG_SERIAL_EARLYCON) += earlycon.o
+
 # These Sparc drivers have to appear before others such as 8250
 # which share ttySx minor node space.  Otherwise console device
 # names change and other unplesantries.
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 13471dd95793..d983370eb05b 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -231,7 +231,9 @@ static void altera_uart_rx_chars(struct altera_uart *pp)
 				 flag);
 	}
 
+	spin_unlock(&port->lock);
 	tty_flip_buffer_push(&port->state->port);
+	spin_lock(&port->lock);
 }
 
 static void altera_uart_tx_chars(struct altera_uart *pp)
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index e2774f9ecd59..7a55fe70434a 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1543,6 +1543,8 @@ static int pl011_startup(struct uart_port *port)
 	/*
 	 * Provoke TX FIFO interrupt into asserting.
 	 */
+	spin_lock_irq(&uap->port.lock);
+
 	cr = UART01x_CR_UARTEN | UART011_CR_TXE | UART011_CR_LBE;
 	writew(cr, uap->port.membase + UART011_CR);
 	writew(0, uap->port.membase + UART011_FBRD);
@@ -1567,6 +1569,8 @@ static int pl011_startup(struct uart_port *port)
 	cr |= UART01x_CR_UARTEN | UART011_CR_RXE | UART011_CR_TXE;
 	writew(cr, uap->port.membase + UART011_CR);
 
+	spin_unlock_irq(&uap->port.lock);
+
 	/*
 	 * initialise the old status of the modem signals
 	 */
@@ -1636,11 +1640,13 @@ static void pl011_shutdown(struct uart_port *port)
 	 * it during startup().
 	 */
 	uap->autorts = false;
+	spin_lock_irq(&uap->port.lock);
 	cr = readw(uap->port.membase + UART011_CR);
 	uap->old_cr = cr;
 	cr &= UART011_CR_RTS | UART011_CR_DTR;
 	cr |= UART01x_CR_UARTEN | UART011_CR_TXE;
 	writew(cr, uap->port.membase + UART011_CR);
+	spin_unlock_irq(&uap->port.lock);
 
 	/*
 	 * disable break condition and fifos
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3467462869ce..82127ac26d6f 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1022,12 +1022,24 @@ static int atmel_startup(struct uart_port *port)
 static void atmel_shutdown(struct uart_port *port)
 {
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
+
 	/*
-	 * Ensure everything is stopped.
+	 * Clear out any scheduled tasklets before
+	 * we destroy the buffers
+	 */
+	tasklet_kill(&atmel_port->tasklet);
+
+	/*
+	 * Ensure everything is stopped and
+	 * disable all interrupts, port and break condition.
 	 */
 	atmel_stop_rx(port);
 	atmel_stop_tx(port);
 
+	UART_PUT_CR(port, ATMEL_US_RSTSTA);
+	UART_PUT_IDR(port, -1);
+
+
 	/*
 	 * Shut-down the DMA.
 	 */
@@ -1054,12 +1066,6 @@ static void atmel_shutdown(struct uart_port *port)
 	}
 
 	/*
-	 * Disable all interrupts, port and break condition.
-	 */
-	UART_PUT_CR(port, ATMEL_US_RSTSTA);
-	UART_PUT_IDR(port, -1);
-
-	/*
 	 * Free the interrupt
 	 */
 	free_irq(port->irq, port);
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
new file mode 100644
index 000000000000..4f27f788ac6f
--- /dev/null
+++ b/drivers/tty/serial/earlycon.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Rob Herring <robh@kernel.org>
+ *
+ * Based on 8250 earlycon:
+ * (c) Copyright 2004 Hewlett-Packard Development Company, L.P.
+ *	Bjorn Helgaas <bjorn.helgaas@hp.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/serial_core.h>
+
+#ifdef CONFIG_FIX_EARLYCON_MEM
+#include <asm/fixmap.h>
+#endif
+
+#include <asm/serial.h>
+
+static struct console early_con = {
+	.name =		"uart", /* 8250 console switch requires this name */
+	.flags =	CON_PRINTBUFFER | CON_BOOT,
+	.index =	-1,
+};
+
+static struct earlycon_device early_console_dev = {
+	.con = &early_con,
+};
+
+static void __iomem * __init earlycon_map(unsigned long paddr, size_t size)
+{
+	void __iomem *base;
+#ifdef CONFIG_FIX_EARLYCON_MEM
+	set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr & PAGE_MASK);
+	base = (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
+	base += paddr & ~PAGE_MASK;
+#else
+	base = ioremap(paddr, size);
+#endif
+	if (!base)
+		pr_err("%s: Couldn't map 0x%llx\n", __func__,
+		       (unsigned long long)paddr);
+
+	return base;
+}
+
+static int __init parse_options(struct earlycon_device *device,
+				char *options)
+{
+	struct uart_port *port = &device->port;
+	int mmio, mmio32, length, ret;
+	unsigned long addr;
+
+	if (!options)
+		return -ENODEV;
+
+	mmio = !strncmp(options, "mmio,", 5);
+	mmio32 = !strncmp(options, "mmio32,", 7);
+	if (mmio || mmio32) {
+		port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
+		options += mmio ? 5 : 7;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->mapbase = addr;
+		if (mmio32)
+			port->regshift = 2;
+	} else if (!strncmp(options, "io,", 3)) {
+		port->iotype = UPIO_PORT;
+		options += 3;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->iobase = addr;
+		mmio = 0;
+	} else if (!strncmp(options, "0x", 2)) {
+		port->iotype = UPIO_MEM;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->mapbase = addr;
+	} else {
+		return -EINVAL;
+	}
+
+	port->uartclk = BASE_BAUD * 16;
+
+	options = strchr(options, ',');
+	if (options) {
+		options++;
+		ret = kstrtouint(options, 0, &device->baud);
+		if (ret)
+			return ret;
+		length = min(strcspn(options, " ") + 1,
+			     (size_t)(sizeof(device->options)));
+		strlcpy(device->options, options, length);
+	}
+
+	if (mmio || mmio32)
+		pr_info("Early serial console at MMIO%s 0x%llx (options '%s')\n",
+			mmio32 ? "32" : "",
+			(unsigned long long)port->mapbase,
+			device->options);
+	else
+		pr_info("Early serial console at I/O port 0x%lx (options '%s')\n",
+			port->iobase,
+			device->options);
+
+	return 0;
+}
+
+int __init setup_earlycon(char *buf, const char *match,
+			  int (*setup)(struct earlycon_device *, const char *))
+{
+	int err;
+	size_t len;
+	struct uart_port *port = &early_console_dev.port;
+
+	if (!buf || !match || !setup)
+		return 0;
+
+	len = strlen(match);
+	if (strncmp(buf, match, len))
+		return 0;
+	if (buf[len] && (buf[len] != ','))
+		return 0;
+
+	buf += len + 1;
+
+	err = parse_options(&early_console_dev, buf);
+	/* On parsing error, pass the options buf to the setup function */
+	if (!err)
+		buf = NULL;
+
+	if (port->mapbase)
+		port->membase = earlycon_map(port->mapbase, 64);
+
+	early_console_dev.con->data = &early_console_dev;
+	err = setup(&early_console_dev, buf);
+	if (err < 0)
+		return err;
+	if (!early_console_dev.con->write)
+		return -ENODEV;
+
+	register_console(early_console_dev.con);
+	return 0;
+}
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 572d48189de9..20e4c9446992 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -658,11 +658,12 @@ static int dma_push_rx(struct eg20t_port *priv, int size)
 		dev_warn(port->dev, "Rx overrun: dropping %u bytes\n",
 			 size - room);
 	if (!room)
-		return room;
+		goto out;
 
 	tty_insert_flip_string(tport, sg_virt(&priv->sg_rx), size);
 
 	port->icount.rx += room;
+out:
 	tty_kref_put(tty);
 
 	return room;
@@ -1071,6 +1072,8 @@ static void pch_uart_err_ir(struct eg20t_port *priv, unsigned int lsr)
 	if (tty == NULL) {
 		for (i = 0; error_msg[i] != NULL; i++)
 			dev_err(&priv->pdev->dev, error_msg[i]);
+	} else {
+		tty_kref_put(tty);
 	}
 }
 
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index b1785f58b6e3..7735bbdccbc9 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -2051,6 +2051,9 @@ static int __init pmz_console_init(void)
 	/* Probe ports */
 	pmz_probe();
 
+	if (pmz_ports_count == 0)
+		return -ENODEV;
+
 	/* TODO: Autoprobe console based on OF */
 	/* pmz_console.index = i; */
 	register_console(&pmz_console);
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 0c8a9fa2be6c..4522aac4449b 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -249,6 +249,8 @@ s3c24xx_serial_rx_chars(int irq, void *dev_id)
 					ufcon |= S3C2410_UFCON_RESETRX;
 					wr_regl(port, S3C2410_UFCON, ufcon);
 					rx_enabled(port) = 1;
+					spin_unlock_irqrestore(&port->lock,
+							flags);
 					goto out;
 				}
 				continue;
@@ -297,10 +299,11 @@ s3c24xx_serial_rx_chars(int irq, void *dev_id)
  ignore_char:
 		continue;
 	}
+
+	spin_unlock_irqrestore(&port->lock, flags);
 	tty_flip_buffer_push(&port->state->port);
 
  out:
-	spin_unlock_irqrestore(&port->lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -534,11 +537,15 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level,
 			      unsigned int old)
 {
 	struct s3c24xx_uart_port *ourport = to_ourport(port);
+	int timeout = 10000;
 
 	ourport->pm_level = level;
 
 	switch (level) {
 	case 3:
+		while (--timeout && !s3c24xx_serial_txempty_nofifo(port))
+			udelay(100);
+
 		if (!IS_ERR(ourport->baudclk))
 			clk_disable_unprepare(ourport->baudclk);
 
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 9799d043a9bd..357a8370ce2a 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -726,7 +726,7 @@ static irqreturn_t tegra_uart_isr(int irq, void *data)
 static void tegra_uart_stop_rx(struct uart_port *u)
 {
 	struct tegra_uart_port *tup = to_tegra_uport(u);
-	struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port);
+	struct tty_struct *tty;
 	struct tty_port *port = &u->state->port;
 	struct dma_tx_state state;
 	unsigned long ier;
@@ -738,6 +738,8 @@ static void tegra_uart_stop_rx(struct uart_port *u)
 	if (!tup->rx_in_progress)
 		return;
 
+	tty = tty_port_tty_get(&tup->uport.state->port);
+
 	tegra_uart_wait_sym_time(tup, 1); /* wait a character interval */
 
 	ier = tup->ier_shadow;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f87dbfd32770..1fabb22ae615 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -241,6 +241,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state)
 		/*
 		 * Turn off DTR and RTS early.
 		 */
+		if (uart_console(uport) && tty)
+			uport->cons->cflag = tty->termios.c_cflag;
+
 		if (!tty || (tty->termios.c_cflag & HUPCL))
 			uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
 
@@ -356,7 +359,7 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		 * The spd_hi, spd_vhi, spd_shi, spd_warp kludge...
 		 * Die! Die! Die!
 		 */
-		if (baud == 38400)
+		if (try == 0 && baud == 38400)
 			baud = altbaud;
 
 		/*
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index a422c8b55a47..aa53fee1df63 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up,
 	    (up->port.line == up->port.cons->index))
 		saw_console_brk = 1;
 
+	if (count == 0) {
+		if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) {
+			stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR |
+					     SAB82532_ISR0_FERR);
+			up->port.icount.brk++;
+			uart_handle_break(&up->port);
+		}
+	}
+
 	for (i = 0; i < count; i++) {
 		unsigned char ch = buf[i], flag;
 
diff --git a/drivers/tty/serial/vt8500_serial.c b/drivers/tty/serial/vt8500_serial.c
index 1a8bc2275ea4..f72b43fbbef9 100644
--- a/drivers/tty/serial/vt8500_serial.c
+++ b/drivers/tty/serial/vt8500_serial.c
@@ -559,12 +559,13 @@ static int vt8500_serial_probe(struct platform_device *pdev)
 	if (!mmres || !irqres)
 		return -ENODEV;
 
-	if (np)
+	if (np) {
 		port = of_alias_get_id(np, "serial");
 		if (port >= VT8500_MAX_PORTS)
 			port = -1;
-	else
+	} else {
 		port = -1;
+	}
 
 	if (port < 0) {
 		/* calculate the port id */
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 59d26ef538d8..d35afccdb6c9 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1267,12 +1267,13 @@ static void pty_line_name(struct tty_driver *driver, int index, char *p)
  *
  *	Locking: None
  */
-static void tty_line_name(struct tty_driver *driver, int index, char *p)
+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
 {
 	if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE)
-		strcpy(p, driver->name);
+		return sprintf(p, "%s", driver->name);
 	else
-		sprintf(p, "%s%d", driver->name, index + driver->name_base);
+		return sprintf(p, "%s%d", driver->name,
+			       index + driver->name_base);
 }
 
 /**
@@ -1697,6 +1698,7 @@ int tty_release(struct inode *inode, struct file *filp)
 	int	pty_master, tty_closing, o_tty_closing, do_sleep;
 	int	idx;
 	char	buf[64];
+	long	timeout = 0;
 
 	if (tty_paranoia_check(tty, inode, __func__))
 		return 0;
@@ -1781,7 +1783,11 @@ int tty_release(struct inode *inode, struct file *filp)
 				__func__, tty_name(tty, buf));
 		tty_unlock_pair(tty, o_tty);
 		mutex_unlock(&tty_mutex);
-		schedule();
+		schedule_timeout_killable(timeout);
+		if (timeout < 120 * HZ)
+			timeout = 2 * timeout + 1;
+		else
+			timeout = MAX_SCHEDULE_TIMEOUT;
 	}
 
 	/*
@@ -3538,9 +3544,19 @@ static ssize_t show_cons_active(struct device *dev,
 		if (i >= ARRAY_SIZE(cs))
 			break;
 	}
-	while (i--)
-		count += sprintf(buf + count, "%s%d%c",
-				 cs[i]->name, cs[i]->index, i ? ' ':'\n');
+	while (i--) {
+		int index = cs[i]->index;
+		struct tty_driver *drv = cs[i]->device(cs[i], &index);
+
+		/* don't resolve tty0 as some programs depend on it */
+		if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
+			count += tty_line_name(drv, index, buf + count);
+		else
+			count += sprintf(buf + count, "%s%d",
+					 cs[i]->name, cs[i]->index);
+
+		count += sprintf(buf + count, "%c", i ? ' ':'\n');
+	}
 	console_unlock();
 
 	return count;
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 3500d4114147..088b4ca7d805 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -1201,6 +1201,9 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 		}
 		return 0;
 	case TCFLSH:
+		retval = tty_check_change(tty);
+		if (retval)
+			return retval;
 		return __tty_perform_flush(tty, arg);
 	default:
 		/* Try the mode commands */
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 740202d8a5c4..0d1b3757cfb6 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1164,6 +1164,8 @@ static void csi_J(struct vc_data *vc, int vpar)
 			scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
 				    vc->vc_screenbuf_size >> 1);
 			set_origin(vc);
+			if (CON_IS_VISIBLE(vc))
+				update_screen(vc);
 			/* fall through */
 		case 2: /* erase whole display */
 			count = vc->vc_cols * vc->vc_rows;
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index b645c47501b4..2d57a00dc173 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -630,36 +630,57 @@ static int uio_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return 0;
 }
 
-static const struct vm_operations_struct uio_vm_ops = {
+static const struct vm_operations_struct uio_logical_vm_ops = {
 	.open = uio_vma_open,
 	.close = uio_vma_close,
 	.fault = uio_vma_fault,
 };
 
+static int uio_mmap_logical(struct vm_area_struct *vma)
+{
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_ops = &uio_logical_vm_ops;
+	uio_vma_open(vma);
+	return 0;
+}
+
+static const struct vm_operations_struct uio_physical_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
 static int uio_mmap_physical(struct vm_area_struct *vma)
 {
 	struct uio_device *idev = vma->vm_private_data;
 	int mi = uio_find_mem_index(vma);
+	struct uio_mem *mem;
 	if (mi < 0)
 		return -EINVAL;
+	mem = idev->info->mem + mi;
 
+	if (vma->vm_end - vma->vm_start > mem->size)
+		return -EINVAL;
+
+	vma->vm_ops = &uio_physical_vm_ops;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
+	/*
+	 * We cannot use the vm_iomap_memory() helper here,
+	 * because vma->vm_pgoff is the map index we looked
+	 * up above in uio_find_mem_index(), rather than an
+	 * actual page offset into the mmap.
+	 *
+	 * So we just do the physical mmap without a page
+	 * offset.
+	 */
 	return remap_pfn_range(vma,
 			       vma->vm_start,
-			       idev->info->mem[mi].addr >> PAGE_SHIFT,
+			       mem->addr >> PAGE_SHIFT,
 			       vma->vm_end - vma->vm_start,
 			       vma->vm_page_prot);
 }
 
-static int uio_mmap_logical(struct vm_area_struct *vma)
-{
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_ops = &uio_vm_ops;
-	uio_vma_open(vma);
-	return 0;
-}
-
 static int uio_mmap(struct file *filep, struct vm_area_struct *vma)
 {
 	struct uio_listener *listener = filep->private_data;
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 92e1dc94ecc8..73f62caa8609 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -2,59 +2,15 @@
 # USB device configuration
 #
 
-# many non-PCI SOC chips embed OHCI
+# These are unused now, remove them once they are no longer selected
 config USB_ARCH_HAS_OHCI
-	boolean
-	# ARM:
-	default y if SA1111
-	default y if ARCH_OMAP
-	default y if ARCH_S3C24XX
-	default y if PXA27x
-	default y if PXA3xx
-	default y if ARCH_EP93XX
-	default y if ARCH_AT91
-	default y if MFD_TC6393XB
-	default y if ARCH_W90X900
-	default y if ARCH_DAVINCI_DA8XX
-	default y if ARCH_CNS3XXX
-	default y if PLAT_SPEAR
-	default y if ARCH_EXYNOS
-	# PPC:
-	default y if STB03xxx
-	default y if PPC_MPC52xx
-	# MIPS:
-	default y if MIPS_ALCHEMY
-	default y if MACH_JZ4740
-	# more:
-	default PCI
-
-# some non-PCI hcds implement EHCI
+	bool
+
 config USB_ARCH_HAS_EHCI
-	boolean
-	default y if FSL_SOC
-	default y if PPC_MPC512x
-	default y if ARCH_IXP4XX
-	default y if ARCH_W90X900
-	default y if ARCH_AT91
-	default y if ARCH_MXC
-	default y if ARCH_MXS
-	default y if ARCH_OMAP3
-	default y if ARCH_CNS3XXX
-	default y if ARCH_VT8500
-	default y if PLAT_SPEAR
-	default y if PLAT_S5P
-	default y if ARCH_MSM
-	default y if MICROBLAZE
-	default y if SPARC_LEON
-	default y if ARCH_MMP
-	default y if MACH_LOONGSON1
-	default y if PLAT_ORION
-	default PCI
-
-# some non-PCI HCDs implement xHCI
+	bool
+
 config USB_ARCH_HAS_XHCI
-	boolean
-	default PCI
+	bool
 
 menuconfig USB_SUPPORT
 	bool "USB support"
@@ -71,19 +27,8 @@ config USB_COMMON
 	default y
 	depends on USB || USB_GADGET
 
-# Host-side USB depends on having a host controller
-# NOTE:  dummy_hcd is always an option, but it's ignored here ...
-# NOTE:  SL-811 option should be board-specific ...
 config USB_ARCH_HAS_HCD
-	boolean
-	default y if USB_ARCH_HAS_OHCI
-	default y if USB_ARCH_HAS_EHCI
-	default y if USB_ARCH_HAS_XHCI
-	default y if PCMCIA && !M32R			# sl811_cs
-	default y if ARM				# SL-811
-	default y if BLACKFIN				# SL-811
-	default y if SUPERH				# r8a66597-hcd
-	default PCI
+	def_bool y
 
 # ARM SA1111 chips have a non-PCI based "OHCI-compatible" USB host interface.
 config USB
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index b501346484ae..f1cab425163f 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -103,7 +103,7 @@ static int hw_ep_flush(struct ci13xxx *ci, int num, int dir)
 
 	do {
 		/* flush any pending transfer */
-		hw_write(ci, OP_ENDPTFLUSH, BIT(n), BIT(n));
+		hw_write(ci, OP_ENDPTFLUSH, ~0, BIT(n));
 		while (hw_read(ci, OP_ENDPTFLUSH, BIT(n)))
 			cpu_relax();
 	} while (hw_read(ci, OP_ENDPTSTAT, BIT(n)));
@@ -203,7 +203,7 @@ static int hw_ep_prime(struct ci13xxx *ci, int num, int dir, int is_ctrl)
 	if (is_ctrl && dir == RX && hw_read(ci, OP_ENDPTSETUPSTAT, BIT(num)))
 		return -EAGAIN;
 
-	hw_write(ci, OP_ENDPTPRIME, BIT(n), BIT(n));
+	hw_write(ci, OP_ENDPTPRIME, ~0, BIT(n));
 
 	while (hw_read(ci, OP_ENDPTPRIME, BIT(n)))
 		cpu_relax();
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 9b1cbcf8fb7f..2800776b2e91 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -122,13 +122,23 @@ static void acm_release_minor(struct acm *acm)
 static int acm_ctrl_msg(struct acm *acm, int request, int value,
 							void *buf, int len)
 {
-	int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
+	int retval;
+
+	retval = usb_autopm_get_interface(acm->control);
+	if (retval)
+		return retval;
+
+	retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
 		request, USB_RT_ACM, value,
 		acm->control->altsetting[0].desc.bInterfaceNumber,
 		buf, len, 5000);
+
 	dev_dbg(&acm->control->dev,
 			"%s - rq 0x%02x, val %#x, len %#x, result %d\n",
 			__func__, request, value, len, retval);
+
+	usb_autopm_put_interface(acm->control);
+
 	return retval < 0 ? retval : 0;
 }
 
@@ -233,12 +243,9 @@ static int acm_write_start(struct acm *acm, int wbn)
 							acm->susp_count);
 	usb_autopm_get_interface_async(acm->control);
 	if (acm->susp_count) {
-		if (!acm->delayed_wb)
-			acm->delayed_wb = wb;
-		else
-			usb_autopm_put_interface_async(acm->control);
+		usb_anchor_urb(wb->urb, &acm->delayed);
 		spin_unlock_irqrestore(&acm->write_lock, flags);
-		return 0;	/* A white lie */
+		return 0;
 	}
 	usb_mark_last_busy(acm->dev);
 
@@ -516,6 +523,7 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)
 {
 	struct acm *acm = container_of(port, struct acm, port);
 	int retval = -ENODEV;
+	int i;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 
@@ -564,6 +572,8 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)
 	return 0;
 
 error_submit_read_urbs:
+	for (i = 0; i < acm->rx_buflimit; i++)
+		usb_kill_urb(acm->read_urbs[i]);
 	acm->ctrlout = 0;
 	acm_set_control(acm, acm->ctrlout);
 error_set_control:
@@ -591,21 +601,35 @@ static void acm_port_destruct(struct tty_port *port)
 static void acm_port_shutdown(struct tty_port *port)
 {
 	struct acm *acm = container_of(port, struct acm, port);
+	struct urb *urb;
+	struct acm_wb *wb;
 	int i;
+	int pm_err;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 
 	mutex_lock(&acm->mutex);
 	if (!acm->disconnected) {
-		usb_autopm_get_interface(acm->control);
+		pm_err = usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
+
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+			wb = urb->context;
+			wb->use = 0;
+			usb_autopm_put_interface_async(acm->control);
+		}
+
 		usb_kill_urb(acm->ctrlurb);
 		for (i = 0; i < ACM_NW; i++)
 			usb_kill_urb(acm->wb[i].urb);
 		for (i = 0; i < acm->rx_buflimit; i++)
 			usb_kill_urb(acm->read_urbs[i]);
 		acm->control->needs_remote_wakeup = 0;
-		usb_autopm_put_interface(acm->control);
+		if (!pm_err)
+			usb_autopm_put_interface(acm->control);
 	}
 	mutex_unlock(&acm->mutex);
 }
@@ -859,11 +883,12 @@ static void acm_tty_set_termios(struct tty_struct *tty,
 	/* FIXME: Needs to clear unsupported bits in the termios */
 	acm->clocal = ((termios->c_cflag & CLOCAL) != 0);
 
-	if (!newline.dwDTERate) {
+	if (C_BAUD(tty) == B0) {
 		newline.dwDTERate = acm->line.dwDTERate;
 		newctrl &= ~ACM_CTRL_DTR;
-	} else
+	} else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) {
 		newctrl |=  ACM_CTRL_DTR;
+	}
 
 	if (newctrl != acm->ctrlout)
 		acm_set_control(acm, acm->ctrlout = newctrl);
@@ -1062,10 +1087,11 @@ next_desc:
 	} else {
 		control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
 		data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
-		if (!control_interface || !data_interface) {
-			dev_dbg(&intf->dev, "no interfaces\n");
-			return -ENODEV;
-		}
+	}
+
+	if (!control_interface || !data_interface) {
+		dev_dbg(&intf->dev, "no interfaces\n");
+		return -ENODEV;
 	}
 
 	if (data_interface_num != call_interface_num)
@@ -1190,6 +1216,7 @@ made_compressed_probe:
 		acm->bInterval = epread->bInterval;
 	tty_port_init(&acm->port);
 	acm->port.ops = &acm_port_ops;
+	init_usb_anchor(&acm->delayed);
 
 	buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
 	if (!buf) {
@@ -1339,6 +1366,7 @@ alloc_fail8:
 				&dev_attr_wCountryCodes);
 		device_remove_file(&acm->control->dev,
 				&dev_attr_iCountryCodeRelDate);
+		kfree(acm->country_codes);
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
 alloc_fail7:
@@ -1434,18 +1462,15 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	struct acm *acm = usb_get_intfdata(intf);
 	int cnt;
 
+	spin_lock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 	if (PMSG_IS_AUTO(message)) {
-		int b;
-
-		spin_lock_irq(&acm->write_lock);
-		b = acm->transmitting;
-		spin_unlock_irq(&acm->write_lock);
-		if (b)
+		if (acm->transmitting) {
+			spin_unlock(&acm->write_lock);
+			spin_unlock_irq(&acm->read_lock);
 			return -EBUSY;
+		}
 	}
-
-	spin_lock_irq(&acm->read_lock);
-	spin_lock(&acm->write_lock);
 	cnt = acm->susp_count++;
 	spin_unlock(&acm->write_lock);
 	spin_unlock_irq(&acm->read_lock);
@@ -1453,8 +1478,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	if (cnt)
 		return 0;
 
-	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags))
-		stop_data_traffic(acm);
+	stop_data_traffic(acm);
 
 	return 0;
 }
@@ -1462,29 +1486,24 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 static int acm_resume(struct usb_interface *intf)
 {
 	struct acm *acm = usb_get_intfdata(intf);
-	struct acm_wb *wb;
+	struct urb *urb;
 	int rv = 0;
-	int cnt;
 
 	spin_lock_irq(&acm->read_lock);
-	acm->susp_count -= 1;
-	cnt = acm->susp_count;
-	spin_unlock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 
-	if (cnt)
-		return 0;
+	if (--acm->susp_count)
+		goto out;
 
 	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) {
-		rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
-
-		spin_lock_irq(&acm->write_lock);
-		if (acm->delayed_wb) {
-			wb = acm->delayed_wb;
-			acm->delayed_wb = NULL;
-			spin_unlock_irq(&acm->write_lock);
-			acm_start_wb(acm, wb);
-		} else {
-			spin_unlock_irq(&acm->write_lock);
+		rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
+
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+
+			acm_start_wb(acm, urb->context);
 		}
 
 		/*
@@ -1492,12 +1511,14 @@ static int acm_resume(struct usb_interface *intf)
 		 * do the write path at all cost
 		 */
 		if (rv < 0)
-			goto err_out;
+			goto out;
 
-		rv = acm_submit_read_urbs(acm, GFP_NOIO);
+		rv = acm_submit_read_urbs(acm, GFP_ATOMIC);
 	}
+out:
+	spin_unlock(&acm->write_lock);
+	spin_unlock_irq(&acm->read_lock);
 
-err_out:
 	return rv;
 }
 
@@ -1529,6 +1550,8 @@ static int acm_reset_resume(struct usb_interface *intf)
 
 static const struct usb_device_id acm_ids[] = {
 	/* quirky and broken devices */
+	{ USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */
+	.driver_info = NO_UNION_NORMAL, },/* has no union descriptor */
 	{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
@@ -1568,17 +1591,32 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
+	{ USB_DEVICE(0x2184, 0x001c) },	/* GW Instek AFG-2225 */
 	{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
 	},
 	/* Motorola H24 HSPA module: */
 	{ USB_DEVICE(0x22b8, 0x2d91) }, /* modem                                */
-	{ USB_DEVICE(0x22b8, 0x2d92) }, /* modem           + diagnostics        */
-	{ USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port                      */
-	{ USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics        */
-	{ USB_DEVICE(0x22b8, 0x2d96) }, /* modem                         + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d97) }, /* modem           + diagnostics + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port               + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+	{ USB_DEVICE(0x22b8, 0x2d92),   /* modem           + diagnostics        */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d93),   /* modem + AT port                      */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d95),   /* modem + AT port + diagnostics        */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d96),   /* modem                         + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d97),   /* modem           + diagnostics + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d99),   /* modem + AT port               + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d9a),   /* modem + AT port + diagnostics + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
 
 	{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
 	.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 0f76e4af600e..1683ac161cf6 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -117,7 +117,7 @@ struct acm {
 	unsigned int throttled:1;			/* actually throttled */
 	unsigned int throttle_req:1;			/* throttle requested */
 	u8 bInterval;
-	struct acm_wb *delayed_wb;			/* write queued for a device about to be woken */
+	struct usb_anchor delayed;			/* writes queued for a device about to be woken */
 };
 
 #define CDC_DATA_INTERFACE_TYPE	0x0a
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index d3318a0df8ee..6463ca3bcfba 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -820,13 +820,11 @@ static int wdm_manage_power(struct usb_interface *intf, int on)
 {
 	/* need autopm_get/put here to ensure the usbcore sees the new value */
 	int rv = usb_autopm_get_interface(intf);
-	if (rv < 0)
-		goto err;
 
 	intf->needs_remote_wakeup = on;
-	usb_autopm_put_interface(intf);
-err:
-	return rv;
+	if (!rv)
+		usb_autopm_put_interface(intf);
+	return 0;
 }
 
 static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id)
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index a6b2cabe7930..652438325197 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -651,10 +651,6 @@ void usb_destroy_configuration(struct usb_device *dev)
  *
  * hub-only!! ... and only in reset path, or usb_new_device()
  * (used by real hubs and virtual root hubs)
- *
- * NOTE: if this is a WUSB device and is not authorized, we skip the
- *       whole thing. A non-authorized USB device has no
- *       configurations.
  */
 int usb_get_configuration(struct usb_device *dev)
 {
@@ -666,8 +662,6 @@ int usb_get_configuration(struct usb_device *dev)
 	struct usb_config_descriptor *desc;
 
 	cfgno = 0;
-	if (dev->authorized == 0)	/* Not really an error */
-		goto out_not_authorized;
 	result = -ENOMEM;
 	if (ncfg > USB_MAXCONFIG) {
 		dev_warn(ddev, "too many configurations: %d, "
@@ -724,6 +718,10 @@ int usb_get_configuration(struct usb_device *dev)
 			result = -ENOMEM;
 			goto err;
 		}
+
+		if (dev->quirks & USB_QUIRK_DELAY_INIT)
+			msleep(100);
+
 		result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
 		    bigbuffer, length);
 		if (result < 0) {
@@ -751,7 +749,6 @@ int usb_get_configuration(struct usb_device *dev)
 
 err:
 	kfree(desc);
-out_not_authorized:
 	dev->descriptor.bNumConfigurations = cfgno;
 err2:
 	if (result == -ENOMEM)
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index c88c4fb9459d..ce773cca2bf5 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -742,6 +742,22 @@ static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
 		if ((index & ~USB_DIR_IN) == 0)
 			return 0;
 		ret = findintfep(ps->dev, index);
+		if (ret < 0) {
+			/*
+			 * Some not fully compliant Win apps seem to get
+			 * index wrong and have the endpoint number here
+			 * rather than the endpoint address (with the
+			 * correct direction). Win does let this through,
+			 * so we'll not reject it here but leave it to
+			 * the device to not break KVM. But we warn.
+			 */
+			ret = findintfep(ps->dev, index ^ 0x80);
+			if (ret >= 0)
+				dev_info(&ps->dev->dev,
+					"%s: process %i (%s) requesting ep %02x but needs %02x\n",
+					__func__, task_pid_nr(current),
+					current->comm, index, index ^ 0x80);
+		}
 		if (ret >= 0)
 			ret = checkintf(ps, ret);
 		break;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 6eab440e1542..2cdd5079ae78 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -953,8 +953,7 @@ EXPORT_SYMBOL_GPL(usb_deregister);
  * it doesn't support pre_reset/post_reset/reset_resume or
  * because it doesn't support suspend/resume.
  *
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
  */
 void usb_forced_unbind_intf(struct usb_interface *intf)
 {
@@ -967,16 +966,37 @@ void usb_forced_unbind_intf(struct usb_interface *intf)
 	intf->needs_binding = 1;
 }
 
+/*
+ * Unbind drivers for @udev's marked interfaces.  These interfaces have
+ * the needs_binding flag set, for example by usb_resume_interface().
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void unbind_marked_interfaces(struct usb_device *udev)
+{
+	struct usb_host_config	*config;
+	int			i;
+	struct usb_interface	*intf;
+
+	config = udev->actconfig;
+	if (config) {
+		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+			intf = config->interface[i];
+			if (intf->dev.driver && intf->needs_binding)
+				usb_forced_unbind_intf(intf);
+		}
+	}
+}
+
 /* Delayed forced unbinding of a USB interface driver and scan
  * for rebinding.
  *
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
  *
  * Note: Rebinds will be skipped if a system sleep transition is in
  * progress and the PM "complete" callback hasn't occurred yet.
  */
-void usb_rebind_intf(struct usb_interface *intf)
+static void usb_rebind_intf(struct usb_interface *intf)
 {
 	int rc;
 
@@ -993,68 +1013,66 @@ void usb_rebind_intf(struct usb_interface *intf)
 	}
 }
 
-#ifdef CONFIG_PM
-
-/* Unbind drivers for @udev's interfaces that don't support suspend/resume
- * There is no check for reset_resume here because it can be determined
- * only during resume whether reset_resume is needed.
+/*
+ * Rebind drivers to @udev's marked interfaces.  These interfaces have
+ * the needs_binding flag set.
  *
  * The caller must hold @udev's device lock.
  */
-static void unbind_no_pm_drivers_interfaces(struct usb_device *udev)
+static void rebind_marked_interfaces(struct usb_device *udev)
 {
 	struct usb_host_config	*config;
 	int			i;
 	struct usb_interface	*intf;
-	struct usb_driver	*drv;
 
 	config = udev->actconfig;
 	if (config) {
 		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
 			intf = config->interface[i];
-
-			if (intf->dev.driver) {
-				drv = to_usb_driver(intf->dev.driver);
-				if (!drv->suspend || !drv->resume)
-					usb_forced_unbind_intf(intf);
-			}
+			if (intf->needs_binding)
+				usb_rebind_intf(intf);
 		}
 	}
 }
 
-/* Unbind drivers for @udev's interfaces that failed to support reset-resume.
- * These interfaces have the needs_binding flag set by usb_resume_interface().
+/*
+ * Unbind all of @udev's marked interfaces and then rebind all of them.
+ * This ordering is necessary because some drivers claim several interfaces
+ * when they are first probed.
  *
  * The caller must hold @udev's device lock.
  */
-static void unbind_no_reset_resume_drivers_interfaces(struct usb_device *udev)
+void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev)
 {
-	struct usb_host_config	*config;
-	int			i;
-	struct usb_interface	*intf;
-
-	config = udev->actconfig;
-	if (config) {
-		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
-			intf = config->interface[i];
-			if (intf->dev.driver && intf->needs_binding)
-				usb_forced_unbind_intf(intf);
-		}
-	}
+	unbind_marked_interfaces(udev);
+	rebind_marked_interfaces(udev);
 }
 
-static void do_rebind_interfaces(struct usb_device *udev)
+#ifdef CONFIG_PM
+
+/* Unbind drivers for @udev's interfaces that don't support suspend/resume
+ * There is no check for reset_resume here because it can be determined
+ * only during resume whether reset_resume is needed.
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void unbind_no_pm_drivers_interfaces(struct usb_device *udev)
 {
 	struct usb_host_config	*config;
 	int			i;
 	struct usb_interface	*intf;
+	struct usb_driver	*drv;
 
 	config = udev->actconfig;
 	if (config) {
 		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
 			intf = config->interface[i];
-			if (intf->needs_binding)
-				usb_rebind_intf(intf);
+
+			if (intf->dev.driver) {
+				drv = to_usb_driver(intf->dev.driver);
+				if (!drv->suspend || !drv->resume)
+					usb_forced_unbind_intf(intf);
+			}
 		}
 	}
 }
@@ -1379,7 +1397,7 @@ int usb_resume_complete(struct device *dev)
 	 * whose needs_binding flag is set
 	 */
 	if (udev->state != USB_STATE_NOTATTACHED)
-		do_rebind_interfaces(udev);
+		rebind_marked_interfaces(udev);
 	return 0;
 }
 
@@ -1401,7 +1419,7 @@ int usb_resume(struct device *dev, pm_message_t msg)
 		pm_runtime_disable(dev);
 		pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
-		unbind_no_reset_resume_drivers_interfaces(udev);
+		unbind_marked_interfaces(udev);
 	}
 
 	/* Avoid PM error messages for devices disconnected while suspended
@@ -1736,10 +1754,13 @@ int usb_runtime_suspend(struct device *dev)
 	if (status == -EAGAIN || status == -EBUSY)
 		usb_mark_last_busy(udev);
 
-	/* The PM core reacts badly unless the return code is 0,
-	 * -EAGAIN, or -EBUSY, so always return -EBUSY on an error.
+	/*
+	 * The PM core reacts badly unless the return code is 0,
+	 * -EAGAIN, or -EBUSY, so always return -EBUSY on an error
+	 * (except for root hubs, because they don't suspend through
+	 * an upstream port like other USB devices).
 	 */
-	if (status != 0)
+	if (status != 0 && udev->parent)
 		return -EBUSY;
 	return status;
 }
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index caeb8d6d39fb..4676917e2b1f 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -75,7 +75,7 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd,
 				PCI_SLOT(companion->devfn) != slot)
 			continue;
 		companion_hcd = pci_get_drvdata(companion);
-		if (!companion_hcd)
+		if (!companion_hcd || !companion_hcd->self.root_hub)
 			continue;
 		fn(pdev, hcd, companion, companion_hcd);
 	}
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d53547d2e4c7..f6e5ceb03afb 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1947,6 +1947,8 @@ int usb_alloc_streams(struct usb_interface *interface,
 		return -EINVAL;
 	if (dev->speed != USB_SPEED_SUPER)
 		return -EINVAL;
+	if (dev->state < USB_STATE_CONFIGURED)
+		return -ENODEV;
 
 	/* Streams only apply to bulk endpoints. */
 	for (i = 0; i < num_eps; i++)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 6cf2ae0aa1f7..c9f56ffdba9a 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -887,6 +887,25 @@ static int hub_usb3_port_disable(struct usb_hub *hub, int port1)
 	if (!hub_is_superspeed(hub->hdev))
 		return -EINVAL;
 
+	ret = hub_port_status(hub, port1, &portstatus, &portchange);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI
+	 * Controller [1022:7814] will have spurious result making the following
+	 * usb 3.0 device hotplugging route to the 2.0 root hub and recognized
+	 * as high-speed device if we set the usb 3.0 port link state to
+	 * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we
+	 * check the state here to avoid the bug.
+	 */
+	if ((portstatus & USB_PORT_STAT_LINK_STATE) ==
+				USB_SS_PORT_LS_RX_DETECT) {
+		dev_dbg(&hub->ports[port1 - 1]->dev,
+			 "Not disabling port; link state is RxDetect\n");
+		return ret;
+	}
+
 	ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED);
 	if (ret)
 		return ret;
@@ -1124,6 +1143,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			usb_clear_port_feature(hub->hdev, port1,
 					USB_PORT_FEAT_C_ENABLE);
 		}
+		if (portchange & USB_PORT_STAT_C_RESET) {
+			need_debounce_delay = true;
+			usb_clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_RESET);
+		}
 		if ((portchange & USB_PORT_STAT_C_BH_RESET) &&
 				hub_is_superspeed(hub->hdev)) {
 			need_debounce_delay = true;
@@ -1141,7 +1165,8 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			/* Tell khubd to disconnect the device or
 			 * check for a new connection
 			 */
-			if (udev || (portstatus & USB_PORT_STAT_CONNECTION))
+			if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
+			    (portstatus & USB_PORT_STAT_OVERCURRENT))
 				set_bit(port1, hub->change_bits);
 
 		} else if (portstatus & USB_PORT_STAT_ENABLE) {
@@ -1557,10 +1582,15 @@ static int hub_configure(struct usb_hub *hub,
 	if (hub->has_indicators && blinkenlights)
 		hub->indicator [0] = INDICATOR_CYCLE;
 
-	for (i = 0; i < hdev->maxchild; i++)
-		if (usb_hub_create_port_device(hub, i + 1) < 0)
+	for (i = 0; i < hdev->maxchild; i++) {
+		ret = usb_hub_create_port_device(hub, i + 1);
+		if (ret < 0) {
 			dev_err(hub->intfdev,
 				"couldn't create port%d device.\n", i + 1);
+			hdev->maxchild = i;
+			goto fail_keep_maxchild;
+		}
+	}
 
 	usb_hub_adjust_deviceremovable(hdev, hub->descriptor);
 
@@ -1568,6 +1598,8 @@ static int hub_configure(struct usb_hub *hub,
 	return 0;
 
 fail:
+	hdev->maxchild = 0;
+fail_keep_maxchild:
 	dev_err (hub_dev, "config failed, %s (err %d)\n",
 			message, ret);
 	/* hub_disconnect() frees urb and descriptor */
@@ -1588,7 +1620,7 @@ static void hub_disconnect(struct usb_interface *intf)
 {
 	struct usb_hub *hub = usb_get_intfdata(intf);
 	struct usb_device *hdev = interface_to_usbdev(intf);
-	int i;
+	int port1;
 
 	/* Take the hub off the event list and don't let it be added again */
 	spin_lock_irq(&hub_event_lock);
@@ -1603,11 +1635,15 @@ static void hub_disconnect(struct usb_interface *intf)
 	hub->error = 0;
 	hub_quiesce(hub, HUB_DISCONNECT);
 
-	usb_set_intfdata (intf, NULL);
+	/* Avoid races with recursively_mark_NOTATTACHED() */
+	spin_lock_irq(&device_state_lock);
+	port1 = hdev->maxchild;
+	hdev->maxchild = 0;
+	usb_set_intfdata(intf, NULL);
+	spin_unlock_irq(&device_state_lock);
 
-	for (i = 0; i < hdev->maxchild; i++)
-		usb_hub_remove_port_device(hub, i + 1);
-	hub->hdev->maxchild = 0;
+	for (; port1 > 0; --port1)
+		usb_hub_remove_port_device(hub, port1);
 
 	if (hub->hdev->speed == USB_SPEED_HIGH)
 		highspeed_hubs--;
@@ -1664,11 +1700,28 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	 * - Change autosuspend delay of hub can avoid unnecessary auto
 	 *   suspend timer for hub, also may decrease power consumption
 	 *   of USB bus.
+	 *
+	 * - If user has indicated to prevent autosuspend by passing
+	 *   usbcore.autosuspend = -1 then keep autosuspend disabled.
 	 */
-	pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#ifdef CONFIG_PM_RUNTIME
+	if (hdev->dev.power.autosuspend_delay >= 0)
+		pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#endif
 
-	/* Hubs have proper suspend/resume support. */
-	usb_enable_autosuspend(hdev);
+	/*
+	 * Hubs have proper suspend/resume support, except for root hubs
+	 * where the controller driver doesn't have bus_suspend and
+	 * bus_resume methods.
+	 */
+	if (hdev->parent) {		/* normal device */
+		usb_enable_autosuspend(hdev);
+	} else {			/* root hub */
+		const struct hc_driver *drv = bus_to_hcd(hdev->bus)->driver;
+
+		if (drv->bus_suspend && drv->bus_resume)
+			usb_enable_autosuspend(hdev);
+	}
 
 	if (hdev->level == MAX_TOPO_LEVEL) {
 		dev_err(&intf->dev,
@@ -1898,8 +1951,10 @@ void usb_set_device_state(struct usb_device *udev,
 					|| new_state == USB_STATE_SUSPENDED)
 				;	/* No change to wakeup settings */
 			else if (new_state == USB_STATE_CONFIGURED)
-				wakeup = udev->actconfig->desc.bmAttributes
-					 & USB_CONFIG_ATT_WAKEUP;
+				wakeup = (udev->quirks &
+					USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 :
+					udev->actconfig->desc.bmAttributes &
+					USB_CONFIG_ATT_WAKEUP;
 			else
 				wakeup = 0;
 		}
@@ -2210,18 +2265,13 @@ static int usb_enumerate_device(struct usb_device *udev)
 			return err;
 		}
 	}
-	if (udev->wusb == 1 && udev->authorized == 0) {
-		udev->product = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-		udev->manufacturer = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-		udev->serial = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-	}
-	else {
-		/* read the standard strings and cache them if present */
-		udev->product = usb_cache_string(udev, udev->descriptor.iProduct);
-		udev->manufacturer = usb_cache_string(udev,
-						      udev->descriptor.iManufacturer);
-		udev->serial = usb_cache_string(udev, udev->descriptor.iSerialNumber);
-	}
+
+	/* read the standard strings and cache them if present */
+	udev->product = usb_cache_string(udev, udev->descriptor.iProduct);
+	udev->manufacturer = usb_cache_string(udev,
+					      udev->descriptor.iManufacturer);
+	udev->serial = usb_cache_string(udev, udev->descriptor.iSerialNumber);
+
 	err = usb_enumerate_device_otg(udev);
 	if (err < 0)
 		return err;
@@ -2400,16 +2450,6 @@ int usb_deauthorize_device(struct usb_device *usb_dev)
 	usb_dev->authorized = 0;
 	usb_set_configuration(usb_dev, -1);
 
-	kfree(usb_dev->product);
-	usb_dev->product = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-	kfree(usb_dev->manufacturer);
-	usb_dev->manufacturer = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-	kfree(usb_dev->serial);
-	usb_dev->serial = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-
-	usb_destroy_configuration(usb_dev);
-	usb_dev->descriptor.bNumConfigurations = 0;
-
 out_unauthorized:
 	usb_unlock_device(usb_dev);
 	return 0;
@@ -2437,17 +2477,7 @@ int usb_authorize_device(struct usb_device *usb_dev)
 		goto error_device_descriptor;
 	}
 
-	kfree(usb_dev->product);
-	usb_dev->product = NULL;
-	kfree(usb_dev->manufacturer);
-	usb_dev->manufacturer = NULL;
-	kfree(usb_dev->serial);
-	usb_dev->serial = NULL;
-
 	usb_dev->authorized = 1;
-	result = usb_enumerate_device(usb_dev);
-	if (result < 0)
-		goto error_enumerate;
 	/* Choose and set the configuration.  This registers the interfaces
 	 * with the driver core and lets interface drivers bind to them.
 	 */
@@ -2463,7 +2493,6 @@ int usb_authorize_device(struct usb_device *usb_dev)
 	}
 	dev_info(&usb_dev->dev, "authorized to connect\n");
 
-error_enumerate:
 error_device_descriptor:
 	usb_autosuspend_device(usb_dev);
 error_autoresume:
@@ -3146,6 +3175,43 @@ static int finish_port_resume(struct usb_device *udev)
 }
 
 /*
+ * There are some SS USB devices which take longer time for link training.
+ * XHCI specs 4.19.4 says that when Link training is successful, port
+ * sets CSC bit to 1. So if SW reads port status before successful link
+ * training, then it will not find device to be present.
+ * USB Analyzer log with such buggy devices show that in some cases
+ * device switch on the RX termination after long delay of host enabling
+ * the VBUS. In few other cases it has been seen that device fails to
+ * negotiate link training in first attempt. It has been
+ * reported till now that few devices take as long as 2000 ms to train
+ * the link after host enabling its VBUS and termination. Following
+ * routine implements a 2000 ms timeout for link training. If in a case
+ * link trains before timeout, loop will exit earlier.
+ *
+ * FIXME: If a device was connected before suspend, but was removed
+ * while system was asleep, then the loop in the following routine will
+ * only exit at timeout.
+ *
+ * This routine should only be called when persist is enabled for a SS
+ * device.
+ */
+static int wait_for_ss_port_enable(struct usb_device *udev,
+		struct usb_hub *hub, int *port1,
+		u16 *portchange, u16 *portstatus)
+{
+	int status = 0, delay_ms = 0;
+
+	while (delay_ms < 2000) {
+		if (status || *portstatus & USB_PORT_STAT_CONNECTION)
+			break;
+		msleep(20);
+		delay_ms += 20;
+		status = hub_port_status(hub, *port1, portstatus, portchange);
+	}
+	return status;
+}
+
+/*
  * usb_port_resume - re-activate a suspended usb device's upstream port
  * @udev: device to re-activate, not a root hub
  * Context: must be able to sleep; device not locked; pm locks held
@@ -3247,6 +3313,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 
 	clear_bit(port1, hub->busy_bits);
 
+	if (udev->persist_enabled && hub_is_superspeed(hub->hdev))
+		status = wait_for_ss_port_enable(udev, hub, &port1, &portchange,
+				&portstatus);
+
 	status = check_port_resume_type(udev,
 			hub, port1, status, portchange, portstatus);
 	if (status == 0)
@@ -4635,9 +4705,10 @@ static void hub_events(void)
 
 		hub = list_entry(tmp, struct usb_hub, event_list);
 		kref_get(&hub->kref);
+		hdev = hub->hdev;
+		usb_get_dev(hdev);
 		spin_unlock_irq(&hub_event_lock);
 
-		hdev = hub->hdev;
 		hub_dev = hub->intfdev;
 		intf = to_usb_interface(hub_dev);
 		dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n",
@@ -4791,8 +4862,9 @@ static void hub_events(void)
 					hub->ports[i - 1]->child;
 
 				dev_dbg(hub_dev, "warm reset port %d\n", i);
-				if (!udev || !(portstatus &
-						USB_PORT_STAT_CONNECTION)) {
+				if (!udev ||
+				    !(portstatus & USB_PORT_STAT_CONNECTION) ||
+				    udev->state == USB_STATE_NOTATTACHED) {
 					status = hub_port_reset(hub, i,
 							NULL, HUB_BH_RESET_TIME,
 							true);
@@ -4851,6 +4923,7 @@ static void hub_events(void)
 		usb_autopm_put_interface(intf);
  loop_disconnected:
 		usb_unlock_device(hdev);
+		usb_put_dev(hdev);
 		kref_put(&hub->kref, hub_release);
 
         } /* end while (1) */
@@ -5261,10 +5334,11 @@ int usb_reset_device(struct usb_device *udev)
 				else if (cintf->condition ==
 						USB_INTERFACE_BOUND)
 					rebind = 1;
+				if (rebind)
+					cintf->needs_binding = 1;
 			}
-			if (ret == 0 && rebind)
-				usb_rebind_intf(cintf);
 		}
+		usb_unbind_and_rebind_marked_interfaces(udev);
 	}
 
 	usb_autosuspend_device(udev);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 5b44cd47da5b..b73f3031a660 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -43,9 +43,16 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Microsoft Wireless Laser Mouse 6000 Receiver */
+	{ USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech HD Pro Webcams C920 and C930e */
+	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Logitech Quickcam Fusion */
 	{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -97,6 +104,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Alcor Micro Corp. Hub */
 	{ USB_DEVICE(0x058f, 0x9254), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* MicroTouch Systems touchscreen */
+	{ USB_DEVICE(0x0596, 0x051e), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* appletouch */
 	{ USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -130,6 +140,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Broadcom BCM92035DGROM BT dongle */
 	{ USB_DEVICE(0x0a5c, 0x2021), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* MAYA44USB sound device */
+	{ USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -152,6 +165,10 @@ static const struct usb_device_id usb_interface_quirk_list[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0),
 	  .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 823857767a16..0923add72b59 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -55,7 +55,7 @@ extern int usb_match_one_id_intf(struct usb_device *dev,
 extern int usb_match_device(struct usb_device *dev,
 			    const struct usb_device_id *id);
 extern void usb_forced_unbind_intf(struct usb_interface *intf);
-extern void usb_rebind_intf(struct usb_interface *intf);
+extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev);
 
 extern int usb_hub_claim_port(struct usb_device *hdev, unsigned port,
 		struct dev_state *owner);
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 358375e0b291..1d386030d3c4 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -603,12 +603,6 @@ static int dwc3_remove(struct platform_device *pdev)
 {
 	struct dwc3	*dwc = platform_get_drvdata(pdev);
 
-	usb_phy_set_suspend(dwc->usb2_phy, 1);
-	usb_phy_set_suspend(dwc->usb3_phy, 1);
-
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-
 	dwc3_debugfs_exit(dwc);
 
 	switch (dwc->mode) {
@@ -629,8 +623,15 @@ static int dwc3_remove(struct platform_device *pdev)
 
 	dwc3_event_buffers_cleanup(dwc);
 	dwc3_free_event_buffers(dwc);
+
+	usb_phy_set_suspend(dwc->usb2_phy, 1);
+	usb_phy_set_suspend(dwc->usb3_phy, 1);
+
 	dwc3_core_exit(dwc);
 
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 27dad993b007..7ab3c9985253 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -836,15 +836,15 @@ struct dwc3_event_depevt {
  *	12	- VndrDevTstRcved
  * @reserved15_12: Reserved, not used
  * @event_info: Information about this event
- * @reserved31_24: Reserved, not used
+ * @reserved31_25: Reserved, not used
  */
 struct dwc3_event_devt {
 	u32	one_bit:1;
 	u32	device_event:7;
 	u32	type:4;
 	u32	reserved15_12:4;
-	u32	event_info:8;
-	u32	reserved31_24:8;
+	u32	event_info:9;
+	u32	reserved31_25:7;
 } __packed;
 
 /**
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 34638b92500d..cb5f8c44eb3a 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -395,9 +395,9 @@ static int dwc3_omap_remove(struct platform_device *pdev)
 	struct dwc3_omap	*omap = platform_get_drvdata(pdev);
 
 	dwc3_omap_disable_irqs(omap);
+	device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
 
 	return 0;
 }
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index eba9e2baf32b..2357c4e5dc43 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -48,6 +48,8 @@
 /* FIXME define these in <linux/pci_ids.h> */
 #define PCI_VENDOR_ID_SYNOPSYS		0x16c3
 #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3	0xabcd
+#define PCI_DEVICE_ID_INTEL_BYT		0x0f37
+#define PCI_DEVICE_ID_INTEL_MRFLD	0x119e
 
 struct dwc3_pci {
 	struct device		*dev;
@@ -208,6 +210,8 @@ static DEFINE_PCI_DEVICE_TABLE(dwc3_pci_id_table) = {
 		PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS,
 				PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3),
 	},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BYT), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MRFLD), },
 	{  }	/* Terminating Entry */
 };
 MODULE_DEVICE_TABLE(pci, dwc3_pci_id_table);
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 5acbb948b704..6cd418f6ac07 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -270,7 +270,7 @@ static void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
 
 	/* stall is always issued on EP0 */
 	dep = dwc->eps[0];
-	__dwc3_gadget_ep_set_halt(dep, 1);
+	__dwc3_gadget_ep_set_halt(dep, 1, false);
 	dep->flags = DWC3_EP_ENABLED;
 	dwc->delayed_status = false;
 
@@ -478,7 +478,9 @@ static int dwc3_ep0_handle_feature(struct dwc3 *dwc,
 			dep = dwc3_wIndex_to_dep(dwc, wIndex);
 			if (!dep)
 				return -EINVAL;
-			ret = __dwc3_gadget_ep_set_halt(dep, set);
+			if (set == 0 && (dep->flags & DWC3_EP_WEDGE))
+				break;
+			ret = __dwc3_gadget_ep_set_halt(dep, set, true);
 			if (ret)
 				return -EINVAL;
 			break;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 14d28d6184f6..8f8e75e392de 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -550,12 +550,11 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		if (!usb_endpoint_xfer_isoc(desc))
 			return 0;
 
-		memset(&trb_link, 0, sizeof(trb_link));
-
 		/* Link TRB for ISOC. The HWO bit is never reset */
 		trb_st_hw = &dep->trb_pool[0];
 
 		trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1];
+		memset(trb_link, 0, sizeof(*trb_link));
 
 		trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
 		trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
@@ -604,6 +603,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 
 	dwc3_remove_requests(dwc, dep);
 
+	/* make sure HW endpoint isn't stalled */
+	if (dep->flags & DWC3_EP_STALL)
+		__dwc3_gadget_ep_set_halt(dep, 0, false);
+
 	reg = dwc3_readl(dwc->regs, DWC3_DALEPENA);
 	reg &= ~DWC3_DALEPENA_EP(dep->number);
 	dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
@@ -1202,7 +1205,7 @@ out0:
 	return ret;
 }
 
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 {
 	struct dwc3_gadget_ep_cmd_params	params;
 	struct dwc3				*dwc = dep->dwc;
@@ -1211,6 +1214,14 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
 	memset(&params, 0x00, sizeof(params));
 
 	if (value) {
+		if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) ||
+				(!list_empty(&dep->req_queued) ||
+				 !list_empty(&dep->request_list)))) {
+			dev_dbg(dwc->dev, "%s: pending request, cannot halt\n",
+					dep->name);
+			return -EAGAIN;
+		}
+
 		ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
 			DWC3_DEPCMD_SETSTALL, &params);
 		if (ret)
@@ -1220,9 +1231,6 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
 		else
 			dep->flags |= DWC3_EP_STALL;
 	} else {
-		if (dep->flags & DWC3_EP_WEDGE)
-			return 0;
-
 		ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
 			DWC3_DEPCMD_CLEARSTALL, &params);
 		if (ret)
@@ -1230,7 +1238,7 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
 					value ? "set" : "clear",
 					dep->name);
 		else
-			dep->flags &= ~DWC3_EP_STALL;
+			dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE);
 	}
 
 	return ret;
@@ -1253,7 +1261,7 @@ static int dwc3_gadget_ep_set_halt(struct usb_ep *ep, int value)
 		goto out;
 	}
 
-	ret = __dwc3_gadget_ep_set_halt(dep, value);
+	ret = __dwc3_gadget_ep_set_halt(dep, value, false);
 out:
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -1273,7 +1281,7 @@ static int dwc3_gadget_ep_set_wedge(struct usb_ep *ep)
 	if (dep->number == 0 || dep->number == 1)
 		return dwc3_gadget_ep0_set_halt(ep, 1);
 	else
-		return dwc3_gadget_ep_set_halt(ep, 1);
+		return __dwc3_gadget_ep_set_halt(dep, 1, false);
 }
 
 /* -------------------------------------------------------------------------- */
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 99e6d7248820..b3f25c302e35 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -114,7 +114,7 @@ void dwc3_ep0_out_start(struct dwc3 *dwc);
 int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value);
 int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request,
 		gfp_t gfp_flags);
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value);
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol);
 int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
 		unsigned cmd, struct dwc3_gadget_ep_cmd_params *params);
 int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param);
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index 073b938f9135..55e96131753e 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -1703,16 +1703,6 @@ static int at91udc_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if (pdev->num_resources != 2) {
-		DBG("invalid num_resources\n");
-		return -ENODEV;
-	}
-	if ((pdev->resource[0].flags != IORESOURCE_MEM)
-			|| (pdev->resource[1].flags != IORESOURCE_IRQ)) {
-		DBG("invalid resource type\n");
-		return -ENODEV;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENXIO;
diff --git a/drivers/usb/gadget/bcm63xx_udc.c b/drivers/usb/gadget/bcm63xx_udc.c
index fd24cb4540a4..5396709cdc07 100644
--- a/drivers/usb/gadget/bcm63xx_udc.c
+++ b/drivers/usb/gadget/bcm63xx_udc.c
@@ -361,24 +361,30 @@ static inline void usb_dma_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
 	bcm_writel(val, udc->iudma_regs + off);
 }
 
-static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off, int chan)
 {
-	return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+	return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+					int chan)
 {
-	bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+	bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off, int chan)
 {
-	return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+	return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+					int chan)
 {
-	bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+	bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
 static inline void set_clocks(struct bcm63xx_udc *udc, bool is_enabled)
@@ -639,7 +645,7 @@ static void iudma_write(struct bcm63xx_udc *udc, struct iudma_ch *iudma,
 	} while (!last_bd);
 
 	usb_dmac_writel(udc, ENETDMAC_CHANCFG_EN_MASK,
-			ENETDMAC_CHANCFG_REG(iudma->ch_idx));
+			ENETDMAC_CHANCFG_REG, iudma->ch_idx);
 }
 
 /**
@@ -695,9 +701,9 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma)
 		bcm63xx_fifo_reset_ep(udc, max(0, iudma->ep_num));
 
 	/* stop DMA, then wait for the hardware to wrap up */
-	usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG(ch_idx));
+	usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG, ch_idx);
 
-	while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)) &
+	while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx) &
 				   ENETDMAC_CHANCFG_EN_MASK) {
 		udelay(1);
 
@@ -714,10 +720,10 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma)
 			dev_warn(udc->dev, "forcibly halting IUDMA channel %d\n",
 				 ch_idx);
 			usb_dmac_writel(udc, ENETDMAC_CHANCFG_BUFHALT_MASK,
-					ENETDMAC_CHANCFG_REG(ch_idx));
+					ENETDMAC_CHANCFG_REG, ch_idx);
 		}
 	}
-	usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG(ch_idx));
+	usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG, ch_idx);
 
 	/* don't leave "live" HW-owned entries for the next guy to step on */
 	for (d = iudma->bd_ring; d <= iudma->end_bd; d++)
@@ -729,11 +735,11 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma)
 
 	/* set up IRQs, UBUS burst size, and BD base for this channel */
 	usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
-			ENETDMAC_IRMASK_REG(ch_idx));
-	usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG(ch_idx));
+			ENETDMAC_IRMASK_REG, ch_idx);
+	usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG, ch_idx);
 
-	usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG(ch_idx));
-	usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG(ch_idx));
+	usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG, ch_idx);
+	usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG, ch_idx);
 }
 
 /**
@@ -2036,7 +2042,7 @@ static irqreturn_t bcm63xx_udc_data_isr(int irq, void *dev_id)
 	spin_lock(&udc->lock);
 
 	usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
-			ENETDMAC_IR_REG(iudma->ch_idx));
+			ENETDMAC_IR_REG, iudma->ch_idx);
 	bep = iudma->bep;
 	rc = iudma_read(udc, iudma);
 
@@ -2176,18 +2182,18 @@ static int bcm63xx_iudma_dbg_show(struct seq_file *s, void *p)
 		seq_printf(s, " [ep%d]:\n",
 			   max_t(int, iudma_defaults[ch_idx].ep_num, 0));
 		seq_printf(s, "  cfg: %08x; irqstat: %08x; irqmask: %08x; maxburst: %08x\n",
-			   usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_IR_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_IRMASK_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG(ch_idx)));
+			   usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_IR_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_IRMASK_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG, ch_idx));
 
-		sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG(ch_idx));
-		sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG(ch_idx));
+		sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG, ch_idx);
+		sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG, ch_idx);
 		seq_printf(s, "  base: %08x; index: %04x_%04x; desc: %04x_%04x %08x\n",
-			   usb_dmas_readl(udc, ENETDMAS_RSTART_REG(ch_idx)),
+			   usb_dmas_readl(udc, ENETDMAS_RSTART_REG, ch_idx),
 			   sram2 >> 16, sram2 & 0xffff,
 			   sram3 >> 16, sram3 & 0xffff,
-			   usb_dmas_readl(udc, ENETDMAS_SRAM4_REG(ch_idx)));
+			   usb_dmas_readl(udc, ENETDMAS_SRAM4_REG, ch_idx));
 		seq_printf(s, "  desc: %d/%d used", iudma->n_bds_used,
 			   iudma->n_bds);
 
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 55f4df60f327..44a292b75012 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -593,6 +593,7 @@ static void reset_config(struct usb_composite_dev *cdev)
 		bitmap_zero(f->endpoints, 32);
 	}
 	cdev->config = NULL;
+	cdev->delayed_status = 0;
 }
 
 static int set_config(struct usb_composite_dev *cdev,
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index c588e8e486e5..ac0e79e2c2e9 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -923,8 +923,9 @@ static int dummy_udc_stop(struct usb_gadget *g,
 	struct dummy_hcd	*dum_hcd = gadget_to_dummy_hcd(g);
 	struct dummy		*dum = dum_hcd->dum;
 
-	dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n",
-			driver->driver.name);
+	if (driver)
+		dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n",
+				driver->driver.name);
 
 	dum->driver = NULL;
 
@@ -1000,8 +1001,8 @@ static int dummy_udc_remove(struct platform_device *pdev)
 {
 	struct dummy	*dum = platform_get_drvdata(pdev);
 
-	usb_del_gadget_udc(&dum->gadget);
 	device_remove_file(&dum->gadget.dev, &dev_attr_function);
+	usb_del_gadget_udc(&dum->gadget);
 	return 0;
 }
 
diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c
index ab1065afbbd0..3384486c2884 100644
--- a/drivers/usb/gadget/f_acm.c
+++ b/drivers/usb/gadget/f_acm.c
@@ -430,11 +430,12 @@ static int acm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (acm->notify->driver_data) {
 			VDBG(cdev, "reset acm control interface %d\n", intf);
 			usb_ep_disable(acm->notify);
-		} else {
-			VDBG(cdev, "init acm ctrl interface %d\n", intf);
+		}
+
+		if (!acm->notify->desc)
 			if (config_ep_by_speed(cdev->gadget, f, acm->notify))
 				return -EINVAL;
-		}
+
 		usb_ep_enable(acm->notify);
 		acm->notify->driver_data = acm;
 
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index f394f295d63d..84219f656051 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1034,37 +1034,19 @@ struct ffs_sb_fill_data {
 	struct ffs_file_perms perms;
 	umode_t root_mode;
 	const char *dev_name;
-	union {
-		/* set by ffs_fs_mount(), read by ffs_sb_fill() */
-		void *private_data;
-		/* set by ffs_sb_fill(), read by ffs_fs_mount */
-		struct ffs_data *ffs_data;
-	};
+	struct ffs_data *ffs_data;
 };
 
 static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 {
 	struct ffs_sb_fill_data *data = _data;
 	struct inode	*inode;
-	struct ffs_data	*ffs;
+	struct ffs_data	*ffs = data->ffs_data;
 
 	ENTER();
 
-	/* Initialise data */
-	ffs = ffs_data_new();
-	if (unlikely(!ffs))
-		goto Enomem;
-
 	ffs->sb              = sb;
-	ffs->dev_name        = kstrdup(data->dev_name, GFP_KERNEL);
-	if (unlikely(!ffs->dev_name))
-		goto Enomem;
-	ffs->file_perms      = data->perms;
-	ffs->private_data    = data->private_data;
-
-	/* used by the caller of this function */
-	data->ffs_data       = ffs;
-
+	data->ffs_data       = NULL;
 	sb->s_fs_info        = ffs;
 	sb->s_blocksize      = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1080,17 +1062,14 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 				  &data->perms);
 	sb->s_root = d_make_root(inode);
 	if (unlikely(!sb->s_root))
-		goto Enomem;
+		return -ENOMEM;
 
 	/* EP0 file */
 	if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs,
 					 &ffs_ep0_operations, NULL)))
-		goto Enomem;
+		return -ENOMEM;
 
 	return 0;
-
-Enomem:
-	return -ENOMEM;
 }
 
 static int ffs_fs_parse_opts(struct ffs_sb_fill_data *data, char *opts)
@@ -1193,6 +1172,7 @@ ffs_fs_mount(struct file_system_type *t, int flags,
 	struct dentry *rv;
 	int ret;
 	void *ffs_dev;
+	struct ffs_data	*ffs;
 
 	ENTER();
 
@@ -1200,18 +1180,30 @@ ffs_fs_mount(struct file_system_type *t, int flags,
 	if (unlikely(ret < 0))
 		return ERR_PTR(ret);
 
+	ffs = ffs_data_new();
+	if (unlikely(!ffs))
+		return ERR_PTR(-ENOMEM);
+	ffs->file_perms = data.perms;
+
+	ffs->dev_name = kstrdup(dev_name, GFP_KERNEL);
+	if (unlikely(!ffs->dev_name)) {
+		ffs_data_put(ffs);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	ffs_dev = functionfs_acquire_dev_callback(dev_name);
-	if (IS_ERR(ffs_dev))
-		return ffs_dev;
+	if (IS_ERR(ffs_dev)) {
+		ffs_data_put(ffs);
+		return ERR_CAST(ffs_dev);
+	}
+	ffs->private_data = ffs_dev;
+	data.ffs_data = ffs;
 
-	data.dev_name = dev_name;
-	data.private_data = ffs_dev;
 	rv = mount_nodev(t, flags, &data, ffs_sb_fill);
-
-	/* data.ffs_data is set by ffs_sb_fill */
-	if (IS_ERR(rv))
+	if (IS_ERR(rv) && data.ffs_data) {
 		functionfs_release_dev_callback(data.ffs_data);
-
+		ffs_data_put(data.ffs_data);
+	}
 	return rv;
 }
 
@@ -1397,11 +1389,13 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev)
 	ffs->ep0req->context = ffs;
 
 	lang = ffs->stringtabs;
-	for (lang = ffs->stringtabs; *lang; ++lang) {
-		struct usb_string *str = (*lang)->strings;
-		int id = first_id;
-		for (; str->s; ++id, ++str)
-			str->id = id;
+	if (lang) {
+		for (; *lang; ++lang) {
+			struct usb_string *str = (*lang)->strings;
+			int id = first_id;
+			for (; str->s; ++id, ++str)
+				str->id = id;
+		}
 	}
 
 	ffs->gadget = cdev->gadget;
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index 570c005062ab..42a30903d4fd 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -1509,7 +1509,7 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		}
 		break;
 
-#ifndef	CONFIG_USB_GADGET_PXA25X
+#ifndef	CONFIG_USB_PXA25X
 	/* PXA automagically handles this request too */
 	case USB_REQ_GET_CONFIGURATION:
 		if (ctrl->bRequestType != 0x80)
diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c
index 7cacd6ae818e..e4d8d79a4993 100644
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -1614,7 +1614,7 @@ static struct se_wwn *usbg_make_tport(
 		return ERR_PTR(-ENOMEM);
 	}
 	tport->tport_wwpn = wwpn;
-	snprintf(tport->tport_name, sizeof(tport->tport_name), wnn_name);
+	snprintf(tport->tport_name, sizeof(tport->tport_name), "%s", wnn_name);
 	return &tport->tport_wwn;
 }
 
diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c
index 5514822114a5..817a26cbfab1 100644
--- a/drivers/usb/gadget/udc-core.c
+++ b/drivers/usb/gadget/udc-core.c
@@ -439,6 +439,11 @@ static ssize_t usb_udc_softconn_store(struct device *dev,
 {
 	struct usb_udc		*udc = container_of(dev, struct usb_udc, dev);
 
+	if (!udc->driver) {
+		dev_err(dev, "soft-connect without a gadget driver\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (sysfs_streq(buf, "connect")) {
 		usb_gadget_udc_start(udc->gadget, udc->driver);
 		usb_gadget_connect(udc->gadget);
diff --git a/drivers/usb/gadget/zero.c b/drivers/usb/gadget/zero.c
index 0deb9d6cde26..d31814c7238f 100644
--- a/drivers/usb/gadget/zero.c
+++ b/drivers/usb/gadget/zero.c
@@ -280,7 +280,7 @@ static int __init zero_bind(struct usb_composite_dev *cdev)
 	ss_opts->isoc_interval = gzero_options.isoc_interval;
 	ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket;
 	ss_opts->isoc_mult = gzero_options.isoc_mult;
-	ss_opts->isoc_maxburst = gzero_options.isoc_maxpacket;
+	ss_opts->isoc_maxburst = gzero_options.isoc_maxburst;
 	ss_opts->bulk_buflen = gzero_options.bulk_buflen;
 
 	func_ss = usb_get_function(func_inst_ss);
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 344d5e2f87d7..8bc8e066c881 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -17,7 +17,6 @@ config USB_C67X00_HCD
 
 config USB_XHCI_HCD
 	tristate "xHCI HCD (USB 3.0) support"
-	depends on USB_ARCH_HAS_XHCI
 	---help---
 	  The eXtensible Host Controller Interface (xHCI) is standard for USB 3.0
 	  "SuperSpeed" host controller hardware.
@@ -43,7 +42,6 @@ endif # USB_XHCI_HCD
 
 config USB_EHCI_HCD
 	tristate "EHCI HCD (USB 2.0) support"
-	depends on USB_ARCH_HAS_EHCI
 	---help---
 	  The Enhanced Host Controller Interface (EHCI) is standard for USB 2.0
 	  "high speed" (480 Mbit/sec, 60 Mbyte/sec) host controller hardware.
@@ -177,6 +175,13 @@ config USB_EHCI_HCD_SPEAR
           Enables support for the on-chip EHCI controller on
           ST SPEAr chips.
 
+config USB_EHCI_HCD_SYNOPSYS
+       tristate "Support for Synopsys Host-AHB USB 2.0 controller"
+	depends on USB_EHCI_HCD
+	---help---
+	  Enable support for onchip USB controllers based on DesignWare USB 2.0
+	  Host-AHB Controller IP from Synopsys.
+
 config USB_EHCI_HCD_AT91
         tristate  "Support for Atmel on-chip EHCI USB controller"
         depends on USB_EHCI_HCD && ARCH_AT91
@@ -347,7 +352,6 @@ config USB_ISP1362_HCD
 
 config USB_OHCI_HCD
 	tristate "OHCI HCD support"
-	depends on USB_ARCH_HAS_OHCI
 	select ISP1301_OMAP if MACH_OMAP_H2 || MACH_OMAP_H3
 	depends on USB_ISP1301 || !ARCH_LPC32XX
 	---help---
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index 4fb73c156d72..70df7c8c6bcd 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_USB_EHCI_HCD_OMAP)	+= ehci-omap.o
 obj-$(CONFIG_USB_EHCI_HCD_ORION)	+= ehci-orion.o
 obj-$(CONFIG_USB_EHCI_HCD_SPEAR)	+= ehci-spear.o
 obj-$(CONFIG_USB_EHCI_S5P)	+= ehci-s5p.o
+obj-$(CONFIG_USB_EHCI_HCD_SYNOPSYS)	+= ehci-h20ahb.o
 obj-$(CONFIG_USB_EHCI_HCD_AT91) += ehci-atmel.o
 obj-$(CONFIG_USB_EHCI_MSM)	+= ehci-msm.o
 
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 3be3df233a0e..bfcf38383f74 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -130,7 +130,7 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver,
 	}
 
 	/* Enable USB controller, 83xx or 8536 */
-	if (pdata->have_sysif_regs)
+	if (pdata->have_sysif_regs && pdata->controller_ver < FSL_USB_VER_1_6)
 		setbits32(hcd->regs + FSL_SOC_USB_CTRL, 0x4);
 
 	/* Don't need to set host mode here. It will be done by tdi_reset() */
@@ -232,15 +232,9 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd,
 	case FSL_USB2_PHY_ULPI:
 		if (pdata->have_sysif_regs && pdata->controller_ver) {
 			/* controller version 1.6 or above */
+			clrbits32(non_ehci + FSL_SOC_USB_CTRL, UTMI_PHY_EN);
 			setbits32(non_ehci + FSL_SOC_USB_CTRL,
-					ULPI_PHY_CLK_SEL);
-			/*
-			 * Due to controller issue of PHY_CLK_VALID in ULPI
-			 * mode, we set USB_CTRL_USB_EN before checking
-			 * PHY_CLK_VALID, otherwise PHY_CLK_VALID doesn't work.
-			 */
-			clrsetbits_be32(non_ehci + FSL_SOC_USB_CTRL,
-					UTMI_PHY_EN, USB_CTRL_USB_EN);
+				ULPI_PHY_CLK_SEL | USB_CTRL_USB_EN);
 		}
 		portsc |= PORT_PTS_ULPI;
 		break;
@@ -267,7 +261,8 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd,
 		break;
 	}
 
-	if (pdata->have_sysif_regs && pdata->controller_ver &&
+	if (pdata->have_sysif_regs &&
+	    pdata->controller_ver > FSL_USB_VER_1_6 &&
 	    (phy_mode == FSL_USB2_PHY_ULPI)) {
 		/* check PHY_CLK_VALID to get phy clk valid */
 		if (!spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) &
diff --git a/drivers/usb/host/ehci-h20ahb.c b/drivers/usb/host/ehci-h20ahb.c
new file mode 100644
index 000000000000..7724bab1828b
--- /dev/null
+++ b/drivers/usb/host/ehci-h20ahb.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright (C) 2007-2013 Texas Instruments, Inc.
+ *	Author: Vikram Pandita <vikram.pandita@ti.com>
+ *	Author: Anand Gadiyar <gadiyar@ti.com>
+ *	Author: Keshava Munegowda <keshava_mgowda@ti.com>
+ *	Author: Roger Quadros <rogerq@ti.com>
+ *
+ * Copyright (C) 2009 Nokia Corporation
+ *	Contact: Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * Based on ehci-omap.c - driver for USBHOST on OMAP3/4 processors
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/usb/ulpi.h>
+#include <linux/pm_runtime.h>
+#include <linux/gpio.h>
+#include <linux/clk.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/of.h>
+#include <linux/dma-mapping.h>
+
+#include "ehci.h"
+
+#define H20AHB_HS_USB_PORTS	1
+
+/* EHCI Synopsys-specific Register Set */
+#define EHCI_INSNREG04					(0xA0)
+#define EHCI_INSNREG04_DISABLE_UNSUSPEND		(1 << 5)
+#define	EHCI_INSNREG05_ULPI				(0xA4)
+#define	EHCI_INSNREG05_ULPI_CONTROL_SHIFT		31
+#define	EHCI_INSNREG05_ULPI_PORTSEL_SHIFT		24
+#define	EHCI_INSNREG05_ULPI_OPSEL_SHIFT			22
+#define	EHCI_INSNREG05_ULPI_REGADD_SHIFT		16
+#define	EHCI_INSNREG05_ULPI_EXTREGADD_SHIFT		8
+#define	EHCI_INSNREG05_ULPI_WRDATA_SHIFT		0
+
+#define DRIVER_DESC "H20AHB-EHCI Host Controller driver"
+
+static const char hcd_name[] = "ehci-h20ahb";
+
+/*-------------------------------------------------------------------------*/
+
+struct h20ahb_hcd {
+	struct usb_phy *phy[H20AHB_HS_USB_PORTS]; /* one PHY for each port */
+	int nports;
+};
+
+static inline void ehci_write(void __iomem *base, u32 reg, u32 val)
+{
+	writel_relaxed(val, base + reg);
+}
+
+static inline u32 ehci_read(void __iomem *base, u32 reg)
+{
+	return readl_relaxed(base + reg);
+}
+
+/* configure so an HC device and id are always provided */
+/* always called with process context; sleeping is OK */
+
+static struct hc_driver __read_mostly ehci_h20ahb_hc_driver;
+
+static const struct ehci_driver_overrides ehci_h20ahb_overrides __initdata = {
+	.extra_priv_size = sizeof(struct h20ahb_hcd),
+};
+
+static int ehci_h20ahb_phy_read(struct usb_phy *x, u32 reg)
+{
+	u32 val = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+		(1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+		(3 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+		(reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT);
+	ehci_write(x->io_priv, 0, val);
+	while ((val = ehci_read(x->io_priv, 0)) &
+		(1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+	return val & 0xff;
+}
+
+static int ehci_h20ahb_phy_write(struct usb_phy *x, u32 val, u32 reg)
+{
+	u32 v = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+		(1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+		(2 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+		(reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT) |
+		(val & 0xff);
+	ehci_write(x->io_priv, 0, v);
+	while ((v = ehci_read(x->io_priv, 0)) &
+		(1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+	return 0;
+}
+
+static struct usb_phy_io_ops ehci_h20ahb_phy_io_ops = {
+	.read = ehci_h20ahb_phy_read,
+	.write = ehci_h20ahb_phy_write,
+};
+
+
+/**
+ * ehci_hcd_h20ahb_probe - initialize Synopsis-based HCDs
+ *
+ * Allocates basic resources for this USB host controller, and
+ * then invokes the start() method for the HCD associated with it
+ * through the hotplug entry's driver_data.
+ */
+static int ehci_hcd_h20ahb_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource	*res;
+	struct usb_hcd	*hcd;
+	void __iomem *regs;
+	int ret;
+	int irq;
+	int i;
+	struct h20ahb_hcd	*h20ahb;
+
+	if (usb_disabled())
+		return -ENODEV;
+
+	/* if (!dev->parent) {
+		dev_err(dev, "Missing parent device\n");
+		return -ENODEV;
+		}*/
+
+	/* For DT boot, get platform data from parent. i.e. usbhshost */
+	/*if (dev->of_node) {
+		pdata = dev_get_platdata(dev->parent);
+		dev->platform_data = pdata;
+	}
+
+	if (!pdata) {
+		dev_err(dev, "Missing platform data\n");
+		return -ENODEV;
+		}*/
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "EHCI irq failed\n");
+		return -ENODEV;
+	}
+
+	res =  platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	/*
+	 * Right now device-tree probed devices don't get dma_mask set.
+	 * Since shared usb code relies on it, set it here for now.
+	 * Once we have dma capability bindings this can go away.
+	 */
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	ret = -ENODEV;
+	hcd = usb_create_hcd(&ehci_h20ahb_hc_driver, dev,
+			dev_name(dev));
+	if (!hcd) {
+		dev_err(dev, "Failed to create HCD\n");
+		return -ENOMEM;
+	}
+
+	hcd->rsrc_start = res->start;
+	hcd->rsrc_len = resource_size(res);
+	hcd->regs = regs;
+	hcd_to_ehci(hcd)->caps = regs;
+
+	h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+	h20ahb->nports = 1;
+
+	platform_set_drvdata(pdev, hcd);
+
+	/* get the PHY devices if needed */
+	for (i = 0 ; i < h20ahb->nports ; i++) {
+		struct usb_phy *phy;
+
+		/* get the PHY device */
+#if 0
+		if (dev->of_node)
+			phy = devm_usb_get_phy_by_phandle(dev, "phys", i);
+		else
+			phy = devm_usb_get_phy_dev(dev, i);
+#endif
+		phy = otg_ulpi_create(&ehci_h20ahb_phy_io_ops, 0);
+		if (IS_ERR(phy)) {
+			ret = PTR_ERR(phy);
+			dev_err(dev, "Can't get PHY device for port %d: %d\n",
+					i, ret);
+			goto err_phy;
+		}
+		phy->dev = dev;
+		usb_add_phy_dev(phy);
+
+		h20ahb->phy[i] = phy;
+		phy->io_priv = hcd->regs + EHCI_INSNREG05_ULPI;
+
+#if 0
+		usb_phy_init(h20ahb->phy[i]);
+		/* bring PHY out of suspend */
+		usb_phy_set_suspend(h20ahb->phy[i], 0);
+#endif
+	}
+
+	/* make the first port's phy the one used by hcd as well */
+	hcd->phy = h20ahb->phy[0];
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
+	/*
+	 * An undocumented "feature" in the H20AHB EHCI controller,
+	 * causes suspended ports to be taken out of suspend when
+	 * the USBCMD.Run/Stop bit is cleared (for example when
+	 * we do ehci_bus_suspend).
+	 * This breaks suspend-resume if the root-hub is allowed
+	 * to suspend. Writing 1 to this undocumented register bit
+	 * disables this feature and restores normal behavior.
+	 */
+	ehci_write(regs, EHCI_INSNREG04,
+				EHCI_INSNREG04_DISABLE_UNSUSPEND);
+
+	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
+	if (ret) {
+		dev_err(dev, "failed to add hcd with err %d\n", ret);
+		goto err_pm_runtime;
+	}
+	device_wakeup_enable(hcd->self.controller);
+
+	/*
+	 * Bring PHYs out of reset for non PHY modes.
+	 * Even though HSIC mode is a PHY-less mode, the reset
+	 * line exists between the chips and can be modelled
+	 * as a PHY device for reset control.
+	 */
+	for (i = 0; i < h20ahb->nports; i++) {
+		usb_phy_init(h20ahb->phy[i]);
+		/* bring PHY out of suspend */
+		usb_phy_set_suspend(h20ahb->phy[i], 0);
+	}
+
+	return 0;
+
+err_pm_runtime:
+	pm_runtime_put_sync(dev);
+
+err_phy:
+	for (i = 0; i < h20ahb->nports; i++) {
+		if (h20ahb->phy[i])
+			usb_phy_shutdown(h20ahb->phy[i]);
+	}
+
+	usb_put_hcd(hcd);
+
+	return ret;
+}
+
+
+/**
+ * ehci_hcd_h20ahb_remove - shutdown processing for EHCI HCDs
+ * @pdev: USB Host Controller being removed
+ *
+ * Reverses the effect of usb_ehci_hcd_h20ahb_probe(), first invoking
+ * the HCD's stop() method.  It is always called from a thread
+ * context, normally "rmmod", "apmd", or something similar.
+ */
+static int ehci_hcd_h20ahb_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct h20ahb_hcd *h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+	int i;
+
+	usb_remove_hcd(hcd);
+
+	for (i = 0; i < h20ahb->nports; i++) {
+		if (h20ahb->phy[i])
+			usb_phy_shutdown(h20ahb->phy[i]);
+	}
+
+	usb_put_hcd(hcd);
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+static const struct of_device_id h20ahb_ehci_dt_ids[] = {
+	{ .compatible = "snps,ehci-h20ahb" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, h20ahb_ehci_dt_ids);
+
+static struct platform_driver ehci_hcd_h20ahb_driver = {
+	.probe			= ehci_hcd_h20ahb_probe,
+	.remove			= ehci_hcd_h20ahb_remove,
+	.shutdown		= usb_hcd_platform_shutdown,
+	/*.suspend		= ehci_hcd_h20ahb_suspend, */
+	/*.resume		= ehci_hcd_h20ahb_resume, */
+	.driver = {
+		.name		= hcd_name,
+		.of_match_table = h20ahb_ehci_dt_ids,
+	}
+};
+
+/*-------------------------------------------------------------------------*/
+
+static int __init ehci_h20ahb_init(void)
+{
+	if (usb_disabled())
+		return -ENODEV;
+
+	pr_info("%s: " DRIVER_DESC "\n", hcd_name);
+
+	ehci_init_driver(&ehci_h20ahb_hc_driver, &ehci_h20ahb_overrides);
+	return platform_driver_register(&ehci_hcd_h20ahb_driver);
+}
+module_init(ehci_h20ahb_init);
+
+static void __exit ehci_h20ahb_cleanup(void)
+{
+	platform_driver_unregister(&ehci_hcd_h20ahb_driver);
+}
+module_exit(ehci_h20ahb_cleanup);
+
+MODULE_ALIAS("platform:ehci-h20ahb");
+MODULE_AUTHOR("Liviu Dudau <Liviu.Dudau@arm.com>");
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 246e124e6ac5..f1c3ad69ca54 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -591,11 +591,16 @@ static int ehci_run (struct usb_hcd *hcd)
 	 */
 	hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params);
 	if (HCC_64BIT_ADDR(hcc_params)) {
-		ehci_writel(ehci, 0, &ehci->regs->segment);
-#if 0
-// this is deeply broken on almost all architectures
+#ifdef CONFIG_ARM64
+		ehci_writel(ehci, ehci->periodic_dma >> 32, &ehci->regs->segment);
+		/*
+		 * this is deeply broken on almost all architectures
+		 * but arm64 can use it so enable it
+		 */
 		if (!dma_set_mask(hcd->self.controller, DMA_BIT_MASK(64)))
 			ehci_info(ehci, "enabled 64bit DMA\n");
+#else
+		ehci_writel(ehci, 0, &ehci->regs->segment);
 #endif
 	}
 
@@ -686,8 +691,15 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd)
 	struct ehci_hcd		*ehci = hcd_to_ehci (hcd);
 	u32			status, masked_status, pcd_status = 0, cmd;
 	int			bh;
+	unsigned long		flags;
 
-	spin_lock (&ehci->lock);
+	/*
+	 * For threadirqs option we use spin_lock_irqsave() variant to prevent
+	 * deadlock with ehci hrtimer callback, because hrtimer callbacks run
+	 * in interrupt context even when threadirqs is specified. We can go
+	 * back to spin_lock() variant when hrtimer callbacks become threaded.
+	 */
+	spin_lock_irqsave(&ehci->lock, flags);
 
 	status = ehci_readl(ehci, &ehci->regs->status);
 
@@ -705,7 +717,7 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd)
 
 	/* Shared IRQ? */
 	if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
-		spin_unlock(&ehci->lock);
+		spin_unlock_irqrestore(&ehci->lock, flags);
 		return IRQ_NONE;
 	}
 
@@ -823,7 +835,7 @@ dead:
 
 	if (bh)
 		ehci_work (ehci);
-	spin_unlock (&ehci->lock);
+	spin_unlock_irqrestore(&ehci->lock, flags);
 	if (pcd_status)
 		usb_hcd_poll_rh_status(hcd);
 	return IRQ_HANDLED;
@@ -965,8 +977,6 @@ rescan:
 	}
 
 	qh->exception = 1;
-	if (ehci->rh_state < EHCI_RH_RUNNING)
-		qh->qh_state = QH_STATE_IDLE;
 	switch (qh->qh_state) {
 	case QH_STATE_LINKED:
 	case QH_STATE_COMPLETING:
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 595d210655b6..fe131565d090 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci";
 #define PCI_DEVICE_ID_INTEL_CE4100_USB	0x2e70
 
 /*-------------------------------------------------------------------------*/
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC		0x0939
+static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
+{
+	return pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC;
+}
+
+/*
+ * 0x84 is the offset of in/out threshold register,
+ * and it is the same offset as the register of 'hostpc'.
+ */
+#define	intel_quark_x1000_insnreg01	hostpc
+
+/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */
+#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD	0x007f007f
 
 /* called after powerup, by probe or system-pm "wakeup" */
 static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
@@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
 	if (!retval)
 		ehci_dbg(ehci, "MWI active\n");
 
+	/* Reset the threshold limit */
+	if (is_intel_quark_x1000(pdev)) {
+		/*
+		 * For the Intel QUARK X1000, raise the I/O threshold to the
+		 * maximum usable value in order to improve performance.
+		 */
+		ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD,
+			ehci->regs->intel_quark_x1000_insnreg01);
+	}
+
 	return 0;
 }
 
@@ -403,7 +428,7 @@ static struct pci_driver ehci_pci_driver = {
 	.remove =	usb_hcd_pci_remove,
 	.shutdown = 	usb_hcd_pci_shutdown,
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver =	{
 		.pm =	&usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h
index 7c978b23520d..03322d9c70dc 100644
--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -200,6 +200,7 @@ struct ehci_hcd {			/* one per controller */
 	unsigned		has_synopsys_hc_bug:1; /* Synopsys HC */
 	unsigned		frame_index_bug:1; /* MosChip (AKA NetMos) */
 	unsigned		need_oc_pp_cycle:1; /* MPC834X port power */
+	unsigned		imx28_write_fix:1; /* For Freescale i.MX28 */
 
 	/* required for usb32 quirk */
 	#define OHCI_CTRL_HCFS          (3 << 6)
@@ -675,6 +676,18 @@ static inline unsigned int ehci_readl(const struct ehci_hcd *ehci,
 #endif
 }
 
+#ifdef CONFIG_SOC_IMX28
+static inline void imx28_ehci_writel(const unsigned int val,
+		volatile __u32 __iomem *addr)
+{
+	__asm__ ("swp %0, %0, [%1]" : : "r"(val), "r"(addr));
+}
+#else
+static inline void imx28_ehci_writel(const unsigned int val,
+		volatile __u32 __iomem *addr)
+{
+}
+#endif
 static inline void ehci_writel(const struct ehci_hcd *ehci,
 		const unsigned int val, __u32 __iomem *regs)
 {
@@ -683,7 +696,10 @@ static inline void ehci_writel(const struct ehci_hcd *ehci,
 		writel_be(val, regs) :
 		writel(val, regs);
 #else
-	writel(val, regs);
+	if (ehci->imx28_write_fix)
+		imx28_ehci_writel(val, regs);
+	else
+		writel(val, regs);
 #endif
 }
 
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index fc627fd54116..8c57e970bb98 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -231,31 +231,26 @@ static int ohci_urb_enqueue (
 			frame &= ~(ed->interval - 1);
 			frame |= ed->branch;
 			urb->start_frame = frame;
+			ed->last_iso = frame + ed->interval * (size - 1);
 		}
 	} else if (ed->type == PIPE_ISOCHRONOUS) {
 		u16	next = ohci_frame_no(ohci) + 1;
 		u16	frame = ed->last_iso + ed->interval;
+		u16	length = ed->interval * (size - 1);
 
 		/* Behind the scheduling threshold? */
 		if (unlikely(tick_before(frame, next))) {
 
-			/* USB_ISO_ASAP: Round up to the first available slot */
+			/* URB_ISO_ASAP: Round up to the first available slot */
 			if (urb->transfer_flags & URB_ISO_ASAP) {
 				frame += (next - frame + ed->interval - 1) &
 						-ed->interval;
 
 			/*
-			 * Not ASAP: Use the next slot in the stream.  If
-			 * the entire URB falls before the threshold, fail.
+			 * Not ASAP: Use the next slot in the stream,
+			 * no matter what.
 			 */
 			} else {
-				if (tick_before(frame + ed->interval *
-					(urb->number_of_packets - 1), next)) {
-					retval = -EXDEV;
-					usb_hcd_unlink_urb_from_ep(hcd, urb);
-					goto fail;
-				}
-
 				/*
 				 * Some OHCI hardware doesn't handle late TDs
 				 * correctly.  After retiring them it proceeds
@@ -266,9 +261,16 @@ static int ohci_urb_enqueue (
 				urb_priv->td_cnt = DIV_ROUND_UP(
 						(u16) (next - frame),
 						ed->interval);
+				if (urb_priv->td_cnt >= urb_priv->length) {
+					++urb_priv->td_cnt;	/* Mark it */
+					ohci_dbg(ohci, "iso underrun %p (%u+%u < %u)\n",
+							urb, frame, length,
+							next);
+				}
 			}
 		}
 		urb->start_frame = frame;
+		ed->last_iso = frame + length;
 	}
 
 	/* fill the TDs and link them to the ed; and
@@ -1194,25 +1196,6 @@ MODULE_LICENSE ("GPL");
 #define PLATFORM_DRIVER		ohci_platform_driver
 #endif
 
-#if	!defined(PCI_DRIVER) &&		\
-	!defined(PLATFORM_DRIVER) &&	\
-	!defined(OMAP1_PLATFORM_DRIVER) &&	\
-	!defined(OMAP3_PLATFORM_DRIVER) &&	\
-	!defined(OF_PLATFORM_DRIVER) &&	\
-	!defined(SA1111_DRIVER) &&	\
-	!defined(PS3_SYSTEM_BUS_DRIVER) && \
-	!defined(SM501_OHCI_DRIVER) && \
-	!defined(TMIO_OHCI_DRIVER) && \
-	!defined(S3C2410_PLATFORM_DRIVER) && \
-	!defined(EXYNOS_PLATFORM_DRIVER) && \
-	!defined(EP93XX_PLATFORM_DRIVER) && \
-	!defined(AT91_PLATFORM_DRIVER) && \
-	!defined(NXP_PLATFORM_DRIVER) && \
-	!defined(DAVINCI_PLATFORM_DRIVER) && \
-	!defined(SPEAR_PLATFORM_DRIVER)
-#error "missing bus glue for ohci-hcd"
-#endif
-
 static int __init ohci_hcd_mod_init(void)
 {
 	int retval = 0;
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index 60ff4220e8b4..cd908066fde9 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -90,6 +90,24 @@ __acquires(ohci->lock)
 	dl_done_list (ohci);
 	finish_unlinks (ohci, ohci_frame_no(ohci));
 
+	/*
+	 * Some controllers don't handle "global" suspend properly if
+	 * there are unsuspended ports.  For these controllers, put all
+	 * the enabled ports into suspend before suspending the root hub.
+	 */
+	if (ohci->flags & OHCI_QUIRK_GLOBAL_SUSPEND) {
+		__hc32 __iomem	*portstat = ohci->regs->roothub.portstatus;
+		int		i;
+		unsigned	temp;
+
+		for (i = 0; i < ohci->num_ports; (++i, ++portstat)) {
+			temp = ohci_readl(ohci, portstat);
+			if ((temp & (RH_PS_PES | RH_PS_PSS)) ==
+					RH_PS_PES)
+				ohci_writel(ohci, RH_PS_PSS, portstat);
+		}
+	}
+
 	/* maybe resume can wake root hub */
 	if (ohci_to_hcd(ohci)->self.root_hub->do_remote_wakeup || autostop) {
 		ohci->hc_control |= OHCI_CTRL_RWE;
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index ef6782bd1fa9..67af8eef6537 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -172,6 +172,7 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
 	pci_dev_put(amd_smbus_dev);
 	amd_smbus_dev = NULL;
 
+	ohci->flags |= OHCI_QUIRK_GLOBAL_SUSPEND;
 	return 0;
 }
 
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index 88731b7c5f42..1e1563da1812 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -41,8 +41,12 @@ finish_urb(struct ohci_hcd *ohci, struct urb *urb, int status)
 __releases(ohci->lock)
 __acquires(ohci->lock)
 {
+	struct usb_host_endpoint *ep = urb->ep;
+	struct urb_priv *urb_priv;
+
 	// ASSERT (urb->hcpriv != 0);
 
+ restart:
 	urb_free_priv (ohci, urb->hcpriv);
 	urb->hcpriv = NULL;
 	if (likely(status == -EINPROGRESS))
@@ -79,6 +83,21 @@ __acquires(ohci->lock)
 		ohci->hc_control &= ~(OHCI_CTRL_PLE|OHCI_CTRL_IE);
 		ohci_writel (ohci, ohci->hc_control, &ohci->regs->control);
 	}
+
+	/*
+	 * An isochronous URB that is sumitted too late won't have any TDs
+	 * (marked by the fact that the td_cnt value is larger than the
+	 * actual number of TDs).  If the next URB on this endpoint is like
+	 * that, give it back now.
+	 */
+	if (!list_empty(&ep->urb_list)) {
+		urb = list_first_entry(&ep->urb_list, struct urb, urb_list);
+		urb_priv = urb->hcpriv;
+		if (urb_priv->td_cnt > urb_priv->length) {
+			status = 0;
+			goto restart;
+		}
+	}
 }
 
 
@@ -295,8 +314,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed)
  *  - ED_OPER: when there's any request queued, the ED gets rescheduled
  *    immediately.  HC should be working on them.
  *
- *  - ED_IDLE:  when there's no TD queue. there's no reason for the HC
- *    to care about this ED; safe to disable the endpoint.
+ *  - ED_IDLE: when there's no TD queue or the HC isn't running.
  *
  * When finish_unlinks() runs later, after SOF interrupt, it will often
  * complete one or more URB unlinks before making that state change.
@@ -545,7 +563,6 @@ td_fill (struct ohci_hcd *ohci, u32 info,
 		td->hwCBP = cpu_to_hc32 (ohci, data & 0xFFFFF000);
 		*ohci_hwPSWp(ohci, td, 0) = cpu_to_hc16 (ohci,
 						(data & 0x0FFF) | 0xE000);
-		td->ed->last_iso = info & 0xffff;
 	} else {
 		td->hwCBP = cpu_to_hc32 (ohci, data);
 	}
@@ -910,6 +927,10 @@ rescan_all:
 		int			completed, modified;
 		__hc32			*prev;
 
+		/* Is this ED already invisible to the hardware? */
+		if (ed->state == ED_IDLE)
+			goto ed_idle;
+
 		/* only take off EDs that the HC isn't using, accounting for
 		 * frame counter wraps and EDs with partially retired TDs
 		 */
@@ -939,12 +960,20 @@ skip_ed:
 			}
 		}
 
+		/* ED's now officially unlinked, hc doesn't see */
+		ed->state = ED_IDLE;
+		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
+			ohci->eds_scheduled--;
+		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
+		ed->hwNextED = 0;
+		wmb();
+		ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
+ed_idle:
+
 		/* reentrancy:  if we drop the schedule lock, someone might
 		 * have modified this list.  normally it's just prepending
 		 * entries (which we'd ignore), but paranoia won't hurt.
 		 */
-		*last = ed->ed_next;
-		ed->ed_next = NULL;
 		modified = 0;
 
 		/* unlink urbs as requested, but rescan the list after
@@ -994,7 +1023,7 @@ rescan_this:
 			urb_priv->td_cnt++;
 
 			/* if URB is done, clean up */
-			if (urb_priv->td_cnt == urb_priv->length) {
+			if (urb_priv->td_cnt >= urb_priv->length) {
 				modified = completed = 1;
 				finish_urb(ohci, urb, 0);
 			}
@@ -1002,19 +1031,20 @@ rescan_this:
 		if (completed && !list_empty (&ed->td_list))
 			goto rescan_this;
 
-		/* ED's now officially unlinked, hc doesn't see */
-		ed->state = ED_IDLE;
-		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
-			ohci->eds_scheduled--;
-		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
-		ed->hwNextED = 0;
-		wmb ();
-		ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE);
-
-		/* but if there's work queued, reschedule */
-		if (!list_empty (&ed->td_list)) {
-			if (ohci->rh_state == OHCI_RH_RUNNING)
-				ed_schedule (ohci, ed);
+		/*
+		 * If no TDs are queued, take ED off the ed_rm_list.
+		 * Otherwise, if the HC is running, reschedule.
+		 * If not, leave it on the list for further dequeues.
+		 */
+		if (list_empty(&ed->td_list)) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+		} else if (ohci->rh_state == OHCI_RH_RUNNING) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+			ed_schedule(ohci, ed);
+		} else {
+			last = &ed->ed_next;
 		}
 
 		if (modified)
@@ -1084,7 +1114,7 @@ static void takeback_td(struct ohci_hcd *ohci, struct td *td)
 	urb_priv->td_cnt++;
 
 	/* If all this urb's TDs are done, call complete() */
-	if (urb_priv->td_cnt == urb_priv->length)
+	if (urb_priv->td_cnt >= urb_priv->length)
 		finish_urb(ohci, urb, status);
 
 	/* clean schedule:  unlink EDs that are no longer busy */
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index d3299143d9e2..f2521f3185d2 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -405,6 +405,8 @@ struct ohci_hcd {
 #define	OHCI_QUIRK_HUB_POWER	0x100			/* distrust firmware power/oc setup */
 #define	OHCI_QUIRK_AMD_PLL	0x200			/* AMD PLL quirk*/
 #define	OHCI_QUIRK_AMD_PREFETCH	0x400			/* pre-fetch for ISO transfer */
+#define	OHCI_QUIRK_GLOBAL_SUSPEND	0x800		/* must suspend ports */
+
 	// there are also chip quirks/bugs in init logic
 
 	struct work_struct	nec_work;	/* Worker for NEC quirk */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 4c338ec03a07..9cfe3af3101a 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -555,6 +555,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
 		},
 	},
+	{
+		/* HASEE E200 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+			DMI_MATCH(DMI_BOARD_NAME, "E210"),
+			DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+		},
+	},
 	{ }
 };
 
@@ -564,9 +572,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev,
 {
 	int try_handoff = 1, tried_handoff = 0;
 
-	/* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
-	 * the handoff on its unused controller.  Skip it. */
-	if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+	/*
+	 * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+	 * the handoff on its unused controller.  Skip it.
+	 *
+	 * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+	 */
+	if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+			pdev->device == 0x27cc)) {
 		if (dmi_check_system(ehci_dmi_nohandoff_table))
 			try_handoff = 0;
 	}
diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c
index c300bd2f7d1c..0f228c46eeda 100644
--- a/drivers/usb/host/uhci-pci.c
+++ b/drivers/usb/host/uhci-pci.c
@@ -293,7 +293,7 @@ static struct pci_driver uhci_pci_driver = {
 	.remove =	usb_hcd_pci_remove,
 	.shutdown =	uhci_shutdown,
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver =	{
 		.pm =	&usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c
index 041c6ddb695c..da6f56d996ce 100644
--- a/drivers/usb/host/uhci-q.c
+++ b/drivers/usb/host/uhci-q.c
@@ -1303,7 +1303,7 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb,
 		}
 
 		/* Fell behind? */
-		if (uhci_frame_before_eq(frame, next)) {
+		if (!uhci_frame_before_eq(next, frame)) {
 
 			/* USB_ISO_ASAP: Round up to the first available slot */
 			if (urb->transfer_flags & URB_ISO_ASAP)
@@ -1311,13 +1311,17 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb,
 						-qh->period;
 
 			/*
-			 * Not ASAP: Use the next slot in the stream.  If
-			 * the entire URB falls before the threshold, fail.
+			 * Not ASAP: Use the next slot in the stream,
+			 * no matter what.
 			 */
 			else if (!uhci_frame_before_eq(next,
 					frame + (urb->number_of_packets - 1) *
 						qh->period))
-				return -EXDEV;
+				dev_dbg(uhci_dev(uhci), "iso underrun %p (%u+%u < %u)\n",
+						urb, frame,
+						(urb->number_of_packets - 1) *
+							qh->period,
+						next);
 		}
 	}
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 187a3ec1069a..d939376c5dee 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -286,7 +286,7 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend)
 		if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue)
 			xhci_queue_stop_endpoint(xhci, slot_id, i, suspend);
 	}
-	cmd->command_trb = xhci->cmd_ring->enqueue;
+	cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	list_add_tail(&cmd->cmd_list, &virt_dev->cmd_list);
 	xhci_queue_stop_endpoint(xhci, slot_id, 0, suspend);
 	xhci_ring_cmd_db(xhci);
@@ -462,7 +462,8 @@ void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
 }
 
 /* Updates Link Status for super Speed port */
-static void xhci_hub_report_link_state(u32 *status, u32 status_reg)
+static void xhci_hub_report_link_state(struct xhci_hcd *xhci,
+		u32 *status, u32 status_reg)
 {
 	u32 pls = status_reg & PORT_PLS_MASK;
 
@@ -501,7 +502,8 @@ static void xhci_hub_report_link_state(u32 *status, u32 status_reg)
 		 * in which sometimes the port enters compliance mode
 		 * caused by a delay on the host-device negotiation.
 		 */
-		if (pls == USB_SS_PORT_LS_COMP_MOD)
+		if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) &&
+				(pls == USB_SS_PORT_LS_COMP_MOD))
 			pls |= USB_PORT_STAT_CONNECTION;
 	}
 
@@ -686,7 +688,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		}
 		/* Update Port Link State for super speed ports*/
 		if (hcd->speed == HCD_USB3) {
-			xhci_hub_report_link_state(&status, temp);
+			xhci_hub_report_link_state(xhci, &status, temp);
 			/*
 			 * Verify if all USB3 Ports Have entered U0 already.
 			 * Delete Compliance Mode Timer if so.
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index f2e57a1112c9..677f032482f7 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1794,6 +1794,16 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 		kfree(cur_cd);
 	}
 
+	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
+	for (i = 0; i < num_ports && xhci->rh_bw; i++) {
+		struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
+		for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
+			struct list_head *ep = &bwt->interval_bw[j].endpoints;
+			while (!list_empty(ep))
+				list_del_init(ep->next);
+		}
+	}
+
 	for (i = 1; i < MAX_HC_SLOTS; ++i)
 		xhci_free_virt_device(xhci, i);
 
@@ -1834,16 +1844,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	if (!xhci->rh_bw)
 		goto no_bw;
 
-	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
-	for (i = 0; i < num_ports; i++) {
-		struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
-		for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
-			struct list_head *ep = &bwt->interval_bw[j].endpoints;
-			while (!list_empty(ep))
-				list_del_init(ep->next);
-		}
-	}
-
 	for (i = 0; i < num_ports; i++) {
 		struct xhci_tt_bw_info *tt, *n;
 		list_for_each_entry_safe(tt, n, &xhci->rh_bw[i].tts, tt_list) {
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index f00cb203faea..0e57bcb8e3f7 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -87,6 +87,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* AMD PLL quirk */
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
+
+	if (pdev->vendor == PCI_VENDOR_ID_AMD)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;
@@ -113,6 +117,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci_dbg(xhci, "QUIRK: Resetting on resume\n");
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
+	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+			pdev->device == 0x0015)
+		xhci->quirks |= XHCI_RESET_ON_RESUME;
 	if (pdev->vendor == PCI_VENDOR_ID_VIA)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 }
@@ -156,6 +163,10 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	struct usb_hcd *hcd;
 
 	driver = (struct hc_driver *)id->driver_data;
+
+	/* Prevent runtime suspending between USB-2 and USB-3 initialization */
+	pm_runtime_get_noresume(&dev->dev);
+
 	/* Register the USB 2.0 roothub.
 	 * FIXME: USB core must know to register the USB 2.0 roothub first.
 	 * This is sort of silly, because we could just set the HCD driver flags
@@ -165,7 +176,7 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	retval = usb_hcd_pci_probe(dev, id);
 
 	if (retval)
-		return retval;
+		goto put_runtime_pm;
 
 	/* USB 2.0 roothub is stored in the PCI device now. */
 	hcd = dev_get_drvdata(&dev->dev);
@@ -194,12 +205,17 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (xhci->quirks & XHCI_LPM_SUPPORT)
 		hcd_to_bus(xhci->shared_hcd)->root_hub->lpm_capable = 1;
 
+	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
+	pm_runtime_put_noidle(&dev->dev);
+
 	return 0;
 
 put_usb3_hcd:
 	usb_put_hcd(xhci->shared_hcd);
 dealloc_usb2_hcd:
 	usb_hcd_pci_remove(dev);
+put_runtime_pm:
+	pm_runtime_put_noidle(&dev->dev);
 	return retval;
 }
 
@@ -345,7 +361,7 @@ static struct pci_driver xhci_pci_driver = {
 	/* suspend and resume implemented later */
 
 	.shutdown = 	usb_hcd_pci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver = {
 		.pm = &usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index cc3bfc5d590d..eb45ac843712 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -122,6 +122,16 @@ static int enqueue_is_link_trb(struct xhci_ring *ring)
 	return TRB_TYPE_LINK_LE32(link->control);
 }
 
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring)
+{
+	/* Enqueue pointer can be left pointing to the link TRB,
+	 * we must handle that
+	 */
+	if (TRB_TYPE_LINK_LE32(ring->enqueue->link.control))
+		return ring->enq_seg->next->trbs;
+	return ring->enqueue;
+}
+
 /* Updates trb to point to the next TRB in the ring, and updates seg if the next
  * TRB is in a new segment.  This does not skip over link TRBs, and it does not
  * effect the ring dequeue or enqueue pointers.
@@ -847,8 +857,12 @@ remove_finished_td:
 		/* Otherwise ring the doorbell(s) to restart queued transfers */
 		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	}
-	ep->stopped_td = NULL;
-	ep->stopped_trb = NULL;
+
+	/* Clear stopped_td and stopped_trb if endpoint is not halted */
+	if (!(ep->ep_state & EP_HALTED)) {
+		ep->stopped_td = NULL;
+		ep->stopped_trb = NULL;
+	}
 
 	/*
 	 * Drop the lock and complete the URBs in the cancelled TD list.
@@ -1164,9 +1178,8 @@ static void handle_reset_ep_completion(struct xhci_hcd *xhci,
 				false);
 		xhci_ring_cmd_db(xhci);
 	} else {
-		/* Clear our internal halted state and restart the ring(s) */
+		/* Clear our internal halted state */
 		xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED;
-		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	}
 }
 
@@ -1390,6 +1403,12 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 			inc_deq(xhci, xhci->cmd_ring);
 			return;
 		}
+		/* There is no command to handle if we get a stop event when the
+		 * command ring is empty, event->cmd_trb points to the next
+		 * unset command
+		 */
+		if (xhci->cmd_ring->dequeue == xhci->cmd_ring->enqueue)
+			return;
 	}
 
 	switch (le32_to_cpu(xhci->cmd_ring->dequeue->generic.field[3])
@@ -2512,7 +2531,8 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		 * last TRB of the previous TD. The command completion handle
 		 * will take care the rest.
 		 */
-		if (!event_seg && trb_comp_code == COMP_STOP_INVAL) {
+		if (!event_seg && (trb_comp_code == COMP_STOP ||
+				   trb_comp_code == COMP_STOP_INVAL)) {
 			ret = 0;
 			goto cleanup;
 		}
@@ -3570,7 +3590,7 @@ static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci,
 		return 0;
 
 	max_burst = urb->ep->ss_ep_comp.bMaxBurst;
-	return roundup(total_packet_count, max_burst + 1) - 1;
+	return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1;
 }
 
 /*
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index f4a49c45299c..10223f2b18d2 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -315,6 +315,9 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci)
 	struct usb_hcd *hcd = xhci_to_hcd(xhci);
 	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
 
+	if (xhci->quirks & XHCI_PLAT)
+		return;
+
 	xhci_free_irq(xhci);
 
 	if (xhci->msix_entries) {
@@ -391,16 +394,16 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 
 #else
 
-static int xhci_try_enable_msi(struct usb_hcd *hcd)
+static inline int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
 	return 0;
 }
 
-static void xhci_cleanup_msix(struct xhci_hcd *xhci)
+static inline void xhci_cleanup_msix(struct xhci_hcd *xhci)
 {
 }
 
-static void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
+static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
 {
 }
 
@@ -957,7 +960,7 @@ int xhci_suspend(struct xhci_hcd *xhci)
  */
 int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 {
-	u32			command, temp = 0;
+	u32			command, temp = 0, status;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
@@ -1081,8 +1084,12 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
  done:
 	if (retval == 0) {
-		usb_hcd_resume_root_hub(hcd);
-		usb_hcd_resume_root_hub(xhci->shared_hcd);
+		/* Resume root hubs only when have pending events. */
+		status = readl(&xhci->op_regs->status);
+		if (status & STS_EINT) {
+			usb_hcd_resume_root_hub(hcd);
+			usb_hcd_resume_root_hub(xhci->shared_hcd);
+		}
 	}
 
 	/*
@@ -2592,15 +2599,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	if (command) {
 		cmd_completion = command->completion;
 		cmd_status = &command->status;
-		command->command_trb = xhci->cmd_ring->enqueue;
-
-		/* Enqueue pointer can be left pointing to the link TRB,
-		 * we must handle that
-		 */
-		if (TRB_TYPE_LINK_LE32(command->command_trb->link.control))
-			command->command_trb =
-				xhci->cmd_ring->enq_seg->next->trbs;
-
+		command->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 		list_add_tail(&command->cmd_list, &virt_dev->cmd_list);
 	} else {
 		cmd_completion = &virt_dev->cmd_completion;
@@ -2608,7 +2607,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	}
 	init_completion(cmd_completion);
 
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	if (!ctx_change)
 		ret = xhci_queue_configure_endpoint(xhci, in_ctx->dma,
 				udev->slot_id, must_succeed);
@@ -3393,14 +3392,7 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 
 	/* Attempt to submit the Reset Device command to the command ring */
 	spin_lock_irqsave(&xhci->lock, flags);
-	reset_device_cmd->command_trb = xhci->cmd_ring->enqueue;
-
-	/* Enqueue pointer can be left pointing to the link TRB,
-	 * we must handle that
-	 */
-	if (TRB_TYPE_LINK_LE32(reset_device_cmd->command_trb->link.control))
-		reset_device_cmd->command_trb =
-			xhci->cmd_ring->enq_seg->next->trbs;
+	reset_device_cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 
 	list_add_tail(&reset_device_cmd->cmd_list, &virt_dev->cmd_list);
 	ret = xhci_queue_reset_device(xhci, slot_id);
@@ -3604,7 +3596,7 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	union xhci_trb *cmd_trb;
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	ret = xhci_queue_slot_control(xhci, TRB_ENABLE_SLOT, 0);
 	if (ret) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
@@ -3731,7 +3723,7 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	xhci_dbg_ctx(xhci, virt_dev->in_ctx, 2);
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	ret = xhci_queue_address_device(xhci, virt_dev->in_ctx->dma,
 					udev->slot_id);
 	if (ret) {
@@ -4415,13 +4407,21 @@ static int xhci_change_max_exit_latency(struct xhci_hcd *xhci,
 	int ret;
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) {
+
+	virt_dev = xhci->devs[udev->slot_id];
+
+	/*
+	 * virt_dev might not exists yet if xHC resumed from hibernate (S4) and
+	 * xHC was re-initialized. Exit latency will be set later after
+	 * hub_port_finish_reset() is done and xhci->devs[] are re-allocated
+	 */
+
+	if (!virt_dev || max_exit_latency == virt_dev->current_mel) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
 		return 0;
 	}
 
 	/* Attempt to issue an Evaluate Context command to change the MEL. */
-	virt_dev = xhci->devs[udev->slot_id];
 	command = xhci->lpm_command;
 	xhci_slot_copy(xhci, command->in_ctx, virt_dev->out_ctx);
 	spin_unlock_irqrestore(&xhci->lock, flags);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3638f1d779e6..627fcd9388ca 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1821,6 +1821,7 @@ int xhci_cancel_cmd(struct xhci_hcd *xhci, struct xhci_command *command,
 		union xhci_trb *cmd_trb);
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring);
 
 /* xHCI roothub code */
 void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array,
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index de98906f786d..0aef801edbc1 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = {
 	{ USB_DEVICE(0x0711, 0x0918) },
 	{ USB_DEVICE(0x0711, 0x0920) },
 	{ USB_DEVICE(0x0711, 0x0950) },
+	{ USB_DEVICE(0x0711, 0x5200) },
 	{ USB_DEVICE(0x182d, 0x021c) },
 	{ USB_DEVICE(0x182d, 0x0269) },
 	{ }
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 8b4ca1cb450a..98438b90838f 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -7,9 +7,10 @@
 #include <linux/moduleparam.h>
 #include <linux/scatterlist.h>
 #include <linux/mutex.h>
-
+#include <linux/timer.h>
 #include <linux/usb.h>
 
+#define SIMPLE_IO_TIMEOUT	10000	/* in milliseconds */
 
 /*-------------------------------------------------------------------------*/
 
@@ -366,6 +367,7 @@ static int simple_io(
 	int			max = urb->transfer_buffer_length;
 	struct completion	completion;
 	int			retval = 0;
+	unsigned long		expire;
 
 	urb->context = &completion;
 	while (retval == 0 && iterations-- > 0) {
@@ -378,9 +380,15 @@ static int simple_io(
 		if (retval != 0)
 			break;
 
-		/* NOTE:  no timeouts; can't be broken out of by interrupt */
-		wait_for_completion(&completion);
-		retval = urb->status;
+		expire = msecs_to_jiffies(SIMPLE_IO_TIMEOUT);
+		if (!wait_for_completion_timeout(&completion, expire)) {
+			usb_kill_urb(urb);
+			retval = (urb->status == -ENOENT ?
+				  -ETIMEDOUT : urb->status);
+		} else {
+			retval = urb->status;
+		}
+
 		urb->dev = udev;
 		if (retval == 0 && usb_pipein(urb->pipe))
 			retval = simple_check_buf(tdev, urb);
@@ -476,6 +484,14 @@ alloc_sglist(int nents, int max, int vary)
 	return sg;
 }
 
+static void sg_timeout(unsigned long _req)
+{
+	struct usb_sg_request	*req = (struct usb_sg_request *) _req;
+
+	req->status = -ETIMEDOUT;
+	usb_sg_cancel(req);
+}
+
 static int perform_sglist(
 	struct usbtest_dev	*tdev,
 	unsigned		iterations,
@@ -487,6 +503,9 @@ static int perform_sglist(
 {
 	struct usb_device	*udev = testdev_to_usbdev(tdev);
 	int			retval = 0;
+	struct timer_list	sg_timer;
+
+	setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req);
 
 	while (retval == 0 && iterations-- > 0) {
 		retval = usb_sg_init(req, udev, pipe,
@@ -497,7 +516,10 @@ static int perform_sglist(
 
 		if (retval)
 			break;
+		mod_timer(&sg_timer, jiffies +
+				msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
 		usb_sg_wait(req);
+		del_timer_sync(&sg_timer);
 		retval = req->status;
 
 		/* FIXME check resulting data pattern */
@@ -1149,6 +1171,11 @@ static int unlink1(struct usbtest_dev *dev, int pipe, int size, int async)
 	urb->context = &completion;
 	urb->complete = unlink1_callback;
 
+	if (usb_pipeout(urb->pipe)) {
+		simple_fill_buf(urb);
+		urb->transfer_flags |= URB_ZERO_PACKET;
+	}
+
 	/* keep the endpoint busy.  there are lots of hc/hcd-internal
 	 * states, and testing should get to all of them over time.
 	 *
@@ -1279,6 +1306,11 @@ static int unlink_queued(struct usbtest_dev *dev, int pipe, unsigned num,
 				unlink_queued_callback, &ctx);
 		ctx.urbs[i]->transfer_dma = buf_dma;
 		ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
+
+		if (usb_pipeout(ctx.urbs[i]->pipe)) {
+			simple_fill_buf(ctx.urbs[i]);
+			ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET;
+		}
 	}
 
 	/* Submit all the URBs and then unlink URBs num - 4 and num - 2. */
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 37a261a6bb6a..da0caf3f4b27 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -440,7 +440,6 @@ void musb_hnp_stop(struct musb *musb)
 static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 				u8 devctl)
 {
-	struct usb_otg *otg = musb->xceiv->otg;
 	irqreturn_t handled = IRQ_NONE;
 
 	dev_dbg(musb->controller, "<== DevCtl=%02x, int_usb=0x%x\n", devctl,
@@ -655,7 +654,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 				break;
 		case OTG_STATE_B_PERIPHERAL:
 			musb_g_suspend(musb);
-			musb->is_active = otg->gadget->b_hnp_enable;
+			musb->is_active = musb->g.b_hnp_enable;
 			if (musb->is_active) {
 				musb->xceiv->state = OTG_STATE_B_WAIT_ACON;
 				dev_dbg(musb->controller, "HNP: Setting timer for b_ase0_brst\n");
@@ -671,7 +670,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 			break;
 		case OTG_STATE_A_HOST:
 			musb->xceiv->state = OTG_STATE_A_SUSPEND;
-			musb->is_active = otg->host->b_hnp_enable;
+			musb->is_active = musb_to_hcd(musb)->self.b_hnp_enable;
 			break;
 		case OTG_STATE_B_HOST:
 			/* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 2311b1e4e43c..be41733a5eac 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -198,7 +198,7 @@ config USB_RCAR_PHY
 
 config USB_ULPI
 	bool "Generic ULPI Transceiver Driver"
-	depends on ARM
+	depends on ARM || ARM64
 	help
 	  Enable this to support ULPI connected USB OTG transceivers which
 	  are likely found on embedded boards.
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index ae481afcb3ec..9201feb97e9e 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -1299,7 +1299,7 @@ isp1301_set_host(struct usb_otg *otg, struct usb_bus *host)
 		return isp1301_otg_enable(isp);
 	return 0;
 
-#elif	!defined(CONFIG_USB_GADGET_OMAP)
+#elif !IS_ENABLED(CONFIG_USB_OMAP)
 	// FIXME update its refcount
 	otg->host = host;
 
diff --git a/drivers/usb/phy/phy-ulpi.c b/drivers/usb/phy/phy-ulpi.c
index 217339dd7a90..4e3877c329f2 100644
--- a/drivers/usb/phy/phy-ulpi.c
+++ b/drivers/usb/phy/phy-ulpi.c
@@ -47,6 +47,9 @@ struct ulpi_info {
 static struct ulpi_info ulpi_ids[] = {
 	ULPI_INFO(ULPI_ID(0x04cc, 0x1504), "NXP ISP1504"),
 	ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB331x"),
+	ULPI_INFO(ULPI_ID(0x0424, 0x0007), "SMSC USB3320"),
+	ULPI_INFO(ULPI_ID(0x0424, 0x0009), "SMSC USB334x"),
+	ULPI_INFO(ULPI_ID(0x0451, 0x1507), "TI TUSB1210"),
 };
 
 static int ulpi_set_otg_flags(struct usb_phy *phy)
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 3c4db6d196c6..7229b265870a 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -98,13 +98,19 @@ static int usb_serial_device_remove(struct device *dev)
 	struct usb_serial_port *port;
 	int retval = 0;
 	int minor;
+	int autopm_err;
 
 	port = to_usb_serial_port(dev);
 	if (!port)
 		return -ENODEV;
 
-	/* make sure suspend/resume doesn't race against port_remove */
-	usb_autopm_get_interface(port->serial->interface);
+	/*
+	 * Make sure suspend/resume doesn't race against port_remove.
+	 *
+	 * Note that no further runtime PM callbacks will be made if
+	 * autopm_get fails.
+	 */
+	autopm_err = usb_autopm_get_interface(port->serial->interface);
 
 	minor = port->number;
 	tty_unregister_device(usb_serial_tty_driver, minor);
@@ -118,7 +124,9 @@ static int usb_serial_device_remove(struct device *dev)
 	dev_info(dev, "%s converter now disconnected from ttyUSB%d\n",
 		 driver->description, minor);
 
-	usb_autopm_put_interface(port->serial->interface);
+	if (!autopm_err)
+		usb_autopm_put_interface(port->serial->interface);
+
 	return retval;
 }
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index c90d960e091b..a24714f6f88f 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -104,6 +104,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */
 	{ USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */
 	{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
+	{ USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
 	{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
 	{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
 	{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
@@ -119,8 +120,10 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+	{ USB_DEVICE(0x10C4, 0x8875) }, /* CEL MeshConnect USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
@@ -152,7 +155,10 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
+	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
+	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */
 	{ USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */
+	{ USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */
 	{ USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */
 	{ USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */
 	{ USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */
diff --git a/drivers/usb/serial/cypress_m8.h b/drivers/usb/serial/cypress_m8.h
index b461311a2ae7..ce13e61b7d55 100644
--- a/drivers/usb/serial/cypress_m8.h
+++ b/drivers/usb/serial/cypress_m8.h
@@ -63,7 +63,7 @@
 #define UART_DSR	0x20	/* data set ready - flow control - device to host */
 #define CONTROL_RTS	0x10	/* request to send - flow control - host to device */
 #define UART_CTS	0x10	/* clear to send - flow control - device to host */
-#define UART_RI		0x10	/* ring indicator - modem - device to host */
+#define UART_RI		0x80	/* ring indicator - modem - device to host */
 #define UART_CD		0x40	/* carrier detect - modem - device to host */
 #define CYP_ERROR	0x08	/* received from input report - device to host */
 /* Note - the below has nothing to do with the "feature report" reset */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index b65e657c641d..c625f55667f1 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -148,13 +148,16 @@ static struct ftdi_sio_quirk ftdi_8u2232c_quirk = {
  * /sys/bus/usb/ftdi_sio/new_id, then send patch/report!
  */
 static struct usb_device_id id_table_combined [] = {
+	{ USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_1_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_2_PID) },
@@ -194,6 +197,8 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) },
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SPROG_II) },
+	{ USB_DEVICE(FTDI_VID, FTDI_TAGSYS_LP101_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_TAGSYS_P200X_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_LENZ_LIUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_632_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_634_PID) },
@@ -481,6 +486,39 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FD_PID) },
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FE_PID) },
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FF_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_4701_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9300_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9301_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9302_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9303_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9304_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9305_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9306_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9307_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9308_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9309_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930A_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930B_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930C_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930D_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930E_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930F_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9310_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9311_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9312_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9313_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9314_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9315_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9316_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9317_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9318_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9319_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931A_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931B_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931C_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931D_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931E_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931F_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PERLE_ULTRAPORT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PIEGROUP_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TNC_X_PID) },
@@ -580,6 +618,8 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_TAVIR_STK500_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TIAO_UMPA_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	/*
 	 * ELV devices:
 	 */
@@ -671,6 +711,10 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
@@ -718,7 +762,8 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) },
-	{ USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_1_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_3_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) },
@@ -735,6 +780,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
 	{ USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) },
+	{ USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) },
@@ -906,6 +952,46 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_LUMEL_PD12_PID) },
 	/* Crucible Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
+	/* Cressi Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
+	/* Brainboxes Devices */
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_001_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_012_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_023_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_034_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_101_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_4_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_5_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_6_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_7_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_8_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_257_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_4_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_313_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_324_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_357_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) },
+	/* ekey Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
+	/* Infineon Devices */
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
 	{ },					/* Optional parameter entry */
 	{ }					/* Terminating entry */
 };
@@ -1536,14 +1622,17 @@ static void ftdi_set_max_packet_size(struct usb_serial_port *port)
 	struct usb_device *udev = serial->dev;
 
 	struct usb_interface *interface = serial->interface;
-	struct usb_endpoint_descriptor *ep_desc = &interface->cur_altsetting->endpoint[1].desc;
+	struct usb_endpoint_descriptor *ep_desc;
 
 	unsigned num_endpoints;
-	int i;
+	unsigned i;
 
 	num_endpoints = interface->cur_altsetting->desc.bNumEndpoints;
 	dev_info(&udev->dev, "Number of endpoints %d\n", num_endpoints);
 
+	if (!num_endpoints)
+		return;
+
 	/* NOTE: some customers have programmed FT232R/FT245R devices
 	 * with an endpoint size of 0 - not good.  In this case, we
 	 * want to override the endpoint descriptor setting and use a
@@ -2130,6 +2219,30 @@ static void ftdi_set_termios(struct tty_struct *tty,
 		termios->c_cflag |= CRTSCTS;
 	}
 
+	/*
+	 * All FTDI UART chips are limited to CS7/8. We shouldn't pretend to
+	 * support CS5/6 and revert the CSIZE setting instead.
+	 *
+	 * CS5 however is used to control some smartcard readers which abuse
+	 * this limitation to switch modes. Original FTDI chips fall back to
+	 * eight data bits.
+	 *
+	 * TODO: Implement a quirk to only allow this with mentioned
+	 *       readers. One I know of (Argolis Smartreader V1)
+	 *       returns "USB smartcard server" as iInterface string.
+	 *       The vendor didn't bother with a custom VID/PID of
+	 *       course.
+	 */
+	if (C_CSIZE(tty) == CS6) {
+		dev_warn(ddev, "requested CSIZE setting not supported\n");
+
+		termios->c_cflag &= ~CSIZE;
+		if (old_termios)
+			termios->c_cflag |= old_termios->c_cflag & CSIZE;
+		else
+			termios->c_cflag |= CS8;
+	}
+
 	cflag = termios->c_cflag;
 
 	if (!old_termios)
@@ -2166,19 +2279,19 @@ no_skip:
 	} else {
 		urb_value |= FTDI_SIO_SET_DATA_PARITY_NONE;
 	}
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS7:
-			urb_value |= 7;
-			dev_dbg(ddev, "Setting CS7\n");
-			break;
-		case CS8:
-			urb_value |= 8;
-			dev_dbg(ddev, "Setting CS8\n");
-			break;
-		default:
-			dev_err(ddev, "CSIZE was set but not CS7-CS8\n");
-		}
+	switch (cflag & CSIZE) {
+	case CS5:
+		dev_dbg(ddev, "Setting CS5 quirk\n");
+		break;
+	case CS7:
+		urb_value |= 7;
+		dev_dbg(ddev, "Setting CS7\n");
+		break;
+	default:
+	case CS8:
+		urb_value |= 8;
+		dev_dbg(ddev, "Setting CS8\n");
+		break;
 	}
 
 	/* This is needed by the break command since it uses the same command
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 1b8af461b522..ac703a6e2115 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -30,6 +30,12 @@
 
 /*** third-party PIDs (using FTDI_VID) ***/
 
+/*
+ * Certain versions of the official Windows FTDI driver reprogrammed
+ * counterfeit FTDI devices to PID 0. Support these devices anyway.
+ */
+#define FTDI_BRICK_PID		0x0000
+
 #define FTDI_LUMEL_PD12_PID	0x6002
 
 /*
@@ -42,6 +48,8 @@
 /* www.candapter.com Ewert Energy Systems CANdapter device */
 #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */
 
+#define FTDI_BM_ATOM_NANO_PID	0xa559	/* Basic Micro ATOM Nano USB2Serial */
+
 /*
  * Texas Instruments XDS100v2 JTAG / BeagleBone A3
  * http://processors.wiki.ti.com/index.php/XDS100
@@ -50,6 +58,7 @@
 #define TI_XDS100V2_PID		0xa6d0
 
 #define FTDI_NXTCAM_PID		0xABB8 /* NXTCam for Mindstorms NXT */
+#define FTDI_EV3CON_PID		0xABB9 /* Mindstorms EV3 Console Adapter */
 
 /* US Interface Navigator (http://www.usinterface.com/) */
 #define FTDI_USINT_CAT_PID	0xb810	/* Navigator CAT and 2nd PTT lines */
@@ -139,12 +148,19 @@
 /*
  * Xsens Technologies BV products (http://www.xsens.com).
  */
-#define XSENS_CONVERTER_0_PID	0xD388
-#define XSENS_CONVERTER_1_PID	0xD389
+#define XSENS_VID		0x2639
+#define XSENS_AWINDA_STATION_PID 0x0101
+#define XSENS_AWINDA_DONGLE_PID 0x0102
+#define XSENS_MTW_PID		0x0200	/* Xsens MTw */
+#define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
+
+/* Xsens devices using FTDI VID */
+#define XSENS_CONVERTER_0_PID	0xD388	/* Xsens USB converter */
+#define XSENS_CONVERTER_1_PID	0xD389	/* Xsens Wireless Receiver */
 #define XSENS_CONVERTER_2_PID	0xD38A
-#define XSENS_CONVERTER_3_PID	0xD38B
-#define XSENS_CONVERTER_4_PID	0xD38C
-#define XSENS_CONVERTER_5_PID	0xD38D
+#define XSENS_CONVERTER_3_PID	0xD38B	/* Xsens USB-serial converter */
+#define XSENS_CONVERTER_4_PID	0xD38C	/* Xsens Wireless Receiver */
+#define XSENS_CONVERTER_5_PID	0xD38D	/* Xsens Awinda Station */
 #define XSENS_CONVERTER_6_PID	0xD38E
 #define XSENS_CONVERTER_7_PID	0xD38F
 
@@ -363,6 +379,12 @@
 /* Sprog II (Andrew Crosland's SprogII DCC interface) */
 #define FTDI_SPROG_II		0xF0C8
 
+/*
+ * Two of the Tagsys RFID Readers
+ */
+#define FTDI_TAGSYS_LP101_PID	0xF0E9	/* Tagsys L-P101 RFID*/
+#define FTDI_TAGSYS_P200X_PID	0xF0EE	/* Tagsys Medio P200x RFID*/
+
 /* an infrared receiver for user access control with IR tags */
 #define FTDI_PIEGROUP_PID	0xF208	/* Product Id */
 
@@ -531,6 +553,11 @@
  */
 #define FTDI_TIAO_UMPA_PID	0x8a98	/* TIAO/DIYGADGET USB Multi-Protocol Adapter */
 
+/*
+ * NovaTech product ids (FTDI_VID)
+ */
+#define FTDI_NT_ORIONLXM_PID	0x7c90	/* OrionLXm Substation Automation Platform */
+
 
 /********************************/
 /** third-party VID/PID combos **/
@@ -572,6 +599,12 @@
 #define RATOC_PRODUCT_ID_USB60F	0xb020
 
 /*
+ * Infineon Technologies
+ */
+#define INFINEON_VID		0x058b
+#define INFINEON_TRIBOARD_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+
+/*
  * Acton Research Corp.
  */
 #define ACTON_VID		0x0647	/* Vendor ID */
@@ -786,7 +819,8 @@
  * Submitted by Colin Leroy
  */
 #define TESTO_VID			0x128D
-#define TESTO_USB_INTERFACE_PID		0x0001
+#define TESTO_1_PID			0x0001
+#define TESTO_3_PID			0x0003
 
 /*
  * Mobility Electronics products.
@@ -813,6 +847,12 @@
 #define TELLDUS_TELLSTICK_PID		0x0C30	/* RF control dongle 433 MHz using FT232RL */
 
 /*
+ * NOVITUS printers
+ */
+#define NOVITUS_VID			0x1a28
+#define NOVITUS_BONO_E_PID		0x6010
+
+/*
  * RT Systems programming cables for various ham radios
  */
 #define RTSYSTEMS_VID		0x2100	/* Vendor ID */
@@ -886,8 +926,8 @@
 #define BAYER_CONTOUR_CABLE_PID        0x6001
 
 /*
- * The following are the values for the Matrix Orbital FTDI Range
- * Anything in this range will use an FT232RL.
+ * Matrix Orbital Intelligent USB displays.
+ * http://www.matrixorbital.com
  */
 #define MTXORB_VID			0x1B3D
 #define MTXORB_FTDI_RANGE_0100_PID	0x0100
@@ -1146,8 +1186,39 @@
 #define MTXORB_FTDI_RANGE_01FD_PID	0x01FD
 #define MTXORB_FTDI_RANGE_01FE_PID	0x01FE
 #define MTXORB_FTDI_RANGE_01FF_PID	0x01FF
-
-
+#define MTXORB_FTDI_RANGE_4701_PID	0x4701
+#define MTXORB_FTDI_RANGE_9300_PID	0x9300
+#define MTXORB_FTDI_RANGE_9301_PID	0x9301
+#define MTXORB_FTDI_RANGE_9302_PID	0x9302
+#define MTXORB_FTDI_RANGE_9303_PID	0x9303
+#define MTXORB_FTDI_RANGE_9304_PID	0x9304
+#define MTXORB_FTDI_RANGE_9305_PID	0x9305
+#define MTXORB_FTDI_RANGE_9306_PID	0x9306
+#define MTXORB_FTDI_RANGE_9307_PID	0x9307
+#define MTXORB_FTDI_RANGE_9308_PID	0x9308
+#define MTXORB_FTDI_RANGE_9309_PID	0x9309
+#define MTXORB_FTDI_RANGE_930A_PID	0x930A
+#define MTXORB_FTDI_RANGE_930B_PID	0x930B
+#define MTXORB_FTDI_RANGE_930C_PID	0x930C
+#define MTXORB_FTDI_RANGE_930D_PID	0x930D
+#define MTXORB_FTDI_RANGE_930E_PID	0x930E
+#define MTXORB_FTDI_RANGE_930F_PID	0x930F
+#define MTXORB_FTDI_RANGE_9310_PID	0x9310
+#define MTXORB_FTDI_RANGE_9311_PID	0x9311
+#define MTXORB_FTDI_RANGE_9312_PID	0x9312
+#define MTXORB_FTDI_RANGE_9313_PID	0x9313
+#define MTXORB_FTDI_RANGE_9314_PID	0x9314
+#define MTXORB_FTDI_RANGE_9315_PID	0x9315
+#define MTXORB_FTDI_RANGE_9316_PID	0x9316
+#define MTXORB_FTDI_RANGE_9317_PID	0x9317
+#define MTXORB_FTDI_RANGE_9318_PID	0x9318
+#define MTXORB_FTDI_RANGE_9319_PID	0x9319
+#define MTXORB_FTDI_RANGE_931A_PID	0x931A
+#define MTXORB_FTDI_RANGE_931B_PID	0x931B
+#define MTXORB_FTDI_RANGE_931C_PID	0x931C
+#define MTXORB_FTDI_RANGE_931D_PID	0x931D
+#define MTXORB_FTDI_RANGE_931E_PID	0x931E
+#define MTXORB_FTDI_RANGE_931F_PID	0x931F
 
 /*
  * The Mobility Lab (TML)
@@ -1307,3 +1378,57 @@
  * Manufacturer: Crucible Technologies
  */
 #define FTDI_CT_COMET_PID	0x8e08
+
+/*
+ * Product: Z3X Box
+ * Manufacturer: Smart GSM Team
+ */
+#define FTDI_Z3X_PID		0x0011
+
+/*
+ * Product: Cressi PC Interface
+ * Manufacturer: Cressi
+ */
+#define FTDI_CRESSI_PID		0x87d0
+
+/*
+ * Brainboxes devices
+ */
+#define BRAINBOXES_VID			0x05d1
+#define BRAINBOXES_VX_001_PID		0x1001 /* VX-001 ExpressCard 1 Port RS232 */
+#define BRAINBOXES_VX_012_PID		0x1002 /* VX-012 ExpressCard 2 Port RS232 */
+#define BRAINBOXES_VX_023_PID		0x1003 /* VX-023 ExpressCard 1 Port RS422/485 */
+#define BRAINBOXES_VX_034_PID		0x1004 /* VX-034 ExpressCard 2 Port RS422/485 */
+#define BRAINBOXES_US_101_PID		0x1011 /* US-101 1xRS232 */
+#define BRAINBOXES_US_324_PID		0x1013 /* US-324 1xRS422/485 1Mbaud */
+#define BRAINBOXES_US_606_1_PID		0x2001 /* US-606 6 Port RS232 Serial Port 1 and 2 */
+#define BRAINBOXES_US_606_2_PID		0x2002 /* US-606 6 Port RS232 Serial Port 3 and 4 */
+#define BRAINBOXES_US_606_3_PID		0x2003 /* US-606 6 Port RS232 Serial Port 4 and 6 */
+#define BRAINBOXES_US_701_1_PID		0x2011 /* US-701 4xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_701_2_PID		0x2012 /* US-701 4xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_1_PID		0x2021 /* US-279 8xRS422 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_279_2_PID		0x2022 /* US-279 8xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_3_PID		0x2023 /* US-279 8xRS422 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_279_4_PID		0x2024 /* US-279 8xRS422 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_346_1_PID		0x3011 /* US-346 4xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_346_2_PID		0x3012 /* US-346 4xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_257_PID		0x5001 /* US-257 2xRS232 1Mbaud */
+#define BRAINBOXES_US_313_PID		0x6001 /* US-313 2xRS422/485 1Mbaud */
+#define BRAINBOXES_US_357_PID		0x7001 /* US_357 1xRS232/422/485 */
+#define BRAINBOXES_US_842_1_PID		0x8001 /* US-842 8xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_842_2_PID		0x8002 /* US-842 8xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_842_3_PID		0x8003 /* US-842 8xRS422/485 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_842_4_PID		0x8004 /* US-842 8xRS422/485 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_1_PID		0x9001 /* US-160 16xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_160_2_PID		0x9002 /* US-160 16xRS232 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_160_3_PID		0x9003 /* US-160 16xRS232 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_160_4_PID		0x9004 /* US-160 16xRS232 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_5_PID		0x9005 /* US-160 16xRS232 1Mbaud Port 9 and 10 */
+#define BRAINBOXES_US_160_6_PID		0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */
+#define BRAINBOXES_US_160_7_PID		0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */
+#define BRAINBOXES_US_160_8_PID		0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */
+
+/*
+ * ekey biometric systems GmbH (http://ekey.net/)
+ */
+#define FTDI_EKEY_CONV_USB_PID		0xCB08	/* Converter USB */
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index ba45170c78e5..8335b484f14e 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -176,14 +176,7 @@ retry:
 		return result;
 	}
 
-	/* Try sending off another urb, unless in irq context (in which case
-	 * there will be no free urb). */
-	if (!in_irq())
-		goto retry;
-
-	clear_bit_unlock(USB_SERIAL_WRITE_BUSY, &port->flags);
-
-	return 0;
+	goto retry;	/* try sending off another urb */
 }
 
 /**
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 1be6ba7bee27..8cd6479a8b43 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/serial.h>
+#include <linux/swab.h>
 #include <linux/kfifo.h>
 #include <linux/ioctl.h>
 #include <linux/firmware.h>
@@ -284,7 +285,7 @@ static int read_download_mem(struct usb_device *dev, int start_address,
 {
 	int status = 0;
 	__u8 read_length;
-	__be16 be_start_address;
+	u16 be_start_address;
 
 	dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, length);
 
@@ -300,10 +301,14 @@ static int read_download_mem(struct usb_device *dev, int start_address,
 		if (read_length > 1) {
 			dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, read_length);
 		}
-		be_start_address = cpu_to_be16(start_address);
+		/*
+		 * NOTE: Must use swab as wIndex is sent in little-endian
+		 *       byte order regardless of host byte order.
+		 */
+		be_start_address = swab16((u16)start_address);
 		status = ti_vread_sync(dev, UMPC_MEMORY_READ,
 					(__u16)address_type,
-					(__force __u16)be_start_address,
+					be_start_address,
 					buffer, read_length);
 
 		if (status) {
@@ -400,7 +405,7 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 	struct device *dev = &serial->serial->dev->dev;
 	int status = 0;
 	int write_length;
-	__be16 be_start_address;
+	u16 be_start_address;
 
 	/* We can only send a maximum of 1 aligned byte page at a time */
 
@@ -415,11 +420,16 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 		__func__, start_address, write_length);
 	usb_serial_debug_data(dev, __func__, write_length, buffer);
 
-	/* Write first page */
-	be_start_address = cpu_to_be16(start_address);
+	/*
+	 * Write first page.
+	 *
+	 * NOTE: Must use swab as wIndex is sent in little-endian byte order
+	 *       regardless of host byte order.
+	 */
+	be_start_address = swab16((u16)start_address);
 	status = ti_vsend_sync(serial->serial->dev,
 				UMPC_MEMORY_WRITE, (__u16)address_type,
-				(__force __u16)be_start_address,
+				be_start_address,
 				buffer,	write_length);
 	if (status) {
 		dev_dbg(dev, "%s - ERROR %d\n", __func__, status);
@@ -442,11 +452,16 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 			__func__, start_address, write_length);
 		usb_serial_debug_data(dev, __func__, write_length, buffer);
 
-		/* Write next page */
-		be_start_address = cpu_to_be16(start_address);
+		/*
+		 * Write next page.
+		 *
+		 * NOTE: Must use swab as wIndex is sent in little-endian byte
+		 *       order regardless of host byte order.
+		 */
+		be_start_address = swab16((u16)start_address);
 		status = ti_vsend_sync(serial->serial->dev, UMPC_MEMORY_WRITE,
 				(__u16)address_type,
-				(__force __u16)be_start_address,
+				be_start_address,
 				buffer, write_length);
 		if (status) {
 			dev_err(dev, "%s - ERROR %d\n", __func__, status);
@@ -593,8 +608,8 @@ static int get_descriptor_addr(struct edgeport_serial *serial,
 		if (rom_desc->Type == desc_type)
 			return start_address;
 
-		start_address = start_address + sizeof(struct ti_i2c_desc)
-							+ rom_desc->Size;
+		start_address = start_address + sizeof(struct ti_i2c_desc) +
+						le16_to_cpu(rom_desc->Size);
 
 	} while ((start_address < TI_MAX_I2C_SIZE) && rom_desc->Type);
 
@@ -607,7 +622,7 @@ static int valid_csum(struct ti_i2c_desc *rom_desc, __u8 *buffer)
 	__u16 i;
 	__u8 cs = 0;
 
-	for (i = 0; i < rom_desc->Size; i++)
+	for (i = 0; i < le16_to_cpu(rom_desc->Size); i++)
 		cs = (__u8)(cs + buffer[i]);
 
 	if (cs != rom_desc->CheckSum) {
@@ -661,7 +676,7 @@ static int check_i2c_image(struct edgeport_serial *serial)
 			break;
 
 		if ((start_address + sizeof(struct ti_i2c_desc) +
-					rom_desc->Size) > TI_MAX_I2C_SIZE) {
+			le16_to_cpu(rom_desc->Size)) > TI_MAX_I2C_SIZE) {
 			status = -ENODEV;
 			dev_dbg(dev, "%s - structure too big, erroring out.\n", __func__);
 			break;
@@ -676,7 +691,8 @@ static int check_i2c_image(struct edgeport_serial *serial)
 			/* Read the descriptor data */
 			status = read_rom(serial, start_address +
 						sizeof(struct ti_i2c_desc),
-						rom_desc->Size, buffer);
+						le16_to_cpu(rom_desc->Size),
+						buffer);
 			if (status)
 				break;
 
@@ -685,7 +701,7 @@ static int check_i2c_image(struct edgeport_serial *serial)
 				break;
 		}
 		start_address = start_address + sizeof(struct ti_i2c_desc) +
-								rom_desc->Size;
+						le16_to_cpu(rom_desc->Size);
 
 	} while ((rom_desc->Type != I2C_DESC_TYPE_ION) &&
 				(start_address < TI_MAX_I2C_SIZE));
@@ -724,7 +740,7 @@ static int get_manuf_info(struct edgeport_serial *serial, __u8 *buffer)
 
 	/* Read the descriptor data */
 	status = read_rom(serial, start_address+sizeof(struct ti_i2c_desc),
-						rom_desc->Size, buffer);
+					le16_to_cpu(rom_desc->Size), buffer);
 	if (status)
 		goto exit;
 
@@ -819,7 +835,7 @@ static int build_i2c_fw_hdr(__u8 *header, struct device *dev)
 	firmware_rec =  (struct ti_i2c_firmware_rec*)i2c_header->Data;
 
 	i2c_header->Type	= I2C_DESC_TYPE_FIRMWARE_BLANK;
-	i2c_header->Size	= (__u16)buffer_size;
+	i2c_header->Size	= cpu_to_le16(buffer_size);
 	i2c_header->CheckSum	= cs;
 	firmware_rec->Ver_Major	= OperationalMajorVersion;
 	firmware_rec->Ver_Minor	= OperationalMinorVersion;
diff --git a/drivers/usb/serial/io_usbvend.h b/drivers/usb/serial/io_usbvend.h
index 51f83fbb73bb..6f6a856bc37c 100644
--- a/drivers/usb/serial/io_usbvend.h
+++ b/drivers/usb/serial/io_usbvend.h
@@ -594,7 +594,7 @@ struct edge_boot_descriptor {
 
 struct ti_i2c_desc {
 	__u8	Type;			// Type of descriptor
-	__u16	Size;			// Size of data only not including header
+	__le16	Size;			// Size of data only not including header
 	__u8	CheckSum;		// Checksum (8 bit sum of data only)
 	__u8	Data[0];		// Data starts here
 } __attribute__((packed));
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 07fbdf0e7ab6..f0e65c970d35 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -308,24 +308,30 @@ static void	usa26_indat_callback(struct urb *urb)
 		if ((data[0] & 0x80) == 0) {
 			/* no errors on individual bytes, only
 			   possible overrun err */
-			if (data[0] & RXERROR_OVERRUN)
-				err = TTY_OVERRUN;
-			else
-				err = 0;
+			if (data[0] & RXERROR_OVERRUN) {
+				tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+			}
 			for (i = 1; i < urb->actual_length ; ++i)
-				tty_insert_flip_char(&port->port, data[i], err);
+				tty_insert_flip_char(&port->port, data[i],
+								TTY_NORMAL);
 		} else {
 			/* some bytes had errors, every byte has status */
 			dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
 			for (i = 0; i + 1 < urb->actual_length; i += 2) {
-				int stat = data[i], flag = 0;
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
+
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						flag);
 			}
@@ -672,14 +678,19 @@ static void	usa49_indat_callback(struct urb *urb)
 		} else {
 			/* some bytes had errors, every byte has status */
 			for (i = 0; i + 1 < urb->actual_length; i += 2) {
-				int stat = data[i], flag = 0;
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
+
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						flag);
 			}
@@ -736,15 +747,19 @@ static void usa49wg_indat_callback(struct urb *urb)
 			 */
 			for (x = 0; x + 1 < len &&
 				    i + 1 < urb->actual_length; x += 2) {
-				int stat = data[i], flag = 0;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
 
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						     flag);
 				i += 2;
@@ -796,25 +811,31 @@ static void usa90_indat_callback(struct urb *urb)
 			if ((data[0] & 0x80) == 0) {
 				/* no errors on individual bytes, only
 				   possible overrun err*/
-				if (data[0] & RXERROR_OVERRUN)
-					err = TTY_OVERRUN;
-				else
-					err = 0;
+				if (data[0] & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				for (i = 1; i < urb->actual_length ; ++i)
 					tty_insert_flip_char(&port->port,
-							data[i], err);
+							data[i], TTY_NORMAL);
 			}  else {
 			/* some bytes had errors, every byte has status */
 				dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
 				for (i = 0; i + 1 < urb->actual_length; i += 2) {
-					int stat = data[i], flag = 0;
-					if (stat & RXERROR_OVERRUN)
-						flag |= TTY_OVERRUN;
-					if (stat & RXERROR_FRAMING)
-						flag |= TTY_FRAME;
-					if (stat & RXERROR_PARITY)
-						flag |= TTY_PARITY;
+					int stat = data[i];
+					int flag = TTY_NORMAL;
+
+					if (stat & RXERROR_OVERRUN) {
+						tty_insert_flip_char(
+								&port->port, 0,
+								TTY_OVERRUN);
+					}
 					/* XXX should handle break (0x10) */
+					if (stat & RXERROR_PARITY)
+						flag = TTY_PARITY;
+					else if (stat & RXERROR_FRAMING)
+						flag = TTY_FRAME;
+
 					tty_insert_flip_char(&port->port,
 							data[i+1], flag);
 				}
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 2c1749da1f7e..d06013033def 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1593,7 +1593,11 @@ static int mos7840_tiocmget(struct tty_struct *tty)
 		return -ENODEV;
 
 	status = mos7840_get_uart_reg(port, MODEM_STATUS_REGISTER, &msr);
+	if (status != 1)
+		return -EIO;
 	status = mos7840_get_uart_reg(port, MODEM_CONTROL_REGISTER, &mcr);
+	if (status != 1)
+		return -EIO;
 	result = ((mcr & MCR_DTR) ? TIOCM_DTR : 0)
 	    | ((mcr & MCR_RTS) ? TIOCM_RTS : 0)
 	    | ((mcr & MCR_LOOPBACK) ? TIOCM_LOOP : 0)
@@ -1871,25 +1875,25 @@ static void mos7840_change_port_settings(struct tty_struct *tty,
 	iflag = tty->termios.c_iflag;
 
 	/* Change the number of bits */
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			lData = LCR_BITS_5;
-			break;
+	switch (cflag & CSIZE) {
+	case CS5:
+		lData = LCR_BITS_5;
+		break;
 
-		case CS6:
-			lData = LCR_BITS_6;
-			break;
+	case CS6:
+		lData = LCR_BITS_6;
+		break;
 
-		case CS7:
-			lData = LCR_BITS_7;
-			break;
-		default:
-		case CS8:
-			lData = LCR_BITS_8;
-			break;
-		}
+	case CS7:
+		lData = LCR_BITS_7;
+		break;
+
+	default:
+	case CS8:
+		lData = LCR_BITS_8;
+		break;
 	}
+
 	/* Change the Parity bit */
 	if (cflag & PARENB) {
 		if (cflag & PARODD) {
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index 5f4b0cd0f6e9..b0eb1dfc601a 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -219,7 +219,7 @@ static int opticon_write(struct tty_struct *tty, struct usb_serial_port *port,
 
 	/* The conncected devices do not have a bulk write endpoint,
 	 * to transmit data to de barcode device the control endpoint is used */
-	dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO);
+	dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC);
 	if (!dr) {
 		dev_err(&port->dev, "out of memory\n");
 		count = -ENOMEM;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 1cf6f125f5f0..8b3484134ab0 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -81,9 +81,11 @@ static void option_instat_callback(struct urb *urb);
 
 #define HUAWEI_VENDOR_ID			0x12D1
 #define HUAWEI_PRODUCT_E173			0x140C
+#define HUAWEI_PRODUCT_E1750			0x1406
 #define HUAWEI_PRODUCT_K4505			0x1464
 #define HUAWEI_PRODUCT_K3765			0x1465
 #define HUAWEI_PRODUCT_K4605			0x14C6
+#define HUAWEI_PRODUCT_E173S6			0x1C07
 
 #define QUANTA_VENDOR_ID			0x0408
 #define QUANTA_PRODUCT_Q101			0xEA02
@@ -159,6 +161,7 @@ static void option_instat_callback(struct urb *urb);
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED	0x9000
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED	0x9001
 #define NOVATELWIRELESS_PRODUCT_E362		0x9010
+#define NOVATELWIRELESS_PRODUCT_E371		0x9011
 #define NOVATELWIRELESS_PRODUCT_G2		0xA010
 #define NOVATELWIRELESS_PRODUCT_MC551		0xB001
 
@@ -232,8 +235,31 @@ static void option_instat_callback(struct urb *urb);
 #define QUALCOMM_VENDOR_ID			0x05C6
 
 #define CMOTECH_VENDOR_ID			0x16d8
-#define CMOTECH_PRODUCT_6008			0x6008
-#define CMOTECH_PRODUCT_6280			0x6280
+#define CMOTECH_PRODUCT_6001			0x6001
+#define CMOTECH_PRODUCT_CMU_300			0x6002
+#define CMOTECH_PRODUCT_6003			0x6003
+#define CMOTECH_PRODUCT_6004			0x6004
+#define CMOTECH_PRODUCT_6005			0x6005
+#define CMOTECH_PRODUCT_CGU_628A		0x6006
+#define CMOTECH_PRODUCT_CHE_628S		0x6007
+#define CMOTECH_PRODUCT_CMU_301			0x6008
+#define CMOTECH_PRODUCT_CHU_628			0x6280
+#define CMOTECH_PRODUCT_CHU_628S		0x6281
+#define CMOTECH_PRODUCT_CDU_680			0x6803
+#define CMOTECH_PRODUCT_CDU_685A		0x6804
+#define CMOTECH_PRODUCT_CHU_720S		0x7001
+#define CMOTECH_PRODUCT_7002			0x7002
+#define CMOTECH_PRODUCT_CHU_629K		0x7003
+#define CMOTECH_PRODUCT_7004			0x7004
+#define CMOTECH_PRODUCT_7005			0x7005
+#define CMOTECH_PRODUCT_CGU_629			0x7006
+#define CMOTECH_PRODUCT_CHU_629S		0x700a
+#define CMOTECH_PRODUCT_CHU_720I		0x7211
+#define CMOTECH_PRODUCT_7212			0x7212
+#define CMOTECH_PRODUCT_7213			0x7213
+#define CMOTECH_PRODUCT_7251			0x7251
+#define CMOTECH_PRODUCT_7252			0x7252
+#define CMOTECH_PRODUCT_7253			0x7253
 
 #define TELIT_VENDOR_ID				0x1bc7
 #define TELIT_PRODUCT_UC864E			0x1003
@@ -241,14 +267,21 @@ static void option_instat_callback(struct urb *urb);
 #define TELIT_PRODUCT_CC864_DUAL		0x1005
 #define TELIT_PRODUCT_CC864_SINGLE		0x1006
 #define TELIT_PRODUCT_DE910_DUAL		0x1010
+#define TELIT_PRODUCT_UE910_V2			0x1012
 #define TELIT_PRODUCT_LE920			0x1200
+#define TELIT_PRODUCT_LE910			0x1201
 
 /* ZTE PRODUCTS */
 #define ZTE_VENDOR_ID				0x19d2
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
+#define ZTE_PRODUCT_AC2726			0xfff1
+#define ZTE_PRODUCT_CDMA_TECH			0xfffe
+#define ZTE_PRODUCT_AC8710T			0xffff
 #define ZTE_PRODUCT_MC2718			0xffe8
+#define ZTE_PRODUCT_AD3812			0xffeb
+#define ZTE_PRODUCT_MC2716			0xffed
 
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
@@ -283,6 +316,7 @@ static void option_instat_callback(struct urb *urb);
 #define ALCATEL_PRODUCT_X060S_X200		0x0000
 #define ALCATEL_PRODUCT_X220_X500D		0x0017
 #define ALCATEL_PRODUCT_L100V			0x011e
+#define ALCATEL_PRODUCT_L800MA			0x0203
 
 #define PIRELLI_VENDOR_ID			0x1266
 #define PIRELLI_PRODUCT_C100_1			0x1002
@@ -317,11 +351,18 @@ static void option_instat_callback(struct urb *urb);
  * It seems to contain a Qualcomm QSC6240/6290 chipset            */
 #define FOUR_G_SYSTEMS_PRODUCT_W14		0x9603
 
+/* iBall 3.5G connect wireless modem */
+#define IBALL_3_5G_CONNECT			0x9605
+
 /* Zoom */
 #define ZOOM_PRODUCT_4597			0x9607
 
+/* SpeedUp SU9800 usb 3g modem */
+#define SPEEDUP_PRODUCT_SU9800			0x9800
+
 /* Haier products */
 #define HAIER_VENDOR_ID				0x201e
+#define HAIER_PRODUCT_CE81B			0x10f8
 #define HAIER_PRODUCT_CE100			0x2009
 
 /* Cinterion (formerly Siemens) products */
@@ -340,8 +381,13 @@ static void option_instat_callback(struct urb *urb);
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
 #define OLIVETTI_PRODUCT_OLICARD100		0xc000
+#define OLIVETTI_PRODUCT_OLICARD120		0xc001
+#define OLIVETTI_PRODUCT_OLICARD140		0xc002
 #define OLIVETTI_PRODUCT_OLICARD145		0xc003
+#define OLIVETTI_PRODUCT_OLICARD155		0xc004
 #define OLIVETTI_PRODUCT_OLICARD200		0xc005
+#define OLIVETTI_PRODUCT_OLICARD160		0xc00a
+#define OLIVETTI_PRODUCT_OLICARD500		0xc00b
 
 /* Celot products */
 #define CELOT_VENDOR_ID				0x211f
@@ -450,6 +496,14 @@ static void option_instat_callback(struct urb *urb);
 #define CHANGHONG_VENDOR_ID			0x2077
 #define CHANGHONG_PRODUCT_CH690			0x7001
 
+/* Inovia */
+#define INOVIA_VENDOR_ID			0x20a6
+#define INOVIA_SEW858				0x1105
+
+/* VIA Telecom */
+#define VIATELECOM_VENDOR_ID			0x15eb
+#define VIATELECOM_PRODUCT_CDS7			0x0001
+
 /* some devices interfaces need special handling due to a number of reasons */
 enum option_blacklist_reason {
 		OPTION_BLACKLIST_NONE = 0,
@@ -483,14 +537,26 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = {
 	.reserved = BIT(4),
 };
 
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+	.sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
 static const struct option_blacklist_info zte_mc2718_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
 
+static const struct option_blacklist_info net_intf0_blacklist = {
+	.reserved = BIT(0),
+};
+
 static const struct option_blacklist_info net_intf1_blacklist = {
 	.reserved = BIT(1),
 };
@@ -524,6 +590,11 @@ static const struct option_blacklist_info zte_1255_blacklist = {
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info telit_le910_blacklist = {
+	.sendsetup = BIT(0),
+	.reserved = BIT(1) | BIT(2),
+};
+
 static const struct option_blacklist_info telit_le920_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(5),
@@ -567,6 +638,10 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1c23, USB_CLASS_COMM, 0x02, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t) &net_intf1_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S6, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t) &net_intf1_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1750, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t) &net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1441, USB_CLASS_COMM, 0x02, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1442, USB_CLASS_COMM, 0x02, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff),
@@ -627,6 +702,10 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6D) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6E) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x75) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x78) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x79) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x7A) },
@@ -681,11 +760,247 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6D) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6E) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x75) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x78) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x79) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7A) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7B) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x01) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x02) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x03) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x04) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x05) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x06) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x10) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x12) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x13) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x14) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x15) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x17) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x18) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x19) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x31) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x32) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x33) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x34) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x35) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x36) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x48) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x49) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x61) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x62) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x63) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x64) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x65) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x66) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x75) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x78) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x79) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x01) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x02) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x03) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x04) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x05) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x06) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x10) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x12) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x13) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x14) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x15) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x17) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x18) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x19) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x31) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x32) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x33) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x34) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x35) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x36) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x48) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x49) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x61) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x62) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x63) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x64) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x65) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x66) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x75) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x78) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x79) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x01) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x02) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x03) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x04) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x05) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x06) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x10) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x12) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x13) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x14) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x15) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x17) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x18) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x19) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x31) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x32) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x33) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x34) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x35) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x36) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x48) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x49) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x61) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x62) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x63) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x64) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x65) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x66) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x75) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x78) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x79) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x01) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x02) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x03) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x04) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x05) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x06) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x10) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x12) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x13) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x14) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x15) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x17) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x18) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x19) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x31) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x32) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x33) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x34) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x35) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x36) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x48) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x49) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4C) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x61) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x62) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x63) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x64) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x65) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x66) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6D) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6E) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6F) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x72) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x73) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x74) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x75) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x78) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x79) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7A) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7B) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7C) },
 
 
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
@@ -728,6 +1043,7 @@ static const struct usb_device_id option_ids[] = {
 	/* Novatel Ovation MC551 a.k.a. Verizon USB551L */
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E371, 0xff, 0xff, 0xff) },
 
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },
@@ -777,16 +1093,59 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
-	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
-	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6004) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6005) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_628A) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHE_628S),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_301),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628S) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_680) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_685A) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720S),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7002),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629K),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7004),
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7005) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_629),
+	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629S),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720I),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7212),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7213),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7251),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7252),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7253),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864G) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
+		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
 		.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
@@ -1108,7 +1467,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1267, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1268, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1269, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1271, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) },
@@ -1153,6 +1513,25 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff),  /* ZTE MF91 */
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff),  /* Telewell TW-LTE 4G v2 */
+		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1545, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1546, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1547, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1565, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1566, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1567, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1589, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1590, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1591, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1592, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1594, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1596, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1598, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1600, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff,
 	  0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_k3765_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) },
@@ -1179,10 +1558,27 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0178, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
-
-	/* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8b, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8c, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8d, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8e, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff90, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff91, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff92, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) },
+
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
@@ -1214,13 +1610,18 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L100V),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L800MA),
+	  .driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },
 	{ USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
   	  .driver_info = (kernel_ulong_t)&four_g_w14_blacklist
   	},
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
+	{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
 	{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) },
 	/* Pirelli  */
 	{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) },
 	{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) },
@@ -1241,7 +1642,8 @@ static const struct usb_device_id option_ids[] = {
 	/* Cinterion */
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) },
-	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) },
+	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
 		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1251,10 +1653,21 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
-
-	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD140),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) },
-	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD155),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD160),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD500),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */
 	{ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) },
@@ -1342,6 +1755,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
+	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
@@ -1535,6 +1950,8 @@ static void option_instat_callback(struct urb *urb)
 			dev_dbg(dev, "%s: type %x req %x\n", __func__,
 				req_pkt->bRequestType, req_pkt->bRequest);
 		}
+	} else if (status == -ENOENT || status == -ESHUTDOWN) {
+		dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status);
 	} else
 		dev_err(dev, "%s: error %d\n", __func__, status);
 
@@ -1559,6 +1976,7 @@ static int option_send_setup(struct usb_serial_port *port)
 	struct option_private *priv = intfdata->private;
 	struct usb_wwan_port_private *portdata;
 	int val = 0;
+	int res;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -1567,9 +1985,17 @@ static int option_send_setup(struct usb_serial_port *port)
 	if (portdata->rts_state)
 		val |= 0x02;
 
-	return usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
+	res = usb_autopm_get_interface(serial->interface);
+	if (res)
+		return res;
+
+	res = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
 				0x22, 0x21, val, priv->bInterfaceNumber, NULL,
 				0, USB_CTRL_SET_TIMEOUT);
+
+	usb_autopm_put_interface(serial->interface);
+
+	return res;
 }
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 048cd44d51b1..de3e15d8eb10 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -47,6 +47,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) },
+	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
 	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },
@@ -82,6 +83,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(YCCABLE_VENDOR_ID, YCCABLE_PRODUCT_ID) },
 	{ USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) },
 	{ USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) },
 	{ USB_DEVICE(ZEAGLE_VENDOR_ID, ZEAGLE_N2ITION3_PRODUCT_ID) },
 	{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
@@ -141,6 +145,8 @@ struct pl2303_private {
 	spinlock_t lock;
 	u8 line_control;
 	u8 line_status;
+
+	u8 line_settings[7];
 };
 
 static int pl2303_vendor_read(__u16 value, __u16 index,
@@ -280,10 +286,6 @@ static void pl2303_set_termios(struct tty_struct *tty,
 	int baud_floor, baud_ceil;
 	int k;
 
-	/* The PL2303 is reported to lose bytes if you change
-	   serial settings even to the same values as before. Thus
-	   we actually need to filter in this specific case */
-
 	if (old_termios && !tty_termios_hw_change(&tty->termios, old_termios))
 		return;
 
@@ -304,24 +306,22 @@ static void pl2303_set_termios(struct tty_struct *tty,
 	dev_dbg(&port->dev, "0xa1:0x21:0:0  %d - %x %x %x %x %x %x %x\n", i,
 	    buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6]);
 
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			buf[6] = 5;
-			break;
-		case CS6:
-			buf[6] = 6;
-			break;
-		case CS7:
-			buf[6] = 7;
-			break;
-		default:
-		case CS8:
-			buf[6] = 8;
-			break;
-		}
-		dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
+	switch (cflag & CSIZE) {
+	case CS5:
+		buf[6] = 5;
+		break;
+	case CS6:
+		buf[6] = 6;
+		break;
+	case CS7:
+		buf[6] = 7;
+		break;
+	default:
+	case CS8:
+		buf[6] = 8;
+		break;
 	}
+	dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
 
 	/* For reference buf[0]:buf[3] baud rate value */
 	/* NOTE: Only the values defined in baud_sup are supported !
@@ -424,10 +424,29 @@ static void pl2303_set_termios(struct tty_struct *tty,
 		dev_dbg(&port->dev, "parity = none\n");
 	}
 
-	i = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
-			    SET_LINE_REQUEST, SET_LINE_REQUEST_TYPE,
-			    0, 0, buf, 7, 100);
-	dev_dbg(&port->dev, "0x21:0x20:0:0  %d\n", i);
+	/*
+	 * Some PL2303 are known to lose bytes if you change serial settings
+	 * even to the same values as before. Thus we actually need to filter
+	 * in this specific case.
+	 *
+	 * Note that the tty_termios_hw_change check above is not sufficient
+	 * as a previously requested baud rate may differ from the one
+	 * actually used (and stored in old_termios).
+	 *
+	 * NOTE: No additional locking needed for line_settings as it is
+	 *       only used in set_termios, which is serialised against itself.
+	 */
+	if (!old_termios || memcmp(buf, priv->line_settings, 7)) {
+		i = usb_control_msg(serial->dev,
+				    usb_sndctrlpipe(serial->dev, 0),
+				    SET_LINE_REQUEST, SET_LINE_REQUEST_TYPE,
+				    0, 0, buf, 7, 100);
+
+		dev_dbg(&port->dev, "0x21:0x20:0:0  %d\n", i);
+
+		if (i == 7)
+			memcpy(priv->line_settings, buf, 7);
+	}
 
 	/* change control lines if we are switching to or from B0 */
 	spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index c38b8c00c06f..71fd9da1d6e7 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -22,6 +22,7 @@
 #define PL2303_PRODUCT_ID_GPRS		0x0609
 #define PL2303_PRODUCT_ID_HCR331	0x331a
 #define PL2303_PRODUCT_ID_MOTOROLA	0x0307
+#define PL2303_PRODUCT_ID_ZTEK		0xe1f1
 
 #define ATEN_VENDOR_ID		0x0557
 #define ATEN_VENDOR_ID2		0x0547
@@ -121,8 +122,11 @@
 #define SUPERIAL_VENDOR_ID	0x5372
 #define SUPERIAL_PRODUCT_ID	0x2303
 
-/* Hewlett-Packard LD220-HP POS Pole Display */
+/* Hewlett-Packard POS Pole Displays */
 #define HP_VENDOR_ID		0x03f0
+#define HP_LD960_PRODUCT_ID	0x0b39
+#define HP_LCM220_PRODUCT_ID	0x3139
+#define HP_LCM960_PRODUCT_ID	0x3239
 #define HP_LD220_PRODUCT_ID	0x3524
 
 /* Cressi Edy (diving computer) PC interface */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index c65437cfd4a2..43d93dbf7d71 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -136,9 +136,57 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 0)},	/* Sierra Wireless MC7710 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 2)},	/* Sierra Wireless MC7710 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 3)},	/* Sierra Wireless MC7710 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 0)},	/* Sierra Wireless MC73xx Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 2)},	/* Sierra Wireless MC73xx NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 3)},	/* Sierra Wireless MC73xx Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)},	/* Sierra Wireless EM7700 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)},	/* Sierra Wireless EM7700 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)},	/* Sierra Wireless EM7700 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)},	/* Sierra Wireless EM7355 Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)},	/* Sierra Wireless EM7355 NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)},	/* Sierra Wireless EM7355 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)},	/* Sierra Wireless MC7305/MC7355 Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)},	/* Sierra Wireless MC7305/MC7355 NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)},	/* Sierra Wireless MC7305/MC7355 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)},	/* Netgear AirCard 341U Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)},	/* Netgear AirCard 341U NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)},	/* Netgear AirCard 341U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */
 
 	{ }				/* Terminating entry */
 };
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 8894665cd610..5aaa2b675116 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -58,6 +58,7 @@ struct sierra_intf_private {
 	spinlock_t susp_lock;
 	unsigned int suspended:1;
 	int in_flight;
+	unsigned int open_ports;
 };
 
 static int sierra_set_power_state(struct usb_device *udev, __u16 swiState)
@@ -281,17 +282,21 @@ static const struct usb_device_id id_table[] = {
 	/* Sierra Wireless HSPA Non-Composite Device */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)},
 	{ USB_DEVICE(0x1199, 0x6893) },	/* Sierra Wireless Device */
-	{ USB_DEVICE(0x1199, 0x68A3), 	/* Sierra Wireless Direct IP modems */
+	/* Sierra Wireless Direct IP modems */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF),
+	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+	},
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
 	/* AT&T Direct IP LTE modems */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
-	{ USB_DEVICE(0x0f3d, 0x68A3), 	/* Airprime/Sierra Wireless Direct IP modems */
+	/* Airprime/Sierra Wireless Direct IP modems */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
-       { USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */
 
 	{ }
 };
@@ -768,6 +773,7 @@ static void sierra_close(struct usb_serial_port *port)
 	struct usb_serial *serial = port->serial;
 	struct sierra_port_private *portdata;
 	struct sierra_intf_private *intfdata = port->serial->private;
+	struct urb *urb;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -776,7 +782,6 @@ static void sierra_close(struct usb_serial_port *port)
 
 	mutex_lock(&serial->disc_mutex);
 	if (!serial->disconnected) {
-		serial->interface->needs_remote_wakeup = 0;
 		/* odd error handling due to pm counters */
 		if (!usb_autopm_get_interface(serial->interface))
 			sierra_send_setup(port);
@@ -787,8 +792,22 @@ static void sierra_close(struct usb_serial_port *port)
 	mutex_unlock(&serial->disc_mutex);
 	spin_lock_irq(&intfdata->susp_lock);
 	portdata->opened = 0;
+	if (--intfdata->open_ports == 0)
+		serial->interface->needs_remote_wakeup = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
 
+	for (;;) {
+		urb = usb_get_from_anchor(&portdata->delayed);
+		if (!urb)
+			break;
+		kfree(urb->transfer_buffer);
+		usb_free_urb(urb);
+		usb_autopm_put_interface_async(serial->interface);
+		spin_lock(&portdata->lock);
+		portdata->outstanding_urbs--;
+		spin_unlock(&portdata->lock);
+	}
+
 	sierra_stop_rx_urbs(port);
 	for (i = 0; i < portdata->num_in_urbs; i++) {
 		sierra_release_urb(portdata->in_urbs[i]);
@@ -825,23 +844,29 @@ static int sierra_open(struct tty_struct *tty, struct usb_serial_port *port)
 			usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN);
 
 	err = sierra_submit_rx_urbs(port, GFP_KERNEL);
-	if (err) {
-		/* get rid of everything as in close */
-		sierra_close(port);
-		/* restore balance for autopm */
-		if (!serial->disconnected)
-			usb_autopm_put_interface(serial->interface);
-		return err;
-	}
+	if (err)
+		goto err_submit;
+
 	sierra_send_setup(port);
 
-	serial->interface->needs_remote_wakeup = 1;
 	spin_lock_irq(&intfdata->susp_lock);
 	portdata->opened = 1;
+	if (++intfdata->open_ports == 1)
+		serial->interface->needs_remote_wakeup = 1;
 	spin_unlock_irq(&intfdata->susp_lock);
 	usb_autopm_put_interface(serial->interface);
 
 	return 0;
+
+err_submit:
+	sierra_stop_rx_urbs(port);
+
+	for (i = 0; i < portdata->num_in_urbs; i++) {
+		sierra_release_urb(portdata->in_urbs[i]);
+		portdata->in_urbs[i] = NULL;
+	}
+
+	return err;
 }
 
 
@@ -937,6 +962,7 @@ static int sierra_port_remove(struct usb_serial_port *port)
 	struct sierra_port_private *portdata;
 
 	portdata = usb_get_serial_port_data(port);
+	usb_set_serial_port_data(port, NULL);
 	kfree(portdata);
 
 	return 0;
@@ -953,6 +979,8 @@ static void stop_read_write_urbs(struct usb_serial *serial)
 	for (i = 0; i < serial->num_ports; ++i) {
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
+		if (!portdata)
+			continue;
 		sierra_stop_rx_urbs(port);
 		usb_kill_anchored_urbs(&portdata->active);
 	}
@@ -995,6 +1023,9 @@ static int sierra_resume(struct usb_serial *serial)
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
 
+		if (!portdata)
+			continue;
+
 		while ((urb = usb_get_from_anchor(&portdata->delayed))) {
 			usb_anchor_urb(urb, &portdata->active);
 			intfdata->in_flight++;
@@ -1002,8 +1033,12 @@ static int sierra_resume(struct usb_serial *serial)
 			if (err < 0) {
 				intfdata->in_flight--;
 				usb_unanchor_urb(urb);
-				usb_scuttle_anchored_urbs(&portdata->delayed);
-				break;
+				kfree(urb->transfer_buffer);
+				usb_free_urb(urb);
+				spin_lock(&portdata->lock);
+				portdata->outstanding_urbs--;
+				spin_unlock(&portdata->lock);
+				continue;
 			}
 		}
 
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index ddf6c47137dc..1694d4ff1639 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -346,22 +346,20 @@ static void spcp8x5_set_termios(struct tty_struct *tty,
 	}
 
 	/* Set Data Length : 00:5bit, 01:6bit, 10:7bit, 11:8bit */
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			buf[1] |= SET_UART_FORMAT_SIZE_5;
-			break;
-		case CS6:
-			buf[1] |= SET_UART_FORMAT_SIZE_6;
-			break;
-		case CS7:
-			buf[1] |= SET_UART_FORMAT_SIZE_7;
-			break;
-		default:
-		case CS8:
-			buf[1] |= SET_UART_FORMAT_SIZE_8;
-			break;
-		}
+	switch (cflag & CSIZE) {
+	case CS5:
+		buf[1] |= SET_UART_FORMAT_SIZE_5;
+		break;
+	case CS6:
+		buf[1] |= SET_UART_FORMAT_SIZE_6;
+		break;
+	case CS7:
+		buf[1] |= SET_UART_FORMAT_SIZE_7;
+		break;
+	default:
+	case CS8:
+		buf[1] |= SET_UART_FORMAT_SIZE_8;
+		break;
 	}
 
 	/* Set Stop bit2 : 0:1bit 1:2bit */
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index 5b62dbbdf996..8f5f36134864 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -495,10 +495,9 @@ static void ssu100_update_lsr(struct usb_serial_port *port, u8 lsr,
 			if (*tty_flag == TTY_NORMAL)
 				*tty_flag = TTY_FRAME;
 		}
-		if (lsr & UART_LSR_OE){
+		if (lsr & UART_LSR_OE) {
 			port->icount.overrun++;
-			if (*tty_flag == TTY_NORMAL)
-				*tty_flag = TTY_OVERRUN;
+			tty_insert_flip_char(&port->port, 0, TTY_OVERRUN);
 		}
 	}
 
@@ -516,12 +515,8 @@ static void ssu100_process_read_urb(struct urb *urb)
 	if ((len >= 4) &&
 	    (packet[0] == 0x1b) && (packet[1] == 0x1b) &&
 	    ((packet[2] == 0x00) || (packet[2] == 0x01))) {
-		if (packet[2] == 0x00) {
+		if (packet[2] == 0x00)
 			ssu100_update_lsr(port, packet[3], &flag);
-			if (flag == TTY_OVERRUN)
-				tty_insert_flip_char(&port->port, 0,
-						TTY_OVERRUN);
-		}
 		if (packet[2] == 0x01)
 			ssu100_update_msr(port, packet[3]);
 
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 32bdd5eac59b..4cc84c0c990d 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -203,6 +203,7 @@ static struct usb_device_id ti_id_table_combined[19+2*TI_EXTRA_VID_PID_COUNT+1]
 	{ USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) },
 	{ USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) },
 	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) },
+	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) },
 	{ USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) },
 	{ }
 };
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 5f6b1ff9d29e..80d689f0fda9 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -778,29 +778,39 @@ static int usb_serial_probe(struct usb_interface *interface,
 		if (usb_endpoint_is_bulk_in(endpoint)) {
 			/* we found a bulk in endpoint */
 			dev_dbg(ddev, "found bulk in on endpoint %d\n", i);
-			bulk_in_endpoint[num_bulk_in] = endpoint;
-			++num_bulk_in;
+			if (num_bulk_in < MAX_NUM_PORTS) {
+				bulk_in_endpoint[num_bulk_in] = endpoint;
+				++num_bulk_in;
+			}
 		}
 
 		if (usb_endpoint_is_bulk_out(endpoint)) {
 			/* we found a bulk out endpoint */
 			dev_dbg(ddev, "found bulk out on endpoint %d\n", i);
-			bulk_out_endpoint[num_bulk_out] = endpoint;
-			++num_bulk_out;
+			if (num_bulk_out < MAX_NUM_PORTS) {
+				bulk_out_endpoint[num_bulk_out] = endpoint;
+				++num_bulk_out;
+			}
 		}
 
 		if (usb_endpoint_is_int_in(endpoint)) {
 			/* we found a interrupt in endpoint */
 			dev_dbg(ddev, "found interrupt in on endpoint %d\n", i);
-			interrupt_in_endpoint[num_interrupt_in] = endpoint;
-			++num_interrupt_in;
+			if (num_interrupt_in < MAX_NUM_PORTS) {
+				interrupt_in_endpoint[num_interrupt_in] =
+						endpoint;
+				++num_interrupt_in;
+			}
 		}
 
 		if (usb_endpoint_is_int_out(endpoint)) {
 			/* we found an interrupt out endpoint */
 			dev_dbg(ddev, "found interrupt out on endpoint %d\n", i);
-			interrupt_out_endpoint[num_interrupt_out] = endpoint;
-			++num_interrupt_out;
+			if (num_interrupt_out < MAX_NUM_PORTS) {
+				interrupt_out_endpoint[num_interrupt_out] =
+						endpoint;
+				++num_interrupt_out;
+			}
 		}
 	}
 
@@ -823,8 +833,10 @@ static int usb_serial_probe(struct usb_interface *interface,
 				if (usb_endpoint_is_int_in(endpoint)) {
 					/* we found a interrupt in endpoint */
 					dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n");
-					interrupt_in_endpoint[num_interrupt_in] = endpoint;
-					++num_interrupt_in;
+					if (num_interrupt_in < MAX_NUM_PORTS) {
+						interrupt_in_endpoint[num_interrupt_in] = endpoint;
+						++num_interrupt_in;
+					}
 				}
 			}
 		}
@@ -864,6 +876,11 @@ static int usb_serial_probe(struct usb_interface *interface,
 			num_ports = type->num_ports;
 	}
 
+	if (num_ports > MAX_NUM_PORTS) {
+		dev_warn(ddev, "too many ports requested: %d\n", num_ports);
+		num_ports = MAX_NUM_PORTS;
+	}
+
 	serial->num_ports = num_ports;
 	serial->num_bulk_in = num_bulk_in;
 	serial->num_bulk_out = num_bulk_out;
@@ -1367,10 +1384,12 @@ static int usb_serial_register(struct usb_serial_driver *driver)
 static void usb_serial_deregister(struct usb_serial_driver *device)
 {
 	pr_info("USB Serial deregistering driver %s\n", device->description);
+
 	mutex_lock(&table_lock);
 	list_del(&device->driver_list);
-	usb_serial_bus_deregister(device);
 	mutex_unlock(&table_lock);
+
+	usb_serial_bus_deregister(device);
 }
 
 /**
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index db0cf536de18..36f6b6a56907 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -228,8 +228,10 @@ int usb_wwan_write(struct tty_struct *tty, struct usb_serial_port *port,
 			usb_pipeendpoint(this_urb->pipe), i);
 
 		err = usb_autopm_get_interface_async(port->serial->interface);
-		if (err < 0)
+		if (err < 0) {
+			clear_bit(i, &portdata->out_busy);
 			break;
+		}
 
 		/* send the data */
 		memcpy(this_urb->transfer_buffer, buf, todo);
@@ -386,6 +388,14 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port)
 	portdata = usb_get_serial_port_data(port);
 	intfdata = serial->private;
 
+	if (port->interrupt_in_urb) {
+		err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
+		if (err) {
+			dev_dbg(&port->dev, "%s: submit int urb failed: %d\n",
+				__func__, err);
+		}
+	}
+
 	/* Start reading from the IN endpoint */
 	for (i = 0; i < N_IN_URB; i++) {
 		urb = portdata->in_urbs[i];
@@ -412,12 +422,26 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port)
 }
 EXPORT_SYMBOL(usb_wwan_open);
 
+static void unbusy_queued_urb(struct urb *urb,
+					struct usb_wwan_port_private *portdata)
+{
+	int i;
+
+	for (i = 0; i < N_OUT_URB; i++) {
+		if (urb == portdata->out_urbs[i]) {
+			clear_bit(i, &portdata->out_busy);
+			break;
+		}
+	}
+}
+
 void usb_wwan_close(struct usb_serial_port *port)
 {
 	int i;
 	struct usb_serial *serial = port->serial;
 	struct usb_wwan_port_private *portdata;
 	struct usb_wwan_intf_private *intfdata = port->serial->private;
+	struct urb *urb;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -426,10 +450,19 @@ void usb_wwan_close(struct usb_serial_port *port)
 	portdata->opened = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
 
+	for (;;) {
+		urb = usb_get_from_anchor(&portdata->delayed);
+		if (!urb)
+			break;
+		unbusy_queued_urb(urb, portdata);
+		usb_autopm_put_interface_async(serial->interface);
+	}
+
 	for (i = 0; i < N_IN_URB; i++)
 		usb_kill_urb(portdata->in_urbs[i]);
 	for (i = 0; i < N_OUT_URB; i++)
 		usb_kill_urb(portdata->out_urbs[i]);
+	usb_kill_urb(port->interrupt_in_urb);
 
 	/* balancing - important as an error cannot be handled*/
 	usb_autopm_get_interface_no_resume(serial->interface);
@@ -467,9 +500,11 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
 	u8 *buffer;
-	int err;
 	int i;
 
+	if (!port->bulk_in_size || !port->bulk_out_size)
+		return -ENODEV;
+
 	portdata = kzalloc(sizeof(*portdata), GFP_KERNEL);
 	if (!portdata)
 		return -ENOMEM;
@@ -477,9 +512,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	init_usb_anchor(&portdata->delayed);
 
 	for (i = 0; i < N_IN_URB; i++) {
-		if (!port->bulk_in_size)
-			break;
-
 		buffer = (u8 *)__get_free_page(GFP_KERNEL);
 		if (!buffer)
 			goto bail_out_error;
@@ -493,9 +525,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	}
 
 	for (i = 0; i < N_OUT_URB; i++) {
-		if (!port->bulk_out_size)
-			break;
-
 		buffer = kmalloc(OUT_BUFLEN, GFP_KERNEL);
 		if (!buffer)
 			goto bail_out_error2;
@@ -510,13 +539,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 
 	usb_set_serial_port_data(port, portdata);
 
-	if (port->interrupt_in_urb) {
-		err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
-		if (err)
-			dev_dbg(&port->dev, "%s: submit irq_in urb failed %d\n",
-				__func__, err);
-	}
-
 	return 0;
 
 bail_out_error2:
@@ -584,44 +606,29 @@ static void stop_read_write_urbs(struct usb_serial *serial)
 int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message)
 {
 	struct usb_wwan_intf_private *intfdata = serial->private;
-	int b;
 
+	spin_lock_irq(&intfdata->susp_lock);
 	if (PMSG_IS_AUTO(message)) {
-		spin_lock_irq(&intfdata->susp_lock);
-		b = intfdata->in_flight;
-		spin_unlock_irq(&intfdata->susp_lock);
-
-		if (b)
+		if (intfdata->in_flight) {
+			spin_unlock_irq(&intfdata->susp_lock);
 			return -EBUSY;
+		}
 	}
-
-	spin_lock_irq(&intfdata->susp_lock);
 	intfdata->suspended = 1;
 	spin_unlock_irq(&intfdata->susp_lock);
+
 	stop_read_write_urbs(serial);
 
 	return 0;
 }
 EXPORT_SYMBOL(usb_wwan_suspend);
 
-static void unbusy_queued_urb(struct urb *urb, struct usb_wwan_port_private *portdata)
-{
-	int i;
-
-	for (i = 0; i < N_OUT_URB; i++) {
-		if (urb == portdata->out_urbs[i]) {
-			clear_bit(i, &portdata->out_busy);
-			break;
-		}
-	}
-}
-
-static void play_delayed(struct usb_serial_port *port)
+static int play_delayed(struct usb_serial_port *port)
 {
 	struct usb_wwan_intf_private *data;
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
-	int err;
+	int err = 0;
 
 	portdata = usb_get_serial_port_data(port);
 	data = port->serial->private;
@@ -638,6 +645,8 @@ static void play_delayed(struct usb_serial_port *port)
 			break;
 		}
 	}
+
+	return err;
 }
 
 int usb_wwan_resume(struct usb_serial *serial)
@@ -647,54 +656,51 @@ int usb_wwan_resume(struct usb_serial *serial)
 	struct usb_wwan_intf_private *intfdata = serial->private;
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
-	int err = 0;
-
-	/* get the interrupt URBs resubmitted unconditionally */
-	for (i = 0; i < serial->num_ports; i++) {
-		port = serial->port[i];
-		if (!port->interrupt_in_urb) {
-			dev_dbg(&port->dev, "%s: No interrupt URB for port\n", __func__);
-			continue;
-		}
-		err = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
-		dev_dbg(&port->dev, "Submitted interrupt URB for port (result %d)\n", err);
-		if (err < 0) {
-			dev_err(&port->dev, "%s: Error %d for interrupt URB\n",
-				__func__, err);
-			goto err_out;
-		}
-	}
+	int err;
+	int err_count = 0;
 
+	spin_lock_irq(&intfdata->susp_lock);
 	for (i = 0; i < serial->num_ports; i++) {
 		/* walk all ports */
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
 
 		/* skip closed ports */
-		spin_lock_irq(&intfdata->susp_lock);
-		if (!portdata || !portdata->opened) {
-			spin_unlock_irq(&intfdata->susp_lock);
+		if (!portdata || !portdata->opened)
 			continue;
+
+		if (port->interrupt_in_urb) {
+			err = usb_submit_urb(port->interrupt_in_urb,
+					GFP_ATOMIC);
+			if (err) {
+				dev_err(&port->dev,
+					"%s: submit int urb failed: %d\n",
+					__func__, err);
+				err_count++;
+			}
 		}
 
+		err = play_delayed(port);
+		if (err)
+			err_count++;
+
 		for (j = 0; j < N_IN_URB; j++) {
 			urb = portdata->in_urbs[j];
 			err = usb_submit_urb(urb, GFP_ATOMIC);
 			if (err < 0) {
 				dev_err(&port->dev, "%s: Error %d for bulk URB %d\n",
 					__func__, err, i);
-				spin_unlock_irq(&intfdata->susp_lock);
-				goto err_out;
+				err_count++;
 			}
 		}
-		play_delayed(port);
-		spin_unlock_irq(&intfdata->susp_lock);
 	}
-	spin_lock_irq(&intfdata->susp_lock);
 	intfdata->suspended = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
-err_out:
-	return err;
+
+	if (err_count)
+		return -EIO;
+
+	return 0;
 }
 EXPORT_SYMBOL(usb_wwan_resume);
 #endif
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 347caad47a12..5e3dd9f87ff5 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -521,6 +521,10 @@ static void command_port_read_callback(struct urb *urb)
 		dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__);
 		return;
 	}
+	if (!urb->actual_length) {
+		dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__);
+		return;
+	}
 	if (status) {
 		dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status);
 		if (status != -ENOENT)
@@ -541,7 +545,8 @@ static void command_port_read_callback(struct urb *urb)
 		/* These are unsolicited reports from the firmware, hence no
 		   waiting command to wakeup */
 		dev_dbg(&urb->dev->dev, "%s - event received\n", __func__);
-	} else if (data[0] == WHITEHEAT_GET_DTR_RTS) {
+	} else if ((data[0] == WHITEHEAT_GET_DTR_RTS) &&
+		(urb->actual_length - 1 <= sizeof(command_info->result_buffer))) {
 		memcpy(command_info->result_buffer, &data[1],
 						urb->actual_length - 1);
 		command_info->command_finished = WHITEHEAT_CMD_COMPLETE;
diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c
index fca4c752a4ed..d6a3fbd029be 100644
--- a/drivers/usb/serial/zte_ev.c
+++ b/drivers/usb/serial/zte_ev.c
@@ -273,29 +273,16 @@ static void zte_ev_usb_serial_close(struct usb_serial_port *port)
 }
 
 static const struct usb_device_id id_table[] = {
-	/* AC8710, AC8710T */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) },
-	 /* AC8700 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) },
-	/* MG880 */
-	{ USB_DEVICE(0x19d2, 0xfffd) },
-	{ USB_DEVICE(0x19d2, 0xfffc) },
-	{ USB_DEVICE(0x19d2, 0xfffb) },
-	/* AC2726, AC8710_V3 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfff1, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE(0x19d2, 0xffec) },
+	{ USB_DEVICE(0x19d2, 0xffee) },
 	{ USB_DEVICE(0x19d2, 0xfff6) },
 	{ USB_DEVICE(0x19d2, 0xfff7) },
 	{ USB_DEVICE(0x19d2, 0xfff8) },
 	{ USB_DEVICE(0x19d2, 0xfff9) },
-	{ USB_DEVICE(0x19d2, 0xffee) },
-	/* AC2716, MC2716 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) },
-	/* AD3812 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE(0x19d2, 0xffec) },
-	{ USB_DEVICE(0x05C6, 0x3197) },
-	{ USB_DEVICE(0x05C6, 0x6000) },
-	{ USB_DEVICE(0x05C6, 0x9008) },
+	{ USB_DEVICE(0x19d2, 0xfffb) },
+	{ USB_DEVICE(0x19d2, 0xfffc) },
+	/* MG880 */
+	{ USB_DEVICE(0x19d2, 0xfffd) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index 8470e1b114f2..1dd0604d1911 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -18,7 +18,9 @@ config USB_STORAGE
 
 	  This option depends on 'SCSI' support being enabled, but you
 	  probably also need 'SCSI device support: SCSI disk support'
-	  (BLK_DEV_SD) for most USB storage devices.
+	  (BLK_DEV_SD) for most USB storage devices.  Some devices also
+	  will require 'Probe all LUNs on each SCSI device'
+	  (SCSI_MULTI_LUN).
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called usb-storage.
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 92b05d95ec5e..bb7bf198caab 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -78,6 +78,8 @@ static const char* host_info(struct Scsi_Host *host)
 
 static int slave_alloc (struct scsi_device *sdev)
 {
+	struct us_data *us = host_to_us(sdev->host);
+
 	/*
 	 * Set the INQUIRY transfer length to 36.  We don't use any of
 	 * the extra data and many devices choke if asked for more or
@@ -102,6 +104,10 @@ static int slave_alloc (struct scsi_device *sdev)
 	 */
 	blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
 
+	/* Tell the SCSI layer if we know there is more than one LUN */
+	if (us->protocol == USB_PR_BULK && us->max_lun > 0)
+		sdev->sdev_bflags |= BLIST_FORCELUN;
+
 	return 0;
 }
 
@@ -211,8 +217,11 @@ static int slave_configure(struct scsi_device *sdev)
 		/*
 		 * Many devices do not respond properly to READ_CAPACITY_16.
 		 * Tell the SCSI layer to try READ_CAPACITY_10 first.
+		 * However some USB 3.0 drive enclosures return capacity
+		 * modulo 2TB. Those must use READ_CAPACITY_16
 		 */
-		sdev->try_rc_10_first = 1;
+		if (!(us->fflags & US_FL_NEEDS_CAP16))
+			sdev->try_rc_10_first = 1;
 
 		/* assume SPC3 or latter devices support sense size > 18 */
 		if (sdev->scsi_level > SCSI_SPC_2)
diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c
index 4ef2a80728f7..008d805c3d21 100644
--- a/drivers/usb/storage/shuttle_usbat.c
+++ b/drivers/usb/storage/shuttle_usbat.c
@@ -1851,7 +1851,7 @@ static int usbat_probe(struct usb_interface *intf,
 	us->transport_name = "Shuttle USBAT";
 	us->transport = usbat_flash_transport;
 	us->transport_reset = usb_stor_CB_reset;
-	us->max_lun = 1;
+	us->max_lun = 0;
 
 	result = usb_stor_probe2(us);
 	return result;
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 22c7d4360fa2..b1d815eb6d0b 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -1118,6 +1118,31 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us)
 		 */
 		if (result == USB_STOR_XFER_LONG)
 			fake_sense = 1;
+
+		/*
+		 * Sometimes a device will mistakenly skip the data phase
+		 * and go directly to the status phase without sending a
+		 * zero-length packet.  If we get a 13-byte response here,
+		 * check whether it really is a CSW.
+		 */
+		if (result == USB_STOR_XFER_SHORT &&
+				srb->sc_data_direction == DMA_FROM_DEVICE &&
+				transfer_length - scsi_get_resid(srb) ==
+					US_BULK_CS_WRAP_LEN) {
+			struct scatterlist *sg = NULL;
+			unsigned int offset = 0;
+
+			if (usb_stor_access_xfer_buf((unsigned char *) bcs,
+					US_BULK_CS_WRAP_LEN, srb, &sg,
+					&offset, FROM_XFER_BUF) ==
+						US_BULK_CS_WRAP_LEN &&
+					bcs->Signature ==
+						cpu_to_le32(US_BULK_CS_SIGN)) {
+				usb_stor_dbg(us, "Device skipped data phase\n");
+				scsi_set_resid(srb, transfer_length);
+				goto skipped_data_phase;
+			}
+		}
 	}
 
 	/* See flow chart on pg 15 of the Bulk Only Transport spec for
@@ -1153,6 +1178,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us)
 	if (result != USB_STOR_XFER_GOOD)
 		return USB_STOR_TRANSPORT_ERROR;
 
+ skipped_data_phase:
 	/* check bulk status */
 	residue = le32_to_cpu(bcs->Residue);
 	usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n",
diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h
index 65a6a75066a8..82e8ed0324e3 100644
--- a/drivers/usb/storage/unusual_cypress.h
+++ b/drivers/usb/storage/unusual_cypress.h
@@ -31,7 +31,7 @@ UNUSUAL_DEV(  0x04b4, 0x6831, 0x0000, 0x9999,
 		"Cypress ISD-300LP",
 		USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
 
-UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x0219,
+UNUSUAL_DEV( 0x14cd, 0x6116, 0x0160, 0x0160,
 		"Super Top",
 		"USB 2.0  SATA BRIDGE",
 		USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index c015f2c16729..7f625306ea80 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -101,6 +101,12 @@ UNUSUAL_DEV(  0x03f0, 0x4002, 0x0001, 0x0001,
 		"PhotoSmart R707",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY),
 
+UNUSUAL_DEV(  0x03f3, 0x0001, 0x0000, 0x9999,
+		"Adaptec",
+		"USBConnect 2000",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Sebastian Kapfer <sebastian_kapfer@gmx.net>
  * and Olaf Hering <olh@suse.de> (different bcd's, same vendor/product)
  * for USB floppies that need the SINGLE_LUN enforcement.
@@ -234,6 +240,27 @@ UNUSUAL_DEV(  0x0421, 0x0495, 0x0370, 0x0370,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Daniele Forsi <dforsi@gmail.com> */
+UNUSUAL_DEV(  0x0421, 0x04b9, 0x0350, 0x0350,
+		"Nokia",
+		"5300",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 ),
+
+/* Patch submitted by Victor A. Santos <victoraur.santos@gmail.com> */
+UNUSUAL_DEV(  0x0421, 0x05af, 0x0742, 0x0742,
+		"Nokia",
+		"305",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64),
+
+/* Patch submitted by Mikhail Zolotaryov <lebon@lebon.org.ua> */
+UNUSUAL_DEV(  0x0421, 0x06aa, 0x1110, 0x1110,
+		"Nokia",
+		"502",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 ),
+
 #ifdef NO_SDDR09
 UNUSUAL_DEV(  0x0436, 0x0005, 0x0100, 0x0100,
 		"Microtech",
@@ -720,6 +747,12 @@ UNUSUAL_DEV(  0x059b, 0x0001, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_SINGLE_LUN ),
 
+UNUSUAL_DEV(  0x059b, 0x0040, 0x0100, 0x0100,
+		"Iomega",
+		"Jaz USB Adapter",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SINGLE_LUN ),
+
 /* Reported by <Hendryk.Pfeiffer@gmx.de> */
 UNUSUAL_DEV(  0x059f, 0x0643, 0x0000, 0x0000,
 		"LaCie",
@@ -1092,6 +1125,18 @@ UNUSUAL_DEV(  0x0851, 0x1543, 0x0200, 0x0200,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NOT_LOCKABLE),
 
+UNUSUAL_DEV(  0x085a, 0x0026, 0x0100, 0x0133,
+		"Xircom",
+		"PortGear USB-SCSI (Mac USB Dock)",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
+UNUSUAL_DEV(  0x085a, 0x0028, 0x0100, 0x0133,
+		"Xircom",
+		"PortGear USB to SCSI Converter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Submitted by Jan De Luyck <lkml@kcore.org> */
 UNUSUAL_DEV(  0x08bd, 0x1100, 0x0000, 0x0000,
 		"CITIZEN",
@@ -1448,6 +1493,13 @@ UNUSUAL_DEV( 0x0f88, 0x042e, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
+/* Reported by Moritz Moeller-Herrmann <moritz-kernel@moeller-herrmann.de> */
+UNUSUAL_DEV(  0x0fca, 0x8004, 0x0201, 0x0201,
+		"Research In Motion",
+		"BlackBerry Bold 9000",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 ),
+
 /* Reported by Michael Stattmann <michael@stattmann.com> */
 UNUSUAL_DEV(  0x0fce, 0xd008, 0x0000, 0x0000,
 		"Sony Ericsson",
@@ -1917,6 +1969,14 @@ UNUSUAL_DEV(  0x152d, 0x2329, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
 
+/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
+ * and Mac USB Dock USB-SCSI */
+UNUSUAL_DEV(  0x1645, 0x0007, 0x0100, 0x0133,
+		"Entrega Technologies",
+		"USB to SCSI Converter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Robert Schedel <r.schedel@yahoo.de>
  * Note: this is a 'super top' device like the above 14cd/6600 device */
 UNUSUAL_DEV(  0x1652, 0x6600, 0x0201, 0x0201,
@@ -1925,6 +1985,13 @@ UNUSUAL_DEV(  0x1652, 0x6600, 0x0201, 0x0201,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV(  0x174c, 0x55aa, 0x0100, 0x0100,
+		"ASMedia",
+		"AS2105",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NEEDS_CAP16),
+
 /* Reported by Jesse Feddema <jdfeddema@gmail.com> */
 UNUSUAL_DEV(  0x177f, 0x0400, 0x0000, 0x0000,
 		"Yarvik",
@@ -1932,6 +1999,12 @@ UNUSUAL_DEV(  0x177f, 0x0400, 0x0000, 0x0000,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
 
+UNUSUAL_DEV(  0x1822, 0x0001, 0x0000, 0x9999,
+		"Ariston Technologies",
+		"iConnect USB to SCSI adapter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Hans de Goede <hdegoede@redhat.com>
  * These Appotech controllers are found in Picture Frames, they provide a
  * (buggy) emulation of a cdrom drive which contains the windows software
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 6f3fbc48a6c7..22080eb6aff6 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -138,12 +138,12 @@ static bool is_invalid_reserved_pfn(unsigned long pfn)
 	if (pfn_valid(pfn)) {
 		bool reserved;
 		struct page *tail = pfn_to_page(pfn);
-		struct page *head = compound_trans_head(tail);
+		struct page *head = compound_head(tail);
 		reserved = !!(PageReserved(head));
 		if (head != tail) {
 			/*
 			 * "head" is not a dangling pointer
-			 * (compound_trans_head takes care of that)
+			 * (compound_head takes care of that)
 			 * but the hugepage may have been split
 			 * from under us (and we may not hold a
 			 * reference count on the head page so it can
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index d6a518ce4d6d..c7fdabd0e5d3 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -513,9 +513,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;
@@ -540,6 +544,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -595,6 +605,14 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 701420297225..962c7e3c3baa 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1017,7 +1017,7 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs,
 		if (data_direction != DMA_NONE) {
 			ret = vhost_scsi_map_iov_to_sgl(tv_cmd,
 					&vq->iov[data_first], data_num,
-					data_direction == DMA_TO_DEVICE);
+					data_direction == DMA_FROM_DEVICE);
 			if (unlikely(ret)) {
 				vq_err(vq, "Failed to map iov to sgl\n");
 				goto err_free;
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 2e937bdace6f..29a5121ce7fd 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -39,6 +39,11 @@ config VIDEOMODE_HELPERS
 config HDMI
 	bool
 
+config VEXPRESS_DVI_CONTROL
+	bool "Versatile Express DVI control"
+	depends on FB && VEXPRESS_CONFIG
+	default y
+
 menuconfig FB
 	tristate "Support for frame buffer devices"
 	---help---
@@ -312,7 +317,8 @@ config FB_PM2_FIFO_DISCONNECT
 
 config FB_ARMCLCD
 	tristate "ARM PrimeCell PL110 support"
-	depends on FB && ARM && ARM_AMBA
+	depends on ARM || ARM64 || COMPILE_TEST
+	depends on FB && ARM_AMBA
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
@@ -326,6 +332,21 @@ config FB_ARMCLCD
 	  here and read <file:Documentation/kbuild/modules.txt>.  The module
 	  will be called amba-clcd.
 
+config FB_ARMHDLCD
+	tristate "ARM High Definition LCD support"
+	depends on FB && ARM
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	help
+	  This framebuffer device driver is for the ARM High Definition
+	  Colour LCD controller.
+
+	  If you want to compile this as a module (=code which can be
+	  inserted into and removed from the running kernel), say M
+	  here and read <file:Documentation/kbuild/modules.txt>.  The module
+	  will be called arm-hdlcd.
+
 config FB_ACORN
 	bool "Acorn VIDC support"
 	depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index e8bae8dd4804..33869eea4981 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -99,6 +99,7 @@ obj-$(CONFIG_FB_ATMEL)		  += atmel_lcdfb.o
 obj-$(CONFIG_FB_PVR2)             += pvr2fb.o
 obj-$(CONFIG_FB_VOODOO1)          += sstfb.o
 obj-$(CONFIG_FB_ARMCLCD)	  += amba-clcd.o
+obj-$(CONFIG_FB_ARMHDLCD)	  += arm-hdlcd.o
 obj-$(CONFIG_FB_GOLDFISH)         += goldfishfb.o
 obj-$(CONFIG_FB_68328)            += 68328fb.o
 obj-$(CONFIG_FB_GBE)              += gbefb.o
@@ -177,3 +178,6 @@ obj-$(CONFIG_VIDEOMODE_HELPERS) += display_timing.o videomode.o
 ifeq ($(CONFIG_OF),y)
 obj-$(CONFIG_VIDEOMODE_HELPERS) += of_display_timing.o of_videomode.o
 endif
+
+# platform specific output drivers
+obj-$(CONFIG_VEXPRESS_DVI_CONTROL) += vexpress-dvi.o
diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c
index 0a2cce7285be..dba653f6badc 100644
--- a/drivers/video/amba-clcd.c
+++ b/drivers/video/amba-clcd.c
@@ -16,7 +16,10 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
+#include <linux/of.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -30,8 +33,20 @@
 
 #define to_clcd(info)	container_of(info, struct clcd_fb, fb)
 
+#ifdef CONFIG_ARM
+#define clcdfb_dma_alloc	dma_alloc_writecombine
+#define clcdfb_dma_free		dma_free_writecombine
+#define clcdfb_dma_mmap		dma_mmap_writecombine
+#else
+#define clcdfb_dma_alloc	dma_alloc_coherent
+#define clcdfb_dma_free		dma_free_coherent
+#define clcdfb_dma_mmap		dma_mmap_coherent
+#endif
+
 /* This is limited to 16 characters when displayed by X startup */
 static const char *clcd_name = "CLCD FB";
+static char *def_mode;
+module_param_named(mode, def_mode, charp, 0);
 
 /*
  * Unfortunately, the enable/disable functions may be called either from
@@ -392,6 +407,44 @@ static int clcdfb_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
+int clcdfb_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	return clcdfb_dma_mmap(&fb->dev->dev, vma,
+			       fb->fb.screen_base,
+			       fb->fb.fix.smem_start,
+			       fb->fb.fix.smem_len);
+}
+
+int clcdfb_mmap_io(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	unsigned long user_count, count, pfn, off;
+
+	user_count	= (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	count		= PAGE_ALIGN(fb->fb.fix.smem_len) >> PAGE_SHIFT;
+	pfn		= fb->fb.fix.smem_start >> PAGE_SHIFT;
+	off		= vma->vm_pgoff;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (off < count && user_count <= (count - off))
+		return remap_pfn_range(vma, vma->vm_start, pfn + off,
+				       user_count << PAGE_SHIFT,
+				       vma->vm_page_prot);
+
+	return -ENXIO;
+}
+
+void clcdfb_remove_dma(struct clcd_fb *fb)
+{
+	clcdfb_dma_free(&fb->dev->dev, fb->fb.fix.smem_len,
+			fb->fb.screen_base, fb->fb.fix.smem_start);
+}
+
+void clcdfb_remove_io(struct clcd_fb *fb)
+{
+	iounmap(fb->fb.screen_base);
+}
+
 static int clcdfb_mmap(struct fb_info *info,
 		       struct vm_area_struct *vma)
 {
@@ -542,14 +595,247 @@ static int clcdfb_register(struct clcd_fb *fb)
 	return ret;
 }
 
+struct string_lookup {
+	const char *string;
+	const u32	val;
+};
+
+static struct string_lookup vmode_lookups[] = {
+	{ "FB_VMODE_NONINTERLACED", FB_VMODE_NONINTERLACED},
+	{ "FB_VMODE_INTERLACED",    FB_VMODE_INTERLACED},
+	{ "FB_VMODE_DOUBLE",        FB_VMODE_DOUBLE},
+	{ "FB_VMODE_ODD_FLD_FIRST", FB_VMODE_ODD_FLD_FIRST},
+	{ NULL, 0 },
+};
+
+static struct string_lookup tim2_lookups[] = {
+	{ "TIM2_CLKSEL", TIM2_CLKSEL},
+	{ "TIM2_IVS",    TIM2_IVS},
+	{ "TIM2_IHS",    TIM2_IHS},
+	{ "TIM2_IPC",    TIM2_IPC},
+	{ "TIM2_IOE",    TIM2_IOE},
+	{ "TIM2_BCD",    TIM2_BCD},
+	{ NULL, 0},
+};
+static struct string_lookup cntl_lookups[] = {
+	{"CNTL_LCDEN",        CNTL_LCDEN},
+	{"CNTL_LCDBPP1",      CNTL_LCDBPP1},
+	{"CNTL_LCDBPP2",      CNTL_LCDBPP2},
+	{"CNTL_LCDBPP4",      CNTL_LCDBPP4},
+	{"CNTL_LCDBPP8",      CNTL_LCDBPP8},
+	{"CNTL_LCDBPP16",     CNTL_LCDBPP16},
+	{"CNTL_LCDBPP16_565", CNTL_LCDBPP16_565},
+	{"CNTL_LCDBPP16_444", CNTL_LCDBPP16_444},
+	{"CNTL_LCDBPP24",     CNTL_LCDBPP24},
+	{"CNTL_LCDBW",        CNTL_LCDBW},
+	{"CNTL_LCDTFT",       CNTL_LCDTFT},
+	{"CNTL_LCDMONO8",     CNTL_LCDMONO8},
+	{"CNTL_LCDDUAL",      CNTL_LCDDUAL},
+	{"CNTL_BGR",          CNTL_BGR},
+	{"CNTL_BEBO",         CNTL_BEBO},
+	{"CNTL_BEPO",         CNTL_BEPO},
+	{"CNTL_LCDPWR",       CNTL_LCDPWR},
+	{"CNTL_LCDVCOMP(1)",  CNTL_LCDVCOMP(1)},
+	{"CNTL_LCDVCOMP(2)",  CNTL_LCDVCOMP(2)},
+	{"CNTL_LCDVCOMP(3)",  CNTL_LCDVCOMP(3)},
+	{"CNTL_LCDVCOMP(4)",  CNTL_LCDVCOMP(4)},
+	{"CNTL_LCDVCOMP(5)",  CNTL_LCDVCOMP(5)},
+	{"CNTL_LCDVCOMP(6)",  CNTL_LCDVCOMP(6)},
+	{"CNTL_LCDVCOMP(7)",  CNTL_LCDVCOMP(7)},
+	{"CNTL_LDMAFIFOTIME", CNTL_LDMAFIFOTIME},
+	{"CNTL_WATERMARK",    CNTL_WATERMARK},
+	{ NULL, 0},
+};
+static struct string_lookup caps_lookups[] = {
+	{"CLCD_CAP_RGB444",  CLCD_CAP_RGB444},
+	{"CLCD_CAP_RGB5551", CLCD_CAP_RGB5551},
+	{"CLCD_CAP_RGB565",  CLCD_CAP_RGB565},
+	{"CLCD_CAP_RGB888",  CLCD_CAP_RGB888},
+	{"CLCD_CAP_BGR444",  CLCD_CAP_BGR444},
+	{"CLCD_CAP_BGR5551", CLCD_CAP_BGR5551},
+	{"CLCD_CAP_BGR565",  CLCD_CAP_BGR565},
+	{"CLCD_CAP_BGR888",  CLCD_CAP_BGR888},
+	{"CLCD_CAP_444",     CLCD_CAP_444},
+	{"CLCD_CAP_5551",    CLCD_CAP_5551},
+	{"CLCD_CAP_565",     CLCD_CAP_565},
+	{"CLCD_CAP_888",     CLCD_CAP_888},
+	{"CLCD_CAP_RGB",     CLCD_CAP_RGB},
+	{"CLCD_CAP_BGR",     CLCD_CAP_BGR},
+	{"CLCD_CAP_ALL",     CLCD_CAP_ALL},
+	{ NULL, 0},
+};
+
+u32 parse_setting(struct string_lookup *lookup, const char *name)
+{
+	int i = 0;
+	while (lookup[i].string != NULL) {
+		if (strcmp(lookup[i].string, name) == 0)
+			return lookup[i].val;
+		++i;
+	}
+	return -EINVAL;
+}
+
+u32 get_string_lookup(struct device_node *node, const char *name,
+		      struct string_lookup *lookup)
+{
+	const char *string;
+	int count, i, ret = 0;
+
+	count = of_property_count_strings(node, name);
+	if (count >= 0)
+		for (i = 0; i < count; i++)
+			if (of_property_read_string_index(node, name, i,
+					&string) == 0)
+				ret |= parse_setting(lookup, string);
+	return ret;
+}
+
+int get_val(struct device_node *node, const char *string)
+{
+	u32 ret = 0;
+
+	if (of_property_read_u32(node, string, &ret))
+		ret = -1;
+	return ret;
+}
+
+struct clcd_panel *getPanel(struct device_node *node)
+{
+	static struct clcd_panel panel;
+
+	panel.mode.refresh      = get_val(node, "refresh");
+	panel.mode.xres         = get_val(node, "xres");
+	panel.mode.yres         = get_val(node, "yres");
+	panel.mode.pixclock     = get_val(node, "pixclock");
+	panel.mode.left_margin  = get_val(node, "left_margin");
+	panel.mode.right_margin = get_val(node, "right_margin");
+	panel.mode.upper_margin = get_val(node, "upper_margin");
+	panel.mode.lower_margin = get_val(node, "lower_margin");
+	panel.mode.hsync_len    = get_val(node, "hsync_len");
+	panel.mode.vsync_len    = get_val(node, "vsync_len");
+	panel.mode.sync         = get_val(node, "sync");
+	panel.bpp               = get_val(node, "bpp");
+	panel.width             = (signed short) get_val(node, "width");
+	panel.height            = (signed short) get_val(node, "height");
+
+	panel.mode.vmode = get_string_lookup(node, "vmode", vmode_lookups);
+	panel.tim2       = get_string_lookup(node, "tim2",  tim2_lookups);
+	panel.cntl       = get_string_lookup(node, "cntl",  cntl_lookups);
+	panel.caps       = get_string_lookup(node, "caps",  caps_lookups);
+
+	return &panel;
+}
+
+struct clcd_panel *clcdfb_get_panel(const char *name)
+{
+	struct device_node *node = NULL;
+	const char *mode;
+	struct clcd_panel *panel = NULL;
+
+	do {
+		node = of_find_compatible_node(node, NULL, "panel");
+		if (node)
+			if (of_property_read_string(node, "mode", &mode) == 0)
+				if (strcmp(mode, name) == 0) {
+					panel = getPanel(node);
+					panel->mode.name = name;
+				}
+	} while (node != NULL);
+
+	return panel;
+}
+
+#ifdef CONFIG_OF
+static int clcdfb_dt_init(struct clcd_fb *fb)
+{
+	int err = 0;
+	struct device_node *node;
+	const char *mode;
+	dma_addr_t dma;
+	u32 use_dma;
+	const __be32 *prop;
+	int len, na, ns;
+	phys_addr_t fb_base, fb_size;
+
+	node = fb->dev->dev.of_node;
+	if (!node)
+		return -ENODEV;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	if (def_mode && strlen(def_mode) > 0) {
+		fb->panel = clcdfb_get_panel(def_mode);
+		if (!fb->panel)
+			printk(KERN_ERR "CLCD: invalid mode specified on the command line (%s)\n", def_mode);
+	}
+
+	if (!fb->panel) {
+		if (WARN_ON(of_property_read_string(node, "mode", &mode)))
+			return -ENODEV;
+		fb->panel = clcdfb_get_panel(mode);
+	}
+
+	if (!fb->panel)
+		return -EINVAL;
+	fb->fb.fix.smem_len = fb->panel->mode.xres * fb->panel->mode.yres * 2;
+
+	fb->board->name		= "Device Tree CLCD PL111";
+	fb->board->caps		= CLCD_CAP_5551 | CLCD_CAP_565;
+	fb->board->check	= clcdfb_check;
+	fb->board->decode	= clcdfb_decode;
+
+	if (of_property_read_u32(node, "use_dma", &use_dma))
+		use_dma = 0;
+
+	if (use_dma) {
+		fb->fb.screen_base = clcdfb_dma_alloc(&fb->dev->dev,
+						      fb->fb.fix.smem_len,
+						      &dma, GFP_KERNEL);
+		if (!fb->fb.screen_base) {
+			pr_err("CLCD: unable to map framebuffer\n");
+			return -ENOMEM;
+		}
+
+		fb->fb.fix.smem_start	= dma;
+		fb->board->mmap		= clcdfb_mmap_dma;
+		fb->board->remove	= clcdfb_remove_dma;
+	} else {
+		prop = of_get_property(node, "framebuffer", &len);
+		if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+			return -EINVAL;
+
+		fb_base = of_read_number(prop, na);
+		fb_size = of_read_number(prop + na, ns);
+
+		fb->fb.fix.smem_start	= fb_base;
+		fb->fb.screen_base	= ioremap_wc(fb_base, fb_size);
+		fb->board->mmap		= clcdfb_mmap_io;
+		fb->board->remove	= clcdfb_remove_io;
+	}
+
+	return err;
+}
+#endif /* CONFIG_OF */
+
 static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
 {
 	struct clcd_board *board = dev->dev.platform_data;
 	struct clcd_fb *fb;
 	int ret;
 
-	if (!board)
-		return -EINVAL;
+	if (!board) {
+#ifdef CONFIG_OF
+		if (dev->dev.of_node) {
+			board = kzalloc(sizeof(struct clcd_board), GFP_KERNEL);
+			if (!board)
+				return -ENOMEM;
+			board->setup   = clcdfb_dt_init;
+		} else
+#endif
+			return -EINVAL;
+	}
 
 	ret = amba_request_regions(dev, NULL);
 	if (ret) {
diff --git a/drivers/video/arm-hdlcd.c b/drivers/video/arm-hdlcd.c
new file mode 100644
index 000000000000..cfd631e3dc52
--- /dev/null
+++ b/drivers/video/arm-hdlcd.c
@@ -0,0 +1,844 @@
+/*
+ * drivers/video/arm-hdlcd.c
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/fb.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/memblock.h>
+#include <linux/arm-hdlcd.h>
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
+
+#include "edid.h"
+
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+int get_edid(u8 *msgbuf);
+#else
+#endif
+
+#define to_hdlcd_device(info)	container_of(info, struct hdlcd_device, fb)
+
+static struct of_device_id  hdlcd_of_matches[] = {
+	{ .compatible	= "arm,hdlcd" },
+	{},
+};
+
+/* Framebuffer size.  */
+static unsigned long framebuffer_size;
+
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+static unsigned long buffer_underrun_events;
+static DEFINE_SPINLOCK(hdlcd_underrun_lock);
+
+static void hdlcd_underrun_set(unsigned long val)
+{
+	spin_lock(&hdlcd_underrun_lock);
+	buffer_underrun_events = val;
+	spin_unlock(&hdlcd_underrun_lock);
+}
+
+static unsigned long hdlcd_underrun_get(void)
+{
+	unsigned long val;
+	spin_lock(&hdlcd_underrun_lock);
+	val = buffer_underrun_events;
+	spin_unlock(&hdlcd_underrun_lock);
+	return val;
+}
+
+#ifdef CONFIG_PROC_FS
+static int hdlcd_underrun_show(struct seq_file *m, void *v)
+{
+	unsigned char underrun_string[32];
+	snprintf(underrun_string, 32, "%lu\n", hdlcd_underrun_get());
+	seq_puts(m, underrun_string);
+	return 0;
+}
+
+static int proc_hdlcd_underrun_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hdlcd_underrun_show, NULL);
+}
+
+static const struct file_operations proc_hdlcd_underrun_operations = {
+	.open		= proc_hdlcd_underrun_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hdlcd_underrun_init(void)
+{
+	hdlcd_underrun_set(0);
+	proc_create("hdlcd_underrun", 0, NULL, &proc_hdlcd_underrun_operations);
+	return 0;
+}
+static void hdlcd_underrun_close(void)
+{
+	remove_proc_entry("hdlcd_underrun", NULL);
+}
+#else
+static int hdlcd_underrun_init(void) { return 0; }
+static void hdlcd_underrun_close(void) { }
+#endif
+#endif
+
+static char *fb_mode = "1680x1050-32@60\0\0\0\0\0";
+
+static struct fb_var_screeninfo cached_var_screeninfo;
+
+static struct fb_videomode hdlcd_default_mode = {
+	.refresh	= 60,
+	.xres		= 1680,
+	.yres		= 1050,
+	.pixclock	= 8403,
+	.left_margin	= 80,
+	.right_margin	= 48,
+	.upper_margin	= 21,
+	.lower_margin	= 3,
+	.hsync_len	= 32,
+	.vsync_len	= 6,
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	.vmode		= FB_VMODE_NONINTERLACED
+};
+
+static inline void hdlcd_enable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output enabled\n");
+	writel(1, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static inline void hdlcd_disable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output disabled\n");
+	writel(0, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static int hdlcd_set_bitfields(struct hdlcd_device *hdlcd,
+				struct fb_var_screeninfo *var)
+{
+	int ret = 0;
+
+	memset(&var->transp, 0, sizeof(var->transp));
+	var->red.msb_right = 0;
+	var->green.msb_right = 0;
+	var->blue.msb_right = 0;
+	var->blue.offset = 0;
+
+	switch (var->bits_per_pixel) {
+	case 8:
+		/* pseudocolor */
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	case 16:
+		/* 565 format */
+		var->red.length = 5;
+		var->green.length = 6;
+		var->blue.length = 5;
+		break;
+	case 32:
+		var->transp.length = 8;
+	case 24:
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	if (!ret) {
+		if(var->bits_per_pixel != 32)
+		{
+			var->green.offset = var->blue.length;
+			var->red.offset = var->green.offset + var->green.length;
+		}
+		else
+		{
+			/* Previously, the byte ordering for 32-bit color was
+			 * (msb)<alpha><red><green><blue>(lsb)
+			 * but this does not match what android expects and
+			 * the colors are odd. Instead, use
+			 * <alpha><blue><green><red>
+			 * Since we tell fb what we are doing, console
+			 * , X and directfb access should work fine.
+			 */
+			var->green.offset = var->red.length;
+			var->blue.offset = var->green.offset + var->green.length;
+			var->transp.offset = var->blue.offset + var->blue.length;
+		}
+	}
+
+	return ret;
+}
+
+static int hdlcd_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = var->bits_per_pixel / 8;
+
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	var->yres_virtual = var->yres;
+#else
+	var->yres_virtual = 2 * var->yres;
+#endif
+
+	if ((var->xres_virtual * bytes_per_pixel * var->yres_virtual) > hdlcd->fb.fix.smem_len)
+		return -ENOMEM;
+
+	if (var->xres > HDLCD_MAX_XRES || var->yres > HDLCD_MAX_YRES)
+		return -EINVAL;
+
+	/* make sure the bitfields are set appropriately */
+	return hdlcd_set_bitfields(hdlcd, var);
+}
+
+/* prototype */
+static int hdlcd_pan_display(struct fb_var_screeninfo *var,
+	struct fb_info *info);
+
+#define WRITE_HDLCD_REG(reg, value)	writel((value), hdlcd->base + (reg))
+#define READ_HDLCD_REG(reg)		readl(hdlcd->base + (reg))
+
+static int hdlcd_set_par(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = hdlcd->fb.var.bits_per_pixel / 8;
+	int polarities;
+	int old_yoffset;
+
+	/* check for shortcuts */
+	old_yoffset = cached_var_screeninfo.yoffset;
+	cached_var_screeninfo.yoffset = info->var.yoffset;
+	if (!memcmp(&info->var, &cached_var_screeninfo,
+				sizeof(struct fb_var_screeninfo))) {
+		if(old_yoffset != info->var.yoffset) {
+			/* we only changed yoffset, and we already
+			 * already recorded it a couple lines up
+			 */
+			hdlcd_pan_display(&info->var, info);
+		}
+		/* or no change */
+		return 0;
+	}
+
+	hdlcd->fb.fix.line_length = hdlcd->fb.var.xres * bytes_per_pixel;
+
+	if (hdlcd->fb.var.bits_per_pixel >= 16)
+		hdlcd->fb.fix.visual = FB_VISUAL_TRUECOLOR;
+	else
+		hdlcd->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
+
+	memcpy(&cached_var_screeninfo, &info->var, sizeof(struct fb_var_screeninfo));
+
+	polarities = HDLCD_POLARITY_DATAEN |
+#ifndef CONFIG_ARCH_TUSCAN
+		HDLCD_POLARITY_PIXELCLK |
+#endif
+		HDLCD_POLARITY_DATA;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_HOR_HIGH_ACT) ? HDLCD_POLARITY_HSYNC : 0;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_VERT_HIGH_ACT) ? HDLCD_POLARITY_VSYNC : 0;
+
+	hdlcd_disable(hdlcd);
+
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_LENGTH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_PITCH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_COUNT, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_SYNC, hdlcd->fb.var.vsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_BACK_PORCH, hdlcd->fb.var.upper_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_DATA, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_FRONT_PORCH, hdlcd->fb.var.lower_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_SYNC, hdlcd->fb.var.hsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_BACK_PORCH, hdlcd->fb.var.left_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_DATA, hdlcd->fb.var.xres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_FRONT_PORCH, hdlcd->fb.var.right_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_POLARITIES, polarities);
+	WRITE_HDLCD_REG(HDLCD_REG_PIXEL_FORMAT, (bytes_per_pixel - 1) << 3);
+#ifdef HDLCD_RED_DEFAULT_COLOUR
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, (0x00ff0000 | (hdlcd->fb.var.red.length & 0xf) << 8) \
+													  | hdlcd->fb.var.red.offset);
+#else
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, ((hdlcd->fb.var.red.length & 0xf) << 8) | hdlcd->fb.var.red.offset);
+#endif
+	WRITE_HDLCD_REG(HDLCD_REG_GREEN_SELECT, ((hdlcd->fb.var.green.length & 0xf) << 8) | hdlcd->fb.var.green.offset);
+	WRITE_HDLCD_REG(HDLCD_REG_BLUE_SELECT, ((hdlcd->fb.var.blue.length & 0xf) << 8) | hdlcd->fb.var.blue.offset);
+
+	clk_set_rate(hdlcd->clk, (1000000000 / hdlcd->fb.var.pixclock) * 1000);
+	clk_enable(hdlcd->clk);
+
+	hdlcd_enable(hdlcd);
+
+	return 0;
+}
+
+static int hdlcd_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
+		unsigned int blue, unsigned int transp, struct fb_info *info)
+{
+	if (regno < 16) {
+		u32 *pal = info->pseudo_palette;
+
+		pal[regno] = ((red >> 8) << info->var.red.offset) |
+			((green >> 8) << info->var.green.offset) |
+			((blue >> 8) << info->var.blue.offset);
+	}
+
+	return 0;
+}
+
+static irqreturn_t hdlcd_irq(int irq, void *data)
+{
+	struct hdlcd_device *hdlcd = data;
+	unsigned long irq_mask, irq_status;
+
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	irq_status = READ_HDLCD_REG(HDLCD_REG_INT_STATUS);
+
+	/* acknowledge interrupt(s) */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_CLEAR, irq_status);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	if (irq_status & HDLCD_INTERRUPT_UNDERRUN) {
+		/* increment the count */
+		hdlcd_underrun_set(hdlcd_underrun_get() + 1);
+	}
+#endif
+	if (irq_status & HDLCD_INTERRUPT_VSYNC) {
+		/* disable future VSYNC interrupts */
+		WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask & ~HDLCD_INTERRUPT_VSYNC);
+
+		complete(&hdlcd->vsync_completion);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hdlcd_wait_for_vsync(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long irq_mask;
+	int err;
+
+	/* enable VSYNC interrupt */
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask | HDLCD_INTERRUPT_VSYNC);
+
+	err = wait_for_completion_interruptible_timeout(&hdlcd->vsync_completion,
+							msecs_to_jiffies(100));
+
+	if (!err)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int hdlcd_blank(int blank_mode, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	switch (blank_mode) {
+	case FB_BLANK_POWERDOWN:
+		clk_disable(hdlcd->clk);
+	case FB_BLANK_NORMAL:
+		hdlcd_disable(hdlcd);
+		break;
+	case FB_BLANK_UNBLANK:
+		clk_enable(hdlcd->clk);
+		hdlcd_enable(hdlcd);
+		break;
+	case FB_BLANK_VSYNC_SUSPEND:
+	case FB_BLANK_HSYNC_SUSPEND:
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static void hdlcd_mmap_open(struct vm_area_struct *vma)
+{
+}
+
+static void hdlcd_mmap_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct hdlcd_mmap_ops = {
+	.open	= hdlcd_mmap_open,
+	.close	= hdlcd_mmap_close,
+};
+
+static int hdlcd_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long off;
+	unsigned long start;
+	unsigned long len = hdlcd->fb.fix.smem_len;
+
+	if (vma->vm_end - vma->vm_start == 0)
+		return 0;
+	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
+		return -EINVAL;
+
+	off = vma->vm_pgoff << PAGE_SHIFT;
+	if ((off >= len) || (vma->vm_end - vma->vm_start + off) > len)
+		return -EINVAL;
+
+	start = hdlcd->fb.fix.smem_start;
+	off += start;
+
+	vma->vm_pgoff = off >> PAGE_SHIFT;
+	vma->vm_flags |= VM_IO;
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	vma->vm_ops = &hdlcd_mmap_ops;
+	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
+				vma->vm_end - vma->vm_start,
+				vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+static int hdlcd_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	hdlcd->fb.var.yoffset = var->yoffset;
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start +
+			(var->yoffset * hdlcd->fb.fix.line_length));
+
+	hdlcd_wait_for_vsync(info);
+
+	return 0;
+}
+
+static int hdlcd_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
+{
+	int err;
+
+	switch (cmd) {
+	case FBIO_WAITFORVSYNC:
+		err = hdlcd_wait_for_vsync(info);
+		break;
+	default:
+		err = -ENOIOCTLCMD;
+		break;
+	}
+
+	return err;
+}
+
+static struct fb_ops hdlcd_ops = {
+	.owner			= THIS_MODULE,
+	.fb_check_var		= hdlcd_check_var,
+	.fb_set_par		= hdlcd_set_par,
+	.fb_setcolreg		= hdlcd_setcolreg,
+	.fb_blank		= hdlcd_blank,
+	.fb_fillrect		= cfb_fillrect,
+	.fb_copyarea		= cfb_copyarea,
+	.fb_imageblit		= cfb_imageblit,
+	.fb_mmap		= hdlcd_mmap,
+	.fb_pan_display		= hdlcd_pan_display,
+	.fb_ioctl		= hdlcd_ioctl,
+	.fb_compat_ioctl	= hdlcd_ioctl
+};
+
+static int hdlcd_setup(struct hdlcd_device *hdlcd)
+{
+	u32 version;
+	int err = -EFAULT;
+
+	hdlcd->fb.device = hdlcd->dev;
+
+	hdlcd->clk = clk_get(hdlcd->dev, NULL);
+	if (IS_ERR(hdlcd->clk)) {
+		dev_err(hdlcd->dev, "HDLCD: unable to find clock data\n");
+		return PTR_ERR(hdlcd->clk);
+	}
+
+	err = clk_prepare(hdlcd->clk);
+	if (err)
+		goto clk_prepare_err;
+
+	hdlcd->base = ioremap_nocache(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+	if (!hdlcd->base) {
+		dev_err(hdlcd->dev, "HDLCD: unable to map registers\n");
+		goto remap_err;
+	}
+
+	hdlcd->fb.pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL);
+	if (!hdlcd->fb.pseudo_palette) {
+		dev_err(hdlcd->dev, "HDLCD: unable to allocate pseudo_palette memory\n");
+		err = -ENOMEM;
+		goto kmalloc_err;
+	}
+
+	version = readl(hdlcd->base + HDLCD_REG_VERSION);
+	if ((version & HDLCD_PRODUCT_MASK) != HDLCD_PRODUCT_ID) {
+		dev_err(hdlcd->dev, "HDLCD: unknown product id: 0x%x\n", version);
+		err = -EINVAL;
+		goto kmalloc_err;
+	}
+	dev_info(hdlcd->dev, "HDLCD: found ARM HDLCD version r%dp%d\n",
+		(version & HDLCD_VERSION_MAJOR_MASK) >> 8,
+		version & HDLCD_VERSION_MINOR_MASK);
+
+	strcpy(hdlcd->fb.fix.id, "hdlcd");
+	hdlcd->fb.fbops			= &hdlcd_ops;
+	hdlcd->fb.flags			= FBINFO_FLAG_DEFAULT/* | FBINFO_VIRTFB*/;
+
+	hdlcd->fb.fix.type		= FB_TYPE_PACKED_PIXELS;
+	hdlcd->fb.fix.type_aux		= 0;
+	hdlcd->fb.fix.xpanstep		= 0;
+	hdlcd->fb.fix.ypanstep		= 1;
+	hdlcd->fb.fix.ywrapstep		= 0;
+	hdlcd->fb.fix.accel		= FB_ACCEL_NONE;
+
+	hdlcd->fb.var.nonstd		= 0;
+	hdlcd->fb.var.activate		= FB_ACTIVATE_NOW;
+	hdlcd->fb.var.height		= -1;
+	hdlcd->fb.var.width		= -1;
+	hdlcd->fb.var.accel_flags	= 0;
+
+	init_completion(&hdlcd->vsync_completion);
+
+	if (hdlcd->edid) {
+		/* build modedb from EDID */
+		fb_edid_to_monspecs(hdlcd->edid, &hdlcd->fb.monspecs);
+		fb_videomode_to_modelist(hdlcd->fb.monspecs.modedb,
+					hdlcd->fb.monspecs.modedb_len,
+					&hdlcd->fb.modelist);
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode,
+			hdlcd->fb.monspecs.modedb,
+			hdlcd->fb.monspecs.modedb_len,
+			&hdlcd_default_mode, 32);
+	} else {
+		hdlcd->fb.monspecs.hfmin	= 0;
+		hdlcd->fb.monspecs.hfmax	= 100000;
+		hdlcd->fb.monspecs.vfmin	= 0;
+		hdlcd->fb.monspecs.vfmax	= 400;
+		hdlcd->fb.monspecs.dclkmin	= 1000000;
+		hdlcd->fb.monspecs.dclkmax	= 100000000;
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode, NULL, 0, &hdlcd_default_mode, 32);
+	}
+
+	dev_info(hdlcd->dev, "using %dx%d-%d@%d mode\n", hdlcd->fb.var.xres,
+		hdlcd->fb.var.yres, hdlcd->fb.var.bits_per_pixel,
+		hdlcd->fb.mode ? hdlcd->fb.mode->refresh : 60);
+	hdlcd->fb.var.xres_virtual	= hdlcd->fb.var.xres;
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres;
+#else
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres * 2;
+#endif
+
+	/* initialise and set the palette */
+	if (fb_alloc_cmap(&hdlcd->fb.cmap, NR_PALETTE, 0)) {
+		dev_err(hdlcd->dev, "failed to allocate cmap memory\n");
+		err = -ENOMEM;
+		goto setup_err;
+	}
+	fb_set_cmap(&hdlcd->fb.cmap, &hdlcd->fb);
+
+	/* Allow max number of outstanding requests with the largest beat burst */
+	WRITE_HDLCD_REG(HDLCD_REG_BUS_OPTIONS, HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
+	/* Set the framebuffer base to start of allocated memory */
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	/* turn on underrun interrupt for counting */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, HDLCD_INTERRUPT_UNDERRUN);
+#else
+	/* Ensure interrupts are disabled */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, 0);
+#endif	
+	fb_set_var(&hdlcd->fb, &hdlcd->fb.var);
+
+	if (!register_framebuffer(&hdlcd->fb)) {
+		return 0;
+	}
+
+	dev_err(hdlcd->dev, "HDLCD: cannot register framebuffer\n");
+
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+setup_err:
+	iounmap(hdlcd->base);
+kmalloc_err:
+	kfree(hdlcd->fb.pseudo_palette);
+remap_err:
+	clk_unprepare(hdlcd->clk);
+clk_prepare_err:
+	clk_put(hdlcd->clk);
+	return err;
+}
+
+static inline unsigned char atohex(u8 data)
+{
+	if (!isxdigit(data))
+		return 0;
+	/* truncate the upper nibble and add 9 to non-digit values */
+	return (data > 0x39) ? ((data & 0xf) + 9) : (data & 0xf);
+}
+
+/* EDID data is passed from devicetree in a literal string that can contain spaces and
+   the hexadecimal dump of the data */
+static int parse_edid_data(struct hdlcd_device *hdlcd, const u8 *edid_data, int data_len)
+{
+	int i, j;
+
+	if (!edid_data)
+		return -EINVAL;
+
+	hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+	if (!hdlcd->edid)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < data_len; i++) {
+		if (isspace(edid_data[i]))
+			continue;
+		hdlcd->edid[j++] = atohex(edid_data[i]);
+		if (j >= EDID_LENGTH)
+			break;
+	}
+
+	if (j < EDID_LENGTH) {
+		kfree(hdlcd->edid);
+		hdlcd->edid = NULL;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hdlcd_probe(struct platform_device *pdev)
+{
+	int err = 0, i;
+	struct hdlcd_device *hdlcd;
+	struct resource *mem;
+#ifdef CONFIG_OF
+	struct device_node *of_node;
+#endif
+
+	memset(&cached_var_screeninfo, 0, sizeof(struct fb_var_screeninfo));
+
+	dev_dbg(&pdev->dev, "HDLCD: probing\n");
+
+	hdlcd = kzalloc(sizeof(*hdlcd), GFP_KERNEL);
+	if (!hdlcd)
+		return -ENOMEM;
+
+#ifdef CONFIG_OF
+	of_node = pdev->dev.of_node;
+	if (of_node) {
+		int len;
+		const u8 *edid;
+		const __be32 *prop = of_get_property(of_node, "mode", &len);
+		if (prop)
+			strncpy(fb_mode, (char *)prop, len);
+		prop = of_get_property(of_node, "framebuffer", &len);
+		if (prop) {
+			hdlcd->fb.fix.smem_start = of_read_ulong(prop,
+					of_n_addr_cells(of_node));
+			prop += of_n_addr_cells(of_node);
+			framebuffer_size = of_read_ulong(prop,
+					of_n_size_cells(of_node));
+			if (framebuffer_size > HDLCD_MAX_FRAMEBUFFER_SIZE)
+				framebuffer_size = HDLCD_MAX_FRAMEBUFFER_SIZE;
+			dev_dbg(&pdev->dev, "HDLCD: phys_addr = 0x%lx, size = 0x%lx\n",
+				hdlcd->fb.fix.smem_start, framebuffer_size);
+		}
+		edid = of_get_property(of_node, "edid", &len);
+		if (edid) {
+			err = parse_edid_data(hdlcd, edid, len);
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+		} else {
+			/* ask the firmware to fetch the EDID */
+			dev_dbg(&pdev->dev, "HDLCD: Requesting EDID data\n");
+			hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+			if (!hdlcd->edid)
+				return -ENOMEM;
+			err = get_edid(hdlcd->edid);
+#endif /* CONFIG_SERIAL_AMBA_PCU_UART */
+		}
+		if (err)
+			dev_info(&pdev->dev, "HDLCD: Failed to parse EDID data\n");
+	}
+#endif /* CONFIG_OF */
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		dev_err(&pdev->dev, "HDLCD: cannot get platform resources\n");
+		err = -EINVAL;
+		goto resource_err;
+	}
+
+	i = platform_get_irq(pdev, 0);
+	if (i < 0) {
+		dev_err(&pdev->dev, "HDLCD: no irq defined for vsync\n");
+		err = -ENOENT;
+		goto resource_err;
+	} else {
+		err = request_irq(i, hdlcd_irq, 0, dev_name(&pdev->dev), hdlcd);
+		if (err) {
+			dev_err(&pdev->dev, "HDLCD: unable to request irq\n");
+			goto resource_err;
+		}
+		hdlcd->irq = i;
+	}
+
+	if (!request_mem_region(mem->start, resource_size(mem),	dev_name(&pdev->dev))) {
+		err = -ENXIO;
+		goto request_err;
+	}
+
+	if (!hdlcd->fb.fix.smem_start) {
+		dev_err(&pdev->dev, "platform did not allocate frame buffer memory\n");
+		err = -ENOMEM;
+		goto memalloc_err;
+	}
+	hdlcd->fb.screen_base = ioremap_wc(hdlcd->fb.fix.smem_start, framebuffer_size);
+	if (!hdlcd->fb.screen_base) {
+		dev_err(&pdev->dev, "unable to ioremap framebuffer\n");
+		err = -ENOMEM;
+		goto probe_err;
+	}
+
+	hdlcd->fb.screen_size = framebuffer_size;
+	hdlcd->fb.fix.smem_len = framebuffer_size;
+	hdlcd->fb.fix.mmio_start = mem->start;
+	hdlcd->fb.fix.mmio_len = resource_size(mem);
+
+	/* Clear the framebuffer */
+	memset(hdlcd->fb.screen_base, 0, framebuffer_size);
+
+	hdlcd->dev = &pdev->dev;
+
+	dev_dbg(&pdev->dev, "HDLCD: framebuffer virt base %p, phys base 0x%lX\n",
+		hdlcd->fb.screen_base, (unsigned long)hdlcd->fb.fix.smem_start);
+
+	err = hdlcd_setup(hdlcd);
+
+	if (err)
+		goto probe_err;
+
+	platform_set_drvdata(pdev, hdlcd);
+	return 0;
+
+probe_err:
+	iounmap(hdlcd->fb.screen_base);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+
+memalloc_err:
+	release_mem_region(mem->start, resource_size(mem));
+
+request_err:
+	free_irq(hdlcd->irq, hdlcd);
+
+resource_err:
+	kfree(hdlcd);
+
+	return err;
+}
+
+static int hdlcd_remove(struct platform_device *pdev)
+{
+	struct hdlcd_device *hdlcd = platform_get_drvdata(pdev);
+
+	clk_disable(hdlcd->clk);
+	clk_unprepare(hdlcd->clk);
+	clk_put(hdlcd->clk);
+
+	/* unmap memory */
+	iounmap(hdlcd->fb.screen_base);
+	iounmap(hdlcd->base);
+
+	/* deallocate fb memory */
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+	kfree(hdlcd->fb.pseudo_palette);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+	release_mem_region(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+
+	free_irq(hdlcd->irq, NULL);
+	kfree(hdlcd);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int hdlcd_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	/* not implemented yet */
+	return 0;
+}
+
+static int hdlcd_resume(struct platform_device *pdev)
+{
+	/* not implemented yet */
+	return 0;
+}
+#else
+#define hdlcd_suspend	NULL
+#define hdlcd_resume	NULL
+#endif
+
+static struct platform_driver hdlcd_driver = {
+	.probe		= hdlcd_probe,
+	.remove		= hdlcd_remove,
+	.suspend	= hdlcd_suspend,
+	.resume		= hdlcd_resume,
+	.driver	= {
+		.name		= "hdlcd",
+		.owner		= THIS_MODULE,
+		.of_match_table	= hdlcd_of_matches,
+	},
+};
+
+static int __init hdlcd_init(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	int err = platform_driver_register(&hdlcd_driver);
+	if (!err)
+		hdlcd_underrun_init();
+	return err;
+#else
+	return platform_driver_register(&hdlcd_driver);
+#endif
+}
+
+void __exit hdlcd_exit(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	hdlcd_underrun_close();
+#endif
+	platform_driver_unregister(&hdlcd_driver);
+}
+
+module_init(hdlcd_init);
+module_exit(hdlcd_exit);
+
+MODULE_AUTHOR("Liviu Dudau");
+MODULE_DESCRIPTION("ARM HDLCD core driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c
index e45833ce975b..182bd680141f 100644
--- a/drivers/video/aty/mach64_accel.c
+++ b/drivers/video/aty/mach64_accel.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <asm/unaligned.h>
 #include <linux/fb.h>
 #include <video/mach64.h>
 #include "atyfb.h"
@@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image)
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;
 		for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
 
diff --git a/drivers/video/aty/mach64_cursor.c b/drivers/video/aty/mach64_cursor.c
index 95ec042ddbf8..0fe02e22d9a4 100644
--- a/drivers/video/aty/mach64_cursor.c
+++ b/drivers/video/aty/mach64_cursor.c
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include "../fb_draw.h"
 
 #include <asm/io.h>
 
@@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 
 	    for (i = 0; i < height; i++) {
 		for (j = 0; j < width; j++) {
+			u16 l = 0xaaaa;
 			b = *src++;
 			m = *msk++;
 			switch (cursor->rop) {
 			case ROP_XOR:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b ^ m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
 			    break;
 			case ROP_COPY:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b & m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b & m) & 0x0f] << 8);
 			    break;
 			}
+			/*
+			 * If cursor size is not a multiple of 8 characters
+			 * we must pad it with transparent pattern (0xaaaa).
+			 */
+			if ((j + 1) * 8 > cursor->image.width) {
+				l = comp(l, 0xaaaa,
+				    (1 << ((cursor->image.width & 7) * 2)) - 1);
+			}
+			fb_writeb(l & 0xff, dst++);
+			fb_writeb(l >> 8, dst++);
 		}
 		dst += offset;
 	    }
diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c
index 700cac067b46..bdc515f5e979 100644
--- a/drivers/video/au1100fb.c
+++ b/drivers/video/au1100fb.c
@@ -361,39 +361,13 @@ void au1100fb_fb_rotate(struct fb_info *fbi, int angle)
 int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
 {
 	struct au1100fb_device *fbdev;
-	unsigned int len;
-	unsigned long start=0, off;
 
 	fbdev = to_au1100fb_device(fbi);
 
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
-		return -EINVAL;
-	}
-
-	start = fbdev->fb_phys & PAGE_MASK;
-	len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-
-	if ((vma->vm_end - vma->vm_start + off) > len) {
-		return -EINVAL;
-	}
-
-	off += start;
-	vma->vm_pgoff = off >> PAGE_SHIFT;
-
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6
 
-	vma->vm_flags |= VM_IO;
-
-	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-				vma->vm_end - vma->vm_start,
-				vma->vm_page_prot)) {
-		return -EAGAIN;
-	}
-
-	return 0;
+	return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
 }
 
 static struct fb_ops au1100fb_ops =
diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c
index 1b59054fc6a4..1d02897d17f2 100644
--- a/drivers/video/au1200fb.c
+++ b/drivers/video/au1200fb.c
@@ -1233,38 +1233,13 @@ static int au1200fb_fb_blank(int blank_mode, struct fb_info *fbi)
  * method mainly to allow the use of the TLB streaming flag (CCA=6)
  */
 static int au1200fb_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
-
 {
-	unsigned int len;
-	unsigned long start=0, off;
 	struct au1200fb_device *fbdev = info->par;
 
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
-		return -EINVAL;
-	}
-
-	start = fbdev->fb_phys & PAGE_MASK;
-	len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-
-	if ((vma->vm_end - vma->vm_start + off) > len) {
-		return -EINVAL;
-	}
-
-	off += start;
-	vma->vm_pgoff = off >> PAGE_SHIFT;
-
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pgprot_val(vma->vm_page_prot) |= _CACHE_MASK; /* CCA=7 */
 
-	vma->vm_flags |= VM_IO;
-
-	return io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-				  vma->vm_end - vma->vm_start,
-				  vma->vm_page_prot);
-
-	return 0;
+	return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
 }
 
 static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata)
diff --git a/drivers/video/backlight/atmel-pwm-bl.c b/drivers/video/backlight/atmel-pwm-bl.c
index a60d6afca97c..27a14a05ff7a 100644
--- a/drivers/video/backlight/atmel-pwm-bl.c
+++ b/drivers/video/backlight/atmel-pwm-bl.c
@@ -70,7 +70,7 @@ static int atmel_pwm_bl_set_intensity(struct backlight_device *bd)
 static int atmel_pwm_bl_get_intensity(struct backlight_device *bd)
 {
 	struct atmel_pwm_bl *pwmbl = bl_get_data(bd);
-	u8 intensity;
+	u32 intensity;
 
 	if (pwmbl->pdata->pwm_active_low) {
 		intensity = pwm_channel_readl(&pwmbl->pwmc, PWM_CDTY) -
@@ -80,7 +80,7 @@ static int atmel_pwm_bl_get_intensity(struct backlight_device *bd)
 			pwm_channel_readl(&pwmbl->pwmc, PWM_CDTY);
 	}
 
-	return intensity;
+	return intensity & 0xffff;
 }
 
 static int atmel_pwm_bl_init_pwm(struct atmel_pwm_bl *pwmbl)
@@ -118,7 +118,7 @@ static const struct backlight_ops atmel_pwm_bl_ops = {
 	.update_status  = atmel_pwm_bl_set_intensity,
 };
 
-static int __init atmel_pwm_bl_probe(struct platform_device *pdev)
+static int atmel_pwm_bl_probe(struct platform_device *pdev)
 {
 	struct backlight_properties props;
 	const struct atmel_pwm_bl_platform_data *pdata;
@@ -203,12 +203,14 @@ err_free_mem:
 	return retval;
 }
 
-static int __exit atmel_pwm_bl_remove(struct platform_device *pdev)
+static int atmel_pwm_bl_remove(struct platform_device *pdev)
 {
 	struct atmel_pwm_bl *pwmbl = platform_get_drvdata(pdev);
 
-	if (pwmbl->gpio_on != -1)
-		gpio_set_value(pwmbl->gpio_on, 0);
+	if (pwmbl->gpio_on != -1) {
+		gpio_set_value(pwmbl->gpio_on,
+					0 ^ pwmbl->pdata->on_active_low);
+	}
 	pwm_channel_disable(&pwmbl->pwmc);
 	pwm_channel_free(&pwmbl->pwmc);
 	backlight_device_unregister(pwmbl->bldev);
@@ -222,10 +224,11 @@ static struct platform_driver atmel_pwm_bl_driver = {
 		.name = "atmel-pwm-bl",
 	},
 	/* REVISIT add suspend() and resume() */
-	.remove = __exit_p(atmel_pwm_bl_remove),
+	.probe = atmel_pwm_bl_probe,
+	.remove = atmel_pwm_bl_remove,
 };
 
-module_platform_driver_probe(atmel_pwm_bl_driver, atmel_pwm_bl_probe);
+module_platform_driver(atmel_pwm_bl_driver);
 
 MODULE_AUTHOR("Hans-Christian egtvedt <hans-christian.egtvedt@atmel.com>");
 MODULE_DESCRIPTION("Atmel PWM backlight driver");
diff --git a/drivers/video/cfbcopyarea.c b/drivers/video/cfbcopyarea.c
index bb5a96b1645d..bcb57235fcc7 100644
--- a/drivers/video/cfbcopyarea.c
+++ b/drivers/video/cfbcopyarea.c
@@ -43,13 +43,22 @@
      */
 
 static void
-bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
-	int left, right;
+
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
 
 	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
 	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
@@ -98,9 +107,8 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		right = shift & (bits - 1);
-		left = -shift & (bits - 1);
-		bswapmask &= shift;
+		int const left = shift & (bits - 1);
+		int const right = -shift & (bits - 1);
 
 		if (dst_idx+n <= bits) {
 			// Single destination word
@@ -110,15 +118,15 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			if (shift > 0) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else if (src_idx+n <= bits) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src + 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0<<left | d1>>right;
+				d0 = d0 >> right | d1 << left;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -135,60 +143,59 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift > 0) {
 				// Single source word
 				d1 = d0;
-				d0 >>= right;
-				dst++;
+				d0 <<= left;
 				n -= bits - dst_idx;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
 
-				d0 = d0<<left | d1>>right;
-				dst++;
+				d0 = d0 >> right | d1 << left;
 				n -= bits - dst_idx;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
 			d0 = d1;
+			dst++;
 
 			// Main chunk
 			m = n % bits;
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 << left | d1 >> right;
+				d0 = d0 >> right | d1 << left;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst++);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= right) {
+			if (m) {
+				if (m <= bits - right) {
 					// Single source word
-					d0 <<= left;
+					d0 >>= right;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0<<left | d1>>right;
+					d0 = d0 >> right | d1 << left;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -202,43 +209,46 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
      */
 
 static void
-bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int shift;
 
-	dst += (n-1)/bits;
-	src += (n-1)/bits;
-	if ((n-1) % bits) {
-		dst_idx += (n-1) % bits;
-		dst += dst_idx >> (ffs(bits) - 1);
-		dst_idx &= bits - 1;
-		src_idx += (n-1) % bits;
-		src += src_idx >> (ffs(bits) - 1);
-		src_idx &= bits - 1;
-	}
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
+
+	dst += (dst_idx + n - 1) / bits;
+	src += (src_idx + n - 1) / bits;
+	dst_idx = (dst_idx + n - 1) % bits;
+	src_idx = (src_idx + n - 1) % bits;
 
 	shift = dst_idx-src_idx;
 
-	first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
-					    bswapmask);
+	first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask);
+	last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single word
-			if (last)
-				first &= last;
-			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
+			if (first)
+				last &= first;
+			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 
 			// Leading bits
-			if (first != ~0UL) {
+			if (first) {
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
 				dst--;
 				src--;
@@ -262,7 +272,7 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 				FB_WRITEL(FB_READL(src--), dst--);
 
 			// Trailing bits
-			if (last)
+			if (last != -1UL)
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		}
 	} else {
@@ -270,29 +280,28 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		int const left = -shift & (bits-1);
-		int const right = shift & (bits-1);
-		bswapmask &= shift;
+		int const left = shift & (bits-1);
+		int const right = -shift & (bits-1);
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single destination word
-			if (last)
-				first &= last;
+			if (first)
+				last &= first;
 			d0 = FB_READL(src);
 			if (shift < 0) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else if (1+(unsigned long)src_idx >= n) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src - 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
-			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+			FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 			/** We must always remember the last value read, because in case
@@ -307,12 +316,12 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift < 0) {
 				// Single source word
 				d1 = d0;
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -325,39 +334,39 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 >> right | d1 << left;
+				d0 = d0 << left | d1 >> right;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst--);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= left) {
+			if (m) {
+				if (m <= bits - left) {
 					// Single source word
-					d0 >>= right;
+					d0 <<= left;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0>>right | d1<<left;
+					d0 = d0 << left | d1 >> right;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -371,9 +380,9 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 	u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
 	u32 height = area->height, width = area->width;
 	unsigned long const bits_per_line = p->fix.line_length*8u;
-	unsigned long __iomem *dst = NULL, *src = NULL;
+	unsigned long __iomem *base = NULL;
 	int bits = BITS_PER_LONG, bytes = bits >> 3;
-	int dst_idx = 0, src_idx = 0, rev_copy = 0;
+	unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
 	u32 bswapmask = fb_compute_bswapmask(p);
 
 	if (p->state != FBINFO_STATE_RUNNING)
@@ -389,7 +398,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 
 	// split the base of the framebuffer into a long-aligned address and the
 	// index of the first bit
-	dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
+	base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
 	dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
 	// add offset of source and target area
 	dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
@@ -402,20 +411,14 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 		while (height--) {
 			dst_idx -= bits_per_line;
 			src_idx -= bits_per_line;
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 		}
 	} else {
 		while (height--) {
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index bc922c47d046..d5fa5f3fe6d1 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -6,7 +6,7 @@ menu "Console display driver support"
 
 config VGA_CONSOLE
 	bool "VGA text console" if EXPERT || !X86
-	depends on !4xx && !8xx && !SPARC && !M68K && !PARISC && !FRV && !SUPERH && !BLACKFIN && !AVR32 && !MN10300 && (!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER)
+	depends on !4xx && !8xx && !SPARC && !M68K && !PARISC && !FRV && !SUPERH && !BLACKFIN && !AVR32 && !MN10300 && (!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER) && !ARM64
 	default y
 	help
 	  Saying Y here will allow you to use Linux in text mode through a
diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c
index 61b182bf32a2..dbfe4eecf12e 100644
--- a/drivers/video/console/bitblit.c
+++ b/drivers/video/console/bitblit.c
@@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info,
 static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 			      int bottom_only)
 {
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	unsigned int cw = vc->vc_font.width;
 	unsigned int ch = vc->vc_font.height;
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
@@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bs = info->var.yres - bh;
 	struct fb_fillrect region;
 
-	region.color = attr_bgcol_ec(bgshift, vc, info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index a92783e480e6..0d8f98c79a6c 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -404,7 +404,7 @@ static void cursor_timer_handler(unsigned long dev_addr)
 	struct fb_info *info = (struct fb_info *) dev_addr;
 	struct fbcon_ops *ops = info->fbcon_par;
 
-	schedule_work(&info->queue);
+	queue_work(system_power_efficient_wq, &info->queue);
 	mod_timer(&ops->cursor_timer, jiffies + HZ/5);
 }
 
diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c
index 41b32ae23dac..5a3cbf6dff4d 100644
--- a/drivers/video/console/fbcon_ccw.c
+++ b/drivers/video/console/fbcon_ccw.c
@@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int bs = vc->vc_rows*ch;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c
index a93670ef7f89..e7ee44db4e98 100644
--- a/drivers/video/console/fbcon_cw.c
+++ b/drivers/video/console/fbcon_cw.c
@@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int rs = info->var.yres - rw;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c
index ff0872c0498b..19e3714abfe8 100644
--- a/drivers/video/console/fbcon_ud.c
+++ b/drivers/video/console/fbcon_ud.c
@@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
 	unsigned int bh = info->var.yres - (vc->vc_rows*ch);
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index 35687fd56456..4ad24f2c6472 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -3,7 +3,7 @@
  *	core code for console driver using HP's STI firmware
  *
  *	Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
- *	Copyright (C) 2001-2003 Helge Deller <deller@gmx.de>
+ *	Copyright (C) 2001-2013 Helge Deller <deller@gmx.de>
  *	Copyright (C) 2001-2002 Thomas Bogendoerfer <tsbogend@alpha.franken.de>
  * 
  * TODO:
@@ -30,7 +30,7 @@
 
 #include "../sticore.h"
 
-#define STI_DRIVERVERSION "Version 0.9a"
+#define STI_DRIVERVERSION "Version 0.9b"
 
 static struct sti_struct *default_sti __read_mostly;
 
@@ -73,28 +73,34 @@ static const struct sti_init_flags default_init_flags = {
 
 static int sti_init_graph(struct sti_struct *sti)
 {
-	struct sti_init_inptr_ext inptr_ext = { 0, };
-	struct sti_init_inptr inptr = {
-		.text_planes	= 3, /* # of text planes (max 3 for STI) */
-		.ext_ptr	= STI_PTR(&inptr_ext)
-	};
-	struct sti_init_outptr outptr = { 0, };
+	struct sti_init_inptr *inptr = &sti->sti_data->init_inptr;
+	struct sti_init_inptr_ext *inptr_ext = &sti->sti_data->init_inptr_ext;
+	struct sti_init_outptr *outptr = &sti->sti_data->init_outptr;
 	unsigned long flags;
-	int ret;
+	int ret, err;
 
 	spin_lock_irqsave(&sti->lock, flags);
 
-	ret = STI_CALL(sti->init_graph, &default_init_flags, &inptr,
-		&outptr, sti->glob_cfg);
+	memset(inptr, 0, sizeof(*inptr));
+	inptr->text_planes = 3; /* # of text planes (max 3 for STI) */
+	memset(inptr_ext, 0, sizeof(*inptr_ext));
+	inptr->ext_ptr = STI_PTR(inptr_ext);
+	outptr->errno = 0;
+
+	ret = sti_call(sti, sti->init_graph, &default_init_flags, inptr,
+		outptr, sti->glob_cfg);
+
+	if (ret >= 0)
+		sti->text_planes = outptr->text_planes;
+	err = outptr->errno;
 
 	spin_unlock_irqrestore(&sti->lock, flags);
 
 	if (ret < 0) {
-		printk(KERN_ERR "STI init_graph failed (ret %d, errno %d)\n",ret,outptr.errno);
+		pr_err("STI init_graph failed (ret %d, errno %d)\n", ret, err);
 		return -1;
 	}
 	
-	sti->text_planes = outptr.text_planes;
 	return 0;
 }
 
@@ -104,16 +110,18 @@ static const struct sti_conf_flags default_conf_flags = {
 
 static void sti_inq_conf(struct sti_struct *sti)
 {
-	struct sti_conf_inptr inptr = { 0, };
+	struct sti_conf_inptr *inptr = &sti->sti_data->inq_inptr;
+	struct sti_conf_outptr *outptr = &sti->sti_data->inq_outptr;
 	unsigned long flags;
 	s32 ret;
 
-	sti->outptr.ext_ptr = STI_PTR(&sti->outptr_ext);
+	outptr->ext_ptr = STI_PTR(&sti->sti_data->inq_outptr_ext);
 	
 	do {
 		spin_lock_irqsave(&sti->lock, flags);
-		ret = STI_CALL(sti->inq_conf, &default_conf_flags,
-			&inptr, &sti->outptr, sti->glob_cfg);
+		memset(inptr, 0, sizeof(*inptr));
+		ret = sti_call(sti, sti->inq_conf, &default_conf_flags,
+			inptr, outptr, sti->glob_cfg);
 		spin_unlock_irqrestore(&sti->lock, flags);
 	} while (ret == 1);
 }
@@ -126,7 +134,8 @@ static const struct sti_font_flags default_font_flags = {
 void
 sti_putc(struct sti_struct *sti, int c, int y, int x)
 {
-	struct sti_font_inptr inptr = {
+	struct sti_font_inptr *inptr = &sti->sti_data->font_inptr;
+	struct sti_font_inptr inptr_default = {
 		.font_start_addr= STI_PTR(sti->font->raw),
 		.index		= c_index(sti, c),
 		.fg_color	= c_fg(sti, c),
@@ -134,14 +143,15 @@ sti_putc(struct sti_struct *sti, int c, int y, int x)
 		.dest_x		= x * sti->font_width,
 		.dest_y		= y * sti->font_height,
 	};
-	struct sti_font_outptr outptr = { 0, };
+	struct sti_font_outptr *outptr = &sti->sti_data->font_outptr;
 	s32 ret;
 	unsigned long flags;
 
 	do {
 		spin_lock_irqsave(&sti->lock, flags);
-		ret = STI_CALL(sti->font_unpmv, &default_font_flags,
-			&inptr, &outptr, sti->glob_cfg);
+		*inptr = inptr_default;
+		ret = sti_call(sti, sti->font_unpmv, &default_font_flags,
+			inptr, outptr, sti->glob_cfg);
 		spin_unlock_irqrestore(&sti->lock, flags);
 	} while (ret == 1);
 }
@@ -156,7 +166,8 @@ void
 sti_set(struct sti_struct *sti, int src_y, int src_x,
 	int height, int width, u8 color)
 {
-	struct sti_blkmv_inptr inptr = {
+	struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+	struct sti_blkmv_inptr inptr_default = {
 		.fg_color	= color,
 		.bg_color	= color,
 		.src_x		= src_x,
@@ -166,14 +177,15 @@ sti_set(struct sti_struct *sti, int src_y, int src_x,
 		.width		= width,
 		.height		= height,
 	};
-	struct sti_blkmv_outptr outptr = { 0, };
+	struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
 	s32 ret;
 	unsigned long flags;
 	
 	do {
 		spin_lock_irqsave(&sti->lock, flags);
-		ret = STI_CALL(sti->block_move, &clear_blkmv_flags,
-			&inptr, &outptr, sti->glob_cfg);
+		*inptr = inptr_default;
+		ret = sti_call(sti, sti->block_move, &clear_blkmv_flags,
+			inptr, outptr, sti->glob_cfg);
 		spin_unlock_irqrestore(&sti->lock, flags);
 	} while (ret == 1);
 }
@@ -182,7 +194,8 @@ void
 sti_clear(struct sti_struct *sti, int src_y, int src_x,
 	  int height, int width, int c)
 {
-	struct sti_blkmv_inptr inptr = {
+	struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+	struct sti_blkmv_inptr inptr_default = {
 		.fg_color	= c_fg(sti, c),
 		.bg_color	= c_bg(sti, c),
 		.src_x		= src_x * sti->font_width,
@@ -192,14 +205,15 @@ sti_clear(struct sti_struct *sti, int src_y, int src_x,
 		.width		= width * sti->font_width,
 		.height		= height* sti->font_height,
 	};
-	struct sti_blkmv_outptr outptr = { 0, };
+	struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
 	s32 ret;
 	unsigned long flags;
 
 	do {
 		spin_lock_irqsave(&sti->lock, flags);
-		ret = STI_CALL(sti->block_move, &clear_blkmv_flags,
-			&inptr, &outptr, sti->glob_cfg);
+		*inptr = inptr_default;
+		ret = sti_call(sti, sti->block_move, &clear_blkmv_flags,
+			inptr, outptr, sti->glob_cfg);
 		spin_unlock_irqrestore(&sti->lock, flags);
 	} while (ret == 1);
 }
@@ -212,7 +226,8 @@ void
 sti_bmove(struct sti_struct *sti, int src_y, int src_x,
 	  int dst_y, int dst_x, int height, int width)
 {
-	struct sti_blkmv_inptr inptr = {
+	struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+	struct sti_blkmv_inptr inptr_default = {
 		.src_x		= src_x * sti->font_width,
 		.src_y		= src_y * sti->font_height,
 		.dest_x		= dst_x * sti->font_width,
@@ -220,14 +235,15 @@ sti_bmove(struct sti_struct *sti, int src_y, int src_x,
 		.width		= width * sti->font_width,
 		.height		= height* sti->font_height,
 	};
-	struct sti_blkmv_outptr outptr = { 0, };
+	struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
 	s32 ret;
 	unsigned long flags;
 
 	do {
 		spin_lock_irqsave(&sti->lock, flags);
-		ret = STI_CALL(sti->block_move, &default_blkmv_flags,
-			&inptr, &outptr, sti->glob_cfg);
+		*inptr = inptr_default;
+		ret = sti_call(sti, sti->block_move, &default_blkmv_flags,
+			inptr, outptr, sti->glob_cfg);
 		spin_unlock_irqrestore(&sti->lock, flags);
 	} while (ret == 1);
 }
@@ -284,7 +300,7 @@ __setup("sti=", sti_setup);
 
 
 
-static char *font_name[MAX_STI_ROMS] = { "VGA8x16", };
+static char *font_name[MAX_STI_ROMS];
 static int font_index[MAX_STI_ROMS],
 	   font_height[MAX_STI_ROMS],
 	   font_width[MAX_STI_ROMS];
@@ -389,10 +405,10 @@ static void sti_dump_outptr(struct sti_struct *sti)
 		"%d used bits\n"
 		"%d planes\n"
 		"attributes %08x\n",
-		 sti->outptr.bits_per_pixel,
-		 sti->outptr.bits_used,
-		 sti->outptr.planes,
-		 sti->outptr.attributes));
+		 sti->sti_data->inq_outptr.bits_per_pixel,
+		 sti->sti_data->inq_outptr.bits_used,
+		 sti->sti_data->inq_outptr.planes,
+		 sti->sti_data->inq_outptr.attributes));
 }
 
 static int sti_init_glob_cfg(struct sti_struct *sti, unsigned long rom_address,
@@ -402,24 +418,21 @@ static int sti_init_glob_cfg(struct sti_struct *sti, unsigned long rom_address,
 	struct sti_glob_cfg_ext *glob_cfg_ext;
 	void *save_addr;
 	void *sti_mem_addr;
-	const int save_addr_size = 1024;	/* XXX */
-	int i;
+	int i, size;
 
-	if (!sti->sti_mem_request)
+	if (sti->sti_mem_request < 256)
 		sti->sti_mem_request = 256; /* STI default */
 
-	glob_cfg = kzalloc(sizeof(*sti->glob_cfg), GFP_KERNEL);
-	glob_cfg_ext = kzalloc(sizeof(*glob_cfg_ext), GFP_KERNEL);
-	save_addr = kzalloc(save_addr_size, GFP_KERNEL);
-	sti_mem_addr = kzalloc(sti->sti_mem_request, GFP_KERNEL);
+	size = sizeof(struct sti_all_data) + sti->sti_mem_request - 256;
 
-	if (!(glob_cfg && glob_cfg_ext && save_addr && sti_mem_addr)) {
-		kfree(glob_cfg);
-		kfree(glob_cfg_ext);
-		kfree(save_addr);
-		kfree(sti_mem_addr);
+	sti->sti_data = kzalloc(size, STI_LOWMEM);
+	if (!sti->sti_data)
 		return -ENOMEM;
-	}
+
+	glob_cfg	= &sti->sti_data->glob_cfg;
+	glob_cfg_ext	= &sti->sti_data->glob_cfg_ext;
+	save_addr	= &sti->sti_data->save_addr;
+	sti_mem_addr	= &sti->sti_data->sti_mem_addr;
 
 	glob_cfg->ext_ptr = STI_PTR(glob_cfg_ext);
 	glob_cfg->save_addr = STI_PTR(save_addr);
@@ -475,32 +488,31 @@ static int sti_init_glob_cfg(struct sti_struct *sti, unsigned long rom_address,
 	return 0;
 }
 
-#ifdef CONFIG_FB
+#ifdef CONFIG_FONTS
 static struct sti_cooked_font *
 sti_select_fbfont(struct sti_cooked_rom *cooked_rom, const char *fbfont_name)
 {
-	const struct font_desc *fbfont;
+	const struct font_desc *fbfont = NULL;
 	unsigned int size, bpc;
 	void *dest;
 	struct sti_rom_font *nf;
 	struct sti_cooked_font *cooked_font;
 	
-	if (!fbfont_name || !strlen(fbfont_name))
-		return NULL;
-	fbfont = find_font(fbfont_name);
+	if (fbfont_name && strlen(fbfont_name))
+		fbfont = find_font(fbfont_name);
 	if (!fbfont)
 		fbfont = get_default_font(1024,768, ~(u32)0, ~(u32)0);
 	if (!fbfont)
 		return NULL;
 
-	DPRINTK((KERN_DEBUG "selected %dx%d fb-font %s\n",
-			fbfont->width, fbfont->height, fbfont->name));
+	pr_info("STI selected %dx%d framebuffer font %s for sticon\n",
+			fbfont->width, fbfont->height, fbfont->name);
 			
 	bpc = ((fbfont->width+7)/8) * fbfont->height; 
 	size = bpc * 256;
 	size += sizeof(struct sti_rom_font);
 
-	nf = kzalloc(size, GFP_KERNEL);
+	nf = kzalloc(size, STI_LOWMEM);
 	if (!nf)
 		return NULL;
 
@@ -637,7 +649,7 @@ static void *sti_bmode_font_raw(struct sti_cooked_font *f)
 	unsigned char *n, *p, *q;
 	int size = f->raw->bytes_per_char*256+sizeof(struct sti_rom_font);
 	
-	n = kzalloc (4*size, GFP_KERNEL);
+	n = kzalloc(4*size, STI_LOWMEM);
 	if (!n)
 		return NULL;
 	p = n + 3;
@@ -673,7 +685,7 @@ static struct sti_rom *sti_get_bmode_rom (unsigned long address)
 	sti_bmode_rom_copy(address + BMODE_LAST_ADDR_OFFS, sizeof(size), &size);
 
 	size = (size+3) / 4;
-	raw = kmalloc(size, GFP_KERNEL);
+	raw = kmalloc(size, STI_LOWMEM);
 	if (raw) {
 		sti_bmode_rom_copy(address, size, raw);
 		memmove (&raw->res004, &raw->type[0], 0x3c);
@@ -707,7 +719,7 @@ static struct sti_rom *sti_get_wmode_rom(unsigned long address)
 	/* read the ROM size directly from the struct in ROM */ 
 	size = gsc_readl(address + offsetof(struct sti_rom,last_addr));
 
-	raw = kmalloc(size, GFP_KERNEL);
+	raw = kmalloc(size, STI_LOWMEM);
 	if (raw)
 		sti_rom_copy(address, size, raw);
 
@@ -743,6 +755,10 @@ static int sti_read_rom(int wordmode, struct sti_struct *sti,
 
 	address = (unsigned long) STI_PTR(raw);
 
+	pr_info("STI ROM supports 32 %sbit firmware functions.\n",
+		raw->alt_code_type == ALT_CODE_TYPE_PA_RISC_64
+		? "and 64 " : "");
+
 	sti->font_unpmv = address + (raw->font_unpmv & 0x03ffffff);
 	sti->block_move = address + (raw->block_move & 0x03ffffff);
 	sti->init_graph = address + (raw->init_graph & 0x03ffffff);
@@ -901,7 +917,8 @@ test_rom:
 	sti_dump_globcfg(sti->glob_cfg, sti->sti_mem_request);
 	sti_dump_outptr(sti);
 	
-	printk(KERN_INFO "    graphics card name: %s\n", sti->outptr.dev_name );
+	pr_info("    graphics card name: %s\n",
+		sti->sti_data->inq_outptr.dev_name);
 
 	sti_roms[num_sti_roms] = sti;
 	num_sti_roms++;
@@ -1073,6 +1090,29 @@ struct sti_struct * sti_get_rom(unsigned int index)
 }
 EXPORT_SYMBOL(sti_get_rom);
 
+
+int sti_call(const struct sti_struct *sti, unsigned long func,
+		const void *flags, void *inptr, void *outptr,
+		struct sti_glob_cfg *glob_cfg)
+{
+	unsigned long _flags = STI_PTR(flags);
+	unsigned long _inptr = STI_PTR(inptr);
+	unsigned long _outptr = STI_PTR(outptr);
+	unsigned long _glob_cfg = STI_PTR(glob_cfg);
+	int ret;
+
+#ifdef CONFIG_64BIT
+	/* Check for overflow when using 32bit STI on 64bit kernel. */
+	if (WARN_ONCE(_flags>>32 || _inptr>>32 || _outptr>>32 || _glob_cfg>>32,
+			"Out of 32bit-range pointers!"))
+		return -1;
+#endif
+
+	ret = pdc_sti_call(func, _flags, _inptr, _outptr, _glob_cfg);
+
+	return ret;
+}
+
 MODULE_AUTHOR("Philipp Rumpf, Helge Deller, Thomas Bogendoerfer");
 MODULE_DESCRIPTION("Core STI driver for HP's NGLE series graphics cards in HP PARISC machines");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/fb-puv3.c b/drivers/video/fb-puv3.c
index 27fc956166fa..520112531eb0 100644
--- a/drivers/video/fb-puv3.c
+++ b/drivers/video/fb-puv3.c
@@ -18,8 +18,10 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/console.h>
+#include <linux/mm.h>
 
 #include <asm/sizes.h>
+#include <asm/pgtable.h>
 #include <mach/hardware.h>
 
 /* Platform_data reserved for unifb registers. */
diff --git a/drivers/video/hyperv_fb.c b/drivers/video/hyperv_fb.c
index d4d2c5fe2488..0f3b33cf13ef 100644
--- a/drivers/video/hyperv_fb.c
+++ b/drivers/video/hyperv_fb.c
@@ -795,12 +795,21 @@ static int hvfb_remove(struct hv_device *hdev)
 }
 
 
+static DEFINE_PCI_DEVICE_TABLE(pci_stub_id_table) = {
+	{
+		.vendor      = PCI_VENDOR_ID_MICROSOFT,
+		.device      = PCI_DEVICE_ID_HYPERV_VIDEO,
+	},
+	{ /* end of list */ }
+};
+
 static const struct hv_vmbus_device_id id_table[] = {
 	/* Synthetic Video Device GUID */
 	{HV_SYNTHVID_GUID},
 	{}
 };
 
+MODULE_DEVICE_TABLE(pci, pci_stub_id_table);
 MODULE_DEVICE_TABLE(vmbus, id_table);
 
 static struct hv_driver hvfb_drv = {
@@ -810,14 +819,43 @@ static struct hv_driver hvfb_drv = {
 	.remove = hvfb_remove,
 };
 
+static int hvfb_pci_stub_probe(struct pci_dev *pdev,
+			       const struct pci_device_id *ent)
+{
+	return 0;
+}
+
+static void hvfb_pci_stub_remove(struct pci_dev *pdev)
+{
+}
+
+static struct pci_driver hvfb_pci_stub_driver = {
+	.name =		KBUILD_MODNAME,
+	.id_table =	pci_stub_id_table,
+	.probe =	hvfb_pci_stub_probe,
+	.remove =	hvfb_pci_stub_remove,
+};
 
 static int __init hvfb_drv_init(void)
 {
-	return vmbus_driver_register(&hvfb_drv);
+	int ret;
+
+	ret = vmbus_driver_register(&hvfb_drv);
+	if (ret != 0)
+		return ret;
+
+	ret = pci_register_driver(&hvfb_pci_stub_driver);
+	if (ret != 0) {
+		vmbus_driver_unregister(&hvfb_drv);
+		return ret;
+	}
+
+	return 0;
 }
 
 static void __exit hvfb_drv_exit(void)
 {
+	pci_unregister_driver(&hvfb_pci_stub_driver);
 	vmbus_driver_unregister(&hvfb_drv);
 }
 
diff --git a/drivers/video/kyro/fbdev.c b/drivers/video/kyro/fbdev.c
index 6157f74ac600..ec7fc87fa5ab 100644
--- a/drivers/video/kyro/fbdev.c
+++ b/drivers/video/kyro/fbdev.c
@@ -625,15 +625,15 @@ static int kyrofb_ioctl(struct fb_info *info,
 		}
 		break;
 	case KYRO_IOCTL_UVSTRIDE:
-		if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(unsigned long)))
+		if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(deviceInfo.ulOverlayUVStride)))
 			return -EFAULT;
 		break;
 	case KYRO_IOCTL_STRIDE:
-		if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(unsigned long)))
+		if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(deviceInfo.ulOverlayStride)))
 			return -EFAULT;
 		break;
 	case KYRO_IOCTL_OVERLAY_OFFSET:
-		if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(unsigned long)))
+		if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(deviceInfo.ulOverlayOffset)))
 			return -EFAULT;
 		break;
 	}
diff --git a/drivers/video/matrox/matroxfb_accel.c b/drivers/video/matrox/matroxfb_accel.c
index 8335a6fe303e..0d5cb85d071a 100644
--- a/drivers/video/matrox/matroxfb_accel.c
+++ b/drivers/video/matrox/matroxfb_accel.c
@@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_info *minfo)
 	minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
 	if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
 	minfo->accel.m_opmode = mopmode;
+	minfo->accel.m_access = maccess;
+	minfo->accel.m_pitch = mpitch;
 }
 
 EXPORT_SYMBOL(matrox_cfbX_init);
 
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+	mga_outl(M_MACCESS, minfo->accel.m_access);
+	mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
 static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 			       int sx, int dy, int dx, int height, int width)
 {
@@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			 M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(4);
+	mga_fifo(6);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct matrox_fb_info *minfo, u_int32_t color,
 
 	CRITBEGIN
 
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
 	mga_outl(M_FCOL, color);
 	mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct matrox_fb_info *minfo, u_int32_t bgx,
 	width >>= 1;
 	sx >>= 1;
 	if (width) {
-		mga_fifo(5);
+		mga_fifo(7);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
 		mga_outl(M_FCOL, bgx);
 		mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 
 	CRITBEGIN
 
-	mga_fifo(3);
+	mga_fifo(5);
+	matrox_accel_restore_maccess(minfo);
 	if (easy)
 		mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
 	else
@@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 	fxbndry = ((xx + width - 1) << 16) | xx;
 	mmio = minfo->mmio.vbase;
 
-	mga_fifo(6);
+	mga_fifo(8);
+	matrox_accel_restore_maccess(minfo);
 	mga_writel(mmio, M_FXBNDRY, fxbndry);
 	mga_writel(mmio, M_AR0, ar0);
 	mga_writel(mmio, M_AR3, 0);
diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h
index 11ed57bb704e..89a8a89a5eb2 100644
--- a/drivers/video/matrox/matroxfb_base.h
+++ b/drivers/video/matrox/matroxfb_base.h
@@ -307,6 +307,8 @@ struct matrox_accel_data {
 #endif
 	u_int32_t	m_dwg_rect;
 	u_int32_t	m_opmode;
+	u_int32_t	m_access;
+	u_int32_t	m_pitch;
 };
 
 struct v4l2_queryctrl;
@@ -696,7 +698,7 @@ void matroxfb_unregister_driver(struct matroxfb_driver* drv);
 
 #define mga_fifo(n)	do {} while ((mga_inl(M_FIFOSTATUS) & 0xFF) < (n))
 
-#define WaitTillIdle()	do {} while (mga_inl(M_STATUS) & 0x10000)
+#define WaitTillIdle()	do { mga_inl(M_STATUS); do {} while (mga_inl(M_STATUS) & 0x10000); } while (0)
 
 /* code speedup */
 #ifdef CONFIG_FB_MATROX_MILLENIUM
diff --git a/drivers/video/sticore.h b/drivers/video/sticore.h
index addf7b615ef8..af1619536ac8 100644
--- a/drivers/video/sticore.h
+++ b/drivers/video/sticore.h
@@ -18,6 +18,9 @@
 #define STI_FONT_HPROMAN8 1
 #define STI_FONT_KANA8 2
 
+#define ALT_CODE_TYPE_UNKNOWN 0x00	/* alt code type values */
+#define ALT_CODE_TYPE_PA_RISC_64 0x01
+
 /* The latency of the STI functions cannot really be reduced by setting
  * this to 0;  STI doesn't seem to be designed to allow calling a different
  * function (or the same function with different arguments) after a
@@ -40,14 +43,6 @@
 
 #define STI_PTR(p)	( virt_to_phys(p) )
 #define PTR_STI(p)	( phys_to_virt((unsigned long)p) )
-#define STI_CALL(func, flags, inptr, outptr, glob_cfg)	\
-       ({						\
-               pdc_sti_call( func, STI_PTR(flags),	\
-				   STI_PTR(inptr),	\
-				   STI_PTR(outptr),	\
-				   STI_PTR(glob_cfg));	\
-       })
-
 
 #define sti_onscreen_x(sti) (sti->glob_cfg->onscreen_x)
 #define sti_onscreen_y(sti) (sti->glob_cfg->onscreen_y)
@@ -56,6 +51,12 @@
 #define sti_font_x(sti) (PTR_STI(sti->font)->width)
 #define sti_font_y(sti) (PTR_STI(sti->font)->height)
 
+#ifdef CONFIG_64BIT
+#define STI_LOWMEM	(GFP_KERNEL | GFP_DMA)
+#else
+#define STI_LOWMEM	(GFP_KERNEL)
+#endif
+
 
 /* STI function configuration structs */
 
@@ -306,6 +307,34 @@ struct sti_blkmv_outptr {
 };
 
 
+/* sti_all_data is an internal struct which needs to be allocated in
+ * low memory (< 4GB) if STI is used with 32bit STI on a 64bit kernel */
+
+struct sti_all_data {
+	struct sti_glob_cfg glob_cfg;
+	struct sti_glob_cfg_ext glob_cfg_ext;
+
+	struct sti_conf_inptr		inq_inptr;
+	struct sti_conf_outptr		inq_outptr; /* configuration */
+	struct sti_conf_outptr_ext	inq_outptr_ext;
+
+	struct sti_init_inptr_ext	init_inptr_ext;
+	struct sti_init_inptr		init_inptr;
+	struct sti_init_outptr		init_outptr;
+
+	struct sti_blkmv_inptr		blkmv_inptr;
+	struct sti_blkmv_outptr		blkmv_outptr;
+
+	struct sti_font_inptr		font_inptr;
+	struct sti_font_outptr		font_outptr;
+
+	/* leave as last entries */
+	unsigned long save_addr[1024 / sizeof(unsigned long)];
+	   /* min 256 bytes which is STI default, max sti->sti_mem_request */
+	unsigned long sti_mem_addr[256 / sizeof(unsigned long)];
+	/* do not add something below here ! */
+};
+
 /* internal generic STI struct */
 
 struct sti_struct {
@@ -330,11 +359,9 @@ struct sti_struct {
 	region_t regions[STI_REGION_MAX];
 	unsigned long regions_phys[STI_REGION_MAX];
 
-	struct sti_glob_cfg *glob_cfg;
-	struct sti_cooked_font *font;	/* ptr to selected font (cooked) */
+	struct sti_glob_cfg *glob_cfg;	/* points into sti_all_data */
 
-	struct sti_conf_outptr outptr; /* configuration */
-	struct sti_conf_outptr_ext outptr_ext;
+	struct sti_cooked_font *font;	/* ptr to selected font (cooked) */
 
 	struct pci_dev *pd;
 
@@ -343,6 +370,9 @@ struct sti_struct {
 
 	/* pointer to the fb_info where this STI device is used */
 	struct fb_info *info;
+
+	/* pointer to all internal data */
+	struct sti_all_data *sti_data;
 };
 
 
@@ -350,6 +380,14 @@ struct sti_struct {
 
 struct sti_struct *sti_get_rom(unsigned int index); /* 0: default sti */
 
+
+/* sticore main function to call STI firmware */
+
+int sti_call(const struct sti_struct *sti, unsigned long func,
+		const void *flags, void *inptr, void *outptr,
+		struct sti_glob_cfg *glob_cfg);
+
+
 /* functions to call the STI ROM directly */
 
 void sti_putc(struct sti_struct *sti, int c, int y, int x);
diff --git a/drivers/video/stifb.c b/drivers/video/stifb.c
index 876648e15e9d..019a1feef995 100644
--- a/drivers/video/stifb.c
+++ b/drivers/video/stifb.c
@@ -1101,6 +1101,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 	var = &info->var;
 
 	fb->sti = sti;
+	dev_name = sti->sti_data->inq_outptr.dev_name;
 	/* store upper 32bits of the graphics id */
 	fb->id = fb->sti->graphics_id[0];
 
@@ -1114,11 +1115,11 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 		  Since this driver only supports standard mode, we check
 		  if the device name contains the string "DX" and tell the
 		  user how to reconfigure the card. */
-		if (strstr(sti->outptr.dev_name, "DX")) {
+		if (strstr(dev_name, "DX")) {
 		   printk(KERN_WARNING
 "WARNING: stifb framebuffer driver does not support '%s' in double-buffer mode.\n"
 "WARNING: Please disable the double-buffer mode in IPL menu (the PARISC-BIOS).\n",
-			sti->outptr.dev_name);
+			dev_name);
 		   goto out_err0;
 		}
 		/* fall though */
@@ -1130,7 +1131,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 		break;
 	default:
 		printk(KERN_WARNING "stifb: '%s' (id: 0x%08x) not supported.\n",
-			sti->outptr.dev_name, fb->id);
+			dev_name, fb->id);
 		goto out_err0;
 	}
 	
@@ -1154,7 +1155,6 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 		fb->id = S9000_ID_A1659A;
 		break;
 	case S9000_ID_TIMBER:	/* HP9000/710 Any (may be a grayscale device) */
-		dev_name = fb->sti->outptr.dev_name;
 		if (strstr(dev_name, "GRAYSCALE") || 
 		    strstr(dev_name, "Grayscale") ||
 		    strstr(dev_name, "grayscale"))
@@ -1290,7 +1290,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 		var->xres, 
 		var->yres,
 		var->bits_per_pixel,
-		sti->outptr.dev_name,
+		dev_name,
 		fb->id, 
 		fix->mmio_start);
 
diff --git a/drivers/video/tgafb.c b/drivers/video/tgafb.c
index c9c8e5a1fdee..a78ca6a01094 100644
--- a/drivers/video/tgafb.c
+++ b/drivers/video/tgafb.c
@@ -188,6 +188,8 @@ tgafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	if (var->xres_virtual != var->xres || var->yres_virtual != var->yres)
 		return -EINVAL;
+	if (var->xres * var->yres * (var->bits_per_pixel >> 3) > info->fix.smem_len)
+		return -EINVAL;
 	if (var->nonstd)
 		return -EINVAL;
 	if (1000000000 / var->pixclock > TGA_PLL_MAX_FREQ)
@@ -268,6 +270,7 @@ tgafb_set_par(struct fb_info *info)
 	par->yres = info->var.yres;
 	par->pll_freq = pll_freq = 1000000000 / info->var.pixclock;
 	par->bits_per_pixel = info->var.bits_per_pixel;
+	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 
 	tga_type = par->tga_type;
 
@@ -1142,222 +1145,57 @@ copyarea_line_32bpp(struct fb_info *info, u32 dy, u32 sy,
 	__raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
 }
 
-/* The general case of forward copy in 8bpp mode.  */
+/* The (almost) general case of backward copy in 8bpp mode.  */
 static inline void
-copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length)
+copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
+	      u32 height, u32 width, u32 line_length,
+	      const struct fb_copyarea *area)
 {
 	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, copied, left;
-	unsigned long dpos, spos, dalign, salign, yincr;
-	u32 smask_first, dmask_first, dmask_last;
-	int pixel_shift, need_prime, need_second;
-	unsigned long n64, n32, xincr_first;
+	unsigned i, yincr;
+	int depos, sepos, backward, last_step, step;
+	u32 mask_last;
+	unsigned n32;
 	void __iomem *tga_regs;
 	void __iomem *tga_fb;
 
-	yincr = line_length;
-	if (dy > sy) {
-		dy += height - 1;
-		sy += height - 1;
-		yincr = -yincr;
-	}
-
-	/* Compute the offsets and alignments in the frame buffer.
-	   More than anything else, these control how we do copies.  */
-	dpos = dy * line_length + dx;
-	spos = sy * line_length + sx;
-	dalign = dpos & 7;
-	salign = spos & 7;
-	dpos &= -8;
-	spos &= -8;
-
-	/* Compute the value for the PIXELSHIFT register.  This controls
-	   both non-co-aligned source and destination and copy direction.  */
-	if (dalign >= salign)
-		pixel_shift = dalign - salign;
-	else
-		pixel_shift = 8 - (salign - dalign);
-
-	/* Figure out if we need an additional priming step for the
-	   residue register.  */
-	need_prime = (salign > dalign);
-	if (need_prime)
-		dpos -= 8;
-
-	/* Begin by copying the leading unaligned destination.  Copy enough
-	   to make the next destination address 32-byte aligned.  */
-	copied = 32 - (dalign + (dpos & 31));
-	if (copied == 32)
-		copied = 0;
-	xincr_first = (copied + 7) & -8;
-	smask_first = dmask_first = (1ul << copied) - 1;
-	smask_first <<= salign;
-	dmask_first <<= dalign + need_prime*8;
-	if (need_prime && copied > 24)
-		copied -= 8;
-	left = width - copied;
-
-	/* Care for small copies.  */
-	if (copied > width) {
-		u32 t;
-		t = (1ul << width) - 1;
-		t <<= dalign + need_prime*8;
-		dmask_first &= t;
-		left = 0;
-	}
-
-	/* Attempt to use 64-byte copies.  This is only possible if the
-	   source and destination are co-aligned at 64 bytes.  */
-	n64 = need_second = 0;
-	if ((dpos & 63) == (spos & 63)
-	    && (height == 1 || line_length % 64 == 0)) {
-		/* We may need a 32-byte copy to ensure 64 byte alignment.  */
-		need_second = (dpos + xincr_first) & 63;
-		if ((need_second & 32) != need_second)
-			printk(KERN_ERR "tgafb: need_second wrong\n");
-		if (left >= need_second + 64) {
-			left -= need_second;
-			n64 = left / 64;
-			left %= 64;
-		} else
-			need_second = 0;
-	}
-
-	/* Copy trailing full 32-byte sections.  This will be the main
-	   loop if the 64 byte loop can't be used.  */
-	n32 = left / 32;
-	left %= 32;
-
-	/* Copy the trailing unaligned destination.  */
-	dmask_last = (1ul << left) - 1;
-
-	tga_regs = par->tga_regs_base;
-	tga_fb = par->tga_fb_base;
-
-	/* Set up the MODE and PIXELSHIFT registers.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG);
-	__raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG);
-	wmb();
-
-	for (i = 0; i < height; ++i) {
-		unsigned long j;
-		void __iomem *sfb;
-		void __iomem *dfb;
-
-		sfb = tga_fb + spos;
-		dfb = tga_fb + dpos;
-		if (dmask_first) {
-			__raw_writel(smask_first, sfb);
-			wmb();
-			__raw_writel(dmask_first, dfb);
-			wmb();
-			sfb += xincr_first;
-			dfb += xincr_first;
-		}
-
-		if (need_second) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63))
-			printk(KERN_ERR
-			       "tgafb: misaligned copy64 (s:%p, d:%p)\n",
-			       sfb, dfb);
-
-		for (j = 0; j < n64; ++j) {
-			__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
-			wmb();
-			__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
-			wmb();
-			sfb += 64;
-			dfb += 64;
-		}
-
-		for (j = 0; j < n32; ++j) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (dmask_last) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(dmask_last, dfb);
-			wmb();
-		}
-
-		spos += yincr;
-		dpos += yincr;
+	/* Do acceleration only if we are aligned on 8 pixels */
+	if ((dx | sx | width) & 7) {
+		cfb_copyarea(info, area);
+		return;
 	}
 
-	/* Reset the MODE register to normal.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
-}
-
-/* The (almost) general case of backward copy in 8bpp mode.  */
-static inline void
-copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length,
-		       const struct fb_copyarea *area)
-{
-	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, left, yincr;
-	unsigned long depos, sepos, dealign, sealign;
-	u32 mask_first, mask_last;
-	unsigned long n32;
-	void __iomem *tga_regs;
-	void __iomem *tga_fb;
-
 	yincr = line_length;
 	if (dy > sy) {
 		dy += height - 1;
 		sy += height - 1;
 		yincr = -yincr;
 	}
+	backward = dy == sy && dx > sx && dx < sx + width;
 
 	/* Compute the offsets and alignments in the frame buffer.
 	   More than anything else, these control how we do copies.  */
-	depos = dy * line_length + dx + width;
-	sepos = sy * line_length + sx + width;
-	dealign = depos & 7;
-	sealign = sepos & 7;
-
-	/* ??? The documentation appears to be incorrect (or very
-	   misleading) wrt how pixel shifting works in backward copy
-	   mode, i.e. when PIXELSHIFT is negative.  I give up for now.
-	   Do handle the common case of co-aligned backward copies,
-	   but frob everything else back on generic code.  */
-	if (dealign != sealign) {
-		cfb_copyarea(info, area);
-		return;
-	}
-
-	/* We begin the copy with the trailing pixels of the
-	   unaligned destination.  */
-	mask_first = (1ul << dealign) - 1;
-	left = width - dealign;
-
-	/* Care for small copies.  */
-	if (dealign > width) {
-		mask_first ^= (1ul << (dealign - width)) - 1;
-		left = 0;
-	}
+	depos = dy * line_length + dx;
+	sepos = sy * line_length + sx;
+	if (backward)
+		depos += width, sepos += width;
 
 	/* Next copy full words at a time.  */
-	n32 = left / 32;
-	left %= 32;
+	n32 = width / 32;
+	last_step = width % 32;
 
 	/* Finally copy the unaligned head of the span.  */
-	mask_last = -1 << (32 - left);
+	mask_last = (1ul << last_step) - 1;
+
+	if (!backward) {
+		step = 32;
+		last_step = 32;
+	} else {
+		step = -32;
+		last_step = -last_step;
+		sepos -= 32;
+		depos -= 32;
+	}
 
 	tga_regs = par->tga_regs_base;
 	tga_fb = par->tga_fb_base;
@@ -1374,25 +1212,33 @@ copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
 
 		sfb = tga_fb + sepos;
 		dfb = tga_fb + depos;
-		if (mask_first) {
-			__raw_writel(mask_first, sfb);
-			wmb();
-			__raw_writel(mask_first, dfb);
-			wmb();
-		}
 
-		for (j = 0; j < n32; ++j) {
-			sfb -= 32;
-			dfb -= 32;
+		for (j = 0; j < n32; j++) {
+			if (j < 2 && j + 1 < n32 && !backward &&
+			    !(((unsigned long)sfb | (unsigned long)dfb) & 63)) {
+				do {
+					__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
+					wmb();
+					__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
+					wmb();
+					sfb += 64;
+					dfb += 64;
+					j += 2;
+				} while (j + 1 < n32);
+				j--;
+				continue;
+			}
 			__raw_writel(0xffffffff, sfb);
 			wmb();
 			__raw_writel(0xffffffff, dfb);
 			wmb();
+			sfb += step;
+			dfb += step;
 		}
 
 		if (mask_last) {
-			sfb -= 32;
-			dfb -= 32;
+			sfb += last_step - step;
+			dfb += last_step - step;
 			__raw_writel(mask_last, sfb);
 			wmb();
 			__raw_writel(mask_last, dfb);
@@ -1453,14 +1299,9 @@ tgafb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 	else if (bpp == 32)
 		cfb_copyarea(info, area);
 
-	/* Detect overlapping source and destination that requires
-	   a backward copy.  */
-	else if (dy == sy && dx > sx && dx < sx + width)
-		copyarea_backward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length, area);
 	else
-		copyarea_foreward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length);
+		copyarea_8bpp(info, dx, dy, sx, sy, height,
+			      width, line_length, area);
 }
 
 
@@ -1476,6 +1317,7 @@ tgafb_init_fix(struct fb_info *info)
 	int tga_bus_tc = TGA_BUS_TC(par->dev);
 	u8 tga_type = par->tga_type;
 	const char *tga_type_name = NULL;
+	unsigned memory_size;
 
 	switch (tga_type) {
 	case TGA_TYPE_8PLANE:
@@ -1483,21 +1325,25 @@ tgafb_init_fix(struct fb_info *info)
 			tga_type_name = "Digital ZLXp-E1";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E1";
+		memory_size = 2097152;
 		break;
 	case TGA_TYPE_24PLANE:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E2";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E2";
+		memory_size = 8388608;
 		break;
 	case TGA_TYPE_24PLUSZ:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E3";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E3";
+		memory_size = 16777216;
 		break;
 	default:
 		tga_type_name = "Unknown";
+		memory_size = 16777216;
 		break;
 	}
 
@@ -1509,9 +1355,8 @@ tgafb_init_fix(struct fb_info *info)
 			    ? FB_VISUAL_PSEUDOCOLOR
 			    : FB_VISUAL_DIRECTCOLOR);
 
-	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 	info->fix.smem_start = (size_t) par->tga_fb_base;
-	info->fix.smem_len = info->fix.line_length * par->yres;
+	info->fix.smem_len = memory_size;
 	info->fix.mmio_start = (size_t) par->tga_regs_base;
 	info->fix.mmio_len = 512;
 
@@ -1635,6 +1480,9 @@ static int tgafb_register(struct device *dev)
 		modedb_tga = &modedb_tc;
 		modedbsize_tga = 1;
 	}
+
+	tgafb_init_fix(info);
+
 	ret = fb_find_mode(&info->var, info,
 			   mode_option ? mode_option : mode_option_tga,
 			   modedb_tga, modedbsize_tga, NULL,
@@ -1652,7 +1500,6 @@ static int tgafb_register(struct device *dev)
 	}
 
 	tgafb_set_par(info);
-	tgafb_init_fix(info);
 
 	if (register_framebuffer(info) < 0) {
 		printk(KERN_ERR "tgafb: Could not register framebuffer\n");
diff --git a/drivers/video/vexpress-dvi.c b/drivers/video/vexpress-dvi.c
new file mode 100644
index 000000000000..f08753450ee4
--- /dev/null
+++ b/drivers/video/vexpress-dvi.c
@@ -0,0 +1,220 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#define pr_fmt(fmt) "vexpress-dvi: " fmt
+
+#include <linux/fb.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/vexpress.h>
+
+
+static struct vexpress_config_func *vexpress_dvimode_func;
+
+static struct {
+	u32 xres, yres, mode;
+} vexpress_dvi_dvimodes[] = {
+	{ 640, 480, 0 }, /* VGA */
+	{ 800, 600, 1 }, /* SVGA */
+	{ 1024, 768, 2 }, /* XGA */
+	{ 1280, 1024, 3 }, /* SXGA */
+	{ 1600, 1200, 4 }, /* UXGA */
+	{ 1920, 1080, 5 }, /* HD1080 */
+};
+
+static void vexpress_dvi_mode_set(struct fb_info *info, u32 xres, u32 yres)
+{
+	int err = -ENOENT;
+	int i;
+
+	if (!vexpress_dvimode_func)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(vexpress_dvi_dvimodes); i++) {
+		if (vexpress_dvi_dvimodes[i].xres == xres &&
+				vexpress_dvi_dvimodes[i].yres == yres) {
+			pr_debug("mode: %ux%u = %d\n", xres, yres,
+					vexpress_dvi_dvimodes[i].mode);
+			err = vexpress_config_write(vexpress_dvimode_func, 0,
+					vexpress_dvi_dvimodes[i].mode);
+			break;
+		}
+	}
+
+	if (err)
+		pr_warn("Failed to set %ux%u mode! (%d)\n", xres, yres, err);
+}
+
+
+static struct vexpress_config_func *vexpress_muxfpga_func;
+static int vexpress_dvi_fb = -1;
+
+static int vexpress_dvi_mux_set(struct fb_info *info)
+{
+	int err;
+	u32 site = vexpress_get_site_by_dev(info->device);
+
+	if (!vexpress_muxfpga_func)
+		return -ENXIO;
+
+	err = vexpress_config_write(vexpress_muxfpga_func, 0, site);
+	if (!err) {
+		pr_debug("Selected MUXFPGA input %d (fb%d)\n", site,
+				info->node);
+		vexpress_dvi_fb = info->node;
+		vexpress_dvi_mode_set(info, info->var.xres,
+				info->var.yres);
+	} else {
+		pr_warn("Failed to select MUXFPGA input %d (fb%d)! (%d)\n",
+				site, info->node, err);
+	}
+
+	return err;
+}
+
+static int vexpress_dvi_fb_select(int fb)
+{
+	int err;
+	struct fb_info *info;
+
+	/* fb0 is the default */
+	if (fb < 0)
+		fb = 0;
+
+	info = registered_fb[fb];
+	if (!info || !lock_fb_info(info))
+		return -ENODEV;
+
+	err = vexpress_dvi_mux_set(info);
+
+	unlock_fb_info(info);
+
+	return err;
+}
+
+static ssize_t vexpress_dvi_fb_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", vexpress_dvi_fb);
+}
+
+static ssize_t vexpress_dvi_fb_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	long value;
+	int err = kstrtol(buf, 0, &value);
+
+	if (!err)
+		err = vexpress_dvi_fb_select(value);
+
+	return err ? err : count;
+}
+
+DEVICE_ATTR(fb, S_IRUGO | S_IWUSR, vexpress_dvi_fb_show,
+		vexpress_dvi_fb_store);
+
+
+static int vexpress_dvi_fb_event_notify(struct notifier_block *self,
+			      unsigned long action, void *data)
+{
+	struct fb_event *event = data;
+	struct fb_info *info = event->info;
+	struct fb_videomode *mode = event->data;
+
+	switch (action) {
+	case FB_EVENT_FB_REGISTERED:
+		if (vexpress_dvi_fb < 0)
+			vexpress_dvi_mux_set(info);
+		break;
+	case FB_EVENT_MODE_CHANGE:
+	case FB_EVENT_MODE_CHANGE_ALL:
+		if (info->node == vexpress_dvi_fb)
+			vexpress_dvi_mode_set(info, mode->xres, mode->yres);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vexpress_dvi_fb_notifier = {
+	.notifier_call = vexpress_dvi_fb_event_notify,
+};
+static bool vexpress_dvi_fb_notifier_registered;
+
+
+enum vexpress_dvi_func { FUNC_MUXFPGA, FUNC_DVIMODE };
+
+static struct of_device_id vexpress_dvi_of_match[] = {
+	{
+		.compatible = "arm,vexpress-muxfpga",
+		.data = (void *)FUNC_MUXFPGA,
+	}, {
+		.compatible = "arm,vexpress-dvimode",
+		.data = (void *)FUNC_DVIMODE,
+	},
+	{}
+};
+
+static int vexpress_dvi_probe(struct platform_device *pdev)
+{
+	enum vexpress_dvi_func func;
+	const struct of_device_id *match =
+			of_match_device(vexpress_dvi_of_match, &pdev->dev);
+
+	if (match)
+		func = (enum vexpress_dvi_func)match->data;
+	else
+		func = pdev->id_entry->driver_data;
+
+	switch (func) {
+	case FUNC_MUXFPGA:
+		vexpress_muxfpga_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		device_create_file(&pdev->dev, &dev_attr_fb);
+		break;
+	case FUNC_DVIMODE:
+		vexpress_dvimode_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		break;
+	}
+
+	if (!vexpress_dvi_fb_notifier_registered) {
+		fb_register_client(&vexpress_dvi_fb_notifier);
+		vexpress_dvi_fb_notifier_registered = true;
+	}
+
+	vexpress_dvi_fb_select(vexpress_dvi_fb);
+
+	return 0;
+}
+
+static const struct platform_device_id vexpress_dvi_id_table[] = {
+	{ .name = "vexpress-muxfpga", .driver_data = FUNC_MUXFPGA, },
+	{ .name = "vexpress-dvimode", .driver_data = FUNC_DVIMODE, },
+	{}
+};
+
+static struct platform_driver vexpress_dvi_driver = {
+	.probe = vexpress_dvi_probe,
+	.driver = {
+		.name = "vexpress-dvi",
+		.of_match_table = vexpress_dvi_of_match,
+	},
+	.id_table = vexpress_dvi_id_table,
+};
+
+static int __init vexpress_dvi_init(void)
+{
+	return platform_driver_register(&vexpress_dvi_driver);
+}
+device_initcall(vexpress_dvi_init);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 71af7b5abe01..7d7add5ceba4 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -311,6 +311,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index a7ce73029f59..933241a6ab10 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -791,6 +791,7 @@ static int virtio_pci_restore(struct device *dev)
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
 	struct virtio_driver *drv;
+	unsigned status = 0;
 	int ret;
 
 	drv = container_of(vp_dev->vdev.dev.driver,
@@ -801,14 +802,40 @@ static int virtio_pci_restore(struct device *dev)
 		return ret;
 
 	pci_set_master(pci_dev);
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	vp_reset(&vp_dev->vdev);
+
+	/* Acknowledge that we've seen the device. */
+	status |= VIRTIO_CONFIG_S_ACKNOWLEDGE;
+	vp_set_status(&vp_dev->vdev, status);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED;
+	vp_set_status(&vp_dev->vdev, status);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	status |= VIRTIO_CONFIG_S_DRIVER;
+	vp_set_status(&vp_dev->vdev, status);
+
 	vp_finalize_features(&vp_dev->vdev);
 
-	if (drv && drv->restore)
+	if (drv->restore) {
 		ret = drv->restore(&vp_dev->vdev);
+		if (ret) {
+			status |= VIRTIO_CONFIG_S_FAILED;
+			vp_set_status(&vp_dev->vdev, status);
+			return ret;
+		}
+	}
 
 	/* Finally, tell the device we're all set */
-	if (!ret)
-		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+	status |= VIRTIO_CONFIG_S_DRIVER_OK;
+	vp_set_status(&vp_dev->vdev, status);
 
 	return ret;
 }
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index 64bfea314429..8ca1030675a6 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -880,7 +880,7 @@ static ssize_t ca91cx42_master_read(struct vme_master_resource *image,
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			*(u8 *)(buf + done) = ioread8(addr + done);
 			done += 1;
@@ -934,7 +934,7 @@ static ssize_t ca91cx42_master_write(struct vme_master_resource *image,
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			iowrite8(*(u8 *)(buf + done), addr + done);
 			done += 1;
diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c
index 9c1aa4dc39c9..63424060b04f 100644
--- a/drivers/vme/bridges/vme_tsi148.c
+++ b/drivers/vme/bridges/vme_tsi148.c
@@ -1283,7 +1283,7 @@ static ssize_t tsi148_master_read(struct vme_master_resource *image, void *buf,
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			*(u8 *)(buf + done) = ioread8(addr + done);
 			done += 1;
@@ -1365,7 +1365,7 @@ static ssize_t tsi148_master_write(struct vme_master_resource *image, void *buf,
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			iowrite8(*(u8 *)(buf + done), addr + done);
 			done += 1;
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index 40788c925d1c..73705aff53cb 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -54,28 +54,29 @@ static void w1_send_slave(struct w1_master *dev, u64 rn)
 	struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1);
 	struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1);
 	int avail;
+	u64 *data;
 
 	/* update kernel slave list */
 	w1_slave_found(dev, rn);
 
 	avail = dev->priv_size - cmd->len;
 
-	if (avail > 8) {
-		u64 *data = (void *)(cmd + 1) + cmd->len;
+	if (avail < 8) {
+		msg->ack++;
+		cn_netlink_send(msg, 0, GFP_KERNEL);
 
-		*data = rn;
-		cmd->len += 8;
-		hdr->len += 8;
-		msg->len += 8;
-		return;
+		msg->len = sizeof(struct w1_netlink_msg) +
+			sizeof(struct w1_netlink_cmd);
+		hdr->len = sizeof(struct w1_netlink_cmd);
+		cmd->len = 0;
 	}
 
-	msg->ack++;
-	cn_netlink_send(msg, 0, GFP_KERNEL);
+	data = (void *)(cmd + 1) + cmd->len;
 
-	msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd);
-	hdr->len = sizeof(struct w1_netlink_cmd);
-	cmd->len = 0;
+	*data = rn;
+	cmd->len += 8;
+	hdr->len += 8;
+	msg->len += 8;
 }
 
 static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg,
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 37cb09b27b63..c97a47ca8971 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -20,6 +20,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -91,6 +92,15 @@ static inline void ath79_wdt_keepalive(void)
 static inline void ath79_wdt_enable(void)
 {
 	ath79_wdt_keepalive();
+
+	/*
+	 * Updating the TIMER register requires a few microseconds
+	 * on the AR934x SoCs at least. Use a small delay to ensure
+	 * that the TIMER register is updated within the hardware
+	 * before enabling the watchdog.
+	 */
+	udelay(2);
+
 	ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR);
 	/* flush write */
 	ath79_wdt_rr(WDOG_REG_CTRL);
diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c
index 3fb83b0c28c2..ab6d3f56cbca 100644
--- a/drivers/watchdog/sc1200wdt.c
+++ b/drivers/watchdog/sc1200wdt.c
@@ -409,8 +409,9 @@ static int __init sc1200wdt_init(void)
 #if defined CONFIG_PNP
 	/* now that the user has specified an IO port and we haven't detected
 	 * any devices, disable pnp support */
+	if (isapnp)
+		pnp_unregister_driver(&scl200wdt_pnp_driver);
 	isapnp = 0;
-	pnp_unregister_driver(&scl200wdt_pnp_driver);
 #endif
 
 	if (!request_region(io, io_len, SC1200_MODULE_NAME)) {
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 8872642505c0..e42118213ba5 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -60,7 +60,6 @@
  * @adev: amba device structure of wdt
  * @status: current status of wdt
  * @load_val: load value to be set for current timeout
- * @timeout: current programmed timeout
  */
 struct sp805_wdt {
 	struct watchdog_device		wdd;
@@ -69,7 +68,6 @@ struct sp805_wdt {
 	struct clk			*clk;
 	struct amba_device		*adev;
 	unsigned int			load_val;
-	unsigned int			timeout;
 };
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -99,7 +97,7 @@ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout)
 	spin_lock(&wdt->lock);
 	wdt->load_val = load;
 	/* roundup timeout to closest positive integer value */
-	wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
+	wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
 	spin_unlock(&wdt->lock);
 
 	return 0;
diff --git a/drivers/watchdog/ts72xx_wdt.c b/drivers/watchdog/ts72xx_wdt.c
index b8a92459f10f..9ad2bd344eb4 100644
--- a/drivers/watchdog/ts72xx_wdt.c
+++ b/drivers/watchdog/ts72xx_wdt.c
@@ -310,7 +310,8 @@ static long ts72xx_wdt_ioctl(struct file *file, unsigned int cmd,
 
 	case WDIOC_GETSTATUS:
 	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
+		error = put_user(0, p);
+		break;
 
 	case WDIOC_KEEPALIVE:
 		ts72xx_wdt_kick(wdt);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index d5418c1be9aa..840604ed0235 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -920,9 +920,10 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		ret = m2p_add_override(mfn, pages[i], kmap_ops ?
 				       &kmap_ops[i] : NULL);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+ out:
 	if (lazy)
 		arch_leave_lazy_mmu_mode();
 
@@ -953,9 +954,10 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		ret = m2p_remove_override(pages[i], kmap_ops ?
 				       &kmap_ops[i] : NULL);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+ out:
 	if (lazy)
 		arch_leave_lazy_mmu_mode();
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1d94316f0ea4..301b08496478 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -390,7 +390,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
+		swiotlb_tbl_unmap_single(hwdev, dev_addr, size, dir);
 		return;
 	}
 
diff --git a/fs/aio.c b/fs/aio.c
index 2bbcacf74d0c..ded94c4fa30d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -310,7 +310,6 @@ static void free_ioctx(struct kioctx *ctx)
 
 		avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
 
-		atomic_sub(avail, &ctx->reqs_active);
 		head += avail;
 		head %= ctx->nr_events;
 	}
@@ -423,10 +422,12 @@ static void kill_ioctx_rcu(struct rcu_head *head)
  *	when the processes owning a context have all exited to encourage
  *	the rapid destruction of the kioctx.
  */
-static void kill_ioctx(struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
 {
 	if (!atomic_xchg(&ctx->dead, 1)) {
+		spin_lock(&mm->ioctx_lock);
 		hlist_del_rcu(&ctx->list);
+		spin_unlock(&mm->ioctx_lock);
 
 		/*
 		 * It'd be more correct to do this in free_ioctx(), after all
@@ -494,7 +495,7 @@ void exit_aio(struct mm_struct *mm)
 		 */
 		ctx->mmap_size = 0;
 
-		kill_ioctx(ctx);
+		kill_ioctx(mm, ctx);
 	}
 }
 
@@ -676,6 +677,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 put_rq:
 	/* everything turned out well, dispose of the aiocb. */
 	aio_put_req(iocb);
+	atomic_dec(&ctx->reqs_active);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -715,6 +717,8 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	if (head == ctx->tail)
 		goto out;
 
+	head %= ctx->nr_events;
+
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
@@ -753,8 +757,6 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	flush_dcache_page(ctx->ring_pages[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, ctx->tail);
-
-	atomic_sub(ret, &ctx->reqs_active);
 out:
 	mutex_unlock(&ctx->ring_lock);
 
@@ -852,7 +854,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
 		if (ret)
-			kill_ioctx(ioctx);
+			kill_ioctx(current->mm, ioctx);
 		put_ioctx(ioctx);
 	}
 
@@ -870,7 +872,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 {
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
-		kill_ioctx(ioctx);
+		kill_ioctx(current->mm, ioctx);
 		put_ioctx(ioctx);
 		return 0;
 	}
diff --git a/fs/attr.c b/fs/attr.c
index 1449adb14ef6..66fa6251c398 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 	if ((ia_valid & ATTR_UID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	     !uid_eq(attr->ia_uid, inode->i_uid)) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 		/* Also check the setgid bit! */
 		if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
 				inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
@@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		umode_t mode = attr->ia_mode;
 
 		if (!in_group_p(inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
@@ -182,11 +182,6 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 			return -EPERM;
 	}
 
-	if ((ia_valid & ATTR_SIZE) && IS_I_VERSION(inode)) {
-		if (attr->ia_size != inode->i_size)
-			inode_inc_iversion(inode);
-	}
-
 	if ((ia_valid & ATTR_MODE)) {
 		umode_t amode = attr->ia_mode;
 		/* Flag setting protected by i_mutex */
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f8a0b0efda44..3aac8e9edac3 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1415,7 +1415,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
  *   long file_ofs
  * followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL...
  */
-static void fill_files_note(struct memelfnote *note)
+static int fill_files_note(struct memelfnote *note)
 {
 	struct vm_area_struct *vma;
 	unsigned count, size, names_ofs, remaining, n;
@@ -1430,11 +1430,11 @@ static void fill_files_note(struct memelfnote *note)
 	names_ofs = (2 + 3 * count) * sizeof(data[0]);
  alloc:
 	if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
-		goto err;
+		return -EINVAL;
 	size = round_up(size, PAGE_SIZE);
 	data = vmalloc(size);
 	if (!data)
-		goto err;
+		return -ENOMEM;
 
 	start_end_ofs = data + 2;
 	name_base = name_curpos = ((char *)data) + names_ofs;
@@ -1487,7 +1487,7 @@ static void fill_files_note(struct memelfnote *note)
 
 	size = name_curpos - (char *)data;
 	fill_note(note, "CORE", NT_FILE, size, data);
- err: ;
+	return 0;
 }
 
 #ifdef CORE_DUMP_USE_REGSET
@@ -1688,8 +1688,8 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 	fill_auxv_note(&info->auxv, current->mm);
 	info->size += notesize(&info->auxv);
 
-	fill_files_note(&info->files);
-	info->size += notesize(&info->files);
+	if (fill_files_note(&info->files) == 0)
+		info->size += notesize(&info->files);
 
 	return 1;
 }
@@ -1721,7 +1721,8 @@ static int write_note_info(struct elf_note_info *info,
 			return 0;
 		if (first && !writenote(&info->auxv, file, foffset))
 			return 0;
-		if (first && !writenote(&info->files, file, foffset))
+		if (first && info->files.data &&
+				!writenote(&info->files, file, foffset))
 			return 0;
 
 		for (i = 1; i < info->thread_notes; ++i)
@@ -1808,6 +1809,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
 
 struct elf_note_info {
 	struct memelfnote *notes;
+	struct memelfnote *notes_files;
 	struct elf_prstatus *prstatus;	/* NT_PRSTATUS */
 	struct elf_prpsinfo *psinfo;	/* NT_PRPSINFO */
 	struct list_head thread_list;
@@ -1898,9 +1900,12 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 
 	fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo);
 	fill_auxv_note(info->notes + 3, current->mm);
-	fill_files_note(info->notes + 4);
+	info->numnote = 4;
 
-	info->numnote = 5;
+	if (fill_files_note(info->notes + info->numnote) == 0) {
+		info->notes_files = info->notes + info->numnote;
+		info->numnote++;
+	}
 
 	/* Try to dump the FPU. */
 	info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs,
@@ -1962,8 +1967,9 @@ static void free_note_info(struct elf_note_info *info)
 		kfree(list_entry(tmp, struct elf_thread_status, list));
 	}
 
-	/* Free data allocated by fill_files_note(): */
-	vfree(info->notes[4].data);
+	/* Free data possibly allocated by fill_files_note(): */
+	if (info->notes_files)
+		vfree(info->notes_files->data);
 
 	kfree(info->prstatus);
 	kfree(info->psinfo);
@@ -2046,7 +2052,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	struct vm_area_struct *vma, *gate_vma;
 	struct elfhdr *elf = NULL;
 	loff_t offset = 0, dataoff, foffset;
-	struct elf_note_info info;
+	struct elf_note_info info = { };
 	struct elf_phdr *phdr4note = NULL;
 	struct elf_shdr *shdr4extnum = NULL;
 	Elf_Half e_phnum;
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 8fb42916d8a2..433c3b828e1d 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -114,6 +114,14 @@ void bio_integrity_free(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_integrity_free);
 
+static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
+{
+	if (bip->bip_slab == BIO_POOL_NONE)
+		return BIP_INLINE_VECS;
+
+	return bvec_nr_vecs(bip->bip_slab);
+}
+
 /**
  * bio_integrity_add_page - Attach integrity metadata
  * @bio:	bio to update
@@ -129,7 +137,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct bio_vec *iv;
 
-	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
+	if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
 		printk(KERN_ERR "%s: bip_vec full\n", __func__);
 		return 0;
 	}
@@ -450,7 +458,7 @@ static int bio_integrity_verify(struct bio *bio)
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
-	bio_for_each_segment(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
 		bix.data_buf = kaddr + bv->bv_offset;
 		bix.data_size = bv->bv_len;
@@ -734,7 +742,7 @@ void bioset_integrity_free(struct bio_set *bs)
 		mempool_destroy(bs->bio_integrity_pool);
 
 	if (bs->bvec_integrity_pool)
-		mempool_destroy(bs->bio_integrity_pool);
+		mempool_destroy(bs->bvec_integrity_pool);
 }
 EXPORT_SYMBOL(bioset_integrity_free);
 
diff --git a/fs/bio.c b/fs/bio.c
index c5eae7251490..5e7507d79297 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -917,8 +917,8 @@ void bio_copy_data(struct bio *dst, struct bio *src)
 		src_p = kmap_atomic(src_bv->bv_page);
 		dst_p = kmap_atomic(dst_bv->bv_page);
 
-		memcpy(dst_p + dst_bv->bv_offset,
-		       src_p + src_bv->bv_offset,
+		memcpy(dst_p + dst_offset,
+		       src_p + src_offset,
 		       bytes);
 
 		kunmap_atomic(dst_p);
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index e15d2b0d8d3b..0890c83643e9 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -229,7 +229,7 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans,
 		if (ret > 0) {
 			/* we need an acl */
 			ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS);
-		} else {
+		} else if (ret < 0) {
 			cache_no_acl(inode);
 		}
 	} else {
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 290e347b6db3..d85f90c92bb4 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1347,9 +1347,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
  * returns <0 on error
  */
 static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				struct btrfs_extent_inline_ref **out_eiref,
-				int *out_type)
+				   struct btrfs_key *key,
+				   struct btrfs_extent_item *ei, u32 item_size,
+				   struct btrfs_extent_inline_ref **out_eiref,
+				   int *out_type)
 {
 	unsigned long end;
 	u64 flags;
@@ -1359,19 +1360,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
 		/* first call */
 		flags = btrfs_extent_flags(eb, ei);
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-			info = (struct btrfs_tree_block_info *)(ei + 1);
-			*out_eiref =
-				(struct btrfs_extent_inline_ref *)(info + 1);
+			if (key->type == BTRFS_METADATA_ITEM_KEY) {
+				/* a skinny metadata extent */
+				*out_eiref =
+				     (struct btrfs_extent_inline_ref *)(ei + 1);
+			} else {
+				WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+				info = (struct btrfs_tree_block_info *)(ei + 1);
+				*out_eiref =
+				   (struct btrfs_extent_inline_ref *)(info + 1);
+			}
 		} else {
 			*out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
 		}
 		*ptr = (unsigned long)*out_eiref;
-		if ((void *)*ptr >= (void *)ei + item_size)
+		if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
 			return -ENOENT;
 	}
 
 	end = (unsigned long)ei + item_size;
-	*out_eiref = (struct btrfs_extent_inline_ref *)*ptr;
+	*out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
 	*out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
@@ -1390,8 +1398,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
  * <0 on error.
  */
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level)
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level)
 {
 	int ret;
 	int type;
@@ -1402,8 +1410,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 		return 1;
 
 	while (1) {
-		ret = __get_extent_inline_ref(ptr, eb, ei, item_size,
-						&eiref, &type);
+		ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+					      &eiref, &type);
 		if (ret < 0)
 			return ret;
 
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 0f446d7ca2c0..526d09e70c93 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -42,8 +42,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 			u64 *flags);
 
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level);
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level);
 
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				u64 extent_item_objectid,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b189bd1e7a3e..ce7067881d36 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1009,6 +1009,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 		bytes = min(bytes, working_bytes);
 		kaddr = kmap_atomic(page_out);
 		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+		if (*pg_index == (vcnt - 1) && *pg_offset == 0)
+			memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
 		kunmap_atomic(kaddr);
 		flush_dcache_page(page_out);
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index f26f38ccd194..019fc5a68a14 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1843,6 +1843,14 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_node *delayed_node;
 	int ret = 0;
 
+	/*
+	 * we don't do delayed inode updates during log recovery because it
+	 * leads to enospc problems.  This means we also can't do
+	 * delayed inode refs
+	 */
+	if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+		return -EAGAIN;
+
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b8b60b660c8f..7360f03ddbe1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3161,6 +3161,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors_send++;
 			continue;
@@ -3175,6 +3177,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
 	/* wait for all the barriers */
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors_wait++;
 			continue;
@@ -3514,6 +3518,11 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_free_block_groups(fs_info);
 
+	/*
+	 * we must make sure there is not any read request to
+	 * submit after we stopping all workers.
+	 */
+	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
 	del_fs_roots(fs_info);
@@ -3848,12 +3857,6 @@ again:
 		if (ret)
 			break;
 
-		/* opt_discard */
-		if (btrfs_test_opt(root, DISCARD))
-			ret = btrfs_error_discard_extent(root, start,
-							 end + 1 - start,
-							 NULL);
-
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0b272d068337..f99c71e40f8b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2402,6 +2402,8 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 			default:
 				WARN_ON(1);
 			}
+		} else {
+			list_del_init(&locked_ref->cluster);
 		}
 		spin_unlock(&delayed_refs->lock);
 
@@ -2424,7 +2426,6 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 		 * list before we release it.
 		 */
 		if (btrfs_delayed_ref_is_head(ref)) {
-			list_del_init(&locked_ref->cluster);
 			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 		}
@@ -5276,7 +5277,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	update_global_block_rsv(fs_info);
 }
 
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+			      const bool return_free_space)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -5300,7 +5302,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 
 		if (start < cache->last_byte_to_unpin) {
 			len = min(len, cache->last_byte_to_unpin - start);
-			btrfs_add_free_space(cache, start, len);
+			if (return_free_space)
+				btrfs_add_free_space(cache, start, len);
 		}
 
 		start += len;
@@ -5363,7 +5366,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
-		unpin_extent_range(root, start, end);
+		unpin_extent_range(root, start, end, true);
 		cond_resched();
 	}
 
@@ -7490,7 +7493,7 @@ out:
 	 */
 	if (root_dropped == false)
 		btrfs_add_dead_root(root);
-	if (err)
+	if (err && err != -EAGAIN)
 		btrfs_std_error(root->fs_info, err);
 	return err;
 }
@@ -8563,7 +8566,7 @@ out:
 
 int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 {
-	return unpin_extent_range(root, start, end);
+	return unpin_extent_range(root, start, end, false);
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e7e7afb4a872..84ceff6abbc1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1624,6 +1624,7 @@ again:
 		 * shortening the size of the delalloc range we're searching
 		 */
 		free_extent_state(cached_state);
+		cached_state = NULL;
 		if (!loops) {
 			unsigned long offset = (*start) & (PAGE_CACHE_SIZE - 1);
 			max_bytes = PAGE_CACHE_SIZE - offset;
@@ -2356,7 +2357,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
-	int ret;
+	int ret = 0;
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
@@ -2370,6 +2371,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
+		ret = ret < 0 ? ret : -EIO;
+		mapping_set_error(page->mapping, ret);
 	}
 	return 0;
 }
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a4a7a1a8da95..0a3809500599 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -263,8 +263,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	if (!em)
 		goto out;
 
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
-		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b193bf324a41..e4bcfec7787e 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -403,7 +403,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	ret = 0;
 fail:
 	while (ret < 0 && !list_empty(&tmplist)) {
-		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+		sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -754,7 +754,7 @@ again:
 				found_next = 1;
 			if (ret != 0)
 				goto insert;
-			slot = 0;
+			slot = path->slots[0];
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
 		if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e53009657f0e..0cbe95dc8113 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -835,7 +835,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 
 	if (!matched) {
 		__btrfs_remove_free_space_cache(ctl);
-		btrfs_err(fs_info, "block group %llu has wrong amount of free space",
+		btrfs_warn(fs_info, "block group %llu has wrong amount of free space",
 			block_group->key.objectid);
 		ret = -1;
 	}
@@ -847,7 +847,7 @@ out:
 		spin_unlock(&block_group->lock);
 		ret = 0;
 
-		btrfs_err(fs_info, "failed to load free space cache for block group %llu",
+		btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
 			block_group->key.objectid);
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17f3064b4a3e..187911fbabce 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2419,10 +2419,23 @@ out_unlock:
 	return ret;
 }
 
+static void free_sa_defrag_extent(struct new_sa_defrag_extent *new)
+{
+	struct old_sa_defrag_extent *old, *tmp;
+
+	if (!new)
+		return;
+
+	list_for_each_entry_safe(old, tmp, &new->head, list) {
+		list_del(&old->list);
+		kfree(old);
+	}
+	kfree(new);
+}
+
 static void relink_file_extents(struct new_sa_defrag_extent *new)
 {
 	struct btrfs_path *path;
-	struct old_sa_defrag_extent *old, *tmp;
 	struct sa_defrag_extent_backref *backref;
 	struct sa_defrag_extent_backref *prev = NULL;
 	struct inode *inode;
@@ -2465,16 +2478,11 @@ static void relink_file_extents(struct new_sa_defrag_extent *new)
 	kfree(prev);
 
 	btrfs_free_path(path);
-
-	list_for_each_entry_safe(old, tmp, &new->head, list) {
-		list_del(&old->list);
-		kfree(old);
-	}
 out:
+	free_sa_defrag_extent(new);
+
 	atomic_dec(&root->fs_info->defrag_running);
 	wake_up(&root->fs_info->transaction_wait);
-
-	kfree(new);
 }
 
 static struct new_sa_defrag_extent *
@@ -2484,7 +2492,7 @@ record_old_file_extents(struct inode *inode,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct old_sa_defrag_extent *old, *tmp;
+	struct old_sa_defrag_extent *old;
 	struct new_sa_defrag_extent *new;
 	int ret;
 
@@ -2532,7 +2540,7 @@ record_old_file_extents(struct inode *inode,
 		if (slot >= btrfs_header_nritems(l)) {
 			ret = btrfs_next_leaf(root, path);
 			if (ret < 0)
-				goto out_free_list;
+				goto out_free_path;
 			else if (ret > 0)
 				break;
 			continue;
@@ -2561,7 +2569,7 @@ record_old_file_extents(struct inode *inode,
 
 		old = kmalloc(sizeof(*old), GFP_NOFS);
 		if (!old)
-			goto out_free_list;
+			goto out_free_path;
 
 		offset = max(new->file_pos, key.offset);
 		end = min(new->file_pos + new->len, key.offset + num_bytes);
@@ -2583,15 +2591,10 @@ next:
 
 	return new;
 
-out_free_list:
-	list_for_each_entry_safe(old, tmp, &new->head, list) {
-		list_del(&old->list);
-		kfree(old);
-	}
 out_free_path:
 	btrfs_free_path(path);
 out_kfree:
-	kfree(new);
+	free_sa_defrag_extent(new);
 	return NULL;
 }
 
@@ -2652,7 +2655,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			EXTENT_DEFRAG, 1, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
-		if (last_snapshot >= BTRFS_I(inode)->generation)
+		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
 			/* the inode is shared */
 			new = record_old_file_extents(inode, ordered_extent);
 
@@ -2743,8 +2746,14 @@ out:
 	btrfs_remove_ordered_extent(inode, ordered_extent);
 
 	/* for snapshot-aware defrag */
-	if (new)
-		relink_file_extents(new);
+	if (new) {
+		if (ret) {
+			free_sa_defrag_extent(new);
+			atomic_dec(&root->fs_info->defrag_running);
+		} else {
+			relink_file_extents(new);
+		}
+	}
 
 	/* once for us */
 	btrfs_put_ordered_extent(ordered_extent);
@@ -3536,7 +3545,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * without delay
 	 */
 	if (!btrfs_is_free_space_inode(inode)
-	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+	    && !root->fs_info->log_root_recovering) {
 		btrfs_update_root_times(trans, root);
 
 		ret = btrfs_delayed_update_inode(trans, root, inode);
@@ -4518,8 +4528,12 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	 * these flags set.  For all other operations the VFS set these flags
 	 * explicitly if it wants a timestamp update.
 	 */
-	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
-		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+	if (newsize != oldsize) {
+		inode_inc_iversion(inode);
+		if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
+			inode->i_ctime = inode->i_mtime =
+				current_fs_time(inode->i_sb);
+	}
 
 	if (newsize > oldsize) {
 		truncate_pagecache(inode, oldsize, newsize);
@@ -8146,7 +8160,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 
 	/* check for collisions, even if the  name isn't there */
-	ret = btrfs_check_dir_item_collision(root, new_dir->i_ino,
+	ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino,
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8dedf4019672..783906c687b5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1528,6 +1528,12 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 			printk(KERN_INFO "btrfs: Snapshot src from "
 			       "another FS\n");
 			ret = -EINVAL;
+		} else if (!inode_owner_or_capable(src_inode)) {
+			/*
+			 * Subvolume creation is not restricted, but snapshots
+			 * are limited to own subvolumes only
+			 */
+			ret = -EPERM;
 		} else {
 			ret = btrfs_mksubvol(&file->f_path, name, namelen,
 					     BTRFS_I(src_inode)->root,
@@ -2093,7 +2099,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 
 	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	if (err == -EINTR)
-		goto out;
+		goto out_drop_write;
 	dentry = lookup_one_len(vol_args->name, parent, namelen);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
@@ -2235,6 +2241,7 @@ out_dput:
 	dput(dentry);
 out_unlock_dir:
 	mutex_unlock(&dir->i_mutex);
+out_drop_write:
 	mnt_drop_write_file(file);
 out:
 	kfree(vol_args);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4febca4fc2de..0e7f7765b3bb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -691,6 +691,7 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
 	int cowonly;
 	int ret;
 	int err = 0;
+	bool need_check = true;
 
 	path1 = btrfs_alloc_path();
 	path2 = btrfs_alloc_path();
@@ -914,6 +915,7 @@ again:
 			cur->bytenr);
 
 		lower = cur;
+		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
 			if (!path2->nodes[level]) {
 				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
@@ -957,18 +959,19 @@ again:
 
 				/*
 				 * add the block to pending list if we
-				 * need check its backrefs. only block
-				 * at 'cur->level + 1' is added to the
-				 * tail of pending list. this guarantees
-				 * we check backrefs from lower level
-				 * blocks to upper level blocks.
+				 * need check its backrefs, we only do this once
+				 * while walking up a tree as we will catch
+				 * anything else later on.
 				 */
-				if (!upper->checked &&
-				    level == cur->level + 1) {
+				if (!upper->checked && need_check) {
+					need_check = false;
 					list_add_tail(&edge->list[UPPER],
 						      &list);
-				} else
+				} else {
+					if (upper->checked)
+						need_check = true;
 					INIT_LIST_HEAD(&edge->list[UPPER]);
+				}
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index eb84c2db1aca..e4f69e3b78b9 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -545,8 +545,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
-			ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
-							&ref_root, &ref_level);
+			ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
+						      item_size, &ref_root,
+						      &ref_level);
 			printk_in_rcu(KERN_WARNING
 				"btrfs: %s at logical %llu on dev %s, "
 				"sector %llu: metadata %s (level %d) in tree "
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ba9690b9ae24..414c1b9eb896 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1550,6 +1550,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root,
 		goto out;
 	}
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+	if (key.type == BTRFS_ROOT_ITEM_KEY) {
+		ret = -ENOENT;
+		goto out;
+	}
 	*found_inode = key.objectid;
 	*found_type = btrfs_dir_type(path->nodes[0], di);
 
@@ -2524,7 +2528,8 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
 		di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
 		btrfs_dir_item_key_to_cpu(eb, di, &di_key);
 
-		if (di_key.objectid < sctx->send_progress) {
+		if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
+		    di_key.objectid < sctx->send_progress) {
 			ret = 1;
 			goto out;
 		}
@@ -4622,8 +4627,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	}
 
 	if (!access_ok(VERIFY_READ, arg->clone_sources,
-			sizeof(*arg->clone_sources *
-			arg->clone_sources_count))) {
+			sizeof(*arg->clone_sources) *
+			arg->clone_sources_count)) {
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0544587d74f4..1f214689fa5e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -524,7 +524,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 		if (transid <= root->fs_info->last_trans_committed)
 			goto out;
 
-		ret = -EINVAL;
 		/* find specified transaction */
 		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -540,9 +539,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 			}
 		}
 		spin_unlock(&root->fs_info->trans_lock);
-		/* The specified transaction doesn't exist */
-		if (!cur_trans)
+
+		/*
+		 * The specified transaction doesn't exist, or we
+		 * raced with btrfs_commit_transaction
+		 */
+		if (!cur_trans) {
+			if (transid > root->fs_info->last_trans_committed)
+				ret = -EINVAL;
 			goto out;
+		}
 	} else {
 		/* find newest transaction that is committing | committed */
 		spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index cf68596b51fb..bca436330681 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3314,7 +3314,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 		btrfs_set_token_file_extent_type(leaf, fi,
 						 BTRFS_FILE_EXTENT_REG,
 						 &token);
-		if (em->block_start == 0)
+		if (em->block_start == EXTENT_MAP_HOLE)
 			skip_csum = true;
 	}
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8bffb9174afb..7fc774639a78 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1384,6 +1384,22 @@ out:
 	return ret;
 }
 
+/*
+ * Function to update ctime/mtime for a given device path.
+ * Mainly used for ctime/mtime based probe like libblkid.
+ */
+static void update_dev_time(char *path_name)
+{
+	struct file *filp;
+
+	filp = filp_open(path_name, O_RDWR, 0);
+	if (!filp)
+		return;
+	file_update_time(filp);
+	filp_close(filp, NULL);
+	return;
+}
+
 static int btrfs_rm_dev_item(struct btrfs_root *root,
 			     struct btrfs_device *device)
 {
@@ -1612,11 +1628,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		struct btrfs_fs_devices *fs_devices;
 		fs_devices = root->fs_info->fs_devices;
 		while (fs_devices) {
-			if (fs_devices->seed == cur_devices)
+			if (fs_devices->seed == cur_devices) {
+				fs_devices->seed = cur_devices->seed;
 				break;
+			}
 			fs_devices = fs_devices->seed;
 		}
-		fs_devices->seed = cur_devices->seed;
 		cur_devices->seed = NULL;
 		lock_chunks(root);
 		__btrfs_close_devices(cur_devices);
@@ -1642,10 +1659,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 
 	ret = 0;
 
-	/* Notify udev that device has changed */
-	if (bdev)
+	if (bdev) {
+		/* Notify udev that device has changed */
 		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
+		/* Update ctime/mtime for device path for libblkid */
+		update_dev_time(device_path);
+	}
+
 error_brelse:
 	brelse(bh);
 	if (bdev)
@@ -1817,7 +1838,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
-	fs_devices->total_devices = 0;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -2089,6 +2109,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		ret = btrfs_commit_transaction(trans, root);
 	}
 
+	/* Update ctime/mtime for libblkid */
+	update_dev_time(device_path);
 	return ret;
 
 error_trans:
@@ -4248,6 +4270,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		btrfs_emerg(fs_info, "Invalid mapping for %Lu-%Lu, got "
 			    "%Lu-%Lu\n", logical, logical+len, em->start,
 			    em->start + em->len);
+		free_extent_map(em);
 		return 1;
 	}
 
@@ -4429,6 +4452,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		btrfs_crit(fs_info, "found a bad mapping, wanted %Lu, "
 			   "found %Lu-%Lu\n", logical, em->start,
 			   em->start + em->len);
+		free_extent_map(em);
 		return -EINVAL;
 	}
 
diff --git a/fs/buffer.c b/fs/buffer.c
index d2a4d1bb2d57..83fedaa53b55 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -620,14 +620,16 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
 static void __set_page_dirty(struct page *page,
 		struct address_space *mapping, int warn)
 {
-	spin_lock_irq(&mapping->tree_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
@@ -983,7 +985,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 		bh = page_buffers(page);
 		if (bh->b_size == size) {
 			end_block = init_page_buffers(page, bdev,
-						index << sizebits, size);
+						(sector_t)index << sizebits,
+						size);
 			goto done;
 		}
 		if (!try_to_free_buffers(page))
@@ -1004,7 +1007,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	 */
 	spin_lock(&inode->i_mapping->private_lock);
 	link_dev_buffers(page, bh);
-	end_block = init_page_buffers(page, bdev, index << sizebits, size);
+	end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+			size);
 	spin_unlock(&inode->i_mapping->private_lock);
 done:
 	ret = (block < end_block) ? 1 : -ENXIO;
@@ -2014,6 +2018,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
 	int i_size_changed = 0;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2033,6 +2038,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
 	 * makes the holding time of page lock longer. Second, it forces lock
@@ -2250,6 +2257,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		err = 0;
 
 		balance_dirty_pages_ratelimited(mapping);
+
+		if (unlikely(fatal_signal_pending(current))) {
+			err = -EINTR;
+			goto out;
+		}
 	}
 
 	/* page covers the boundary, find the boundary offset */
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3e68ac101040..5da06f020986 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -213,9 +213,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		goto out;
-	} else if (err < PAGE_CACHE_SIZE) {
+	} else {
+		if (err < PAGE_CACHE_SIZE) {
 		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+			zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		} else {
+			flush_dcache_page(page);
+		}
 	}
 	SetPageUptodate(page);
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 656e16907430..5de16f5ac7e9 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -313,9 +313,9 @@ static int striped_read(struct inode *inode,
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	u64 pos, this_len;
+	u64 pos, this_len, left;
 	int io_align, page_align;
-	int left, pages_left;
+	int pages_left;
 	int read;
 	struct page **page_pos;
 	int ret;
@@ -346,47 +346,40 @@ more:
 		ret = 0;
 	hit_stripe = this_len < left;
 	was_short = ret >= 0 && ret < this_len;
-	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
+	dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
 	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
 
-	if (ret > 0) {
-		int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
-
-		if (read < pos - off) {
-			dout(" zero gap %llu to %llu\n", off + read, pos);
-			ceph_zero_page_vector_range(page_align + read,
-						    pos - off - read, pages);
+	if (ret >= 0) {
+		int didpages;
+		if (was_short && (pos + ret < inode->i_size)) {
+			u64 tmp = min(this_len - ret,
+					inode->i_size - pos - ret);
+			dout(" zero gap %llu to %llu\n",
+				pos + ret, pos + ret + tmp);
+			ceph_zero_page_vector_range(page_align + read + ret,
+							tmp, pages);
+			ret += tmp;
 		}
+
+		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
 		pos += ret;
 		read = pos - off;
 		left -= ret;
 		page_pos += didpages;
 		pages_left -= didpages;
 
-		/* hit stripe? */
-		if (left && hit_stripe)
+		/* hit stripe and need continue*/
+		if (left && hit_stripe && pos < inode->i_size)
 			goto more;
 	}
 
-	if (was_short) {
+	if (read > 0) {
+		ret = read;
 		/* did we bounce off eof? */
 		if (pos + left > inode->i_size)
 			*checkeof = 1;
-
-		/* zero trailing bytes (inside i_size) */
-		if (left > 0 && pos < inode->i_size) {
-			if (pos + left > inode->i_size)
-				left = inode->i_size - pos;
-
-			dout("zero tail %d\n", left);
-			ceph_zero_page_vector_range(page_align + read, left,
-						    pages);
-			read += left;
-		}
 	}
 
-	if (ret >= 0)
-		ret = read;
 	dout("striped_read returns %d\n", ret);
 	return ret;
 }
@@ -618,6 +611,8 @@ out:
 		if (check_caps)
 			ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
 					NULL);
+	} else if (ret != -EOLDSNAPC && written > 0) {
+		ret = written;
 	}
 	return ret;
 }
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index a5ce62eb7806..669622fd1ae3 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -211,8 +211,12 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
 		 ceph_ino(inode), dl.object_no);
 
-	ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
-		ceph_file_layout_pg_pool(ci->i_layout));
+	r = ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
+				ceph_file_layout_pg_pool(ci->i_layout));
+	if (r < 0) {
+		up_read(&osdc->map_sem);
+		return r;
+	}
 
 	dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
 	if (dl.osd >= 0) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4d2920304be8..d6a536886472 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -414,6 +414,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 {
 	struct ceph_mds_session *s;
 
+	if (mds >= mdsc->mdsmap->m_max_mds)
+		return ERR_PTR(-EINVAL);
+
 	s = kzalloc(sizeof(*s), GFP_NOFS);
 	if (!s)
 		return ERR_PTR(-ENOMEM);
@@ -639,6 +642,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 		req->r_unsafe_dir = NULL;
 	}
 
+	complete_all(&req->r_safe_completion);
+
 	ceph_mdsc_put_request(req);
 }
 
@@ -1840,8 +1845,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	int err = -EAGAIN;
 
-	if (req->r_err || req->r_got_result)
+	if (req->r_err || req->r_got_result) {
+		if (req->r_aborted)
+			__unregister_request(mdsc, req);
 		goto out;
+	}
 
 	if (req->r_timeout &&
 	    time_after_eq(jiffies, req->r_started + req->r_timeout)) {
@@ -2151,7 +2159,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (head->safe) {
 		req->r_got_safe = true;
 		__unregister_request(mdsc, req);
-		complete_all(&req->r_safe_completion);
 
 		if (req->r_got_unsafe) {
 			/*
@@ -3040,8 +3047,10 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	fsc->mdsc = mdsc;
 	mutex_init(&mdsc->mutex);
 	mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
-	if (mdsc->mdsmap == NULL)
+	if (mdsc->mdsmap == NULL) {
+		kfree(mdsc);
 		return -ENOMEM;
+	}
 
 	init_completion(&mdsc->safe_umount_waiters);
 	init_waitqueue_head(&mdsc->session_close_wq);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 9278dec9e940..d4d38977dcbb 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -138,6 +138,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 				m->m_info[mds].export_targets =
 					kcalloc(num_export_targets, sizeof(u32),
 						GFP_NOFS);
+				if (m->m_info[mds].export_targets == NULL)
+					goto badmem;
 				for (j = 0; j < num_export_targets; j++)
 					m->m_info[mds].export_targets[j] =
 					       ceph_decode_32(&pexport_targets);
@@ -170,7 +172,7 @@ bad:
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       start, end - start, true);
 	ceph_mdsmap_destroy(m);
-	return ERR_PTR(-EINVAL);
+	return ERR_PTR(err);
 }
 
 void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7d377c9a5e35..6627b26a800c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -357,7 +357,7 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	}
 	err = -EINVAL;
 	dev_name_end--;		/* back up to ':' separator */
-	if (*dev_name_end != ':') {
+	if (dev_name_end < dev_name || *dev_name_end != ':') {
 		pr_err("device name is missing path (no : separator in %s)\n",
 				dev_name);
 		goto out;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45ef00a..15e9505aa35f 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@ int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		 const struct nls_table *cp, int mapChars)
 {
-	int i, j, charlen;
+	int i, charlen;
+	int j = 0;
 	char src_char;
 	__le16 dst_char;
 	wchar_t tmp;
@@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	if (!mapChars)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
-	for (i = 0, j = 0; i < srclen; j++) {
+	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
 		switch (src_char) {
 		case 0:
-			put_unaligned(0, &target[j]);
 			goto ctoUTF16_out;
 		case ':':
 			dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	}
 
 ctoUTF16_out:
+	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
 	return j;
 }
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 51f5e0ee7237..494b68349667 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1027,15 +1027,30 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 	__u32 secdesclen = 0;
 	struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
 	struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+	struct cifs_tcon *tcon;
+
+	if (IS_ERR(tlink))
+		return PTR_ERR(tlink);
+	tcon = tlink_tcon(tlink);
 
 	cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
 
 	/* Get the security descriptor */
-	pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
+
+	if (tcon->ses->server->ops->get_acl == NULL) {
+		cifs_put_tlink(tlink);
+		return -EOPNOTSUPP;
+	}
+
+	pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+						&secdesclen);
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
 		cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
-		goto out;
+		cifs_put_tlink(tlink);
+		return rc;
 	}
 
 	/*
@@ -1048,6 +1063,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 	pnntsd = kmalloc(secdesclen, GFP_KERNEL);
 	if (!pnntsd) {
 		kfree(pntsd);
+		cifs_put_tlink(tlink);
 		return -ENOMEM;
 	}
 
@@ -1056,14 +1072,18 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 
 	cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
 
+	if (tcon->ses->server->ops->set_acl == NULL)
+		rc = -EOPNOTSUPP;
+
 	if (!rc) {
 		/* Set the security descriptor */
-		rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag);
+		rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
+						     path, aclflag);
 		cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
 	}
+	cifs_put_tlink(tlink);
 
 	kfree(pnntsd);
 	kfree(pntsd);
-out:
 	return rc;
 }
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index ea3a0b3018a5..f74dfa89c4c4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -74,11 +74,6 @@
 #define SERVER_NAME_LENGTH 40
 #define SERVER_NAME_LEN_WITH_NULL     (SERVER_NAME_LENGTH + 1)
 
-/* used to define string lengths for reversing unicode strings */
-/*         (256+1)*2 = 514                                     */
-/*           (max path length + 1 for null) * 2 for unicode    */
-#define MAX_NAME 514
-
 /* SMB echo "timeout" -- FIXME: tunable? */
 #define SMB_ECHO_INTERVAL (60 * HZ)
 
@@ -370,6 +365,18 @@ struct smb_version_operations {
 	void (*new_lease_key)(struct cifs_fid *fid);
 	int (*calc_signature)(struct smb_rqst *rqst,
 				   struct TCP_Server_Info *server);
+	ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
+			const unsigned char *, const unsigned char *, char *,
+			size_t, const struct nls_table *, int);
+	int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
+			const char *, const void *, const __u16,
+			const struct nls_table *, int);
+	struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
+			const char *, u32 *);
+	int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
+			int);
+	/* check if we need to issue closedir */
+	bool (*dir_needs_close)(struct cifsFileInfo *);
 };
 
 struct smb_version_values {
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index a58dc77cc443..d17c5d72cd29 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -3306,11 +3306,13 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
 		return 0;
 	}
 	cifs_acl->version = cpu_to_le16(1);
-	if (acl_type == ACL_TYPE_ACCESS)
+	if (acl_type == ACL_TYPE_ACCESS) {
 		cifs_acl->access_entry_count = cpu_to_le16(count);
-	else if (acl_type == ACL_TYPE_DEFAULT)
+		cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+	} else if (acl_type == ACL_TYPE_DEFAULT) {
 		cifs_acl->default_entry_count = cpu_to_le16(count);
-	else {
+		cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+	} else {
 		cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
 		return 0;
 	}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 5699b5036ed8..0c2425b21974 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -491,6 +491,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
 		cifs_del_pending_open(&open);
+		fput(file);
 		rc = -ENOMEM;
 	}
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c2934f8701da..5fcc10fa62bd 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -735,7 +735,7 @@ int cifs_closedir(struct inode *inode, struct file *file)
 
 	cifs_dbg(FYI, "Freeing private data in close dir\n");
 	spin_lock(&cifs_file_list_lock);
-	if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+	if (server->ops->dir_needs_close(cfile)) {
 		cfile->invalidHandle = true;
 		spin_unlock(&cifs_file_list_lock);
 		if (server->ops->close_dir)
@@ -2353,7 +2353,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 		 unsigned long nr_segs, loff_t *poffset)
 {
 	unsigned long nr_pages, i;
-	size_t copied, len, cur_len;
+	size_t bytes, copied, len, cur_len;
 	ssize_t total_written = 0;
 	loff_t offset;
 	struct iov_iter it;
@@ -2408,14 +2408,45 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 
 		save_len = cur_len;
 		for (i = 0; i < nr_pages; i++) {
-			copied = min_t(const size_t, cur_len, PAGE_SIZE);
+			bytes = min_t(const size_t, cur_len, PAGE_SIZE);
 			copied = iov_iter_copy_from_user(wdata->pages[i], &it,
-							 0, copied);
+							 0, bytes);
 			cur_len -= copied;
 			iov_iter_advance(&it, copied);
+			/*
+			 * If we didn't copy as much as we expected, then that
+			 * may mean we trod into an unmapped area. Stop copying
+			 * at that point. On the next pass through the big
+			 * loop, we'll likely end up getting a zero-length
+			 * write and bailing out of it.
+			 */
+			if (copied < bytes)
+				break;
 		}
 		cur_len = save_len - cur_len;
 
+		/*
+		 * If we have no data to send, then that probably means that
+		 * the copy above failed altogether. That's most likely because
+		 * the address in the iovec was bogus. Set the rc to -EFAULT,
+		 * free anything we allocated and bail out.
+		 */
+		if (!cur_len) {
+			for (i = 0; i < nr_pages; i++)
+				put_page(wdata->pages[i]);
+			kfree(wdata);
+			rc = -EFAULT;
+			break;
+		}
+
+		/*
+		 * i + 1 now represents the number of pages we actually used in
+		 * the copy phase above. Bring nr_pages down to that, and free
+		 * any pages that we didn't use.
+		 */
+		for ( ; nr_pages > i + 1; nr_pages--)
+			put_page(wdata->pages[nr_pages - 1]);
+
 		wdata->sync_mode = WB_SYNC_ALL;
 		wdata->nr_pages = nr_pages;
 		wdata->offset = (__u64)offset;
@@ -2778,7 +2809,7 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 		total_read += result;
 	}
 
-	return total_read > 0 ? total_read : result;
+	return total_read > 0 && result != -EAGAIN ? total_read : result;
 }
 
 static ssize_t
@@ -3201,7 +3232,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 		total_read += result;
 	}
 
-	return total_read > 0 ? total_read : result;
+	return total_read > 0 && result != -EAGAIN ? total_read : result;
 }
 
 static int cifs_readpages(struct file *file, struct address_space *mapping,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 449b6cf09b09..0dee93706c98 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -490,10 +490,15 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
 
-	rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS",
-			    ea_value, 4 /* size of buf */, cifs_sb->local_nls,
-			    cifs_sb->mnt_cifs_flags &
-				CIFS_MOUNT_MAP_SPECIAL_CHR);
+	if (tcon->ses->server->ops->query_all_EAs == NULL) {
+		cifs_put_tlink(tlink);
+		return -EOPNOTSUPP;
+	}
+
+	rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
+			"SETFILEBITS", ea_value, 4 /* size of buf */,
+			cifs_sb->local_nls,
+			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	cifs_put_tlink(tlink);
 	if (rc < 0)
 		return (int)rc;
@@ -1635,13 +1640,22 @@ cifs_rename(struct inode *source_dir, struct dentry *source_dentry,
 unlink_target:
 	/* Try unlinking the target dentry if it's not negative */
 	if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) {
-		tmprc = cifs_unlink(target_dir, target_dentry);
+		if (S_ISDIR(target_dentry->d_inode->i_mode))
+			tmprc = cifs_rmdir(target_dir, target_dentry);
+		else
+			tmprc = cifs_unlink(target_dir, target_dentry);
 		if (tmprc)
 			goto cifs_rename_exit;
 		rc = cifs_do_rename(xid, source_dentry, from_name,
 				    target_dentry, to_name);
 	}
 
+	/* force revalidate to go get info when needed */
+	CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0;
+
+	source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime =
+		target_dir->i_mtime = current_fs_time(source_dir->i_sb);
+
 cifs_rename_exit:
 	kfree(info_buf_source);
 	kfree(from_name);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 036279c064ff..85ebdaa21015 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -582,11 +582,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon,
 		/* close and restart search */
 		cifs_dbg(FYI, "search backing up - close and restart search\n");
 		spin_lock(&cifs_file_list_lock);
-		if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+		if (server->ops->dir_needs_close(cfile)) {
 			cfile->invalidHandle = true;
 			spin_unlock(&cifs_file_list_lock);
-			if (server->ops->close)
-				server->ops->close(xid, tcon, &cfile->fid);
+			if (server->ops->close_dir)
+				server->ops->close_dir(xid, tcon, &cfile->fid);
 		} else
 			spin_unlock(&cifs_file_list_lock);
 		if (cfile->srch_inf.ntwrk_buf_start) {
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 3efdb9d5c0b8..610c6c24d41d 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -885,6 +885,12 @@ cifs_mand_lock(const unsigned int xid, struct cifsFileInfo *cfile, __u64 offset,
 			   (__u8)type, wait, 0);
 }
 
+static bool
+cifs_dir_needs_close(struct cifsFileInfo *cfile)
+{
+	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -948,6 +954,15 @@ struct smb_version_operations smb1_operations = {
 	.mand_lock = cifs_mand_lock,
 	.mand_unlock_range = cifs_unlock_range,
 	.push_mand_locks = cifs_push_mandatory_locks,
+	.dir_needs_close = cifs_dir_needs_close,
+#ifdef CONFIG_CIFS_XATTR
+	.query_all_EAs = CIFSSMBQAllEAs,
+	.set_EA = CIFSSMBSetEA,
+#endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_cifs_acl,
+	.set_acl = set_cifs_acl,
+#endif /* CIFS_ACL */
 };
 
 struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 5da1b55a2258..d801f63cddd0 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -73,7 +73,7 @@ smb2_open_file(const unsigned int xid, struct cifs_tcon *tcon, const char *path,
 		goto out;
 	}
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL) {
 		rc = -ENOMEM;
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 7c0e2143e775..cc592ef6584a 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -55,4 +55,7 @@
 #define SMB2_NTLMV2_SESSKEY_SIZE (16)
 #define SMB2_HMACSHA256_SIZE (32)
 
+/* Maximum buffer size value we can send with 1 credit */
+#define SMB2_MAX_BUFFER_SIZE 65536
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index fff6dfba6204..6d535797ec76 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -123,7 +123,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	*adjust_tz = false;
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL)
 		return -ENOMEM;
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 7c2f45c06fc2..4768cf8be6e2 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"},
 	{STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"},
 	{STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"},
-	{STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"},
+	{STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"},
 	{STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"},
 	{STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"},
 	{STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"},
@@ -605,7 +605,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"},
 	{STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"},
 	{STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"},
-	{STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"},
+	{STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"},
 	{STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"},
 	{STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"},
 	{STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"},
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f2e76f3b0c61..e12f258a5ffa 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -181,11 +181,8 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 	/* start with specified wsize, or default */
 	wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
 	wsize = min_t(unsigned int, wsize, server->max_write);
-	/*
-	 * limit write size to 2 ** 16, because we don't support multicredit
-	 * requests now.
-	 */
-	wsize = min_t(unsigned int, wsize, 2 << 15);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
 
 	return wsize;
 }
@@ -199,11 +196,8 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 	/* start with specified rsize, or default */
 	rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
 	rsize = min_t(unsigned int, rsize, server->max_read);
-	/*
-	 * limit write size to 2 ** 16, because we don't support multicredit
-	 * requests now.
-	 */
-	rsize = min_t(unsigned int, rsize, 2 << 15);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
 
 	return rsize;
 }
@@ -249,7 +243,7 @@ smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	struct smb2_file_all_info *smb2_data;
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL)
 		return -ENOMEM;
@@ -560,6 +554,12 @@ smb2_new_lease_key(struct cifs_fid *fid)
 	get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE);
 }
 
+static bool
+smb2_dir_needs_close(struct cifsFileInfo *cfile)
+{
+	return !cfile->invalidHandle;
+}
+
 struct smb_version_operations smb21_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -624,6 +624,7 @@ struct smb_version_operations smb21_operations = {
 	.set_lease_key = smb2_set_lease_key,
 	.new_lease_key = smb2_new_lease_key,
 	.calc_signature = smb2_calc_signature,
+	.dir_needs_close = smb2_dir_needs_close,
 };
 
 
@@ -691,6 +692,7 @@ struct smb_version_operations smb30_operations = {
 	.set_lease_key = smb2_set_lease_key,
 	.new_lease_key = smb2_new_lease_key,
 	.calc_signature = smb3_calc_signature,
+	.dir_needs_close = smb2_dir_needs_close,
 };
 
 struct smb_version_values smb20_values = {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2b95ce2b54e8..eb0de4c3ca76 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -408,6 +408,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
 	server->maxBuf = le32_to_cpu(rsp->MaxTransactSize);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize),
+			       SMB2_MAX_BUFFER_SIZE);
 	server->max_read = le32_to_cpu(rsp->MaxReadSize);
 	server->max_write = le32_to_cpu(rsp->MaxWriteSize);
 	/* BB Do we need to validate the SecurityMode? */
@@ -806,7 +809,8 @@ tcon_exit:
 tcon_error_exit:
 	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		tcon->bad_network_name = true;
+		if (tcon)
+			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -1200,7 +1204,7 @@ SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
 			  FILE_ALL_INFORMATION,
-			  sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+			  sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			  sizeof(struct smb2_file_all_info), data);
 }
 
@@ -1796,6 +1800,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base;
 
 	if (rc) {
+		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
+			srch_inf->endOfSearch = true;
+			rc = 0;
+		}
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
 		goto qdir_exit;
 	}
@@ -1833,11 +1841,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	else
 		cifs_dbg(VFS, "illegal search buffer type\n");
 
-	if (rsp->hdr.Status == STATUS_NO_MORE_FILES)
-		srch_inf->endOfSearch = 1;
-	else
-		srch_inf->endOfSearch = 0;
-
 	return rc;
 
 qdir_exit:
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 09afda4cc58e..5ac836a86b18 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -82,9 +82,11 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name)
 			goto remove_ea_exit;
 
 		ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
-		rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, NULL,
-			(__u16)0, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (pTcon->ses->server->ops->set_EA)
+			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+				full_path, ea_name, NULL, (__u16)0,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 remove_ea_exit:
 	kfree(full_path);
@@ -149,18 +151,22 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 			cifs_dbg(FYI, "attempt to set cifs inode metadata\n");
 
 		ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
-		rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
-			(__u16)value_size, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (pTcon->ses->server->ops->set_EA)
+			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+				full_path, ea_name, ea_value, (__u16)value_size,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 	} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)
 		   == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto set_ea_exit;
 
 		ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
-		rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
-			(__u16)value_size, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (pTcon->ses->server->ops->set_EA)
+			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+				full_path, ea_name, ea_value, (__u16)value_size,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 	} else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
 			strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
 #ifdef CONFIG_CIFS_ACL
@@ -170,8 +176,12 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 			rc = -ENOMEM;
 		} else {
 			memcpy(pacl, ea_value, value_size);
-			rc = set_cifs_acl(pacl, value_size,
-				direntry->d_inode, full_path, CIFS_ACL_DACL);
+			if (pTcon->ses->server->ops->set_acl)
+				rc = pTcon->ses->server->ops->set_acl(pacl,
+						value_size, direntry->d_inode,
+						full_path, CIFS_ACL_DACL);
+			else
+				rc = -EOPNOTSUPP;
 			if (rc == 0) /* force revalidate of the inode */
 				CIFS_I(direntry->d_inode)->time = 0;
 			kfree(pacl);
@@ -272,17 +282,21 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 			/* revalidate/getattr then populate from inode */
 		} /* BB add else when above is implemented */
 		ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
-		rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
-			buf_size, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (pTcon->ses->server->ops->query_all_EAs)
+			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+				full_path, ea_name, ea_value, buf_size,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 	} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto get_ea_exit;
 
 		ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
-		rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
-			buf_size, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (pTcon->ses->server->ops->query_all_EAs)
+			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+				full_path, ea_name, ea_value, buf_size,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 	} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
 			  strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
@@ -313,8 +327,11 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 			u32 acllen;
 			struct cifs_ntsd *pacl;
 
-			pacl = get_cifs_acl(cifs_sb, direntry->d_inode,
-						full_path, &acllen);
+			if (pTcon->ses->server->ops->get_acl == NULL)
+				goto get_ea_exit; /* rc already EOPNOTSUPP */
+
+			pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+					direntry->d_inode, full_path, &acllen);
 			if (IS_ERR(pacl)) {
 				rc = PTR_ERR(pacl);
 				cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
@@ -400,11 +417,12 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 	/* if proc/fs/cifs/streamstoxattr is set then
 		search server for EAs or streams to
 		returns as xattrs */
-	rc = CIFSSMBQAllEAs(xid, pTcon, full_path, NULL, data,
-				buf_size, cifs_sb->local_nls,
-				cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
 
+	if (pTcon->ses->server->ops->query_all_EAs)
+		rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+				full_path, NULL, data, buf_size,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
 list_ea_exit:
 	kfree(full_path);
 	free_xid(xid);
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e2e4ef..4d24d17bcfc1 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@ static void cputime_to_compat_timeval(const cputime_t cputime,
 #define	ELF_HWCAP		COMPAT_ELF_HWCAP
 #endif
 
+#ifdef	COMPAT_ELF_HWCAP2
+#undef	ELF_HWCAP2
+#define	ELF_HWCAP2		COMPAT_ELF_HWCAP2
+#endif
+
 #ifdef	COMPAT_ARCH_DLINFO
 #undef	ARCH_DLINFO
 #define	ARCH_DLINFO		COMPAT_ARCH_DLINFO
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 7aabc6ad4e9b..fa38d076697d 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -56,10 +56,19 @@ static void configfs_d_iput(struct dentry * dentry,
 	struct configfs_dirent *sd = dentry->d_fsdata;
 
 	if (sd) {
-		BUG_ON(sd->s_dentry != dentry);
 		/* Coordinate with configfs_readdir */
 		spin_lock(&configfs_dirent_lock);
-		sd->s_dentry = NULL;
+		/* Coordinate with configfs_attach_attr where will increase
+		 * sd->s_count and update sd->s_dentry to new allocated one.
+		 * Only set sd->dentry to null when this dentry is the only
+		 * sd owner.
+		 * If not do so, configfs_d_iput may run just after
+		 * configfs_attach_attr and set sd->s_dentry to null
+		 * even it's still in use.
+		 */
+		if (atomic_read(&sd->s_count) <= 2)
+			sd->s_dentry = NULL;
+
 		spin_unlock(&configfs_dirent_lock);
 		configfs_put(sd);
 	}
@@ -426,8 +435,11 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 	struct configfs_attribute * attr = sd->s_element;
 	int error;
 
+	spin_lock(&configfs_dirent_lock);
 	dentry->d_fsdata = configfs_get(sd);
 	sd->s_dentry = dentry;
+	spin_unlock(&configfs_dirent_lock);
+
 	error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
 				configfs_init_file);
 	if (error) {
diff --git a/fs/coredump.c b/fs/coredump.c
index dafafbafa731..1d402ce5b72f 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -299,7 +299,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	if (unlikely(nr < 0))
 		return nr;
 
-	tsk->flags = PF_DUMPCORE;
+	tsk->flags |= PF_DUMPCORE;
 	if (atomic_read(&mm->mm_users) == nr + 1)
 		goto done;
 	/*
diff --git a/fs/dcache.c b/fs/dcache.c
index f09b9085f7d8..25c0a1b5f6c0 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -96,8 +96,6 @@ static struct kmem_cache *dentry_cache __read_mostly;
  * This hash-function tries to avoid losing too many bits of hash
  * information, yet avoid using a prime hash-size or similar.
  */
-#define D_HASHBITS     d_hash_shift
-#define D_HASHMASK     d_hash_mask
 
 static unsigned int d_hash_mask __read_mostly;
 static unsigned int d_hash_shift __read_mostly;
@@ -108,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned int hash)
 {
 	hash += (unsigned long) parent / L1_CACHE_BYTES;
-	hash = hash + (hash >> D_HASHBITS);
-	return dentry_hashtable + (hash & D_HASHMASK);
+	return dentry_hashtable + hash_32(hash, d_hash_shift);
 }
 
 /* Statistics gathering. */
@@ -2686,8 +2683,13 @@ char *d_path(const struct path *path, char *buf, int buflen)
 	 * thus don't need to be hashed.  They also don't need a name until a
 	 * user wants to identify the object in /proc/pid/fd/.  The little hack
 	 * below allows us to generate a name for these objects on demand:
+	 *
+	 * Some pseudo inodes are mountable.  When they are mounted
+	 * path->dentry == path->mnt->mnt_root.  In that case don't call d_dname
+	 * and instead have d_path return the mounted path.
 	 */
-	if (path->dentry->d_op && path->dentry->d_op->d_dname)
+	if (path->dentry->d_op && path->dentry->d_op->d_dname &&
+	    (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
 		return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
 	get_fs_root(current->fs, &root);
@@ -2724,6 +2726,17 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
 	return memcpy(buffer, temp, sz);
 }
 
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	char *end = buffer + buflen;
+	/* these dentries are never renamed, so d_lock is not needed */
+	if (prepend(&end, &buflen, " (deleted)", 11) ||
+	    prepend_name(&end, &buflen, &dentry->d_name) ||
+	    prepend(&end, &buflen, "/", 1))
+		end = ERR_PTR(-ENAMETOOLONG);
+	return end;
+}
+
 /*
  * Write full pathname from the root of the filesystem into the buffer.
  */
diff --git a/fs/dcookies.c b/fs/dcookies.c
index ab5954b50267..ac44a69fbea9 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -204,7 +204,7 @@ out:
 }
 
 #ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, size_t, len)
+COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len)
 {
 #ifdef __BIG_ENDIAN
 	return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 073d30b9d1ac..a726b9f29cb7 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -498,6 +498,7 @@ static void devpts_kill_sb(struct super_block *sb)
 {
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
 
+	ida_destroy(&fsi->allocated_ptys);
 	kfree(fsi);
 	kill_litter_super(sb);
 }
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index f71ec125290d..1da2446bf6b0 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -2102,7 +2102,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
 			break;
 		case 2:
 			dst[dst_byte_offset++] |= (src_byte);
-			dst[dst_byte_offset] = 0;
 			current_bit_offset = 0;
 			break;
 		}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index a7abbea2c096..9ff3664bb3ea 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -196,23 +196,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 {
 	int rc = 0;
 	struct ecryptfs_crypt_stat *crypt_stat = NULL;
-	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
 	struct ecryptfs_file_info *file_info;
 
-	mount_crypt_stat = &ecryptfs_superblock_to_private(
-		ecryptfs_dentry->d_sb)->mount_crypt_stat;
-	if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
-	    && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
-		|| (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
-		|| (file->f_flags & O_APPEND))) {
-		printk(KERN_WARNING "Mount has encrypted view enabled; "
-		       "files may only be read\n");
-		rc = -EPERM;
-		goto out;
-	}
 	/* Released in ecryptfs_release or end of function if failure */
 	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
 	ecryptfs_set_file_private(file, file_info);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 5eab400e2590..41baf8b5e0eb 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1051,7 +1051,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
-	if (!rc)
+	if (!rc && dentry->d_inode)
 		fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
 out:
 	return rc;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 7d52806c2119..4725a07f003c 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1149,7 +1149,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	struct ecryptfs_msg_ctx *msg_ctx;
 	struct ecryptfs_message *msg = NULL;
 	char *auth_tok_sig;
-	char *payload;
+	char *payload = NULL;
 	size_t payload_len = 0;
 	int rc;
 
@@ -1203,6 +1203,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	}
 out:
 	kfree(msg);
+	kfree(payload);
 	return rc;
 }
 
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index e924cf45aad9..329a9cc2b2eb 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -494,6 +494,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 {
 	struct super_block *s;
 	struct ecryptfs_sb_info *sbi;
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
 	struct inode *inode;
@@ -512,6 +513,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		err = "Error parsing options";
 		goto out;
 	}
+	mount_crypt_stat = &sbi->mount_crypt_stat;
 
 	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
@@ -558,11 +560,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
 	/**
 	 * Set the POSIX ACL flag based on whether they're enabled in the lower
-	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
-	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 * mount.
 	 */
 	s->s_flags = flags & ~MS_POSIXACL;
-	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+	s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+	/**
+	 * Force a read-only eCryptfs mount when:
+	 *   1) The lower mount is ro
+	 *   2) The ecryptfs_encrypted_view mount option is specified
+	 */
+	if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+	    mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+		s->s_flags |= MS_RDONLY;
 
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/exec.c b/fs/exec.c
index 1f446705636b..dd6aa61c8548 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -654,10 +654,10 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long rlim_stack;
 
 #ifdef CONFIG_STACK_GROWSUP
-	/* Limit stack size to 1GB */
+	/* Limit stack size */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
@@ -1669,6 +1669,12 @@ int __get_dumpable(unsigned long mm_flags)
 	return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret;
 }
 
+/*
+ * This returns the actual value of the suid_dumpable flag. For things
+ * that are using this for checking for privilege transitions, it must
+ * test against SUID_DUMP_USER rather than treating it as a boolean
+ * value.
+ */
 int get_dumpable(struct mm_struct *mm)
 {
 	return __get_dumpable(mm->flags);
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index b74422888604..85cde3e76290 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -103,7 +103,7 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
 
 	layout->max_io_length =
 		(BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
-							layout->group_width;
+					(layout->group_width - layout->parity);
 	if (layout->parity) {
 		unsigned stripe_length =
 				(layout->group_width - layout->parity) *
@@ -286,7 +286,8 @@ int  ore_get_rw_state(struct ore_layout *layout, struct ore_components *oc,
 	if (length) {
 		ore_calc_stripe_info(layout, offset, length, &ios->si);
 		ios->length = ios->si.length;
-		ios->nr_pages = (ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
+		ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
+				 ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
 		if (layout->parity)
 			_ore_post_alloc_raid_stuff(ios);
 	}
@@ -536,6 +537,7 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
 	u64	H = LmodS - G * T;
 
 	u32	N = div_u64(H, U);
+	u32	Nlast;
 
 	/* "H - (N * U)" is just "H % U" so it's bound to u32 */
 	u32	C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
@@ -568,6 +570,10 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
 	si->length = T - H;
 	if (si->length > length)
 		si->length = length;
+
+	Nlast = div_u64(H + si->length + U - 1, U);
+	si->maxdevUnits = Nlast - N;
+
 	si->M = M;
 }
 EXPORT_SYMBOL(ore_calc_stripe_info);
@@ -583,13 +589,16 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
 	int ret;
 
 	if (per_dev->bio == NULL) {
-		unsigned pages_in_stripe = ios->layout->group_width *
-					(ios->layout->stripe_unit / PAGE_SIZE);
-		unsigned nr_pages = ios->nr_pages * ios->layout->group_width /
-					(ios->layout->group_width -
-					 ios->layout->parity);
-		unsigned bio_size = (nr_pages + pages_in_stripe) /
-					ios->layout->group_width;
+		unsigned bio_size;
+
+		if (!ios->reading) {
+			bio_size = ios->si.maxdevUnits;
+		} else {
+			bio_size = (ios->si.maxdevUnits + 1) *
+			     (ios->layout->group_width - ios->layout->parity) /
+			     ios->layout->group_width;
+		}
+		bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
 
 		per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
 		if (unlikely(!per_dev->bio)) {
@@ -609,8 +618,12 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
 		added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
 					    pglen, pgbase);
 		if (unlikely(pglen != added_len)) {
-			ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n",
-				   per_dev->bio->bi_vcnt);
+			/* If bi_vcnt == bi_max then this is a SW BUG */
+			ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
+				   "bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
+				   per_dev->bio->bi_vcnt,
+				   per_dev->bio->bi_max_vecs,
+				   BIO_MAX_PAGES_KMALLOC, cur_len);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1098,7 +1111,7 @@ int ore_truncate(struct ore_layout *layout, struct ore_components *oc,
 		size_attr->attr = g_attr_logical_length;
 		size_attr->attr.val_ptr = &size_attr->newsize;
 
-		ORE_DBGMSG("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
+		ORE_DBGMSG2("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
 			     _LLU(oc->comps->obj.id), _LLU(obj_size), i);
 		ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1,
 					&size_attr->attr);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0a87bb10998d..99d84ce038b8 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -632,6 +632,8 @@ static int ext2_get_blocks(struct inode *inode,
 	int count = 0;
 	ext2_fsblk_t first_block = 0;
 
+	BUG_ON(maxblocks == 0);
+
 	depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
 
 	if (depth == 0)
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 288534920fe5..20d6697bd638 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1493,6 +1493,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
+		tmp_bh.b_size = sb->s_blocksize;
 		err = ext2_get_block(inode, blk, &tmp_bh, 1);
 		if (err < 0)
 			goto out;
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index 1c3312858fcf..e98171a11cfe 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -35,6 +35,7 @@ __ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
 	int rc;
 
 	memset(&tmp, 0, sizeof(struct buffer_head));
+	tmp.b_size = 1 << inode->i_blkbits;
 	rc = ext2_get_block(inode, pgoff, &tmp, create);
 	*result = tmp.b_blocknr;
 
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 6356665a74bb..882d4bdfd428 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1300,13 +1300,6 @@ set_qf_format:
 					"not specified.");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext3_msg(sb, KERN_ERR, "error: journaled quota format "
-					"specified with no journaling "
-					"enabled.");
-			return 0;
-		}
 	}
 #endif
 	return 1;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5aae3d12d400..e4c4ac07cc32 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -280,6 +280,16 @@ struct ext4_io_submit {
 /* Translate # of blks to # of clusters */
 #define EXT4_NUM_B2C(sbi, blks)	(((blks) + (sbi)->s_cluster_ratio - 1) >> \
 				 (sbi)->s_cluster_bits)
+/* Mask out the low bits to get the starting block of the cluster */
+#define EXT4_PBLK_CMASK(s, pblk) ((pblk) &				\
+				  ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_CMASK(s, lblk) ((lblk) &				\
+				  ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
+/* Get the cluster offset */
+#define EXT4_PBLK_COFF(s, pblk) ((pblk) &				\
+				 ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_COFF(s, lblk) ((lblk) &				\
+				 ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
 
 /*
  * Structure of a blocks group descriptor
@@ -764,6 +774,8 @@ do {									       \
 	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
 		(einode)->xtime.tv_sec = 				       \
 			(signed)le32_to_cpu((raw_inode)->xtime);	       \
+	else								       \
+		(einode)->xtime.tv_sec = 0;				       \
 	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
 		ext4_decode_extra_time(&(einode)->xtime,		       \
 				       raw_inode->xtime ## _extra);	       \
@@ -2076,6 +2088,7 @@ int do_journal_get_write_access(handle_t *handle,
 #define CONVERT_INLINE_DATA	 2
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
+extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -2248,8 +2261,8 @@ extern int ext4_register_li_request(struct super_block *sb,
 static inline int ext4_has_group_desc_csum(struct super_block *sb)
 {
 	return EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
-					  EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
+					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM) ||
+	       (EXT4_SB(sb)->s_chksum_driver != NULL);
 }
 
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 1c88061da526..1be3996b5942 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -223,6 +223,15 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		if (WARN_ON_ONCE(err)) {
 			ext4_journal_abort_handle(where, line, __func__, bh,
 						  handle, err);
+			ext4_error_inode(inode, where, line,
+					 bh->b_blocknr,
+					 "journal_dirty_metadata failed: "
+					 "handle type %u started at line %u, "
+					 "credits %u/%u, errcode %d",
+					 handle->h_type,
+					 handle->h_line_no,
+					 handle->h_requested_credits,
+					 handle->h_buffer_credits, err);
 		}
 	} else {
 		if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index dc1e03047226..84d817b842a8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -360,8 +360,10 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 {
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
+	ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+	ext4_lblk_t last = lblock + len - 1;
 
-	if (len == 0)
+	if (lblock > last)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -387,11 +389,26 @@ static int ext4_valid_extent_entries(struct inode *inode,
 	if (depth == 0) {
 		/* leaf entries */
 		struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+		struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+		ext4_fsblk_t pblock = 0;
+		ext4_lblk_t lblock = 0;
+		ext4_lblk_t prev = 0;
+		int len = 0;
 		while (entries) {
 			if (!ext4_valid_extent(inode, ext))
 				return 0;
+
+			/* Check for overlapping extents */
+			lblock = le32_to_cpu(ext->ee_block);
+			len = ext4_ext_get_actual_len(ext);
+			if ((lblock <= prev) && prev) {
+				pblock = ext4_ext_pblock(ext);
+				es->s_last_error_block = cpu_to_le64(pblock);
+				return 0;
+			}
 			ext++;
 			entries--;
+			prev = lblock + len - 1;
 		}
 	} else {
 		struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
@@ -1755,8 +1772,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 	depth = ext_depth(inode);
 	if (!path[depth].p_ext)
 		goto out;
-	b2 = le32_to_cpu(path[depth].p_ext->ee_block);
-	b2 &= ~(sbi->s_cluster_ratio - 1);
+	b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
 
 	/*
 	 * get the next allocated block if the extent in the path
@@ -1766,7 +1782,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 		b2 = ext4_ext_next_allocated_block(path);
 		if (b2 == EXT_MAX_BLOCKS)
 			goto out;
-		b2 &= ~(sbi->s_cluster_ratio - 1);
+		b2 = EXT4_LBLK_CMASK(sbi, b2);
 	}
 
 	/* check for wrap through zero on extent logical start block*/
@@ -2427,7 +2443,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		 * truncate operation has removed all of the blocks in
 		 * the cluster.
 		 */
-		if (pblk & (sbi->s_cluster_ratio - 1) &&
+		if (EXT4_PBLK_COFF(sbi, pblk) &&
 		    (ee_len == num))
 			*partial_cluster = EXT4_B2C(sbi, pblk);
 		else
@@ -2495,6 +2511,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	/*
+	 * If we're starting with an extent other than the last one in the
+	 * node, we need to see if it shares a cluster with the extent to
+	 * the right (towards the end of the file). If its leftmost cluster
+	 * is this extent's rightmost cluster and it is not cluster aligned,
+	 * we'll mark it as a partial that is not to be deallocated.
+	 */
+
+	if (ex != EXT_LAST_EXTENT(eh)) {
+		ext4_fsblk_t current_pblk, right_pblk;
+		long long current_cluster, right_cluster;
+
+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+		right_pblk = ext4_ext_pblock(ex + 1);
+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+		if (current_cluster == right_cluster &&
+			EXT4_PBLK_COFF(sbi, right_pblk))
+			*partial_cluster = -right_cluster;
+	}
+
 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -3658,7 +3695,7 @@ int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_lblk_t lblk_start, lblk_end;
-	lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+	lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
 	lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
 
 	return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
@@ -3717,9 +3754,9 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
 
 	/* Check towards left side */
-	c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
 	if (c_offset) {
-		lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+		lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
 		lblk_to = lblk_from + c_offset - 1;
 
 		if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
@@ -3727,7 +3764,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	}
 
 	/* Now check towards right. */
-	c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
 	if (allocated_clusters && c_offset) {
 		lblk_from = lblk_start + num_blks;
 		lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
@@ -3935,7 +3972,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 				     struct ext4_ext_path *path)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ext4_lblk_t ex_cluster_start, ex_cluster_end;
 	ext4_lblk_t rr_cluster_start;
 	ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
@@ -3953,8 +3990,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	    (rr_cluster_start == ex_cluster_start)) {
 		if (rr_cluster_start == ex_cluster_end)
 			ee_start += ee_len - 1;
-		map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
-			c_offset;
+		map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
 		map->m_len = min(map->m_len,
 				 (unsigned) sbi->s_cluster_ratio - c_offset);
 		/*
@@ -4017,7 +4053,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	struct ext4_extent newex, *ex, *ex2;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_fsblk_t newblock = 0;
-	int free_on_err = 0, err = 0, depth;
+	int free_on_err = 0, err = 0, depth, ret;
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
@@ -4078,9 +4114,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			if (!ext4_ext_is_uninitialized(ex))
 				goto out;
 
-			allocated = ext4_ext_handle_uninitialized_extents(
+			ret = ext4_ext_handle_uninitialized_extents(
 				handle, inode, map, path, flags,
 				allocated, newblock);
+			if (ret < 0)
+				err = ret;
+			else
+				allocated = ret;
 			goto out3;
 		}
 	}
@@ -4108,7 +4148,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
 	newex.ee_block = cpu_to_le32(map->m_lblk);
-	cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 
 	/*
 	 * If we are doing bigalloc, check to see if the extent returned
@@ -4176,7 +4216,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * needed so that future calls to get_implied_cluster_alloc()
 	 * work correctly.
 	 */
-	offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+	offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
 	ar.goal -= offset;
 	ar.logical -= offset;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b19f0a457f32..4635788e14bf 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -82,7 +82,7 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
 	size_t count = iov_length(iov, nr_segs);
 	loff_t final_size = pos + count;
 
-	if (pos >= inode->i_size)
+	if (pos >= i_size_read(inode))
 		return 0;
 
 	if ((pos & blockmask) || (final_size & blockmask))
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3da3bf1b2cd0..4d4718cf25ab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -780,12 +780,23 @@ got:
 		goto out;
 	}
 
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		struct buffer_head *block_bitmap_bh;
 
 		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (!block_bitmap_bh) {
+			err = -EIO;
+			goto out;
+		}
 		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
 		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
@@ -816,13 +827,6 @@ got:
 		}
 	}
 
-	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto out;
-	}
-
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8d5d351e24f..589061469687 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -390,7 +390,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 	return 0;
 failed:
 	for (; i >= 0; i--) {
-		if (i != indirect_blks && branch[i].bh)
+		/*
+		 * We want to ext4_forget() only freshly allocated indirect
+		 * blocks.  Buffer for new_blocks[i-1] is at branch[i].bh and
+		 * buffer at branch[0].bh is indirect block / inode already
+		 * existing before ext4_alloc_branch() was called.
+		 */
+		if (i > 0 && i != indirect_blks && branch[i].bh)
 			ext4_forget(handle, 1, inode, branch[i].bh,
 				    branch[i].bh->b_blocknr);
 		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
@@ -1325,16 +1331,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		blk = *i_data;
 		if (level > 0) {
 			ext4_lblk_t first2;
+			ext4_lblk_t count2;
+
 			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
 			if (!bh) {
 				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
 						       "Read failure");
 				return -EIO;
 			}
-			first2 = (first > offset) ? first - offset : 0;
+			if (first > offset) {
+				first2 = first - offset;
+				count2 = count;
+			} else {
+				first2 = 0;
+				count2 = count - (offset - first);
+			}
 			ret = free_hole_blocks(handle, inode, bh,
 					       (__le32 *)bh->b_data, level - 1,
-					       first2, count - offset,
+					       first2, count2,
 					       inode->i_sb->s_blocksize >> 2);
 			if (ret) {
 				brelse(bh);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 33331b4c2178..e350be6c7ac6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1957,9 +1957,11 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 		}
 
 		/* Clear the content within i_blocks. */
-		if (i_size < EXT4_MIN_INLINE_DATA_SIZE)
-			memset(ext4_raw_inode(&is.iloc)->i_block + i_size, 0,
-					EXT4_MIN_INLINE_DATA_SIZE - i_size);
+		if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
+			void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
+			memset(p + i_size, 0,
+			       EXT4_MIN_INLINE_DATA_SIZE - i_size);
+		}
 
 		EXT4_I(inode)->i_inline_size = i_size <
 					EXT4_MIN_INLINE_DATA_SIZE ?
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 904ca1a21dce..e48bd5a1814b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 #include <linux/aio.h>
+#include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -1263,7 +1264,6 @@ static int ext4_journalled_write_end(struct file *file,
  */
 static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1275,7 +1275,6 @@ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1295,10 +1294,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		return -ENOSPC;
 	}
 	ei->i_reserved_meta_blocks += md_needed;
@@ -1312,7 +1307,6 @@ repeat:
  */
 static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1334,7 +1328,6 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1354,10 +1347,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		return -ENOSPC;
 	}
@@ -2658,6 +2647,20 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
+/* We always reserve for an inode update; the superblock could be there too */
+static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
+{
+	if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				EXT4_FEATURE_RO_COMPAT_LARGE_FILE)))
+		return 1;
+
+	if (pos + len <= 0x7fffffffULL)
+		return 1;
+
+	/* We might need to update the superblock to set LARGE_FILE */
+	return 2;
+}
+
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
@@ -2708,7 +2711,8 @@ retry_grab:
 	 * of file which has an already mapped buffer.
 	 */
 retry_journal:
-	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
+	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+				ext4_da_write_credits(inode, pos, len));
 	if (IS_ERR(handle)) {
 		page_cache_release(page);
 		return PTR_ERR(handle);
@@ -4056,18 +4060,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 void ext4_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
+	unsigned int new_fl = 0;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 	if (flags & EXT4_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & EXT4_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & EXT4_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4360,6 +4366,13 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
+struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino)
+{
+	if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+		return ERR_PTR(-EIO);
+	return ext4_iget(sb, ino);
+}
+
 static int ext4_inode_blocks_set(handle_t *handle,
 				struct ext4_inode *raw_inode,
 				struct ext4_inode_info *ei)
@@ -4716,6 +4729,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			if (attr->ia_size > sbi->s_bitmap_maxbytes)
 				return -EFBIG;
 		}
+
+		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
+			inode_inc_iversion(inode);
+
 		if (S_ISREG(inode->i_mode) &&
 		    (attr->ia_size < inode->i_size)) {
 			if (ext4_should_order_data(inode)) {
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index c0427e2f6648..d4fd81c44f55 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -145,7 +145,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
 	if (IS_ERR(handle)) {
 		err = -EINVAL;
-		goto swap_boot_out;
+		goto journal_err_out;
 	}
 
 	/* Protect extent tree against block allocations via delalloc */
@@ -203,6 +203,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
+journal_err_out:
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
 
@@ -548,9 +549,17 @@ group_add_out:
 	}
 
 	case EXT4_IOC_SWAP_BOOT:
+	{
+		int err;
 		if (!(filp->f_mode & FMODE_WRITE))
 			return -EBADF;
-		return swap_inode_boot_loader(sb, inode);
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+		err = swap_inode_boot_loader(sb, inode);
+		mnt_drop_write_file(filp);
+		return err;
+	}
 
 	case EXT4_IOC_RESIZE_FS: {
 		ext4_fsblk_t n_blocks_count;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 59c6750b894f..162b80d527a0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1396,6 +1396,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	int last = first + count - 1;
 	struct super_block *sb = e4b->bd_sb;
 
+	if (WARN_ON(count == 0))
+		return;
 	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	mb_check_buddy(e4b);
@@ -3116,7 +3118,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
@@ -3177,8 +3179,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
 static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 {
 	struct ext4_prealloc_space *pa = ac->ac_pa;
+	struct ext4_buddy e4b;
+	int err;
 
-	if (pa && pa->pa_type == MB_INODE_PA)
+	if (pa == NULL) {
+		if (ac->ac_f_ex.fe_len == 0)
+			return;
+		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
+		if (err) {
+			/*
+			 * This should never happen since we pin the
+			 * pages in the ext4_allocation_context so
+			 * ext4_mb_load_buddy() should never fail.
+			 */
+			WARN(1, "mb_load_buddy failed (%d)", err);
+			return;
+		}
+		ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
+			       ac->ac_f_ex.fe_len);
+		ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		ext4_mb_unload_buddy(&e4b);
+		return;
+	}
+	if (pa->pa_type == MB_INODE_PA)
 		pa->pa_free += ac->ac_b_ex.fe_len;
 }
 
@@ -3423,6 +3447,9 @@ static void ext4_mb_pa_callback(struct rcu_head *head)
 {
 	struct ext4_prealloc_space *pa;
 	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+
+	BUG_ON(atomic_read(&pa->pa_count));
+	BUG_ON(pa->pa_deleted == 0);
 	kmem_cache_free(ext4_pspace_cachep, pa);
 }
 
@@ -3436,11 +3463,13 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	ext4_group_t grp;
 	ext4_fsblk_t grp_blk;
 
-	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
-		return;
-
 	/* in this short window concurrent discard can set pa_deleted */
 	spin_lock(&pa->pa_lock);
+	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) {
+		spin_unlock(&pa->pa_lock);
+		return;
+	}
+
 	if (pa->pa_deleted == 1) {
 		spin_unlock(&pa->pa_lock);
 		return;
@@ -4102,7 +4131,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ext4_get_group_no_and_offset(sb, goal, &group, &block);
 
 	/* set up allocation goals */
-	ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
+	ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical);
 	ac->ac_status = AC_STATUS_CONTINUE;
 	ac->ac_sb = sb;
 	ac->ac_inode = ar->inode;
@@ -4639,7 +4668,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	 * blocks at the beginning or the end unless we are explicitly
 	 * requested to avoid doing so.
 	 */
-	overflow = block & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_PBLK_COFF(sbi, block);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
 			overflow = sbi->s_cluster_ratio - overflow;
@@ -4653,7 +4682,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			count += overflow;
 		}
 	}
-	overflow = count & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_LBLK_COFF(sbi, count);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
 			if (count > overflow)
@@ -4766,8 +4795,8 @@ do_more:
 					 " group:%d block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
 					 err);
-		}
-
+		} else
+			EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
 
 		ext4_lock_group(sb, block_group);
 		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index ab2f6dc44b3a..f1312173fa90 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1430,7 +1430,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 					 dentry->d_name.name);
 			return ERR_PTR(-EIO);
 		}
-		inode = ext4_iget(dir->i_sb, ino);
+		inode = ext4_iget_normal(dir->i_sb, ino);
 		if (inode == ERR_PTR(-ESTALE)) {
 			EXT4_ERROR_INODE(dir,
 					 "deleted inode referenced: %u",
@@ -1461,7 +1461,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
 		return ERR_PTR(-EIO);
 	}
 
-	return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
+	return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino));
 }
 
 /*
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 4acf1f78881b..b12a4427aedc 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -384,6 +384,17 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	ClearPageError(page);
 
 	/*
+	 * Comments copied from block_write_full_page_endio:
+	 *
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	if (len < PAGE_CACHE_SIZE)
+		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
 	 * mark all buffers in the page before submitting so that
 	 * end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -394,19 +405,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
-			/*
-			 * Comments copied from block_write_full_page_endio:
-			 *
-			 * The page straddles i_size.  It must be zeroed out on
-			 * each and every writepage invocation because it may
-			 * be mmapped.  "A file is mapped in multiples of the
-			 * page size.  For a file that is not a multiple of
-			 * the  page size, the remaining memory is zeroed when
-			 * mapped, and writes to that region are not written
-			 * out to the file."
-			 */
-			zero_user_segment(page, block_start,
-					  block_start + blocksize);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 49d3c01eabf8..a69bd74ed390 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -238,6 +238,7 @@ static int ext4_alloc_group_tables(struct super_block *sb,
 	ext4_group_t group;
 	ext4_group_t last_group;
 	unsigned overhead;
+	__u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
 
 	BUG_ON(flex_gd->count == 0 || group_data == NULL);
 
@@ -261,7 +262,7 @@ next_group:
 	src_group++;
 	for (; src_group <= last_group; src_group++) {
 		overhead = ext4_group_overhead_blocks(sb, src_group);
-		if (overhead != 0)
+		if (overhead == 0)
 			last_blk += group_data[src_group - group].blocks_count;
 		else
 			break;
@@ -275,8 +276,7 @@ next_group:
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode bitmaps */
@@ -287,22 +287,30 @@ next_group:
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode tables */
 	for (; it_index < flex_gd->count; it_index++) {
-		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+		unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+		ext4_fsblk_t next_group_start;
+
+		if (start_blk + itb > last_blk)
 			goto next_group;
 		group_data[it_index].inode_table = start_blk;
-		group = ext4_get_group_number(sb, start_blk - 1);
+		group = ext4_get_group_number(sb, start_blk);
+		next_group_start = ext4_group_first_block_no(sb, group + 1);
 		group -= group_data[0].group;
-		group_data[group].free_blocks_count -=
-					EXT4_SB(sb)->s_itb_per_group;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
 
+		if (start_blk + itb > next_group_start) {
+			flex_gd->bg_flags[group + 1] &= uninit_mask;
+			overhead = start_blk + itb - next_group_start;
+			group_data[group + 1].free_blocks_count -= overhead;
+			itb -= overhead;
+		}
+
+		group_data[group].free_blocks_count -= itb;
+		flex_gd->bg_flags[group] &= uninit_mask;
 		start_blk += EXT4_SB(sb)->s_itb_per_group;
 	}
 
@@ -396,7 +404,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 		start = ext4_group_first_block_no(sb, group);
 		group -= flex_gd->groups[0].group;
 
-		count2 = sb->s_blocksize * 8 - (block - start);
+		count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start);
 		if (count2 > count)
 			count2 = count;
 
@@ -615,7 +623,7 @@ handle_ib:
 			if (err)
 				goto out;
 			count = group_table_count[j];
-			start = group_data[i].block_bitmap;
+			start = (&group_data[i].block_bitmap)[j];
 			block = start;
 		}
 
@@ -1058,7 +1066,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
 			break;
 
 		if (meta_bg == 0)
-			backup_block = group * bpg + blk_off;
+			backup_block = ((ext4_fsblk_t)group) * bpg + blk_off;
 		else
 			backup_block = (ext4_group_first_block_no(sb, group) +
 					ext4_bg_has_super(sb, group));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3f7c39e6d097..21a0b43a7d31 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -964,7 +964,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb,
 	 * Currently we don't know the generation for parent directory, so
 	 * a generation of 0 means "accept any"
 	 */
-	inode = ext4_iget(sb, ino);
+	inode = ext4_iget_normal(sb, ino);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 	if (generation && inode->i_generation != generation) {
@@ -1483,8 +1483,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_max_batch_time) {
-		if (arg == 0)
-			arg = EXT4_DEF_MAX_BATCH_TIME;
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
 		sbi->s_min_batch_time = arg;
@@ -1634,13 +1632,6 @@ static int parse_options(char *options, struct super_block *sb,
 					"not specified");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext4_msg(sb, KERN_ERR, "journaled quota format "
-					"specified with no journaling "
-					"enabled");
-			return 0;
-		}
 	}
 #endif
 	if (test_opt(sb, DIOREAD_NOLOCK)) {
@@ -1959,6 +1950,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	}
 
 	/* old crc16 code */
+	if (!(sbi->s_es->s_feature_ro_compat &
+	      cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)))
+		return 0;
+
 	offset = offsetof(struct ext4_group_desc, bg_checksum);
 
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
@@ -2687,10 +2682,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2704,7 +2700,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
@@ -3213,11 +3209,19 @@ int ext4_calculate_overhead(struct super_block *sb)
 }
 
 
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t resv_clusters;
 
 	/*
+	 * There's no need to reserve anything when we aren't using extents.
+	 * The space estimates are exact, there are no unwritten extents,
+	 * hole punching doesn't need new metadata... This is needed especially
+	 * to keep ext2/3 backward compatibility.
+	 */
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+		return 0;
+	/*
 	 * By default we reserve 2% or 4096 clusters, whichever is smaller.
 	 * This should cover the situations where we can not afford to run
 	 * out of space like for example punch hole, or converting
@@ -3225,7 +3229,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
 	 * allocation would require 1, or 2 blocks, higher numbers are
 	 * very rare.
 	 */
-	resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+	resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+			EXT4_SB(sb)->s_cluster_bits;
 
 	do_div(resv_clusters, 50);
 	resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -3583,16 +3588,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
-	i = le32_to_cpu(es->s_flags);
-	if (i & EXT2_FLAGS_UNSIGNED_HASH)
-		sbi->s_hash_unsigned = 3;
-	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+		i = le32_to_cpu(es->s_flags);
+		if (i & EXT2_FLAGS_UNSIGNED_HASH)
+			sbi->s_hash_unsigned = 3;
+		else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
 #ifdef __CHAR_UNSIGNED__
-		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
-		sbi->s_hash_unsigned = 3;
+			if (!(sb->s_flags & MS_RDONLY))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+			sbi->s_hash_unsigned = 3;
 #else
-		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+			if (!(sb->s_flags & MS_RDONLY))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
 #endif
+		}
 	}
 
 	/* Handle clustersize */
@@ -3969,10 +3980,10 @@ no_journal:
 			 "available");
 	}
 
-	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
-			 "reserved pool", ext4_calculate_resv_clusters(sbi));
+			 "reserved pool", ext4_calculate_resv_clusters(sb));
 		goto failed_mount4a;
 	}
 
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c081e34f717f..a20816e7eb3a 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -189,14 +189,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
 }
 
 static int
-ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
+		       void *value_start)
 {
-	while (!IS_LAST_ENTRY(entry)) {
-		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+	struct ext4_xattr_entry *e = entry;
+
+	while (!IS_LAST_ENTRY(e)) {
+		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EIO;
-		entry = next;
+		e = next;
+	}
+
+	while (!IS_LAST_ENTRY(entry)) {
+		if (entry->e_value_size != 0 &&
+		    (value_start + le16_to_cpu(entry->e_value_offs) <
+		     (void *)e + sizeof(__u32) ||
+		     value_start + le16_to_cpu(entry->e_value_offs) +
+		    le32_to_cpu(entry->e_value_size) > end))
+			return -EIO;
+		entry = EXT4_XATTR_NEXT(entry);
 	}
+
 	return 0;
 }
 
@@ -213,7 +227,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 		return -EIO;
 	if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
 		return -EIO;
-	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
+				       bh->b_data);
 	if (!error)
 		set_buffer_verified(bh);
 	return error;
@@ -329,7 +344,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(entry, end);
+	error = ext4_xattr_check_names(entry, end, entry);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -457,7 +472,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	raw_inode = ext4_raw_inode(&iloc);
 	header = IHDR(inode, raw_inode);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(IFIRST(header), end);
+	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -517,8 +532,8 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 }
 
 /*
- * Release the xattr block BH: If the reference count is > 1, decrement
- * it; otherwise free the block.
+ * Release the xattr block BH: If the reference count is > 1, decrement it;
+ * otherwise free the block.
  */
 static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
@@ -538,16 +553,31 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		if (ce)
 			mb_cache_entry_free(ce);
 		get_bh(bh);
+		unlock_buffer(bh);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
-		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
 		if (ce)
 			mb_cache_entry_release(ce);
+		/*
+		 * Beware of this ugliness: Releasing of xattr block references
+		 * from different inodes can race and so we have to protect
+		 * from a race where someone else frees the block (and releases
+		 * its journal_head) before we are done dirtying the buffer. In
+		 * nojournal mode this race is harmless and we actually cannot
+		 * call ext4_handle_dirty_xattr_block() with locked buffer as
+		 * that function can call sync_dirty_buffer() so for that case
+		 * we handle the dirtying after unlocking the buffer.
+		 */
+		if (ext4_handle_valid(handle))
+			error = ext4_handle_dirty_xattr_block(handle, inode,
+							      bh);
 		unlock_buffer(bh);
-		error = ext4_handle_dirty_xattr_block(handle, inode, bh);
+		if (!ext4_handle_valid(handle))
+			error = ext4_handle_dirty_xattr_block(handle, inode,
+							      bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -957,7 +987,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	is->s.here = is->s.first;
 	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
-		error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+		error = ext4_xattr_check_names(IFIRST(header), is->s.end,
+					       IFIRST(header));
 		if (error)
 			return error;
 		/* Find the named attribute. */
@@ -1350,6 +1381,9 @@ retry:
 				    s_min_extra_isize) {
 					tried_min_extra_isize++;
 					new_extra_isize = s_min_extra_isize;
+					kfree(is); is = NULL;
+					kfree(bs); bs = NULL;
+					brelse(bh);
 					goto retry;
 				}
 				error = -1;
diff --git a/fs/file.c b/fs/file.c
index 4a78f981557a..9de20265a78c 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@ static void *alloc_fdmem(size_t size)
 	 * vmalloc() if the allocation size will be considered "large" by the VM.
 	 */
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
 		if (data != NULL)
 			return data;
 	}
diff --git a/fs/file_table.c b/fs/file_table.c
index 485dc0eddd67..54a34be444f9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -211,10 +211,10 @@ static void drop_file_write_access(struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 
-	put_write_access(inode);
-
 	if (special_file(inode->i_mode))
 		return;
+
+	put_write_access(inode);
 	if (file_check_writeable(file) != 0)
 		return;
 	__mnt_drop_write(mnt);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3be57189efd5..b44306378193 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -87,16 +87,29 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -112,7 +125,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
 		trace_writeback_nowork(bdi);
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -159,7 +172,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -457,12 +470,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
-	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
-	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-		inode->i_state &= ~I_DIRTY_PAGES;
+
 	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	inode->i_state &= ~I_DIRTY;
+
+	/*
+	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
+	 * __mark_inode_dirty() to test i_state without grabbing i_lock -
+	 * either they see the I_DIRTY bits cleared or we see the dirtied
+	 * inode.
+	 *
+	 * I_DIRTY_PAGES is always cleared together above even if @mapping
+	 * still has dirty pages.  The flag is reinstated after smp_mb() if
+	 * necessary.  This guarantees that either __mark_inode_dirty()
+	 * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+	 */
+	smp_mb();
+
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		inode->i_state |= I_DIRTY_PAGES;
+
 	spin_unlock(&inode->i_lock);
+
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		int err = write_inode(inode, wbc);
@@ -505,13 +534,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
-	 * Skip inode if it is clean. We don't want to mess with writeback
-	 * lists in this function since flusher thread may be doing for example
-	 * sync in parallel and if we move the inode, it could get skipped. So
-	 * here we make sure inode is on some writeback list and leave it there
-	 * unless we have completely cleaned the inode.
+	 * Skip inode if it is clean and we have no outstanding writeback in
+	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+	 * function since flusher thread may be doing for example sync in
+	 * parallel and if we move the inode, it could get skipped. So here we
+	 * make sure inode is on some writeback list and leave it there unless
+	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode != WB_SYNC_ALL ||
+	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
 	inode->i_state |= I_SYNC;
 	spin_unlock(&inode->i_lock);
@@ -1013,7 +1045,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   list_empty(&bdi->bdi_list))) {
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken
@@ -1035,10 +1067,10 @@ void bdi_writeback_workfn(struct work_struct *work)
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list) ||
-	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
-		queue_delayed_work(bdi_wq, &wb->dwork,
-			msecs_to_jiffies(dirty_writeback_interval * 10));
+	if (!list_empty(&bdi->work_list))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+		bdi_wakeup_thread_delayed(bdi);
 
 	current->flags &= ~PF_SWAPWRITE;
 }
@@ -1130,12 +1162,11 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	}
 
 	/*
-	 * make sure that changes are seen by all cpus before we test i_state
-	 * -- mikulas
+	 * Paired with smp_mb() in __writeback_single_inode() for the
+	 * following lockless i_state test.  See there for details.
 	 */
 	smp_mb();
 
-	/* avoid the locking if we can */
 	if ((inode->i_state & flags) == flags)
 		return;
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1d55f9465400..23bf1a52a5da 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1296,22 +1296,6 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov,
 	return fuse_dev_do_read(fc, file, &cs, iov_length(iov, nr_segs));
 }
 
-static int fuse_dev_pipe_buf_steal(struct pipe_inode_info *pipe,
-				   struct pipe_buffer *buf)
-{
-	return 1;
-}
-
-static const struct pipe_buf_operations fuse_dev_pipe_buf_ops = {
-	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
-	.confirm = generic_pipe_buf_confirm,
-	.release = generic_pipe_buf_release,
-	.steal = fuse_dev_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
-};
-
 static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
@@ -1358,7 +1342,11 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 		buf->page = bufs[page_nr].page;
 		buf->offset = bufs[page_nr].offset;
 		buf->len = bufs[page_nr].len;
-		buf->ops = &fuse_dev_pipe_buf_ops;
+		/*
+		 * Need to be careful about this.  Having buf->ops in module
+		 * code can Oops if the buffer persists after module unload.
+		 */
+		buf->ops = &nosteal_pipe_buf_ops;
 
 		pipe->nrbufs++;
 		page_nr++;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 473e8453a7df..4fafb8484bbc 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2468,6 +2468,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 {
 	struct fuse_file *ff = file->private_data;
 	struct inode *inode = file->f_inode;
+	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = ff->fc;
 	struct fuse_req *req;
 	struct fuse_fallocate_in inarg = {
@@ -2485,10 +2486,20 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 
 	if (lock_inode) {
 		mutex_lock(&inode->i_mutex);
-		if (mode & FALLOC_FL_PUNCH_HOLE)
-			fuse_set_nowrite(inode);
+		if (mode & FALLOC_FL_PUNCH_HOLE) {
+			loff_t endbyte = offset + length - 1;
+			err = filemap_write_and_wait_range(inode->i_mapping,
+							   offset, endbyte);
+			if (err)
+				goto out;
+
+			fuse_sync_writes(inode);
+		}
 	}
 
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
 	req = fuse_get_req_nopages(fc);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -2521,11 +2532,11 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 	fuse_invalidate_attr(inode);
 
 out:
-	if (lock_inode) {
-		if (mode & FALLOC_FL_PUNCH_HOLE)
-			fuse_release_nowrite(inode);
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
+	if (lock_inode)
 		mutex_unlock(&inode->i_mutex);
-	}
 
 	return err;
 }
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index b5718516825b..39a986e1da9e 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -461,6 +461,17 @@ static const match_table_t tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+	int err = -ENOMEM;
+	char *buf = match_strdup(s);
+	if (buf) {
+		err = kstrtouint(buf, 10, res);
+		kfree(buf);
+	}
+	return err;
+}
+
 static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 {
 	char *p;
@@ -471,6 +482,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	while ((p = strsep(&opt, ",")) != NULL) {
 		int token;
 		int value;
+		unsigned uv;
 		substring_t args[MAX_OPT_ARGS];
 		if (!*p)
 			continue;
@@ -494,18 +506,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 			break;
 
 		case OPT_USER_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), value);
+			d->user_id = make_kuid(current_user_ns(), uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
 			break;
 
 		case OPT_GROUP_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), value);
+			d->group_id = make_kgid(current_user_ns(), uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 0bad69ed6336..76251600cbea 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -999,6 +999,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int rv;
@@ -1019,6 +1020,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
+	/*
+	 * Now since we are holding a deferred (CW) lock at this point, you
+	 * might be wondering why this is ever needed. There is a case however
+	 * where we've granted a deferred local lock against a cached exclusive
+	 * glock. That is ok provided all granted local locks are deferred, but
+	 * it also means that it is possible to encounter pages which are
+	 * cached and possibly also mapped. So here we check for that and sort
+	 * them out ahead of the dio. The glock state machine will take care of
+	 * everything else.
+	 *
+	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+	 * the first place, mapping->nr_pages will always be zero.
+	 */
+	if (mapping->nrpages) {
+		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t len = iov_length(iov, nr_segs);
+		loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+		rv = 0;
+		if (len == 0)
+			goto out;
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+		rv = filemap_write_and_wait_range(mapping, lstart, end);
+		if (rv)
+			return rv;
+		truncate_inode_pages_range(mapping, lstart, end);
+	}
+
 	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
 				  offset, nr_segs, gfs2_get_block_direct,
 				  NULL, NULL, 0);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 62b484e4a9e4..bc5dac400125 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1536,10 +1536,22 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
 		ogid = ngid = NO_GID_QUOTA_CHANGE;
 
-	error = gfs2_quota_lock(ip, nuid, ngid);
+	error = get_write_access(inode);
 	if (error)
 		return error;
 
+	error = gfs2_rs_alloc(ip);
+	if (error)
+		goto out;
+
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		goto out;
+
+	error = gfs2_quota_lock(ip, nuid, ngid);
+	if (error)
+		goto out;
+
 	if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) ||
 	    !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) {
 		error = gfs2_quota_check(ip, nuid, ngid);
@@ -1566,6 +1578,8 @@ out_end_trans:
 	gfs2_trans_end(sdp);
 out_gunlock_q:
 	gfs2_quota_unlock(ip);
+out:
+	put_write_access(inode);
 	return error;
 }
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 60ede2a0f43f..f7dd3b4f8ab0 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1317,8 +1317,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	if (IS_ERR(s))
 		goto error_bdev;
 
-	if (s->s_root)
+	if (s->s_root) {
+		/*
+		 * s_umount nests inside bd_mutex during
+		 * __invalidate_device().  blkdev_put() acquires
+		 * bd_mutex and can't be called under s_umount.  Drop
+		 * s_umount temporarily.  This is safe as we're
+		 * holding an active reference.
+		 */
+		up_write(&s->s_umount);
 		blkdev_put(bdev, mode);
+		down_write(&s->s_umount);
+	}
 
 	memset(&args, 0, sizeof(args));
 	args.ar_quota = GFS2_QUOTA_DEFAULT;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a3f868ae3fd4..4e5f332f15d9 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -916,14 +916,8 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
-{
-	return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
-				dentry->d_name.name);
-}
-
 static struct dentry_operations anon_ops = {
-	.d_dname = hugetlb_dname
+	.d_dname = simple_dname
 };
 
 /*
diff --git a/fs/inode.c b/fs/inode.c
index 00d5fc3b86e1..1b300a06b8be 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1837,14 +1837,18 @@ EXPORT_SYMBOL(inode_init_owner);
  * inode_owner_or_capable - check current task permissions to inode
  * @inode: inode being checked
  *
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
  */
 bool inode_owner_or_capable(const struct inode *inode)
 {
+	struct user_namespace *ns;
+
 	if (uid_eq(current_fsuid(), inode->i_uid))
 		return true;
-	if (inode_capable(inode, CAP_FOWNER))
+
+	ns = current_user_ns();
+	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
 		return true;
 	return false;
 }
diff --git a/fs/ioprio.c b/fs/ioprio.c
index e50170ca7c33..31666c92b46a 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -157,14 +157,16 @@ out:
 
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
-	unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+	unsigned short aclass;
+	unsigned short bclass;
 
-	if (aclass == IOPRIO_CLASS_NONE)
-		aclass = IOPRIO_CLASS_BE;
-	if (bclass == IOPRIO_CLASS_NONE)
-		bclass = IOPRIO_CLASS_BE;
+	if (!ioprio_valid(aprio))
+		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+	if (!ioprio_valid(bprio))
+		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 
+	aclass = IOPRIO_PRIO_CLASS(aprio);
+	bclass = IOPRIO_PRIO_CLASS(bprio);
 	if (aclass == bclass)
 		return min(aprio, bprio);
 	if (aclass > bclass)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d3705490ff9c..10489bbd40fc 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -69,7 +69,7 @@ static void isofs_put_super(struct super_block *sb)
 	return;
 }
 
-static int isofs_read_inode(struct inode *);
+static int isofs_read_inode(struct inode *, int relocated);
 static int isofs_statfs (struct dentry *, struct kstatfs *);
 
 static struct kmem_cache *isofs_inode_cachep;
@@ -1274,7 +1274,7 @@ out_toomany:
 	goto out;
 }
 
-static int isofs_read_inode(struct inode *inode)
+static int isofs_read_inode(struct inode *inode, int relocated)
 {
 	struct super_block *sb = inode->i_sb;
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
@@ -1419,7 +1419,7 @@ static int isofs_read_inode(struct inode *inode)
 	 */
 
 	if (!high_sierra) {
-		parse_rock_ridge_inode(de, inode);
+		parse_rock_ridge_inode(de, inode, relocated);
 		/* if we want uid/gid set, override the rock ridge setting */
 		if (sbi->s_uid_set)
 			inode->i_uid = sbi->s_uid;
@@ -1498,9 +1498,10 @@ static int isofs_iget5_set(struct inode *ino, void *data)
  * offset that point to the underlying meta-data for the inode.  The
  * code below is otherwise similar to the iget() code in
  * include/linux/fs.h */
-struct inode *isofs_iget(struct super_block *sb,
-			 unsigned long block,
-			 unsigned long offset)
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated)
 {
 	unsigned long hashval;
 	struct inode *inode;
@@ -1522,7 +1523,7 @@ struct inode *isofs_iget(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 
 	if (inode->i_state & I_NEW) {
-		ret = isofs_read_inode(inode);
+		ret = isofs_read_inode(inode, relocated);
 		if (ret < 0) {
 			iget_failed(inode);
 			inode = ERR_PTR(ret);
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 99167238518d..0ac4c1f73fbd 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -107,7 +107,7 @@ extern int iso_date(char *, int);
 
 struct inode;		/* To make gcc happy */
 
-extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *);
+extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated);
 extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *);
 extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *);
 
@@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int
 extern struct buffer_head *isofs_bread(struct inode *, sector_t);
 extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
 
-extern struct inode *isofs_iget(struct super_block *sb,
-                                unsigned long block,
-                                unsigned long offset);
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated);
+
+static inline struct inode *isofs_iget(struct super_block *sb,
+				       unsigned long block,
+				       unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 0);
+}
+
+static inline struct inode *isofs_iget_reloc(struct super_block *sb,
+					     unsigned long block,
+					     unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 1);
+}
 
 /* Because the inode number is no longer relevant to finding the
  * underlying meta-data for an inode, we are free to choose a more
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c0bf42472e40..735d7522a3a9 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -30,6 +30,7 @@ struct rock_state {
 	int cont_size;
 	int cont_extent;
 	int cont_offset;
+	int cont_loops;
 	struct inode *inode;
 };
 
@@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode)
 	rs->inode = inode;
 }
 
+/* Maximum number of Rock Ridge continuation entries */
+#define RR_MAX_CE_ENTRIES 32
+
 /*
  * Returns 0 if the caller should continue scanning, 1 if the scan must end
  * and -ve on error.
@@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs)
 			goto out;
 		}
 		ret = -EIO;
+		if (++rs->cont_loops >= RR_MAX_CE_ENTRIES)
+			goto out;
 		bh = sb_bread(rs->inode->i_sb, rs->cont_extent);
 		if (bh) {
 			memcpy(rs->buffer, bh->b_data + rs->cont_offset,
@@ -288,12 +294,16 @@ eio:
 	goto out;
 }
 
+#define RR_REGARD_XA 1
+#define RR_RELOC_DE 2
+
 static int
 parse_rock_ridge_inode_internal(struct iso_directory_record *de,
-				struct inode *inode, int regard_xa)
+				struct inode *inode, int flags)
 {
 	int symlink_len = 0;
 	int cnt, sig;
+	unsigned int reloc_block;
 	struct inode *reloc;
 	struct rock_ridge *rr;
 	int rootflag;
@@ -305,7 +315,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de,
 
 	init_rock_state(&rs, inode);
 	setup_rock_ridge(de, inode, &rs);
-	if (regard_xa) {
+	if (flags & RR_REGARD_XA) {
 		rs.chr += 14;
 		rs.len -= 14;
 		if (rs.len < 0)
@@ -352,6 +362,9 @@ repeat:
 			rs.cont_size = isonum_733(rr->u.CE.size);
 			break;
 		case SIG('E', 'R'):
+			/* Invalid length of ER tag id? */
+			if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len)
+				goto out;
 			ISOFS_SB(inode->i_sb)->s_rock = 1;
 			printk(KERN_DEBUG "ISO 9660 Extensions: ");
 			{
@@ -485,12 +498,22 @@ repeat:
 					"relocated directory\n");
 			goto out;
 		case SIG('C', 'L'):
-			ISOFS_I(inode)->i_first_extent =
-			    isonum_733(rr->u.CL.location);
-			reloc =
-			    isofs_iget(inode->i_sb,
-				       ISOFS_I(inode)->i_first_extent,
-				       0);
+			if (flags & RR_RELOC_DE) {
+				printk(KERN_ERR
+				       "ISOFS: Recursive directory relocation "
+				       "is not supported\n");
+				goto eio;
+			}
+			reloc_block = isonum_733(rr->u.CL.location);
+			if (reloc_block == ISOFS_I(inode)->i_iget5_block &&
+			    ISOFS_I(inode)->i_iget5_offset == 0) {
+				printk(KERN_ERR
+				       "ISOFS: Directory relocation points to "
+				       "itself\n");
+				goto eio;
+			}
+			ISOFS_I(inode)->i_first_extent = reloc_block;
+			reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0);
 			if (IS_ERR(reloc)) {
 				ret = PTR_ERR(reloc);
 				goto out;
@@ -637,9 +660,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit)
 	return rpnt;
 }
 
-int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
+int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode,
+			   int relocated)
 {
-	int result = parse_rock_ridge_inode_internal(de, inode, 0);
+	int flags = relocated ? RR_RELOC_DE : 0;
+	int result = parse_rock_ridge_inode_internal(de, inode, flags);
 
 	/*
 	 * if rockridge flag was reset and we didn't look for attributes
@@ -647,7 +672,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
 	 */
 	if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1)
 	    && (ISOFS_SB(inode->i_sb)->s_rock == 2)) {
-		result = parse_rock_ridge_inode_internal(de, inode, 14);
+		result = parse_rock_ridge_inode_internal(de, inode,
+							 flags | RR_REGARD_XA);
 	}
 	return result;
 }
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 626846bac32f..6e2fb5cbacde 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -427,6 +427,7 @@ static int do_one_pass(journal_t *journal,
 	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
 	int			descr_csum_size = 0;
+	int			block_error = 0;
 
 	/*
 	 * First thing is to establish what we expect to find in the log
@@ -521,6 +522,7 @@ static int do_one_pass(journal_t *journal,
 			    !jbd2_descr_block_csum_verify(journal,
 							  bh->b_data)) {
 				err = -EIO;
+				brelse(bh);
 				goto failed;
 			}
 
@@ -599,7 +601,8 @@ static int do_one_pass(journal_t *journal,
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
-						continue;
+						block_error = 1;
+						goto skip_write;
 					}
 
 					/* Find a buffer for the new
@@ -798,7 +801,8 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
-
+	if (block_error && success == 0)
+		success = -EIO;
 	return success;
 
  failed:
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e0c0bc275924..ec34e11d6854 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1151,7 +1151,10 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		 * once a transaction -bzzz
 		 */
 		jh->b_modified = 1;
-		J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+		if (handle->h_buffer_credits <= 0) {
+			ret = -ENOSPC;
+			goto out_unlock_bh;
+		}
 		handle->h_buffer_credits--;
 	}
 
@@ -1234,7 +1237,6 @@ out_unlock_bh:
 	jbd2_journal_put_journal_head(jh);
 out:
 	JBUFFER_TRACE(jh, "exit");
-	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
 	return ret;
 }
 
@@ -1440,9 +1442,12 @@ int jbd2_journal_stop(handle_t *handle)
 	 * to perform a synchronous write.  We do this to detect the
 	 * case where a single process is doing a stream of sync
 	 * writes.  No point in waiting for joiners in that case.
+	 *
+	 * Setting max_batch_time to 0 disables this completely.
 	 */
 	pid = current->pid;
-	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+	if (handle->h_sync && journal->j_last_sync_writer != pid &&
+	    journal->j_max_batch_time) {
 		u64 commit_time, trans_time;
 
 		journal->j_last_sync_writer = pid;
diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c
index 16a5047903a6..406d9cc84ba8 100644
--- a/fs/jffs2/compr_rtime.c
+++ b/fs/jffs2/compr_rtime.c
@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in,
 				unsigned char *cpage_out,
 				uint32_t *sourcelen, uint32_t *dstlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 
@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in,
 				  unsigned char *cpage_out,
 				  uint32_t srclen, uint32_t destlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 413ef89c2d1b..046fee8b6e9b 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -134,8 +134,6 @@ struct jffs2_sb_info {
 	struct rw_semaphore wbuf_sem;	/* Protects the write buffer */
 
 	struct delayed_work wbuf_dwork; /* write-buffer write-out work */
-	int wbuf_queued;                /* non-zero delayed work is queued */
-	spinlock_t wbuf_dwork_lock;     /* protects wbuf_dwork and and wbuf_queued */
 
 	unsigned char *oobbuf;
 	int oobavail; /* How many bytes are available for JFFS2 in OOB */
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index e4619b00f7c5..fa35ff79ab35 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
 	uint32_t version;
 	uint32_t data_crc;
 	uint32_t partial_crc;
-	uint16_t csize;
+	uint32_t csize;
 	uint16_t overlapped;
 };
 
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 03310721712f..b6bd4affd9ad 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -179,6 +179,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
+					remove_wait_queue(&c->erase_wait, &wait);
 				} else
 					spin_unlock(&c->erase_completion_lock);
 			} else if (ret)
@@ -211,20 +212,25 @@ out:
 int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 			   uint32_t *len, uint32_t sumsize)
 {
-	int ret = -EAGAIN;
+	int ret;
 	minsize = PAD(minsize);
 
 	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
 
-	spin_lock(&c->erase_completion_lock);
-	while(ret == -EAGAIN) {
+	while (true) {
+		spin_lock(&c->erase_completion_lock);
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
 			jffs2_dbg(1, "%s(): looping, ret is %d\n",
 				  __func__, ret);
 		}
+		spin_unlock(&c->erase_completion_lock);
+
+		if (ret == -EAGAIN)
+			cond_resched();
+		else
+			break;
 	}
-	spin_unlock(&c->erase_completion_lock);
 	if (!ret)
 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
 
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index a6597d60d76d..09ed55190ee2 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work)
 	struct jffs2_sb_info *c = work_to_sb(work);
 	struct super_block *sb = OFNI_BS_2SFFJ(c);
 
-	spin_lock(&c->wbuf_dwork_lock);
-	c->wbuf_queued = 0;
-	spin_unlock(&c->wbuf_dwork_lock);
-
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_dbg(1, "%s()\n", __func__);
 		jffs2_flush_wbuf_gc(c, 0);
@@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	spin_lock(&c->wbuf_dwork_lock);
-	if (!c->wbuf_queued) {
+	delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+	if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
 		jffs2_dbg(1, "%s()\n", __func__);
-		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay);
-		c->wbuf_queued = 1;
-	}
-	spin_unlock(&c->wbuf_dwork_lock);
 }
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
@@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize = c->mtd->writesize;
 	c->wbuf_ofs = 0xFFFFFFFF;
@@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize =  c->mtd->erasesize;
 
@@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize = c->mtd->writesize;
@@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) {
 		return 0;
 
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize =  c->mtd->writesize;
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index c1a3e603279c..7f464c513ba0 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -95,7 +95,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 
 	if (insert_inode_locked(inode) < 0) {
 		rc = -EINVAL;
-		goto fail_unlock;
+		goto fail_put;
 	}
 
 	inode_init_owner(inode, parent, mode);
@@ -156,7 +156,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
-fail_unlock:
 	clear_nlink(inode);
 	unlock_new_inode(inode);
 fail_put:
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1812f026960c..6ae664b489af 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
 	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	if (status == -ECONNREFUSED) {
+		dprintk("lockd:	NSM upcall RPC failed, status=%d, forcing rebind\n",
+				status);
+		rpc_force_rebind(clnt);
+		status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	}
 	if (status < 0)
 		dprintk("lockd: NSM upcall RPC failed, status=%d\n",
 				status);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index a2aa97d45670..9c8a5a6d33df 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -235,6 +235,7 @@ out_err:
 	if (warned++ == 0)
 		printk(KERN_WARNING
 			"lockd_up: makesock failed, error=%d\n", err);
+	svc_shutdown_net(serv, net);
 	return err;
 }
 
@@ -252,13 +253,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net)
 
 	error = make_socks(serv, net);
 	if (error < 0)
-		goto err_socks;
+		goto err_bind;
 	set_grace_period(net);
 	dprintk("lockd_up_net: per-net data created; net=%p\n", net);
 	return 0;
 
-err_socks:
-	svc_rpcb_cleanup(serv, net);
 err_bind:
 	ln->nlmsvc_users--;
 	return error;
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 8ebd3f551e0c..ffc4045fc62e 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -767,6 +767,7 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 	struct nlm_file		*file = block->b_file;
 	struct nlm_lock		*lock = &block->b_call->a_args.lock;
 	int			error;
+	loff_t			fl_start, fl_end;
 
 	dprintk("lockd: grant blocked lock %p\n", block);
 
@@ -784,9 +785,16 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 	}
 
 	/* Try the lock operation again */
+	/* vfs_lock_file() can mangle fl_start and fl_end, but we need
+	 * them unchanged for the GRANT_MSG
+	 */
 	lock->fl.fl_flags |= FL_SLEEP;
+	fl_start = lock->fl.fl_start;
+	fl_end = lock->fl.fl_end;
 	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
 	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.fl_start = fl_start;
+	lock->fl.fl_end = fl_end;
 
 	switch (error) {
 	case 0:
diff --git a/fs/locks.c b/fs/locks.c
index cb424a4fed71..0274c953b07d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1243,11 +1243,10 @@ int __break_lease(struct inode *inode, unsigned int mode)
 
 restart:
 	break_time = flock->fl_break_time;
-	if (break_time != 0) {
+	if (break_time != 0)
 		break_time -= jiffies;
-		if (break_time == 0)
-			break_time++;
-	}
+	if (break_time == 0)
+		break_time++;
 	locks_insert_block(flock, new_fl);
 	unlock_flocks();
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
diff --git a/fs/mount.h b/fs/mount.h
index 64a858143ff9..68d80bdcd081 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -73,7 +73,7 @@ static inline int mnt_has_parent(struct mount *mnt)
 static inline int is_mounted(struct vfsmount *mnt)
 {
 	/* neither detached nor internal? */
-	return !IS_ERR_OR_NULL(real_mount(mnt));
+	return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns);
 }
 
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
diff --git a/fs/namei.c b/fs/namei.c
index 9ed9361223c0..f7c4393f8535 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -34,6 +34,7 @@
 #include <linux/device_cgroup.h>
 #include <linux/fs_struct.h>
 #include <linux/posix_acl.h>
+#include <linux/hash.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -321,10 +322,11 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 		if (!(mask & MAY_WRITE))
-			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+			if (capable_wrt_inode_uidgid(inode,
+						     CAP_DAC_READ_SEARCH))
 				return 0;
 		return -EACCES;
 	}
@@ -334,7 +336,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 
 	/*
@@ -342,7 +344,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
 			return 0;
 
 	return -EACCES;
@@ -1646,8 +1648,7 @@ static inline int can_lookup(struct inode *inode)
 
 static inline unsigned int fold_hash(unsigned long hash)
 {
-	hash += hash >> (8*sizeof(int));
-	return hash;
+	return hash_64(hash, 32);
 }
 
 #else	/* 32-bit case */
@@ -2199,7 +2200,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-	return !inode_capable(inode, CAP_FOWNER);
+	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
 }
 
 /*
@@ -2263,6 +2264,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
  */
 static inline int may_create(struct inode *dir, struct dentry *child)
 {
+	audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
 	if (child->d_inode)
 		return -EEXIST;
 	if (IS_DEADDIR(dir))
@@ -3654,6 +3656,7 @@ retry:
 out_dput:
 	done_path_create(&new_path, new_dentry);
 	if (retry_estale(error, how)) {
+		path_put(&old_path);
 		how |= LOOKUP_REVAL;
 		goto retry;
 	}
diff --git a/fs/namespace.c b/fs/namespace.c
index a45ba4f267fe..d0244c8ba09c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -828,8 +828,21 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
 	/* Don't allow unprivileged users to change mount flags */
-	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
-		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+	if (flag & CL_UNPRIVILEGED) {
+		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+		if (mnt->mnt.mnt_flags & MNT_READONLY)
+			mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+		if (mnt->mnt.mnt_flags & MNT_NODEV)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+		if (mnt->mnt.mnt_flags & MNT_NOSUID)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+		if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+	}
 
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_sb = sb;
@@ -1261,6 +1274,8 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
@@ -1327,6 +1342,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 	if (!check_mnt(mnt))
 		goto dput_and_out;
+	retval = -EPERM;
+	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+		goto dput_and_out;
 
 	retval = do_umount(mnt, flags);
 dput_and_out:
@@ -1764,9 +1782,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
-	if (mnt->mnt_flags & MNT_LOCK_READONLY)
-		return -EPERM;
-
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
@@ -1792,6 +1807,39 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
+	/* Don't allow changing of locked mnt flags.
+	 *
+	 * No locks need to be held here while testing the various
+	 * MNT_LOCK flags because those flags can never be cleared
+	 * once they are set.
+	 */
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+	    !(mnt_flags & MNT_READONLY)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+	    !(mnt_flags & MNT_NODEV)) {
+		/* Was the nodev implicitly added in mount? */
+		if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+		    !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+			mnt_flags |= MNT_NODEV;
+		} else {
+			return -EPERM;
+		}
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+	    !(mnt_flags & MNT_NOSUID)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+	    !(mnt_flags & MNT_NOEXEC)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+	    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+		return -EPERM;
+	}
+
 	err = security_sb_remount(sb, data);
 	if (err)
 		return err;
@@ -1805,7 +1853,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 		err = do_remount_sb(sb, flags, data, 0);
 	if (!err) {
 		br_write_lock(&vfsmount_lock);
-		mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
 		mnt->mnt.mnt_flags = mnt_flags;
 		br_write_unlock(&vfsmount_lock);
 	}
@@ -1991,7 +2039,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 		 */
 		if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
 			flags |= MS_NODEV;
-			mnt_flags |= MNT_NODEV;
+			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 	}
 
@@ -2309,6 +2357,14 @@ long do_mount(const char *dev_name, const char *dir_name,
 	if (flags & MS_RDONLY)
 		mnt_flags |= MNT_READONLY;
 
+	/* The default atime for remount is preservation */
+	if ((flags & MS_REMOUNT) &&
+	    ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+		       MS_STRICTATIME)) == 0)) {
+		mnt_flags &= ~MNT_ATIME_MASK;
+		mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+	}
+
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
 		   MS_STRICTATIME);
@@ -2649,6 +2705,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make sure we can reach put_old from new_root */
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
+	/* make certain new is below the root */
+	if (!is_path_reachable(new_mnt, new.dentry, &root))
+		goto out4;
 	root_mp->m_count++; /* pin it so it won't go away */
 	br_write_lock(&vfsmount_lock);
 	detach_mnt(new_mnt, &parent_path);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 60426ccb3b65..2f970de02b16 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 						result = -EIO;
 					}
 				}
-				result = 0;
 			}
 			mutex_unlock(&server->root_setup_lock);
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117c3ed1..4d0161442565 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
 static inline sector_t normalize(sector_t s, int base)
 {
 	sector_t tmp = s; /* Since do_div modifies its argument */
-	return s - do_div(tmp, base);
+	return s - sector_div(tmp, base);
 }
 
 static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 57db3244f4d9..ef0c394b7bf5 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -108,6 +108,8 @@ again:
 			continue;
 		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
 			continue;
+		if (!nfs4_valid_open_stateid(state))
+			continue;
 		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
 		get_nfs_open_context(ctx);
@@ -175,7 +177,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
 {
 	int res = 0;
 
-	res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+		res = nfs4_proc_delegreturn(inode,
+				delegation->cred,
+				&delegation->stateid,
+				issync);
 	nfs_free_delegation(delegation);
 	return res;
 }
@@ -361,11 +367,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	int err;
+	int err = 0;
 
 	if (delegation == NULL)
 		return 0;
 	do {
+		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+			break;
 		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
 		if (!issync || err != -EAGAIN)
 			break;
@@ -586,10 +594,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
 	rcu_read_unlock();
 }
 
+static void nfs_revoke_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL) {
+		set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+		nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+	}
+	rcu_read_unlock();
+}
+
 void nfs_remove_bad_delegation(struct inode *inode)
 {
 	struct nfs_delegation *delegation;
 
+	nfs_revoke_delegation(inode);
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation) {
 		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
@@ -656,16 +677,19 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation == NULL)
+		goto out_enoent;
 
-	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
-		rcu_read_unlock();
-		return -ENOENT;
-	}
+	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+		goto out_enoent;
 	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
 	return 0;
+out_enoent:
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 static struct inode *
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9a79c7a99d6d..e02b090ab9da 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
 	NFS_DELEGATION_RETURN_IF_CLOSED,
 	NFS_DELEGATION_REFERENCED,
 	NFS_DELEGATION_RETURNING,
+	NFS_DELEGATION_REVOKED,
 };
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0bd7a55a5f07..725e87538c98 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -180,6 +180,7 @@ static void nfs_direct_req_free(struct kref *kref)
 {
 	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+	nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
 	if (dreq->l_ctx != NULL)
 		nfs_put_lock_context(dreq->l_ctx);
 	if (dreq->ctx != NULL)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c1c7a9d78722..e9be01b2cc5a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -519,7 +519,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
-	int err;
+	int err = 0;
 
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
@@ -1382,18 +1382,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_version = fattr->change_attr;
 		}
 	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
-		invalid |= save_cache_validity;
+		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	} else if (server->caps & NFS_CAP_MTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	} else if (server->caps & NFS_CAP_CTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
@@ -1416,7 +1418,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)new_isize);
 		}
 	} else
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
 
@@ -1424,7 +1427,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
 	else if (server->caps & NFS_CAP_ATIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATIME
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1435,7 +1439,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 		}
 	} else if (server->caps & NFS_CAP_MODE)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1446,7 +1451,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_uid = fattr->uid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1457,7 +1463,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_gid = fattr->gid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER_GROUP)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1470,7 +1477,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		}
 	} else if (server->caps & NFS_CAP_NLINK)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 4a1aafba6a20..8c34f57a9aef 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -305,7 +305,10 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		.rpc_argp	= &args,
 		.rpc_resp	= &fattr,
 	};
-	int status;
+	int status = 0;
+
+	if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+		goto out;
 
 	status = -EOPNOTSUPP;
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 4cbad5d6b276..cc143ee7a56e 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -240,13 +240,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	error = nfs4_discover_server_trunking(clp, &old);
 	if (error < 0)
 		goto error;
-	nfs_put_client(clp);
-	if (clp != old) {
-		clp->cl_preserve_clid = true;
-		clp = old;
-	}
 
-	return clp;
+	if (clp != old)
+		clp->cl_preserve_clid = true;
+	nfs_put_client(clp);
+	return old;
 
 error:
 	nfs_mark_client_ready(clp, error);
@@ -313,6 +311,16 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos" */
 		if (pos->cl_cons_state > NFS_CS_READY) {
@@ -324,22 +332,14 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				goto out;
+			status = -NFS4ERR_STALE_CLIENTID;
+			spin_lock(&nn->nfs_client_lock);
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_proto != new->cl_proto)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
 		if (pos->cl_clientid != new->cl_clientid)
 			continue;
 
@@ -445,6 +445,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos", especially the client
 		 * ID and serverowner fields.  Wait for CREATE_SESSION
@@ -464,20 +474,12 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				break;
+			status = -NFS4ERR_STALE_CLIENTID;
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_proto != new->cl_proto)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
 		if (!nfs4_match_clientids(pos, new))
 			continue;
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 22d10623f5ee..b039f7f26d95 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -1300,7 +1300,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
 	struct nfs4_filelayout *flo;
 
 	flo = kzalloc(sizeof(*flo), gfp_flags);
-	return &flo->generic_hdr;
+	return flo != NULL ? &flo->generic_hdr : NULL;
 }
 
 static void
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 661a0f611215..678cb8964532 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -797,34 +797,34 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
-
-	if (filelayout_test_devid_unavailable(devid))
-		return NULL;
+	struct nfs4_pnfs_ds *ret = ds;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
 		filelayout_mark_devid_invalid(devid);
-		return NULL;
+		goto out;
 	}
 	if (ds->ds_clp)
-		return ds;
+		goto out_test_devid;
 
 	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 		int err;
 
 		err = nfs4_ds_connect(s, ds);
-		if (err) {
+		if (err)
 			nfs4_mark_deviceid_unavailable(devid);
-			ds = NULL;
-		}
 		nfs4_clear_ds_conn_bit(ds);
 	} else {
 		/* Either ds is connected, or ds is NULL */
 		nfs4_wait_ds_connect(ds);
 	}
-	return ds;
+out_test_devid:
+	if (filelayout_test_devid_unavailable(devid))
+		ret = NULL;
+out:
+	return ret;
 }
 
 module_param(dataserver_retrans, uint, 0644);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d7ba5616989c..20ebcfa3c92e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1160,29 +1160,24 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
 	int ret;
 
 	if (!data->rpc_done) {
-		ret = data->rpc_status;
-		goto err;
+		if (data->rpc_status) {
+			ret = data->rpc_status;
+			goto err;
+		}
+		/* cached opens have already been processed */
+		goto update;
 	}
 
-	ret = -ESTALE;
-	if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) ||
-	    !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) ||
-	    !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE))
-		goto err;
-
-	ret = -ENOMEM;
-	state = nfs4_get_open_state(inode, data->owner);
-	if (state == NULL)
-		goto err;
-
 	ret = nfs_refresh_inode(inode, &data->f_attr);
 	if (ret)
 		goto err;
 
 	if (data->o_res.delegation_type != 0)
 		nfs4_opendata_check_deleg(data, state);
+update:
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			    data->o_arg.fmode);
+	atomic_inc(&state->count);
 
 	return state;
 err:
@@ -1421,7 +1416,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 			nfs_inode_find_state_and_recover(state->inode,
 					stateid);
 			nfs4_schedule_stateid_recovery(server, state);
-			return 0;
+			return -EAGAIN;
 		case -NFS4ERR_DELAY:
 		case -NFS4ERR_GRACE:
 			set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -1850,6 +1845,28 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+	nfs_remove_bad_delegation(state->inode);
+	write_seqlock(&state->seqlock);
+	nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+	write_sequnlock(&state->seqlock);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+	if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+		nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	/* NFSv4.0 doesn't allow for delegation recovery on open expire */
+	nfs40_clear_delegation_stateid(state);
+	return nfs4_open_expired(sp, state);
+}
+
 #if defined(CONFIG_NFS_V4_1)
 static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 {
@@ -2292,6 +2309,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct inode *inode = calldata->inode;
+	bool is_rdonly, is_wronly, is_rdwr;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2299,21 +2317,27 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_wait;
 
 	task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-	calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
 	spin_lock(&state->owner->so_lock);
+	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
 	/* Calculate the change in open mode */
+	calldata->arg.fmode = 0;
 	if (state->n_rdwr == 0) {
-		if (state->n_rdonly == 0) {
-			call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-			calldata->arg.fmode &= ~FMODE_READ;
-		}
-		if (state->n_wronly == 0) {
-			call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-			calldata->arg.fmode &= ~FMODE_WRITE;
-		}
-	}
+		if (state->n_rdonly == 0)
+			call_close |= is_rdonly;
+		else if (is_rdonly)
+			calldata->arg.fmode |= FMODE_READ;
+		if (state->n_wronly == 0)
+			call_close |= is_wronly;
+		else if (is_wronly)
+			calldata->arg.fmode |= FMODE_WRITE;
+	} else if (is_rdwr)
+		calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
+
+	if (calldata->arg.fmode == 0)
+		call_close |= is_rdwr;
+
 	if (!nfs4_valid_open_stateid(state))
 		call_close = 0;
 	spin_unlock(&state->owner->so_lock);
@@ -3612,8 +3636,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
 {
 	nfs4_stateid current_stateid;
 
-	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
-		return false;
+	/* If the current stateid represents a lost lock, then exit */
+	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+		return true;
 	return nfs4_stateid_match(stateid, &current_stateid);
 }
 
@@ -4227,8 +4252,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
 			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-			task->tk_status = 0;
-			return -EAGAIN;
+			goto wait_on_recovery;
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4406,11 +4430,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	switch (task->tk_status) {
-	case -NFS4ERR_STALE_STATEID:
-	case -NFS4ERR_EXPIRED:
 	case 0:
 		renew_lease(data->res.server, data->timestamp);
 		break;
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		task->tk_status = 0;
+		break;
 	default:
 		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
 				-EAGAIN) {
@@ -4572,6 +4602,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 			status = 0;
 	}
 	request->fl_ops->fl_release_private(request);
+	request->fl_ops = NULL;
 out:
 	return status;
 }
@@ -6058,7 +6089,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 	int ret = 0;
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
-		return 0;
+		return -EAGAIN;
 	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
@@ -6231,9 +6262,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	struct nfs4_state *state = NULL;
-	unsigned long timeo, giveup;
+	unsigned long timeo, now, giveup;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
 	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
 		goto out;
@@ -6241,12 +6272,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+	/*
+	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+	 * (or clients) writing to the same RAID stripe
+	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
+	/*
+	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+	 * existing layout before getting a new one).
+	 */
 	case -NFS4ERR_RECALLCONFLICT:
 		timeo = rpc_get_timeout(task->tk_client);
 		giveup = lgp->args.timestamp + timeo;
-		if (time_after(giveup, jiffies))
-			task->tk_status = -NFS4ERR_DELAY;
+		now = jiffies;
+		if (time_after(giveup, now)) {
+			unsigned long delay;
+
+			/* Delay for:
+			 * - Not less then NFS4_POLL_RETRY_MIN.
+			 * - One last time a jiffie before we give up
+			 * - exponential backoff (time_now minus start_attempt)
+			 */
+			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+				    min((giveup - now - 1),
+					now - lgp->args.timestamp));
+
+			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+				__func__, delay);
+			rpc_delay(task, delay);
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			goto out; /* Do not call nfs4_async_handle_error() */
+		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
@@ -6361,6 +6418,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 
 	dprintk("--> %s\n", __func__);
 
+	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+	pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
 	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
 	if (!lgp->args.layout.pages) {
 		nfs4_layoutget_release(lgp);
@@ -6373,9 +6433,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 
-	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
-	pnfs_get_layout_hdr(NFS_I(inode)->layout);
-
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return ERR_CAST(task);
@@ -6682,7 +6739,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
-		case -NFS4ERR_NOTSUPP:
+		case -ENOTSUPP:
 			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
@@ -6714,7 +6771,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	 * Fall back on "guess and check" method if
 	 * the server doesn't support SECINFO_NO_NAME
 	 */
-	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+	if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
 		err = nfs4_find_root_sec(server, fhandle, info);
 		goto out_freepage;
 	}
@@ -6939,7 +6996,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
+	.recover_open	= nfs40_open_expired,
 	.recover_lock	= nfs4_lock_expired,
 	.establish_clid = nfs4_init_clientid,
 	.get_clid_cred	= nfs4_get_setclientid_cred,
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1720d32ffa54..e1ba58c3d1ad 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work)
 			}
 			nfs_expire_all_delegations(clp);
 		} else {
+			int ret;
+
 			/* Queue an asynchronous RENEW. */
-			ops->sched_state_renewal(clp, cred, renew_flags);
+			ret = ops->sched_state_renewal(clp, cred, renew_flags);
 			put_rpccred(cred);
-			goto out_exp;
+			switch (ret) {
+			default:
+				goto out_exp;
+			case -EAGAIN:
+			case -ENOMEM:
+				break;
+			}
 		}
 	} else {
 		dprintk("%s: failed to call renewd. Reason: lease not expired \n",
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2c37442ed936..d482b86d0e0b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1699,7 +1699,8 @@ restart:
 			if (status < 0) {
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
-				return nfs4_recovery_handle_error(clp, status);
+				status = nfs4_recovery_handle_error(clp, status);
+				return (status != 0) ? status : -EAGAIN;
 			}
 
 			nfs4_put_state_owner(sp);
@@ -1708,7 +1709,7 @@ restart:
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
-	return status;
+	return 0;
 }
 
 static int nfs4_check_lease(struct nfs_client *clp)
@@ -1755,7 +1756,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-		nfs4_state_clear_reclaim_reboot(clp);
 		nfs4_state_start_reclaim_reboot(clp);
 		break;
 	case -NFS4ERR_CLID_INUSE:
@@ -2174,14 +2174,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
-				continue;
-			nfs4_state_end_reclaim_reboot(clp);
-			if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
+			nfs4_state_end_reclaim_reboot(clp);
 		}
 
 		/* Now recover expired state... */
@@ -2189,9 +2186,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4be8d135ed61..988efb4caac0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3002,7 +3002,8 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+		int *nfs_retval)
 {
 	__be32 *p;
 	uint32_t opnum;
@@ -3012,19 +3013,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	if (unlikely(!p))
 		goto out_overflow;
 	opnum = be32_to_cpup(p++);
-	if (opnum != expected) {
-		dprintk("nfs: Server returned operation"
-			" %d but we issued a request for %d\n",
-				opnum, expected);
-		return -EIO;
-	}
+	if (unlikely(opnum != expected))
+		goto out_bad_operation;
 	nfserr = be32_to_cpup(p);
-	if (nfserr != NFS_OK)
-		return nfs4_stat_to_errno(nfserr);
-	return 0;
+	if (nfserr == NFS_OK)
+		*nfs_retval = 0;
+	else
+		*nfs_retval = nfs4_stat_to_errno(nfserr);
+	return true;
+out_bad_operation:
+	dprintk("nfs: Server returned operation"
+		" %d but we issued a request for %d\n",
+			opnum, expected);
+	*nfs_retval = -EREMOTEIO;
+	return false;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	*nfs_retval = -EIO;
+	return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+	int retval;
+
+	__decode_op_hdr(xdr, expected, &retval);
+	return retval;
 }
 
 /* Dummy routine */
@@ -4842,11 +4856,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 	uint32_t savewords, bmlen, i;
 	int status;
 
-	status = decode_op_hdr(xdr, OP_OPEN);
-	if (status != -EIO)
-		nfs_increment_open_seqid(status, res->seqid);
-	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+	if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+		return status;
+	nfs_increment_open_seqid(status, res->seqid);
+	if (status)
+		return status;
+	status = decode_stateid(xdr, &res->stateid);
 	if (unlikely(status))
 		return status;
 
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 5f38ea36e266..af51cf9bf2e3 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -536,16 +536,12 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (err)
 			goto out3;
 		exp.ex_anon_uid= make_kuid(&init_user_ns, an_int);
-		if (!uid_valid(exp.ex_anon_uid))
-			goto out3;
 
 		/* anon gid */
 		err = get_int(&mesg, &an_int);
 		if (err)
 			goto out3;
 		exp.ex_anon_gid= make_kgid(&init_user_ns, an_int);
-		if (!gid_valid(exp.ex_anon_gid))
-			goto out3;
 
 		/* fsid */
 		err = get_int(&mesg, &an_int);
@@ -583,6 +579,17 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 				   exp.ex_uuid);
 		if (err)
 			goto out4;
+		/*
+		 * For some reason exportfs has been passing down an
+		 * invalid (-1) uid & gid on the "dummy" export which it
+		 * uses to test export support.  To make sure exportfs
+		 * sees errors from check_export we therefore need to
+		 * delay these checks till after check_export:
+		 */
+		if (!uid_valid(exp.ex_anon_uid))
+			goto out4;
+		if (!gid_valid(exp.ex_anon_gid))
+			goto out4;
 	}
 
 	expp = svc_export_lookup(&exp);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 8a50b3c18093..e15bcbd5043c 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -385,8 +385,10 @@ sort_pacl(struct posix_acl *pacl)
 	 * by uid/gid. */
 	int i, j;
 
-	if (pacl->a_count <= 4)
-		return; /* no users or groups */
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
 	i = 1;
 	while (pacl->a_entries[i].e_tag == ACL_USER)
 		i++;
@@ -513,13 +515,12 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
 
 	/*
 	 * ACLs with no ACEs are treated differently in the inheritable
-	 * and effective cases: when there are no inheritable ACEs, we
-	 * set a zero-length default posix acl:
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
 	 */
-	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) {
-		pacl = posix_acl_alloc(0, GFP_KERNEL);
-		return pacl ? pacl : ERR_PTR(-ENOMEM);
-	}
+	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
 	/*
 	 * When there are no effective ACEs, the following will end
 	 * up setting a 3-element effective posix ACL with all
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7f05cd140de3..f42bbe5fbc0a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -637,9 +637,11 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
+	int maxtime = max_cb_time(clp->net);
 	struct rpc_timeout	timeparms = {
-		.to_initval	= max_cb_time(clp->net),
+		.to_initval	= maxtime,
 		.to_retries	= 0,
+		.to_maxval	= maxtime,
 	};
 	struct rpc_create_args args = {
 		.net		= clp->net,
@@ -670,7 +672,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		clp->cl_cb_session = ses;
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
-		args.protocol = XPRT_TRANSPORT_BC_TCP;
+		args.protocol = conn->cb_xprt->xpt_class->xcl_ident |
+				XPRT_TRANSPORT_BC;
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
@@ -781,8 +784,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
 {
 	if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
 		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
-		dprintk("%s slot is busy\n", __func__);
-		return false;
+		/* Race breaker */
+		if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+			dprintk("%s slot is busy\n", __func__);
+			return false;
+		}
+		rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
 	}
 	return true;
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 27d74a294515..9240dd1678da 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -576,15 +576,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (create->cr_type) {
 	case NF4LNK:
-		/* ugh! we have to null-terminate the linktext, or
-		 * vfs_symlink() will choke.  it is always safe to
-		 * null-terminate by brute force, since at worst we
-		 * will overwrite the first byte of the create namelen
-		 * in the XDR buffer, which has already been extracted
-		 * during XDR decode.
-		 */
-		create->cr_linkname[create->cr_linklen] = 0;
-
 		status = nfsd_symlink(rqstp, &cstate->current_fh,
 				      create->cr_name, create->cr_namelen,
 				      create->cr_linkname, create->cr_linklen,
@@ -1200,7 +1191,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
 	 */
 	if (argp->opcnt == resp->opcnt)
 		return false;
-
+	if (next->opnum == OP_ILLEGAL)
+		return false;
 	nextd = OPDESC(next);
 	/*
 	 * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
@@ -1307,6 +1299,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		/* If op is non-idempotent */
 		if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
 			plen = opdesc->op_rsize_bop(rqstp, op);
+			/*
+			 * If there's still another operation, make sure
+			 * we'll have space to at least encode an error:
+			 */
+			if (resp->opcnt < args->opcnt)
+				plen += COMPOUND_ERR_SLACK_SPACE;
 			op->status = nfsd4_check_resp_size(resp, plen);
 		}
 
@@ -1471,7 +1469,8 @@ static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *o
 
 static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32);
+	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
+								sizeof(__be32);
 }
 
 static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 316ec843dec2..4a58afa99654 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -367,7 +367,6 @@ static struct nfs4_delegation *
 alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh, u32 type)
 {
 	struct nfs4_delegation *dp;
-	struct nfs4_file *fp = stp->st_file;
 
 	dprintk("NFSD alloc_init_deleg\n");
 	/*
@@ -377,8 +376,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
 	 */
 	if (type != NFS4_OPEN_DELEGATE_READ)
 		return NULL;
-	if (fp->fi_had_conflict)
-		return NULL;
 	if (num_delegations > max_delegations)
 		return NULL;
 	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
@@ -395,8 +392,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
 	INIT_LIST_HEAD(&dp->dl_perfile);
 	INIT_LIST_HEAD(&dp->dl_perclnt);
 	INIT_LIST_HEAD(&dp->dl_recall_lru);
-	get_nfs4_file(fp);
-	dp->dl_file = fp;
+	dp->dl_file = NULL;
 	dp->dl_type = type;
 	fh_copy_shallow(&dp->dl_fh, &current_fh->fh_handle);
 	dp->dl_time = 0;
@@ -1081,6 +1077,18 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 		return NULL;
 	}
 	clp->cl_name.len = name.len;
+	INIT_LIST_HEAD(&clp->cl_sessions);
+	idr_init(&clp->cl_stateids);
+	atomic_set(&clp->cl_refcount, 0);
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+	INIT_LIST_HEAD(&clp->cl_idhash);
+	INIT_LIST_HEAD(&clp->cl_openowners);
+	INIT_LIST_HEAD(&clp->cl_delegations);
+	INIT_LIST_HEAD(&clp->cl_lru);
+	INIT_LIST_HEAD(&clp->cl_callbacks);
+	INIT_LIST_HEAD(&clp->cl_revoked);
+	spin_lock_init(&clp->cl_lock);
+	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
 }
 
@@ -1098,6 +1106,7 @@ free_client(struct nfs4_client *clp)
 		WARN_ON_ONCE(atomic_read(&ses->se_ref));
 		free_session(ses);
 	}
+	rpc_destroy_wait_queue(&clp->cl_cb_waitq);
 	free_svc_cred(&clp->cl_cred);
 	kfree(clp->cl_name.data);
 	idr_destroy(&clp->cl_stateids);
@@ -1191,15 +1200,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source)
 	return 0;
 }
 
-static long long
+static int
 compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
 {
-	long long res;
-
-	res = o1->len - o2->len;
-	if (res)
-		return res;
-	return (long long)memcmp(o1->data, o2->data, o1->len);
+	if (o1->len < o2->len)
+		return -1;
+	if (o1->len > o2->len)
+		return 1;
+	return memcmp(o1->data, o2->data, o1->len);
 }
 
 static int same_name(const char *n1, const char *n2)
@@ -1315,7 +1323,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	if (clp == NULL)
 		return NULL;
 
-	INIT_LIST_HEAD(&clp->cl_sessions);
 	ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
 	if (ret) {
 		spin_lock(&nn->client_lock);
@@ -1323,20 +1330,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		spin_unlock(&nn->client_lock);
 		return NULL;
 	}
-	idr_init(&clp->cl_stateids);
-	atomic_set(&clp->cl_refcount, 0);
-	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
-	INIT_LIST_HEAD(&clp->cl_idhash);
-	INIT_LIST_HEAD(&clp->cl_openowners);
-	INIT_LIST_HEAD(&clp->cl_delegations);
-	INIT_LIST_HEAD(&clp->cl_lru);
-	INIT_LIST_HEAD(&clp->cl_callbacks);
-	INIT_LIST_HEAD(&clp->cl_revoked);
-	spin_lock_init(&clp->cl_lock);
 	nfsd4_init_callback(&clp->cl_cb_null);
 	clp->cl_time = get_seconds();
 	clear_bit(0, &clp->cl_cb_slot_busy);
-	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	copy_verf(clp, verf);
 	rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
 	gen_confirm(clp);
@@ -1368,7 +1364,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
 static struct nfs4_client *
 find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
 {
-	long long cmp;
+	int cmp;
 	struct rb_node *node = root->rb_node;
 	struct nfs4_client *clp;
 
@@ -2964,22 +2960,35 @@ static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
 	return 0;
 }
 
-static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
+static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag, struct nfs4_file *fp)
 {
-	struct nfs4_file *fp = dp->dl_file;
+	int status;
 
-	if (!fp->fi_lease)
-		return nfs4_setlease(dp, flag);
+	if (fp->fi_had_conflict)
+		return -EAGAIN;
+	get_nfs4_file(fp);
+	dp->dl_file = fp;
+	if (!fp->fi_lease) {
+		status = nfs4_setlease(dp, flag);
+		if (status)
+			goto out_free;
+		return 0;
+	}
 	spin_lock(&recall_lock);
 	if (fp->fi_had_conflict) {
 		spin_unlock(&recall_lock);
-		return -EAGAIN;
+		status = -EAGAIN;
+		goto out_free;
 	}
 	atomic_inc(&fp->fi_delegees);
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
 	spin_unlock(&recall_lock);
 	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
 	return 0;
+out_free:
+	put_nfs4_file(fp);
+	dp->dl_file = fp;
+	return status;
 }
 
 static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
@@ -3045,7 +3054,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
 	dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh, flag);
 	if (dp == NULL)
 		goto out_no_deleg;
-	status = nfs4_set_delegation(dp, flag);
+	status = nfs4_set_delegation(dp, flag, stp->st_file);
 	if (status)
 		goto out_free;
 
@@ -3598,9 +3607,16 @@ out:
 static __be32
 nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner)))
+	struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
+
+	if (check_for_locks(stp->st_file, lo))
 		return nfserr_locks_held;
-	release_lock_stateid(stp);
+	/*
+	 * Currently there's a 1-1 lock stateid<->lockowner
+	 * correspondance, and we have to delete the lockowner when we
+	 * delete the lock stateid:
+	 */
+	release_lockowner(lo);
 	return nfs_ok;
 }
 
@@ -4044,6 +4060,10 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c
 
 	if (!same_owner_str(&lo->lo_owner, owner, clid))
 		return false;
+	if (list_empty(&lo->lo_owner.so_stateids)) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
 	lst = list_first_entry(&lo->lo_owner.so_stateids,
 			       struct nfs4_ol_stateid, st_perstateowner);
 	return lst->st_file->fi_inode == inode;
@@ -4958,7 +4978,6 @@ nfs4_state_destroy_net(struct net *net)
 	int i;
 	struct nfs4_client *clp = NULL;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	struct rb_node *node, *tmp;
 
 	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
 		while (!list_empty(&nn->conf_id_hashtbl[i])) {
@@ -4967,13 +4986,11 @@ nfs4_state_destroy_net(struct net *net)
 		}
 	}
 
-	node = rb_first(&nn->unconf_name_tree);
-	while (node != NULL) {
-		tmp = node;
-		node = rb_next(tmp);
-		clp = rb_entry(tmp, struct nfs4_client, cl_namenode);
-		rb_erase(tmp, &nn->unconf_name_tree);
-		destroy_client(clp);
+	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
+		while (!list_empty(&nn->unconf_id_hashtbl[i])) {
+			clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
+			destroy_client(clp);
+		}
 	}
 
 	kfree(nn->sessionid_hashtbl);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 582321a978b0..acf179d7615f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -553,7 +553,18 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 		READ_BUF(4);
 		READ32(create->cr_linklen);
 		READ_BUF(create->cr_linklen);
-		SAVEMEM(create->cr_linkname, create->cr_linklen);
+		/*
+		 * The VFS will want a null-terminated string, and
+		 * null-terminating in place isn't safe since this might
+		 * end on a page boundary:
+		 */
+		create->cr_linkname =
+				kmalloc(create->cr_linklen + 1, GFP_KERNEL);
+		if (!create->cr_linkname)
+			return nfserr_jukebox;
+		memcpy(create->cr_linkname, p, create->cr_linklen);
+		create->cr_linkname[create->cr_linklen] = '\0';
+		defer_free(argp, kfree, create->cr_linkname);
 		break;
 	case NF4BLK:
 	case NF4CHR:
@@ -1732,6 +1743,9 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components,
 		}
 		else
 			end++;
+		if (found_esc)
+			end = next;
+
 		str = end;
 	}
 	*pp = p;
@@ -2035,8 +2049,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	err = vfs_getattr(&path, &stat);
 	if (err)
 		goto out_nfserr;
-	if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
-			FATTR4_WORD0_MAXNAME)) ||
+	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+			FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
 	    (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
 		       FATTR4_WORD1_SPACE_TOTAL))) {
 		err = vfs_statfs(&path, &statfs);
@@ -2401,6 +2415,8 @@ out_acl:
 		WRITE64(stat.ino);
 	}
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		if ((buflen -= 16) < 0)
+			goto out_resource;
 		WRITE32(3);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
@@ -3382,6 +3398,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_test_stateid_id *stateid, *next;
 	__be32 *p;
 
+	if (nfserr)
+		return nfserr;
+
 	RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
 	*p++ = htonl(test_stateid->ts_num_ids);
 
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index e76244edd748..e5e4675b7e75 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -221,13 +221,6 @@ hash_refile(struct svc_cacherep *rp)
 	hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits));
 }
 
-static inline bool
-nfsd_cache_entry_expired(struct svc_cacherep *rp)
-{
-	return rp->c_state != RC_INPROG &&
-	       time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
-}
-
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -238,8 +231,14 @@ prune_cache_entries(void)
 	struct svc_cacherep *rp, *tmp;
 
 	list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
-		if (!nfsd_cache_entry_expired(rp) &&
-		    num_drc_entries <= max_drc_entries)
+		/*
+		 * Don't free entries attached to calls that are still
+		 * in-progress, but do keep scanning the list.
+		 */
+		if (rp->c_state == RC_INPROG)
+			continue;
+		if (num_drc_entries <= max_drc_entries &&
+		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(rp);
 	}
@@ -395,22 +394,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 
 	/*
 	 * Since the common case is a cache miss followed by an insert,
-	 * preallocate an entry. First, try to reuse the first entry on the LRU
-	 * if it works, then go ahead and prune the LRU list.
+	 * preallocate an entry.
 	 */
-	spin_lock(&cache_lock);
-	if (!list_empty(&lru_head)) {
-		rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
-		if (nfsd_cache_entry_expired(rp) ||
-		    num_drc_entries >= max_drc_entries) {
-			lru_put_end(rp);
-			prune_cache_entries();
-			goto search_cache;
-		}
-	}
-
-	/* No expired ones available, allocate a new one. */
-	spin_unlock(&cache_lock);
 	rp = nfsd_reply_cache_alloc();
 	spin_lock(&cache_lock);
 	if (likely(rp)) {
@@ -418,7 +403,9 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 		drc_mem_usage += sizeof(*rp);
 	}
 
-search_cache:
+	/* go ahead and prune the cache */
+	prune_cache_entries();
+
 	found = nfsd_cache_search(rqstp, csum);
 	if (found) {
 		if (likely(rp))
@@ -432,15 +419,6 @@ search_cache:
 		goto out;
 	}
 
-	/*
-	 * We're keeping the one we just allocated. Are we now over the
-	 * limit? Prune one off the tip of the LRU in trade for the one we
-	 * just allocated if so.
-	 */
-	if (num_drc_entries >= max_drc_entries)
-		nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
-						struct svc_cacherep, c_lru));
-
 	nfsdstats.rcmisses++;
 	rqstp->rq_cacherep = rp;
 	rp->c_state = RC_INPROG;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7f555179bf81..f34d9de802ab 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -699,6 +699,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net)
 	if (err != 0 || fd < 0)
 		return -EINVAL;
 
+	if (svc_alien_sock(net, fd)) {
+		printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__);
+		return -EINVAL;
+	}
+
 	err = nfsd_create_serv(net);
 	if (err != 0)
 		return err;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 262df5ccbf59..8016892f3f05 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -220,7 +220,8 @@ static int nfsd_startup_generic(int nrservs)
 	 */
 	ret = nfsd_racache_init(2*nrservs);
 	if (ret)
-		return ret;
+		goto dec_users;
+
 	ret = nfs4_state_start();
 	if (ret)
 		goto out_racache;
@@ -228,6 +229,8 @@ static int nfsd_startup_generic(int nrservs)
 
 out_racache:
 	nfsd_racache_shutdown();
+dec_users:
+	nfsd_users--;
 	return ret;
 }
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index baf149a85263..81325ba8660a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -297,41 +297,12 @@ commit_metadata(struct svc_fh *fhp)
 }
 
 /*
- * Set various file attributes.
- * N.B. After this call fhp needs an fh_put
+ * Go over the attributes and take care of the small differences between
+ * NFS semantics and what Linux expects.
  */
-__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
-	     int check_guard, time_t guardtime)
+static void
+nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
-	struct dentry	*dentry;
-	struct inode	*inode;
-	int		accmode = NFSD_MAY_SATTR;
-	umode_t		ftype = 0;
-	__be32		err;
-	int		host_err;
-	int		size_change = 0;
-
-	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
-		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
-	if (iap->ia_valid & ATTR_SIZE)
-		ftype = S_IFREG;
-
-	/* Get inode */
-	err = fh_verify(rqstp, fhp, ftype, accmode);
-	if (err)
-		goto out;
-
-	dentry = fhp->fh_dentry;
-	inode = dentry->d_inode;
-
-	/* Ignore any mode updates on symlinks */
-	if (S_ISLNK(inode->i_mode))
-		iap->ia_valid &= ~ATTR_MODE;
-
-	if (!iap->ia_valid)
-		goto out;
-
 	/*
 	 * NFSv2 does not differentiate between "set-[ac]time-to-now"
 	 * which only requires access, and "set-[ac]time-to-X" which
@@ -341,8 +312,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	 * convert to "set to now" instead of "set to explicit time"
 	 *
 	 * We only call inode_change_ok as the last test as technically
-	 * it is not an interface that we should be using.  It is only
-	 * valid if the filesystem does not define it's own i_op->setattr.
+	 * it is not an interface that we should be using.
 	 */
 #define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
 #define	MAX_TOUCH_TIME_ERROR (30*60)
@@ -368,30 +338,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			iap->ia_valid &= ~BOTH_TIME_SET;
 		}
 	}
-	    
-	/*
-	 * The size case is special.
-	 * It changes the file as well as the attributes.
-	 */
-	if (iap->ia_valid & ATTR_SIZE) {
-		if (iap->ia_size < inode->i_size) {
-			err = nfsd_permission(rqstp, fhp->fh_export, dentry,
-					NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
-			if (err)
-				goto out;
-		}
-
-		host_err = get_write_access(inode);
-		if (host_err)
-			goto out_nfserr;
-
-		size_change = 1;
-		host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
-		if (host_err) {
-			put_write_access(inode);
-			goto out_nfserr;
-		}
-	}
 
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
@@ -414,32 +360,120 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
 		}
 	}
+}
 
-	/* Change the attributes. */
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct iattr *iap)
+{
+	struct inode *inode = fhp->fh_dentry->d_inode;
+	int host_err;
 
-	iap->ia_valid |= ATTR_CTIME;
+	if (iap->ia_size < inode->i_size) {
+		__be32 err;
+
+		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+				NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+		if (err)
+			return err;
+	}
+
+	host_err = get_write_access(inode);
+	if (host_err)
+		goto out_nfserrno;
+
+	host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+	if (host_err)
+		goto out_put_write_access;
+	return 0;
+
+out_put_write_access:
+	put_write_access(inode);
+out_nfserrno:
+	return nfserrno(host_err);
+}
+
+/*
+ * Set various file attributes.  After this call fhp needs an fh_put.
+ */
+__be32
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+	     int check_guard, time_t guardtime)
+{
+	struct dentry	*dentry;
+	struct inode	*inode;
+	int		accmode = NFSD_MAY_SATTR;
+	umode_t		ftype = 0;
+	__be32		err;
+	int		host_err;
+	bool		get_write_count;
+	int		size_change = 0;
+
+	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
+	if (iap->ia_valid & ATTR_SIZE)
+		ftype = S_IFREG;
 
-	err = nfserr_notsync;
-	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
-		host_err = nfsd_break_lease(inode);
+	/* Callers that do fh_verify should do the fh_want_write: */
+	get_write_count = !fhp->fh_dentry;
+
+	/* Get inode */
+	err = fh_verify(rqstp, fhp, ftype, accmode);
+	if (err)
+		goto out;
+	if (get_write_count) {
+		host_err = fh_want_write(fhp);
 		if (host_err)
-			goto out_nfserr;
-		fh_lock(fhp);
+			return nfserrno(host_err);
+	}
 
-		host_err = notify_change(dentry, iap);
-		err = nfserrno(host_err);
-		fh_unlock(fhp);
+	dentry = fhp->fh_dentry;
+	inode = dentry->d_inode;
+
+	/* Ignore any mode updates on symlinks */
+	if (S_ISLNK(inode->i_mode))
+		iap->ia_valid &= ~ATTR_MODE;
+
+	if (!iap->ia_valid)
+		goto out;
+
+	nfsd_sanitize_attrs(inode, iap);
+
+	/*
+	 * The size case is special, it changes the file in addition to the
+	 * attributes.
+	 */
+	if (iap->ia_valid & ATTR_SIZE) {
+		err = nfsd_get_write_access(rqstp, fhp, iap);
+		if (err)
+			goto out;
+		size_change = 1;
 	}
+
+	iap->ia_valid |= ATTR_CTIME;
+
+	if (check_guard && guardtime != inode->i_ctime.tv_sec) {
+		err = nfserr_notsync;
+		goto out_put_write_access;
+	}
+
+	host_err = nfsd_break_lease(inode);
+	if (host_err)
+		goto out_put_write_access_nfserror;
+
+	fh_lock(fhp);
+	host_err = notify_change(dentry, iap);
+	fh_unlock(fhp);
+
+out_put_write_access_nfserror:
+	err = nfserrno(host_err);
+out_put_write_access:
 	if (size_change)
 		put_write_access(inode);
 	if (!err)
 		commit_metadata(fhp);
 out:
 	return err;
-
-out_nfserr:
-	err = nfserrno(host_err);
-	goto out;
 }
 
 #if defined(CONFIG_NFSD_V2_ACL) || \
@@ -474,6 +508,9 @@ set_nfsv4_acl_one(struct dentry *dentry, struct posix_acl *pacl, char *key)
 	char *buf = NULL;
 	int error = 0;
 
+	if (!pacl)
+		return vfs_setxattr(dentry, key, NULL, 0, 0);
+
 	buflen = posix_acl_xattr_size(pacl->a_count);
 	buf = kmalloc(buflen, GFP_KERNEL);
 	error = -ENOMEM;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index bccfec8343c5..587d699bdc2c 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -24,6 +24,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
+#include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/aio.h>
 #include "nilfs.h"
@@ -48,6 +49,8 @@ struct nilfs_iget_args {
 	int for_gc;
 };
 
+static int nilfs_iget_test(struct inode *inode, void *opaque);
+
 void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
@@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 
 static int nilfs_set_page_dirty(struct page *page)
 {
+	struct inode *inode = page->mapping->host;
 	int ret = __set_page_dirty_nobuffers(page);
 
 	if (page_has_buffers(page)) {
-		struct inode *inode = page->mapping->host;
 		unsigned nr_dirty = 0;
 		struct buffer_head *bh, *head;
 
@@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page)
 
 		if (nr_dirty)
 			nilfs_set_file_dirty(inode, nr_dirty);
+	} else if (ret) {
+		unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+		nilfs_set_file_dirty(inode, nr_dirty);
 	}
 	return ret;
 }
@@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = {
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 
+static int nilfs_insert_inode_locked(struct inode *inode,
+				     struct nilfs_root *root,
+				     unsigned long ino)
+{
+	struct nilfs_iget_args args = {
+		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+	};
+
+	return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
+}
+
 struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
@@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		err = nilfs_bmap_read(ii->i_bmap, NULL);
 		if (err < 0)
-			goto failed_bmap;
+			goto failed_after_creation;
 
 		set_bit(NILFS_I_BMAP, &ii->i_state);
 		/* No lock is needed; iget() ensures it. */
@@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	spin_lock(&nilfs->ns_next_gen_lock);
 	inode->i_generation = nilfs->ns_next_generation++;
 	spin_unlock(&nilfs->ns_next_gen_lock);
-	insert_inode_hash(inode);
+	if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
+		err = -EIO;
+		goto failed_after_creation;
+	}
 
 	err = nilfs_init_acl(inode, dir);
 	if (unlikely(err))
-		goto failed_acl; /* never occur. When supporting
+		goto failed_after_creation; /* never occur. When supporting
 				    nilfs_init_acl(), proper cancellation of
 				    above jobs should be considered */
 
 	return inode;
 
- failed_acl:
- failed_bmap:
+ failed_after_creation:
 	clear_nlink(inode);
+	unlock_new_inode(inode);
 	iput(inode);  /* raw_inode will be deleted through
-			 generic_delete_inode() */
+			 nilfs_evict_inode() */
 	goto failed;
 
  failed_ifile_create_inode:
@@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode,
 	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
 	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-	if (inode->i_nlink == 0 && inode->i_mode == 0)
-		return -EINVAL; /* this inode is deleted */
+	if (inode->i_nlink == 0)
+		return -ESTALE; /* this inode is deleted */
 
 	inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
 	ii->i_flags = le32_to_cpu(raw_inode->i_flags);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9de78f08989e..0f84b257932c 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
 	int err = nilfs_add_link(dentry, inode);
 	if (!err) {
 		d_instantiate(dentry, inode);
+		unlock_new_inode(inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	return err;
 }
@@ -182,6 +184,7 @@ out:
 out_fail:
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	goto out;
 }
@@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	err = nilfs_add_nondir(dentry, inode);
-	if (!err)
+	err = nilfs_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
 		err = nilfs_transaction_commit(dir->i_sb);
-	else
+	} else {
+		inode_dec_link_count(inode);
+		iput(inode);
 		nilfs_transaction_abort(dir->i_sb);
+	}
 
 	return err;
 }
@@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	nilfs_mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 out:
 	if (!err)
 		err = nilfs_transaction_commit(dir->i_sb);
@@ -255,6 +263,7 @@ out_fail:
 	drop_nlink(inode);
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 out_dir:
 	drop_nlink(dir);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 0ba679866e50..da276640f776 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -94,6 +94,7 @@ void nilfs_forget_buffer(struct buffer_head *bh)
 	clear_buffer_nilfs_volatile(bh);
 	clear_buffer_nilfs_checked(bh);
 	clear_buffer_nilfs_redirected(bh);
+	clear_buffer_async_write(bh);
 	clear_buffer_dirty(bh);
 	if (nilfs_page_buffers_clean(page))
 		__nilfs_clear_page_dirty(page);
@@ -429,6 +430,7 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 					"discard block %llu, size %zu",
 					(u64)bh->b_blocknr, bh->b_size);
 			}
+			clear_buffer_async_write(bh);
 			clear_buffer_dirty(bh);
 			clear_buffer_nilfs_volatile(bh);
 			clear_buffer_nilfs_checked(bh);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a5752a589932..958a5b57ed4a 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -665,7 +665,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 
 		bh = head = page_buffers(page);
 		do {
-			if (!buffer_dirty(bh))
+			if (!buffer_dirty(bh) || buffer_async_write(bh))
 				continue;
 			get_bh(bh);
 			list_add_tail(&bh->b_assoc_buffers, listp);
@@ -699,7 +699,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			bh = head = page_buffers(pvec.pages[i]);
 			do {
-				if (buffer_dirty(bh)) {
+				if (buffer_dirty(bh) &&
+						!buffer_async_write(bh)) {
 					get_bh(bh);
 					list_add_tail(&bh->b_assoc_buffers,
 						      listp);
@@ -1439,17 +1440,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 
 		nilfs_clear_logs(&sci->sc_segbufs);
 
-		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
-		if (unlikely(err))
-			return err;
-
 		if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
 			err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
 							sci->sc_freesegs,
 							sci->sc_nfreesegs,
 							NULL);
 			WARN_ON(err); /* do not happen */
+			sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
 		}
+
+		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+		if (unlikely(err))
+			return err;
+
 		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
 		sci->sc_stage = prev_stage;
 	}
@@ -1579,6 +1582,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
+			set_buffer_async_write(bh);
 			if (bh->b_page != bd_page) {
 				if (bd_page) {
 					lock_page(bd_page);
@@ -1592,6 +1596,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
+			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_page != bd_page) {
 					lock_page(bd_page);
@@ -1677,6 +1682,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 	list_for_each_entry(segbuf, logs, sb_list) {
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
+			clear_buffer_async_write(bh);
 			if (bh->b_page != bd_page) {
 				if (bd_page)
 					end_page_writeback(bd_page);
@@ -1686,6 +1692,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
+			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_page != bd_page) {
 					end_page_writeback(bd_page);
@@ -1755,6 +1762,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				    b_assoc_buffers) {
 			set_buffer_uptodate(bh);
 			clear_buffer_dirty(bh);
+			clear_buffer_async_write(bh);
 			if (bh->b_page != bd_page) {
 				if (bd_page)
 					end_page_writeback(bd_page);
@@ -1776,6 +1784,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				    b_assoc_buffers) {
 			set_buffer_uptodate(bh);
 			clear_buffer_dirty(bh);
+			clear_buffer_async_write(bh);
 			clear_buffer_delay(bh);
 			clear_buffer_nilfs_volatile(bh);
 			clear_buffer_nilfs_redirected(bh);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 77cc85dd0db0..9be6b4163406 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -69,7 +69,7 @@ static int create_fd(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	client_fd = get_unused_fd();
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
 	if (client_fd < 0)
 		return client_fd;
 
@@ -867,9 +867,9 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
 {
 	return sys_fanotify_mark(fanotify_fd, flags,
 #ifdef __BIG_ENDIAN
-				((__u64)mask1 << 32) | mask0,
-#else
 				((__u64)mask0 << 32) | mask1,
+#else
+				((__u64)mask1 << 32) | mask0,
 #endif
 				 dfd, pathname);
 }
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 238a5930cb3c..9d7e2b9659cb 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
 	struct {
 		struct file_handle handle;
-		u8 pad[64];
+		u8 pad[MAX_HANDLE_SZ];
 	} f;
 	int size, ret, i;
 
@@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 	size = f.handle.handle_bytes >> 2;
 
 	ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
-	if ((ret == 255) || (ret == -ENOSPC)) {
+	if ((ret == FILEID_INVALID) || (ret < 0)) {
 		WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
 		return 0;
 	}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 20dfec72e903..f998c6009ad4 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -917,7 +917,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -938,7 +938,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -2060,11 +2064,19 @@ out_write_size:
 	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 5d18ad10c27f..4f66e007dae1 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		 * information for this bh as it's not marked locally
 		 * uptodate. */
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}
 
@@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 
 	if (!buffer_uptodate(bh)) {
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 33ecbe0e6734..2b941113e423 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -653,12 +653,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
 	clear_bit(bit, res->refmap);
 }
 
-
-void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res)
 {
-	assert_spin_locked(&res->spinlock);
-
 	res->inflight_locks++;
 
 	mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
@@ -666,6 +663,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 	     __builtin_return_address(0));
 }
 
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	__dlm_lockres_grab_inflight_ref(dlm, res);
+}
+
 void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res)
 {
@@ -855,10 +859,8 @@ lookup:
 	/* finally add the lockres to its hash bucket */
 	__dlm_insert_lockres(dlm, res);
 
-	/* Grab inflight ref to pin the resource */
-	spin_lock(&res->spinlock);
-	dlm_lockres_grab_inflight_ref(dlm, res);
-	spin_unlock(&res->spinlock);
+	/* since this lockres is new it doesn't not require the spinlock */
+	__dlm_lockres_grab_inflight_ref(dlm, res);
 
 	/* get an extra ref on the mle in case this is a BLOCK
 	 * if so, the creator of the BLOCK may try to put the last
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index e68588e6b1e8..9bd981cd3142 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -540,7 +540,10 @@ master_here:
 		/* success!  see if any other nodes need recovery */
 		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
 		     dlm->name, dlm->reco.dead_node, dlm->node_num);
-		dlm_reset_recovery(dlm);
+		spin_lock(&dlm->spinlock);
+		__dlm_reset_recovery(dlm);
+		dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+		spin_unlock(&dlm->spinlock);
 	}
 	dlm_end_recovery(dlm);
 
@@ -698,6 +701,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		if (all_nodes_done) {
 			int ret;
 
+			/* Set this flag on recovery master to avoid
+			 * a new recovery for another dead node start
+			 * before the recovery is not done. That may
+			 * cause recovery hung.*/
+			spin_lock(&dlm->spinlock);
+			dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+			spin_unlock(&dlm->spinlock);
+
 			/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
 	 		 * just send a finalize message to everyone and
 	 		 * clean up */
@@ -1751,13 +1762,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 				     struct dlm_migratable_lockres *mres)
 {
 	struct dlm_migratable_lock *ml;
-	struct list_head *queue;
+	struct list_head *queue, *iter;
 	struct list_head *tmpq = NULL;
 	struct dlm_lock *newlock = NULL;
 	struct dlm_lockstatus *lksb = NULL;
 	int ret = 0;
 	int i, j, bad;
-	struct dlm_lock *lock = NULL;
+	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
 	unsigned int added = 0;
 	__be64 c;
@@ -1792,14 +1803,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* MIGRATION ONLY! */
 			BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+			lock = NULL;
 			spin_lock(&res->spinlock);
 			for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
 				tmpq = dlm_list_idx_to_ptr(res, j);
-				list_for_each_entry(lock, tmpq, list) {
-					if (lock->ml.cookie != ml->cookie)
-						lock = NULL;
-					else
+				list_for_each(iter, tmpq) {
+					lock = list_entry(iter,
+						  struct dlm_lock, list);
+					if (lock->ml.cookie == ml->cookie)
 						break;
+					lock = NULL;
 				}
 				if (lock)
 					break;
@@ -2867,8 +2880,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
 				BUG();
 			}
 			dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+			__dlm_reset_recovery(dlm);
 			spin_unlock(&dlm->spinlock);
-			dlm_reset_recovery(dlm);
 			dlm_kick_recovery_thread(dlm);
 			break;
 		default:
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ff54014a24ec..46387e49aa46 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2374,8 +2374,8 @@ out_dio:
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
 	    ((file->f_flags & O_DIRECT) && !direct_io)) {
-		ret = filemap_fdatawrite_range(file->f_mapping, pos,
-					       pos + count - 1);
+		ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+					       *ppos + count - 1);
 		if (ret < 0)
 			written = ret;
 
@@ -2388,8 +2388,8 @@ out_dio:
 		}
 
 		if (!ret)
-			ret = filemap_fdatawait_range(file->f_mapping, pos,
-						      pos + count - 1);
+			ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+						      *ppos + count - 1);
 	}
 
 	/*
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 332a281f217e..e49b4f1cb26b 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 	 */
 	if (status < 0)
 		mlog_errno(status);
+	/*
+	 * Clear dq_off so that we search for the structure in quota file next
+	 * time we acquire it. The structure might be deleted and reallocated
+	 * elsewhere by another node while our dquot structure is on freelist.
+	 */
+	dquot->dq_off = 0;
 	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_trans:
 	ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
 	status = ocfs2_lock_global_qf(info, 1);
 	if (status < 0)
 		goto out;
-	if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
-		status = ocfs2_qinfo_lock(info, 0);
-		if (status < 0)
-			goto out_dq;
-		status = qtree_read_dquot(&info->dqi_gi, dquot);
-		ocfs2_qinfo_unlock(info, 0);
-		if (status < 0)
-			goto out_dq;
-	}
-	set_bit(DQ_READ_B, &dquot->dq_flags);
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_dq;
+	/*
+	 * We always want to read dquot structure from disk because we don't
+	 * know what happened with it while it was on freelist.
+	 */
+	status = qtree_read_dquot(&info->dqi_gi, dquot);
+	ocfs2_qinfo_unlock(info, 0);
+	if (status < 0)
+		goto out_dq;
 
 	OCFS2_DQUOT(dquot)->dq_use_count++;
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 27fe7ee4874c..d0f323da0b5c 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
 	ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
 
 out:
-	/* Clear the read bit so that next time someone uses this
-	 * dquot he reads fresh info from disk and allocates local
-	 * dquot structure */
-	clear_bit(DQ_READ_B, &dquot->dq_flags);
 	return status;
 }
 
diff --git a/fs/open.c b/fs/open.c
index 8c741002f947..86092bde31f4 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -628,23 +628,12 @@ out:
 static inline int __get_file_write_access(struct inode *inode,
 					  struct vfsmount *mnt)
 {
-	int error;
-	error = get_write_access(inode);
+	int error = get_write_access(inode);
 	if (error)
 		return error;
-	/*
-	 * Do not take mount writer counts on
-	 * special files since no writes to
-	 * the mount itself will occur.
-	 */
-	if (!special_file(inode->i_mode)) {
-		/*
-		 * Balanced in __fput()
-		 */
-		error = __mnt_want_write(mnt);
-		if (error)
-			put_write_access(inode);
-	}
+	error = __mnt_want_write(mnt);
+	if (error)
+		put_write_access(inode);
 	return error;
 }
 
@@ -677,12 +666,11 @@ static int do_dentry_open(struct file *f,
 
 	path_get(&f->f_path);
 	inode = f->f_inode = f->f_path.dentry->d_inode;
-	if (f->f_mode & FMODE_WRITE) {
+	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
 		error = __get_file_write_access(inode, f->f_path.mnt);
 		if (error)
 			goto cleanup_file;
-		if (!special_file(inode->i_mode))
-			file_take_write(f);
+		file_take_write(f);
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -723,7 +711,6 @@ cleanup_all:
 	fops_put(f->f_op);
 	file_sb_list_del(f);
 	if (f->f_mode & FMODE_WRITE) {
-		put_write_access(inode);
 		if (!special_file(inode->i_mode)) {
 			/*
 			 * We don't consider this a real
@@ -731,6 +718,7 @@ cleanup_all:
 			 * because it all happenend right
 			 * here, so just reset the state.
 			 */
+			put_write_access(inode);
 			file_reset_write(f);
 			__mnt_drop_write(f->f_path.mnt);
 		}
diff --git a/fs/pipe.c b/fs/pipe.c
index d2c45e14e6d8..0e0752ef2715 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -726,11 +726,25 @@ pipe_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+	int kill = 0;
+
+	spin_lock(&inode->i_lock);
+	if (!--pipe->files) {
+		inode->i_pipe = NULL;
+		kill = 1;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (kill)
+		free_pipe_info(pipe);
+}
+
 static int
 pipe_release(struct inode *inode, struct file *file)
 {
-	struct pipe_inode_info *pipe = inode->i_pipe;
-	int kill = 0;
+	struct pipe_inode_info *pipe = file->private_data;
 
 	__pipe_lock(pipe);
 	if (file->f_mode & FMODE_READ)
@@ -743,17 +757,9 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
 
-	if (kill)
-		free_pipe_info(pipe);
-
+	put_pipe_info(inode, pipe);
 	return 0;
 }
 
@@ -1014,7 +1020,6 @@ static int fifo_open(struct inode *inode, struct file *filp)
 {
 	struct pipe_inode_info *pipe;
 	bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
-	int kill = 0;
 	int ret;
 
 	filp->f_version = 0;
@@ -1130,15 +1135,9 @@ err_wr:
 	goto err;
 
 err:
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
-	if (kill)
-		free_pipe_info(pipe);
+
+	put_pipe_info(inode, pipe);
 	return ret;
 }
 
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 8bd2135b7f82..3542f1f814e2 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -158,6 +158,12 @@ posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p)
 	umode_t mode = 0;
 	int not_equiv = 0;
 
+	/*
+	 * A null ACL can always be presented as mode bits.
+	 */
+	if (!acl)
+		return 0;
+
 	FOREACH_ACL_ENTRY(pa, acl, pe) {
 		switch (pa->e_tag) {
 			case ACL_USER_OBJ:
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cbd0f1b324b9..09f0d9c374a3 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -304,15 +304,11 @@ static void render_cap_t(struct seq_file *m, const char *header,
 	seq_puts(m, header);
 	CAP_FOR_EACH_U32(__capi) {
 		seq_printf(m, "%08x",
-			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+			   a->cap[CAP_LAST_U32 - __capi]);
 	}
 	seq_putc(m, '\n');
 }
 
-/* Remove non-existent capabilities */
-#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \
-				CAP_TO_MASK(CAP_LAST_CAP + 1) - 1)
-
 static inline void task_cap(struct seq_file *m, struct task_struct *p)
 {
 	const struct cred *cred;
@@ -326,11 +322,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
 	cap_bset	= cred->cap_bset;
 	rcu_read_unlock();
 
-	NORM_CAPS(cap_inheritable);
-	NORM_CAPS(cap_permitted);
-	NORM_CAPS(cap_effective);
-	NORM_CAPS(cap_bset);
-
 	render_cap_t(m, "CapInh:\t", &cap_inheritable);
 	render_cap_t(m, "CapPrm:\t", &cap_permitted);
 	render_cap_t(m, "CapEff:\t", &cap_effective);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c3834dad09b3..8fc784aef0b8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1825,6 +1825,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
 	if (rc)
 		goto out_mmput;
 
+	rc = -ENOENT;
 	down_read(&mm->mmap_sem);
 	vma = find_exact_vma(mm, vm_start, vm_end);
 	if (vma && vma->vm_file) {
@@ -2611,6 +2612,57 @@ static const struct file_operations proc_projid_map_operations = {
 	.llseek		= seq_lseek,
 	.release	= proc_id_map_release,
 };
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
 #endif /* CONFIG_USER_NS */
 
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2719,6 +2771,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
@@ -3072,6 +3125,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 };
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index b8730d9ebaee..2a8cc94bb641 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,7 +121,7 @@ u64 stable_page_flags(struct page *page)
 	 * just checks PG_head/PG_tail, so we need to check PageLRU to make
 	 * sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) && PageLRU(compound_trans_head(page)))
+	else if (PageTransCompound(page) && PageLRU(compound_head(page)))
 		u |= 1 << KPF_THP;
 
 	/*
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index e4bcb2cf055a..3ba30825f387 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -316,10 +316,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		sprintf(name, "dmesg-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		sprintf(name, "console-%s", psname);
+		sprintf(name, "console-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		sprintf(name, "ftrace-%s", psname);
+		sprintf(name, "ftrace-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_MCE:
 		sprintf(name, "mce-%s-%lld", psname, id);
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 1376e5a8f0d6..42d5911c7e29 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400);
 MODULE_PARM_DESC(mem_size,
 		"size of reserved RAM used to store oops/panic logs");
 
+static unsigned int mem_type;
+module_param(mem_type, uint, 0600);
+MODULE_PARM_DESC(mem_type,
+		"set to 1 to try to use unbuffered memory (default 0)");
+
 static int dump_oops = 1;
 module_param(dump_oops, int, 0600);
 MODULE_PARM_DESC(dump_oops,
@@ -79,6 +84,7 @@ struct ramoops_context {
 	struct persistent_ram_zone *fprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
+	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
@@ -331,7 +337,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 		size_t sz = cxt->record_size;
 
 		cxt->przs[i] = persistent_ram_new(*paddr, sz, 0,
-						  &cxt->ecc_info);
+						  &cxt->ecc_info,
+						  cxt->memtype);
 		if (IS_ERR(cxt->przs[i])) {
 			err = PTR_ERR(cxt->przs[i]);
 			dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -361,7 +368,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 		return -ENOMEM;
 	}
 
-	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info);
+	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
@@ -411,6 +418,7 @@ static int ramoops_probe(struct platform_device *pdev)
 	cxt->dump_read_cnt = 0;
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
+	cxt->memtype = pdata->mem_type;
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
@@ -541,6 +549,7 @@ static void ramoops_register_dummy(void)
 
 	dummy_data->mem_size = mem_size;
 	dummy_data->mem_address = mem_address;
+	dummy_data->mem_type = 0;
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 59337326e288..6ff97553331b 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -333,7 +333,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz)
 	persistent_ram_update_header_ecc(prz);
 }
 
-static void *persistent_ram_vmap(phys_addr_t start, size_t size)
+static void *persistent_ram_vmap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
 	struct page **pages;
 	phys_addr_t page_start;
@@ -345,7 +346,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	page_start = start - offset_in_page(start);
 	page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
 
-	prot = pgprot_noncached(PAGE_KERNEL);
+	if (memtype)
+		prot = pgprot_noncached(PAGE_KERNEL);
+	else
+		prot = pgprot_writecombine(PAGE_KERNEL);
 
 	pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL);
 	if (!pages) {
@@ -364,27 +368,35 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	return vaddr;
 }
 
-static void *persistent_ram_iomap(phys_addr_t start, size_t size)
+static void *persistent_ram_iomap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
+	void *va;
+
 	if (!request_mem_region(start, size, "persistent_ram")) {
 		pr_err("request mem region (0x%llx@0x%llx) failed\n",
 			(unsigned long long)size, (unsigned long long)start);
 		return NULL;
 	}
 
-	return ioremap(start, size);
+	if (memtype)
+		va = ioremap(start, size);
+	else
+		va = ioremap_wc(start, size);
+
+	return va;
 }
 
 static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
-		struct persistent_ram_zone *prz)
+		struct persistent_ram_zone *prz, int memtype)
 {
 	prz->paddr = start;
 	prz->size = size;
 
 	if (pfn_valid(start >> PAGE_SHIFT))
-		prz->vaddr = persistent_ram_vmap(start, size);
+		prz->vaddr = persistent_ram_vmap(start, size, memtype);
 	else
-		prz->vaddr = persistent_ram_iomap(start, size);
+		prz->vaddr = persistent_ram_iomap(start, size, memtype);
 
 	if (!prz->vaddr) {
 		pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__,
@@ -452,7 +464,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 }
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info)
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
@@ -463,7 +476,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
-	ret = persistent_ram_buffer_map(start, size, prz);
+	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
 		goto err;
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 3e64169ef527..7a10e047bc33 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb,
 		dqstats_inc(DQST_LOOKUPS);
 		dqput(old_dquot);
 		old_dquot = dquot;
-		ret = fn(dquot, priv);
-		if (ret < 0)
-			goto out;
+		/*
+		 * ->release_dquot() can be racing with us. Our reference
+		 * protects us from new calls to it so just wait for any
+		 * outstanding call and recheck the DQ_ACTIVE_B after that.
+		 */
+		wait_on_dquot(dquot);
+		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+			ret = fn(dquot, priv);
+			if (ret < 0)
+				goto out;
+		}
 		spin_lock(&dq_list_lock);
 		/* We are safe to continue now because our dquot could not
 		 * be moved out of the inuse list while we hold the reference */
@@ -629,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			dqstats_inc(DQST_LOOKUPS);
 			err = sb->dq_op->write_dquot(dquot);
 			if (!ret && err)
-				err = ret;
+				ret = err;
 			dqput(dquot);
 			spin_lock(&dq_list_lock);
 		}
diff --git a/fs/read_write.c b/fs/read_write.c
index 2cefa417be34..f6b7c600eb7f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -947,9 +947,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen)
+		compat_ulong_t, vlen)
 {
 	struct fd f = fdget(fd);
 	ssize_t ret;
@@ -983,9 +983,9 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, u32, pos_low, u32, pos_high)
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	return compat_sys_preadv64(fd, vec, vlen, pos);
@@ -1013,9 +1013,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 		const struct compat_iovec __user *, vec,
-		unsigned long, vlen)
+		compat_ulong_t, vlen)
 {
 	struct fd f = fdget(fd);
 	ssize_t ret;
@@ -1049,9 +1049,9 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, u32, pos_low, u32, pos_high)
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	return compat_sys_pwritev64(fd, vec, vlen, pos);
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 6c2d136561cb..2b96b59f75da 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -128,6 +128,7 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				char *d_name;
 				off_t d_off;
 				ino_t d_ino;
+				loff_t cur_pos = deh_offset(deh);
 
 				if (!de_visible(deh))
 					/* it is hidden entry */
@@ -200,8 +201,9 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
-				// next entry should be looked for with such offset
-				next_pos = deh_offset(deh) + 1;
+
+				/* deh_offset(deh) may be invalid now. */
+				next_pos = cur_pos + 1;
 
 				if (item_moved(&tmp_ih, &path_to_entry)) {
 					set_cpu_key_k_offset(&pos_key,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index f844533792ee..36166443bc45 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3211,8 +3211,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		error = inode_newsize_ok(inode, attr->ia_size);
 		if (!error) {
+			/*
+			 * Could race against reiserfs_file_release
+			 * if called from NFS, so take tailpack mutex.
+			 */
+			mutex_lock(&REISERFS_I(inode)->tailpack);
 			truncate_setsize(inode, attr->ia_size);
-			reiserfs_vfs_truncate_file(inode);
+			reiserfs_truncate_file(inode, 1);
+			mutex_unlock(&REISERFS_I(inode)->tailpack);
 		}
 	}
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 774c1eb7f1c9..3dd44db1465e 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -328,6 +328,8 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence)
 				m->read_pos = offset;
 				retval = file->f_pos = offset;
 			}
+		} else {
+			file->f_pos = offset;
 		}
 	}
 	file->f_version = m->version;
diff --git a/fs/splice.c b/fs/splice.c
index d37431dd60a1..4b5a5fac3383 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -555,6 +555,24 @@ static const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
+static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	return 1;
+}
+
+/* Pipe buffer operations for a socket and similar. */
+const struct pipe_buf_operations nosteal_pipe_buf_ops = {
+	.can_merge = 0,
+	.map = generic_pipe_buf_map,
+	.unmap = generic_pipe_buf_unmap,
+	.confirm = generic_pipe_buf_confirm,
+	.release = generic_pipe_buf_release,
+	.steal = generic_pipe_buf_nosteal,
+	.get = generic_pipe_buf_get,
+};
+EXPORT_SYMBOL(nosteal_pipe_buf_ops);
+
 static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
 			    unsigned long vlen, loff_t offset)
 {
diff --git a/fs/statfs.c b/fs/statfs.c
index c219e733f553..083dc0ac9140 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -94,7 +94,7 @@ retry:
 
 int fd_statfs(int fd, struct kstatfs *st)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_raw(fd);
 	int error = -EBADF;
 	if (f.file) {
 		error = vfs_statfs(&f.file->f_path, st);
diff --git a/fs/super.c b/fs/super.c
index 68307c029228..e028b508db25 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -76,6 +76,8 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
 
 	total_objects = sb->s_nr_dentry_unused +
 			sb->s_nr_inodes_unused + fs_objects + 1;
+	if (!total_objects)
+		total_objects = 1;
 
 	if (sc->nr_to_scan) {
 		int	dentries;
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index d0c6a007ce83..eda10959714f 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -487,6 +487,7 @@ static int v7_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb = sb;
 	sbi->s_block_base = 0;
 	sbi->s_type = FSTYPE_V7;
+	mutex_init(&sbi->s_lock);
 	sb->s_fs_info = sbi;
 	
 	sb_set_blocksize(sb, 512);
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index ff8229340cd5..26b69b2d4a45 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c)
 	err = ubifs_orphan_end_commit(c);
 	if (err)
 		goto out;
-	old_ltail_lnum = c->ltail_lnum;
-	err = ubifs_log_end_commit(c, new_ltail_lnum);
-	if (err)
-		goto out;
 	err = dbg_check_old_index(c, &zroot);
 	if (err)
 		goto out;
 
-	mutex_lock(&c->mst_mutex);
 	c->mst_node->cmt_no      = cpu_to_le64(c->cmt_no);
 	c->mst_node->log_lnum    = cpu_to_le32(new_ltail_lnum);
 	c->mst_node->root_lnum   = cpu_to_le32(zroot.lnum);
@@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c)
 		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
 	else
 		c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS);
-	err = ubifs_write_master(c);
-	mutex_unlock(&c->mst_mutex);
+
+	old_ltail_lnum = c->ltail_lnum;
+	err = ubifs_log_end_commit(c, new_ltail_lnum);
 	if (err)
 		goto out;
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 14374530784c..881324c08430 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1524,8 +1524,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 	}
 
 	wait_for_stable_page(page);
-	unlock_page(page);
-	return 0;
+	return VM_FAULT_LOCKED;
 
 out_unlock:
 	unlock_page(page);
diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index 36bd4efd0819..06649d21b056 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c)
 	h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs;
 	t = (long long)c->ltail_lnum * c->leb_size;
 
-	if (h >= t)
+	if (h > t)
 		return c->log_bytes - h + t;
-	else
+	else if (h != t)
 		return t - h;
+	else if (c->lhead_lnum != c->ltail_lnum)
+		return 0;
+	else
+		return c->log_bytes;
 }
 
 /**
@@ -447,9 +451,9 @@ out:
  * @ltail_lnum: new log tail LEB number
  *
  * This function is called on when the commit operation was finished. It
- * moves log tail to new position and unmaps LEBs which contain obsolete data.
- * Returns zero in case of success and a negative error code in case of
- * failure.
+ * moves log tail to new position and updates the master node so that it stores
+ * the new log tail LEB number. Returns zero in case of success and a negative
+ * error code in case of failure.
  */
 int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 {
@@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 	spin_unlock(&c->buds_lock);
 
 	err = dbg_check_bud_bytes(c);
+	if (err)
+		goto out;
 
+	err = ubifs_write_master(c);
+
+out:
 	mutex_unlock(&c->log_mutex);
 	return err;
 }
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index ab83ace9910a..1a4bb9e8b3b8 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c)
  * ubifs_write_master - write master node.
  * @c: UBIFS file-system description object
  *
- * This function writes the master node. The caller has to take the
- * @c->mst_mutex lock before calling this function. Returns zero in case of
- * success and a negative error code in case of failure. The master node is
- * written twice to enable recovery.
+ * This function writes the master node. Returns zero in case of success and a
+ * negative error code in case of failure. The master node is written twice to
+ * enable recovery.
  */
 int ubifs_write_master(struct ubifs_info *c)
 {
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 9e1d05666fed..e0a7a764a903 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention)
 			freed = ubifs_destroy_tnc_subtree(znode);
 			atomic_long_sub(freed, &ubifs_clean_zn_cnt);
 			atomic_long_sub(freed, &c->clean_zn_cnt);
-			ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
 			total_freed += freed;
 			znode = zprev;
 		}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 879b9976c12b..05115d719408 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1970,7 +1970,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 		mutex_init(&c->lp_mutex);
 		mutex_init(&c->tnc_mutex);
 		mutex_init(&c->log_mutex);
-		mutex_init(&c->mst_mutex);
 		mutex_init(&c->umount_mutex);
 		mutex_init(&c->bu_mutex);
 		mutex_init(&c->write_reserve_mutex);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index b2babce4d70f..bd51277f6fe1 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1042,7 +1042,6 @@ struct ubifs_debug_info;
  *
  * @mst_node: master node
  * @mst_offs: offset of valid master node
- * @mst_mutex: protects the master node area, @mst_node, and @mst_offs
  *
  * @max_bu_buf_len: maximum bulk-read buffer length
  * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu
@@ -1282,7 +1281,6 @@ struct ubifs_info {
 
 	struct ubifs_mst_node *mst_node;
 	int mst_offs;
-	struct mutex mst_mutex;
 
 	int max_bu_buf_len;
 	struct mutex bu_mutex;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index b6d15d349810..aa023283cc8a 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1270,13 +1270,22 @@ update_time:
 	return 0;
 }
 
+/*
+ * Maximum length of linked list formed by ICB hierarchy. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_ICB_NESTING 1024
+
 static void __udf_read_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
 	uint16_t ident;
 	struct udf_inode_info *iinfo = UDF_I(inode);
+	unsigned int indirections = 0;
 
+reread:
 	/*
 	 * Set defaults, but the inode is still incomplete!
 	 * Note: get_new_inode() sets the following on a new inode:
@@ -1313,28 +1322,26 @@ static void __udf_read_inode(struct inode *inode)
 		ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
 					&ident);
 		if (ident == TAG_IDENT_IE && ibh) {
-			struct buffer_head *nbh = NULL;
 			struct kernel_lb_addr loc;
 			struct indirectEntry *ie;
 
 			ie = (struct indirectEntry *)ibh->b_data;
 			loc = lelb_to_cpu(ie->indirectICB.extLocation);
 
-			if (ie->indirectICB.extLength &&
-				(nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
-							&ident))) {
-				if (ident == TAG_IDENT_FE ||
-					ident == TAG_IDENT_EFE) {
-					memcpy(&iinfo->i_location,
-						&loc,
-						sizeof(struct kernel_lb_addr));
-					brelse(bh);
-					brelse(ibh);
-					brelse(nbh);
-					__udf_read_inode(inode);
+			if (ie->indirectICB.extLength) {
+				brelse(bh);
+				brelse(ibh);
+				memcpy(&iinfo->i_location, &loc,
+				       sizeof(struct kernel_lb_addr));
+				if (++indirections > UDF_MAX_ICB_NESTING) {
+					udf_err(inode->i_sb,
+						"too many ICBs in ICB hierarchy"
+						" (max %d supported)\n",
+						UDF_MAX_ICB_NESTING);
+					make_bad_inode(inode);
 					return;
 				}
-				brelse(nbh);
+				goto reread;
 			}
 		}
 		brelse(ibh);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 9ac4057a86c9..839a2bad7f45 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -630,6 +630,12 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	int error = 0;
 
+	if (sbi->s_lvid_bh) {
+		int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
+		if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))
+			return -EACCES;
+	}
+
 	uopt.flags = sbi->s_flags;
 	uopt.uid   = sbi->s_uid;
 	uopt.gid   = sbi->s_gid;
@@ -649,12 +655,6 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	sbi->s_dmode = uopt.dmode;
 	write_unlock(&sbi->s_cred_lock);
 
-	if (sbi->s_lvid_bh) {
-		int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
-		if (write_rev > UDF_MAX_WRITE_VERSION)
-			*flags |= MS_RDONLY;
-	}
-
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		goto out_unlock;
 
@@ -843,27 +843,38 @@ static int udf_find_fileset(struct super_block *sb,
 	return 1;
 }
 
+/*
+ * Load primary Volume Descriptor Sequence
+ *
+ * Return <0 on error, 0 on success. -EAGAIN is special meaning next sequence
+ * should be tried.
+ */
 static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 {
 	struct primaryVolDesc *pvoldesc;
 	struct ustr *instr, *outstr;
 	struct buffer_head *bh;
 	uint16_t ident;
-	int ret = 1;
+	int ret = -ENOMEM;
 
 	instr = kmalloc(sizeof(struct ustr), GFP_NOFS);
 	if (!instr)
-		return 1;
+		return -ENOMEM;
 
 	outstr = kmalloc(sizeof(struct ustr), GFP_NOFS);
 	if (!outstr)
 		goto out1;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
-	if (!bh)
+	if (!bh) {
+		ret = -EAGAIN;
 		goto out2;
+	}
 
-	BUG_ON(ident != TAG_IDENT_PVD);
+	if (ident != TAG_IDENT_PVD) {
+		ret = -EIO;
+		goto out_bh;
+	}
 
 	pvoldesc = (struct primaryVolDesc *)bh->b_data;
 
@@ -889,8 +900,9 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 		if (udf_CS0toUTF8(outstr, instr))
 			udf_debug("volSetIdent[] = '%s'\n", outstr->u_name);
 
-	brelse(bh);
 	ret = 0;
+out_bh:
+	brelse(bh);
 out2:
 	kfree(outstr);
 out1:
@@ -947,7 +959,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 
 		if (mdata->s_mirror_fe == NULL) {
 			udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
-			goto error_exit;
+			return -EIO;
 		}
 	}
 
@@ -964,23 +976,18 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 			  addr.logicalBlockNum, addr.partitionReferenceNum);
 
 		mdata->s_bitmap_fe = udf_iget(sb, &addr);
-
 		if (mdata->s_bitmap_fe == NULL) {
 			if (sb->s_flags & MS_RDONLY)
 				udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n");
 			else {
 				udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n");
-				goto error_exit;
+				return -EIO;
 			}
 		}
 	}
 
 	udf_debug("udf_load_metadata_files Ok\n");
-
 	return 0;
-
-error_exit:
-	return 1;
 }
 
 static void udf_load_fileset(struct super_block *sb, struct buffer_head *bh,
@@ -1069,7 +1076,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 		if (!map->s_uspace.s_table) {
 			udf_debug("cannot load unallocSpaceTable (part %d)\n",
 				  p_index);
-			return 1;
+			return -EIO;
 		}
 		map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_TABLE;
 		udf_debug("unallocSpaceTable (part %d) @ %ld\n",
@@ -1079,7 +1086,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 	if (phd->unallocSpaceBitmap.extLength) {
 		struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index);
 		if (!bitmap)
-			return 1;
+			return -ENOMEM;
 		map->s_uspace.s_bitmap = bitmap;
 		bitmap->s_extPosition = le32_to_cpu(
 				phd->unallocSpaceBitmap.extPosition);
@@ -1102,7 +1109,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 		if (!map->s_fspace.s_table) {
 			udf_debug("cannot load freedSpaceTable (part %d)\n",
 				  p_index);
-			return 1;
+			return -EIO;
 		}
 
 		map->s_partition_flags |= UDF_PART_FLAG_FREED_TABLE;
@@ -1113,7 +1120,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 	if (phd->freedSpaceBitmap.extLength) {
 		struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index);
 		if (!bitmap)
-			return 1;
+			return -ENOMEM;
 		map->s_fspace.s_bitmap = bitmap;
 		bitmap->s_extPosition = le32_to_cpu(
 				phd->freedSpaceBitmap.extPosition);
@@ -1165,7 +1172,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 		udf_find_vat_block(sb, p_index, type1_index, blocks - 1);
 	}
 	if (!sbi->s_vat_inode)
-		return 1;
+		return -EIO;
 
 	if (map->s_partition_type == UDF_VIRTUAL_MAP15) {
 		map->s_type_specific.s_virtual.s_start_offset = 0;
@@ -1177,7 +1184,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 			pos = udf_block_map(sbi->s_vat_inode, 0);
 			bh = sb_bread(sb, pos);
 			if (!bh)
-				return 1;
+				return -EIO;
 			vat20 = (struct virtualAllocationTable20 *)bh->b_data;
 		} else {
 			vat20 = (struct virtualAllocationTable20 *)
@@ -1195,6 +1202,12 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 	return 0;
 }
 
+/*
+ * Load partition descriptor block
+ *
+ * Returns <0 on error, 0 on success, -EAGAIN is special - try next descriptor
+ * sequence.
+ */
 static int udf_load_partdesc(struct super_block *sb, sector_t block)
 {
 	struct buffer_head *bh;
@@ -1204,13 +1217,15 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
 	int i, type1_idx;
 	uint16_t partitionNumber;
 	uint16_t ident;
-	int ret = 0;
+	int ret;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh)
-		return 1;
-	if (ident != TAG_IDENT_PD)
+		return -EAGAIN;
+	if (ident != TAG_IDENT_PD) {
+		ret = 0;
 		goto out_bh;
+	}
 
 	p = (struct partitionDesc *)bh->b_data;
 	partitionNumber = le16_to_cpu(p->partitionNumber);
@@ -1229,10 +1244,13 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
 	if (i >= sbi->s_partitions) {
 		udf_debug("Partition (%d) not found in partition map\n",
 			  partitionNumber);
+		ret = 0;
 		goto out_bh;
 	}
 
 	ret = udf_fill_partdesc_info(sb, p, i);
+	if (ret < 0)
+		goto out_bh;
 
 	/*
 	 * Now rescan for VIRTUAL or METADATA partitions when SPARABLE and
@@ -1249,32 +1267,37 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
 			break;
 	}
 
-	if (i >= sbi->s_partitions)
+	if (i >= sbi->s_partitions) {
+		ret = 0;
 		goto out_bh;
+	}
 
 	ret = udf_fill_partdesc_info(sb, p, i);
-	if (ret)
+	if (ret < 0)
 		goto out_bh;
 
 	if (map->s_partition_type == UDF_METADATA_MAP25) {
 		ret = udf_load_metadata_files(sb, i);
-		if (ret) {
+		if (ret < 0) {
 			udf_err(sb, "error loading MetaData partition map %d\n",
 				i);
 			goto out_bh;
 		}
 	} else {
-		ret = udf_load_vat(sb, i, type1_idx);
-		if (ret)
-			goto out_bh;
 		/*
-		 * Mark filesystem read-only if we have a partition with
-		 * virtual map since we don't handle writing to it (we
-		 * overwrite blocks instead of relocating them).
+		 * If we have a partition with virtual map, we don't handle
+		 * writing to it (we overwrite blocks instead of relocating
+		 * them).
 		 */
-		sb->s_flags |= MS_RDONLY;
-		pr_notice("Filesystem marked read-only because writing to pseudooverwrite partition is not implemented\n");
+		if (!(sb->s_flags & MS_RDONLY)) {
+			ret = -EACCES;
+			goto out_bh;
+		}
+		ret = udf_load_vat(sb, i, type1_idx);
+		if (ret < 0)
+			goto out_bh;
 	}
+	ret = 0;
 out_bh:
 	/* In case loading failed, we handle cleanup in udf_fill_super */
 	brelse(bh);
@@ -1340,11 +1363,11 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 	uint16_t ident;
 	struct buffer_head *bh;
 	unsigned int table_len;
-	int ret = 0;
+	int ret;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh)
-		return 1;
+		return -EAGAIN;
 	BUG_ON(ident != TAG_IDENT_LVD);
 	lvd = (struct logicalVolDesc *)bh->b_data;
 	table_len = le32_to_cpu(lvd->mapTableLength);
@@ -1352,7 +1375,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 		udf_err(sb, "error loading logical volume descriptor: "
 			"Partition table too long (%u > %lu)\n", table_len,
 			sb->s_blocksize - sizeof(*lvd));
-		ret = 1;
+		ret = -EIO;
 		goto out_bh;
 	}
 
@@ -1396,11 +1419,10 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 			} else if (!strncmp(upm2->partIdent.ident,
 						UDF_ID_SPARABLE,
 						strlen(UDF_ID_SPARABLE))) {
-				if (udf_load_sparable_map(sb, map,
-				    (struct sparablePartitionMap *)gpm) < 0) {
-					ret = 1;
+				ret = udf_load_sparable_map(sb, map,
+					(struct sparablePartitionMap *)gpm);
+				if (ret < 0)
 					goto out_bh;
-				}
 			} else if (!strncmp(upm2->partIdent.ident,
 						UDF_ID_METADATA,
 						strlen(UDF_ID_METADATA))) {
@@ -1465,7 +1487,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 	}
 	if (lvd->integritySeqExt.extLength)
 		udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt));
-
+	ret = 0;
 out_bh:
 	brelse(bh);
 	return ret;
@@ -1503,22 +1525,18 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_
 }
 
 /*
- * udf_process_sequence
- *
- * PURPOSE
- *	Process a main/reserve volume descriptor sequence.
- *
- * PRE-CONDITIONS
- *	sb			Pointer to _locked_ superblock.
- *	block			First block of first extent of the sequence.
- *	lastblock		Lastblock of first extent of the sequence.
+ * Process a main/reserve volume descriptor sequence.
+ *   @block		First block of first extent of the sequence.
+ *   @lastblock		Lastblock of first extent of the sequence.
+ *   @fileset		There we store extent containing root fileset
  *
- * HISTORY
- *	July 1, 1997 - Andrew E. Mileski
- *	Written, tested, and released.
+ * Returns <0 on error, 0 on success. -EAGAIN is special - try next descriptor
+ * sequence
  */
-static noinline int udf_process_sequence(struct super_block *sb, long block,
-				long lastblock, struct kernel_lb_addr *fileset)
+static noinline int udf_process_sequence(
+		struct super_block *sb,
+		sector_t block, sector_t lastblock,
+		struct kernel_lb_addr *fileset)
 {
 	struct buffer_head *bh = NULL;
 	struct udf_vds_record vds[VDS_POS_LENGTH];
@@ -1529,6 +1547,7 @@ static noinline int udf_process_sequence(struct super_block *sb, long block,
 	uint32_t vdsn;
 	uint16_t ident;
 	long next_s = 0, next_e = 0;
+	int ret;
 
 	memset(vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH);
 
@@ -1543,7 +1562,7 @@ static noinline int udf_process_sequence(struct super_block *sb, long block,
 			udf_err(sb,
 				"Block %llu of volume descriptor sequence is corrupted or we could not read it\n",
 				(unsigned long long)block);
-			return 1;
+			return -EAGAIN;
 		}
 
 		/* Process each descriptor (ISO 13346 3/8.3-8.4) */
@@ -1616,14 +1635,19 @@ static noinline int udf_process_sequence(struct super_block *sb, long block,
 	 */
 	if (!vds[VDS_POS_PRIMARY_VOL_DESC].block) {
 		udf_err(sb, "Primary Volume Descriptor not found!\n");
-		return 1;
+		return -EAGAIN;
+	}
+	ret = udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block);
+	if (ret < 0)
+		return ret;
+
+	if (vds[VDS_POS_LOGICAL_VOL_DESC].block) {
+		ret = udf_load_logicalvol(sb,
+					  vds[VDS_POS_LOGICAL_VOL_DESC].block,
+					  fileset);
+		if (ret < 0)
+			return ret;
 	}
-	if (udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block))
-		return 1;
-
-	if (vds[VDS_POS_LOGICAL_VOL_DESC].block && udf_load_logicalvol(sb,
-	    vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset))
-		return 1;
 
 	if (vds[VDS_POS_PARTITION_DESC].block) {
 		/*
@@ -1632,19 +1656,27 @@ static noinline int udf_process_sequence(struct super_block *sb, long block,
 		 */
 		for (block = vds[VDS_POS_PARTITION_DESC].block;
 		     block < vds[VDS_POS_TERMINATING_DESC].block;
-		     block++)
-			if (udf_load_partdesc(sb, block))
-				return 1;
+		     block++) {
+			ret = udf_load_partdesc(sb, block);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
 }
 
+/*
+ * Load Volume Descriptor Sequence described by anchor in bh
+ *
+ * Returns <0 on error, 0 on success
+ */
 static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh,
 			     struct kernel_lb_addr *fileset)
 {
 	struct anchorVolDescPtr *anchor;
-	long main_s, main_e, reserve_s, reserve_e;
+	sector_t main_s, main_e, reserve_s, reserve_e;
+	int ret;
 
 	anchor = (struct anchorVolDescPtr *)bh->b_data;
 
@@ -1662,18 +1694,26 @@ static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh,
 
 	/* Process the main & reserve sequences */
 	/* responsible for finding the PartitionDesc(s) */
-	if (!udf_process_sequence(sb, main_s, main_e, fileset))
-		return 1;
-	udf_sb_free_partitions(sb);
-	if (!udf_process_sequence(sb, reserve_s, reserve_e, fileset))
-		return 1;
+	ret = udf_process_sequence(sb, main_s, main_e, fileset);
+	if (ret != -EAGAIN)
+		return ret;
 	udf_sb_free_partitions(sb);
-	return 0;
+	ret = udf_process_sequence(sb, reserve_s, reserve_e, fileset);
+	if (ret < 0) {
+		udf_sb_free_partitions(sb);
+		/* No sequence was OK, return -EIO */
+		if (ret == -EAGAIN)
+			ret = -EIO;
+	}
+	return ret;
 }
 
 /*
  * Check whether there is an anchor block in the given block and
  * load Volume Descriptor Sequence if so.
+ *
+ * Returns <0 on error, 0 on success, -EAGAIN is special - try next anchor
+ * block
  */
 static int udf_check_anchor_block(struct super_block *sb, sector_t block,
 				  struct kernel_lb_addr *fileset)
@@ -1685,33 +1725,40 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block,
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
 	    udf_fixed_to_variable(block) >=
 	    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
-		return 0;
+		return -EAGAIN;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh)
-		return 0;
+		return -EAGAIN;
 	if (ident != TAG_IDENT_AVDP) {
 		brelse(bh);
-		return 0;
+		return -EAGAIN;
 	}
 	ret = udf_load_sequence(sb, bh, fileset);
 	brelse(bh);
 	return ret;
 }
 
-/* Search for an anchor volume descriptor pointer */
-static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock,
-				 struct kernel_lb_addr *fileset)
+/*
+ * Search for an anchor volume descriptor pointer.
+ *
+ * Returns < 0 on error, 0 on success. -EAGAIN is special - try next set
+ * of anchors.
+ */
+static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock,
+			    struct kernel_lb_addr *fileset)
 {
 	sector_t last[6];
 	int i;
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	int last_count = 0;
+	int ret;
 
 	/* First try user provided anchor */
 	if (sbi->s_anchor) {
-		if (udf_check_anchor_block(sb, sbi->s_anchor, fileset))
-			return lastblock;
+		ret = udf_check_anchor_block(sb, sbi->s_anchor, fileset);
+		if (ret != -EAGAIN)
+			return ret;
 	}
 	/*
 	 * according to spec, anchor is in either:
@@ -1720,39 +1767,46 @@ static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock,
 	 *     lastblock
 	 *  however, if the disc isn't closed, it could be 512.
 	 */
-	if (udf_check_anchor_block(sb, sbi->s_session + 256, fileset))
-		return lastblock;
+	ret = udf_check_anchor_block(sb, sbi->s_session + 256, fileset);
+	if (ret != -EAGAIN)
+		return ret;
 	/*
 	 * The trouble is which block is the last one. Drives often misreport
 	 * this so we try various possibilities.
 	 */
-	last[last_count++] = lastblock;
-	if (lastblock >= 1)
-		last[last_count++] = lastblock - 1;
-	last[last_count++] = lastblock + 1;
-	if (lastblock >= 2)
-		last[last_count++] = lastblock - 2;
-	if (lastblock >= 150)
-		last[last_count++] = lastblock - 150;
-	if (lastblock >= 152)
-		last[last_count++] = lastblock - 152;
+	last[last_count++] = *lastblock;
+	if (*lastblock >= 1)
+		last[last_count++] = *lastblock - 1;
+	last[last_count++] = *lastblock + 1;
+	if (*lastblock >= 2)
+		last[last_count++] = *lastblock - 2;
+	if (*lastblock >= 150)
+		last[last_count++] = *lastblock - 150;
+	if (*lastblock >= 152)
+		last[last_count++] = *lastblock - 152;
 
 	for (i = 0; i < last_count; i++) {
 		if (last[i] >= sb->s_bdev->bd_inode->i_size >>
 				sb->s_blocksize_bits)
 			continue;
-		if (udf_check_anchor_block(sb, last[i], fileset))
-			return last[i];
+		ret = udf_check_anchor_block(sb, last[i], fileset);
+		if (ret != -EAGAIN) {
+			if (!ret)
+				*lastblock = last[i];
+			return ret;
+		}
 		if (last[i] < 256)
 			continue;
-		if (udf_check_anchor_block(sb, last[i] - 256, fileset))
-			return last[i];
+		ret = udf_check_anchor_block(sb, last[i] - 256, fileset);
+		if (ret != -EAGAIN) {
+			if (!ret)
+				*lastblock = last[i];
+			return ret;
+		}
 	}
 
 	/* Finally try block 512 in case media is open */
-	if (udf_check_anchor_block(sb, sbi->s_session + 512, fileset))
-		return last[0];
-	return 0;
+	return udf_check_anchor_block(sb, sbi->s_session + 512, fileset);
 }
 
 /*
@@ -1760,54 +1814,59 @@ static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock,
  * area specified by it. The function expects sbi->s_lastblock to be the last
  * block on the media.
  *
- * Return 1 if ok, 0 if not found.
- *
+ * Return <0 on error, 0 if anchor found. -EAGAIN is special meaning anchor
+ * was not found.
  */
 static int udf_find_anchor(struct super_block *sb,
 			   struct kernel_lb_addr *fileset)
 {
-	sector_t lastblock;
 	struct udf_sb_info *sbi = UDF_SB(sb);
+	sector_t lastblock = sbi->s_last_block;
+	int ret;
 
-	lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
-	if (lastblock)
+	ret = udf_scan_anchors(sb, &lastblock, fileset);
+	if (ret != -EAGAIN)
 		goto out;
 
 	/* No anchor found? Try VARCONV conversion of block numbers */
 	UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
+	lastblock = udf_variable_to_fixed(sbi->s_last_block);
 	/* Firstly, we try to not convert number of the last block */
-	lastblock = udf_scan_anchors(sb,
-				udf_variable_to_fixed(sbi->s_last_block),
-				fileset);
-	if (lastblock)
+	ret = udf_scan_anchors(sb, &lastblock, fileset);
+	if (ret != -EAGAIN)
 		goto out;
 
+	lastblock = sbi->s_last_block;
 	/* Secondly, we try with converted number of the last block */
-	lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
-	if (!lastblock) {
+	ret = udf_scan_anchors(sb, &lastblock, fileset);
+	if (ret < 0) {
 		/* VARCONV didn't help. Clear it. */
 		UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV);
-		return 0;
 	}
 out:
-	sbi->s_last_block = lastblock;
-	return 1;
+	if (ret == 0)
+		sbi->s_last_block = lastblock;
+	return ret;
 }
 
 /*
  * Check Volume Structure Descriptor, find Anchor block and load Volume
- * Descriptor Sequence
+ * Descriptor Sequence.
+ *
+ * Returns < 0 on error, 0 on success. -EAGAIN is special meaning anchor
+ * block was not found.
  */
 static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
 			int silent, struct kernel_lb_addr *fileset)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	loff_t nsr_off;
+	int ret;
 
 	if (!sb_set_blocksize(sb, uopt->blocksize)) {
 		if (!silent)
 			udf_warn(sb, "Bad block size\n");
-		return 0;
+		return -EINVAL;
 	}
 	sbi->s_last_block = uopt->lastblock;
 	if (!uopt->novrs) {
@@ -1828,12 +1887,13 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
 
 	/* Look for anchor block and load Volume Descriptor Sequence */
 	sbi->s_anchor = uopt->anchor;
-	if (!udf_find_anchor(sb, fileset)) {
-		if (!silent)
+	ret = udf_find_anchor(sb, fileset);
+	if (ret < 0) {
+		if (!silent && ret == -EAGAIN)
 			udf_warn(sb, "No anchor found\n");
-		return 0;
+		return ret;
 	}
-	return 1;
+	return 0;
 }
 
 static void udf_open_lvid(struct super_block *sb)
@@ -1939,7 +1999,7 @@ u64 lvid_get_unique_id(struct super_block *sb)
 
 static int udf_fill_super(struct super_block *sb, void *options, int silent)
 {
-	int ret;
+	int ret = -EINVAL;
 	struct inode *inode = NULL;
 	struct udf_options uopt;
 	struct kernel_lb_addr rootdir, fileset;
@@ -2011,7 +2071,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	} else {
 		uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
 		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
-		if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
+		if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
 			if (!silent)
 				pr_notice("Rescanning with blocksize %d\n",
 					  UDF_DEFAULT_BLOCKSIZE);
@@ -2021,8 +2081,11 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 			ret = udf_load_vrs(sb, &uopt, silent, &fileset);
 		}
 	}
-	if (!ret) {
-		udf_warn(sb, "No partition found (1)\n");
+	if (ret < 0) {
+		if (ret == -EAGAIN) {
+			udf_warn(sb, "No partition found (1)\n");
+			ret = -EINVAL;
+		}
 		goto error_out;
 	}
 
@@ -2040,9 +2103,13 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 			udf_err(sb, "minUDFReadRev=%x (max is %x)\n",
 				le16_to_cpu(lvidiu->minUDFReadRev),
 				UDF_MAX_READ_VERSION);
+			ret = -EINVAL;
+			goto error_out;
+		} else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION &&
+			   !(sb->s_flags & MS_RDONLY)) {
+			ret = -EACCES;
 			goto error_out;
-		} else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION)
-			sb->s_flags |= MS_RDONLY;
+		}
 
 		sbi->s_udfrev = minUDFWriteRev;
 
@@ -2054,17 +2121,20 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 
 	if (!sbi->s_partitions) {
 		udf_warn(sb, "No partition found (2)\n");
+		ret = -EINVAL;
 		goto error_out;
 	}
 
 	if (sbi->s_partmaps[sbi->s_partition].s_partition_flags &
-			UDF_PART_FLAG_READ_ONLY) {
-		pr_notice("Partition marked readonly; forcing readonly mount\n");
-		sb->s_flags |= MS_RDONLY;
+			UDF_PART_FLAG_READ_ONLY &&
+	    !(sb->s_flags & MS_RDONLY)) {
+		ret = -EACCES;
+		goto error_out;
 	}
 
 	if (udf_find_fileset(sb, &fileset, &rootdir)) {
 		udf_warn(sb, "No fileset found\n");
+		ret = -EINVAL;
 		goto error_out;
 	}
 
@@ -2086,6 +2156,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	if (!inode) {
 		udf_err(sb, "Error in udf_iget, block=%d, partition=%d\n",
 		       rootdir.logicalBlockNum, rootdir.partitionReferenceNum);
+		ret = -EIO;
 		goto error_out;
 	}
 
@@ -2093,6 +2164,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root) {
 		udf_err(sb, "Couldn't allocate root dentry\n");
+		ret = -ENOMEM;
 		goto error_out;
 	}
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -2113,7 +2185,7 @@ error_out:
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 
-	return -EINVAL;
+	return ret;
 }
 
 void _udf_err(struct super_block *sb, const char *function,
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index d7c6dbe4194b..d89f324bc387 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct buffer_head *bh = NULL;
 	unsigned char *symlink;
-	int err = -EIO;
+	int err;
 	unsigned char *p = kmap(page);
 	struct udf_inode_info *iinfo;
 	uint32_t pos;
 
+	/* We don't support symlinks longer than one block */
+	if (inode->i_size > inode->i_sb->s_blocksize) {
+		err = -ENAMETOOLONG;
+		goto out_unmap;
+	}
+
 	iinfo = UDF_I(inode);
 	pos = udf_block_map(inode, 0);
 
@@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	} else {
 		bh = sb_bread(inode->i_sb, pos);
 
-		if (!bh)
-			goto out;
+		if (!bh) {
+			err = -EIO;
+			goto out_unlock_inode;
+		}
 
 		symlink = bh->b_data;
 	}
@@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	unlock_page(page);
 	return 0;
 
-out:
+out_unlock_inode:
 	up_read(&iinfo->i_data_sem);
 	SetPageError(page);
+out_unmap:
 	kunmap(page);
 	unlock_page(page);
 	return err;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 41a695048be7..cfbb4c1b2f17 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1661,11 +1661,72 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
+/*
+ * This is basically a copy of __set_page_dirty_buffers() with one
+ * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
+ * dirty, we'll never be able to clean them because we don't write buffers
+ * beyond EOF, and that means we can't invalidate pages that span EOF
+ * that have been marked dirty. Further, the dirty state can leak into
+ * the file interior if the file is extended, resulting in all sorts of
+ * bad things happening as the state does not match the underlying data.
+ *
+ * XXX: this really indicates that bufferheads in XFS need to die. Warts like
+ * this only exist because of bufferheads and how the generic code manages them.
+ */
+STATIC int
+xfs_vm_set_page_dirty(
+	struct page		*page)
+{
+	struct address_space	*mapping = page->mapping;
+	struct inode		*inode = mapping->host;
+	loff_t			end_offset;
+	loff_t			offset;
+	int			newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	end_offset = i_size_read(inode);
+	offset = page_offset(page);
+
+	spin_lock(&mapping->private_lock);
+	if (page_has_buffers(page)) {
+		struct buffer_head *head = page_buffers(page);
+		struct buffer_head *bh = head;
+
+		do {
+			if (offset < end_offset)
+				set_buffer_dirty(bh);
+			bh = bh->b_this_page;
+			offset += 1 << inode->i_blkbits;
+		} while (bh != head);
+	}
+	newly_dirty = !TestSetPageDirty(page);
+	spin_unlock(&mapping->private_lock);
+
+	if (newly_dirty) {
+		/* sigh - __set_page_dirty() is static, so copy it here, too */
+		unsigned long flags;
+
+		spin_lock_irqsave(&mapping->tree_lock, flags);
+		if (page->mapping) {	/* Race with truncate? */
+			WARN_ON_ONCE(!PageUptodate(page));
+			account_page_dirtied(page, mapping);
+			radix_tree_tag_set(&mapping->page_tree,
+					page_index(page), PAGECACHE_TAG_DIRTY);
+		}
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	}
+	return newly_dirty;
+}
+
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
+	.set_page_dirty		= xfs_vm_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.write_begin		= xfs_vm_write_begin,
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 0b8b2a13cd24..79ddbaf93206 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1223,6 +1223,7 @@ xfs_da3_node_toosmall(
 	/* start with smaller blk num */
 	forward = nodehdr.forw < nodehdr.back;
 	for (i = 0; i < 2; forward = !forward, i++) {
+		struct xfs_da3_icnode_hdr thdr;
 		if (forward)
 			blkno = nodehdr.forw;
 		else
@@ -1235,10 +1236,10 @@ xfs_da3_node_toosmall(
 			return(error);
 
 		node = bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
+		xfs_da3_node_hdr_from_disk(&thdr, node);
 		xfs_trans_brelse(state->args->trans, bp);
 
-		if (count - nodehdr.count >= 0)
+		if (count - thdr.count >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
 	if (i >= 2) {
@@ -1333,7 +1334,7 @@ xfs_da3_fixhashpath(
 		node = blk->bp->b_addr;
 		xfs_da3_node_hdr_from_disk(&nodehdr, node);
 		btree = xfs_da3_node_tree_p(node);
-		if (be32_to_cpu(btree->hashval) == lasthash)
+		if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
 			break;
 		blk->hashval = lasthash;
 		btree[blk->index].hashval = cpu_to_be32(lasthash);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 044e97a33c8d..bac3e1635b7d 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1104,7 +1104,8 @@ xfs_qm_dqflush(
 	 * Get the buffer containing the on-disk dquot
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
-				   mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
+				   mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+				   &xfs_dquot_buf_ops);
 	if (error)
 		goto out_unlock;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a5f2042aec8b..9f457fedbcfc 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -298,7 +298,16 @@ xfs_file_aio_read(
 				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
 				return ret;
 			}
-			truncate_pagecache_range(VFS_I(ip), pos, -1);
+
+			/*
+			 * Invalidate whole pages. This can return an error if
+			 * we fail to invalidate a page, but this should never
+			 * happen on XFS. Warn if it does fail.
+			 */
+			ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+						pos >> PAGE_CACHE_SHIFT, -1);
+			WARN_ON_ONCE(ret);
+			ret = 0;
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
 	}
@@ -677,7 +686,15 @@ xfs_file_dio_aio_write(
 						    pos, -1);
 		if (ret)
 			goto out;
-		truncate_pagecache_range(VFS_I(ip), pos, -1);
+		/*
+		 * Invalidate whole pages. This can return an error if
+		 * we fail to invalidate a page, but this should never
+		 * happen on XFS. Warn if it does fail.
+		 */
+		ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+						pos >> PAGE_CACHE_SHIFT, -1);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	/*
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 3c3644ea825b..2288db4e1784 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -216,6 +216,8 @@ xfs_growfs_data_private(
 	 */
 	nfree = 0;
 	for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
+		__be32	*agfl_bno;
+
 		/*
 		 * AG freespace header block
 		 */
@@ -275,8 +277,10 @@ xfs_growfs_data_private(
 			agfl->agfl_seqno = cpu_to_be32(agno);
 			uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid);
 		}
+
+		agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
 		for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
-			agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+			agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
 
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5e999680094a..83dfe6e73235 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -409,7 +409,8 @@ xfs_attrlist_by_handle(
 		return -XFS_ERROR(EPERM);
 	if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
@@ -1612,6 +1613,12 @@ xfs_file_ioctl(
 	case XFS_IOC_FREE_EOFBLOCKS: {
 		struct xfs_eofblocks eofb;
 
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (mp->m_flags & XFS_MOUNT_RDONLY)
+			return -XFS_ERROR(EROFS);
+
 		if (copy_from_user(&eofb, arg, sizeof(eofb)))
 			return -XFS_ERROR(EFAULT);
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c0c66259cc91..68799d7f02cc 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -359,7 +359,8 @@ xfs_compat_attrlist_by_handle(
 	if (copy_from_user(&al_hreq, arg,
 			   sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b75c9bb6e71e..29d1ca567ed3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -935,6 +935,12 @@ xfs_qm_dqiter_bufs(
 		if (error)
 			break;
 
+		/*
+		 * A corrupt buffer might not have a verifier attached, so
+		 * make sure we have the correct one attached before writeback
+		 * occurs.
+		 */
+		bp->b_ops = &xfs_dquot_buf_ops;
 		xfs_qm_reset_dqcounts(mp, bp, firstid, type);
 		xfs_buf_delwri_queue(bp, buffer_list);
 		xfs_buf_relse(bp);
@@ -1018,7 +1024,7 @@ xfs_qm_dqiterate(
 					xfs_buf_readahead(mp->m_ddev_targp,
 					       XFS_FSB_TO_DADDR(mp, rablkno),
 					       mp->m_quotainfo->qi_dqchunklen,
-					       NULL);
+					       &xfs_dquot_buf_ops);
 					rablkno++;
 				}
 			}
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f45b2a7800c4..6b66efdcd197 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -97,6 +97,7 @@ enum acpi_hotplug_mode {
 struct acpi_hotplug_profile {
 	struct kobject kobj;
 	bool enabled:1;
+	bool ignore:1;
 	enum acpi_hotplug_mode mode;
 };
 
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index d06079c774a0..99b490b4d05a 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -6,12 +6,12 @@ static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
 	return mk_pte(page, pgprot);
 }
 
-static inline int huge_pte_write(pte_t pte)
+static inline unsigned long huge_pte_write(pte_t pte)
 {
 	return pte_write(pte);
 }
 
-static inline int huge_pte_dirty(pte_t pte)
+static inline unsigned long huge_pte_dirty(pte_t pte)
 {
 	return pte_dirty(pte);
 }
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a59ff51b0166..17bccd3a4b03 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -220,7 +220,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #endif
 
 #ifndef pte_accessible
-# define pte_accessible(pte)		((void)(pte),1)
+# define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
 #ifndef flush_tlb_fix_spurious_fault
@@ -620,32 +620,47 @@ static inline int pmd_numa(pmd_t pmd)
 #ifndef pte_mknonnuma
 static inline pte_t pte_mknonnuma(pte_t pte)
 {
-	pte = pte_clear_flags(pte, _PAGE_NUMA);
-	return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+	pteval_t val = pte_val(pte);
+
+	val &= ~_PAGE_NUMA;
+	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+	return __pte(val);
 }
 #endif
 
 #ifndef pmd_mknonnuma
 static inline pmd_t pmd_mknonnuma(pmd_t pmd)
 {
-	pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
-	return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+	pmdval_t val = pmd_val(pmd);
+
+	val &= ~_PAGE_NUMA;
+	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+
+	return __pmd(val);
 }
 #endif
 
 #ifndef pte_mknuma
 static inline pte_t pte_mknuma(pte_t pte)
 {
-	pte = pte_set_flags(pte, _PAGE_NUMA);
-	return pte_clear_flags(pte, _PAGE_PRESENT);
+	pteval_t val = pte_val(pte);
+
+	val &= ~_PAGE_PRESENT;
+	val |= _PAGE_NUMA;
+
+	return __pte(val);
 }
 #endif
 
 #ifndef pmd_mknuma
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
-	pmd = pmd_set_flags(pmd, _PAGE_NUMA);
-	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+	pmdval_t val = pmd_val(pmd);
+
+	val &= ~_PAGE_PRESENT;
+	val |= _PAGE_NUMA;
+
+	return __pmd(val);
 }
 #endif
 #else
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
new file mode 100644
index 000000000000..f57eb7b5c23b
--- /dev/null
+++ b/include/asm-generic/simd.h
@@ -0,0 +1,14 @@
+
+#include <linux/hardirq.h>
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ *                instructions or access the SIMD register file
+ *
+ * As architectures typically don't preserve the SIMD register file when
+ * taking an interrupt, !in_interrupt() should be a reasonable default.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	return !in_interrupt();
+}
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 3f21f1b72e45..94f9ea8abcae 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -49,4 +49,8 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 	return (val + c->high_bits) & ~rhs;
 }
 
+#ifndef zero_bytemask
+#define zero_bytemask(mask) (~1ul << __fls(mask))
+#endif
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index c463ce990c48..6d26b40cbf5d 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -23,16 +23,30 @@
 #define ARCH_TIMER_CTRL_IT_MASK		(1 << 1)
 #define ARCH_TIMER_CTRL_IT_STAT		(1 << 2)
 
-#define ARCH_TIMER_REG_CTRL		0
-#define ARCH_TIMER_REG_TVAL		1
+enum arch_timer_reg {
+	ARCH_TIMER_REG_CTRL,
+	ARCH_TIMER_REG_TVAL,
+};
 
 #define ARCH_TIMER_PHYS_ACCESS		0
 #define ARCH_TIMER_VIRT_ACCESS		1
+#define ARCH_TIMER_MEM_PHYS_ACCESS	2
+#define ARCH_TIMER_MEM_VIRT_ACCESS	3
+
+#define ARCH_TIMER_USR_PCT_ACCESS_EN	(1 << 0) /* physical counter */
+#define ARCH_TIMER_USR_VCT_ACCESS_EN	(1 << 1) /* virtual counter */
+#define ARCH_TIMER_VIRT_EVT_EN		(1 << 2)
+#define ARCH_TIMER_EVT_TRIGGER_SHIFT	(4)
+#define ARCH_TIMER_EVT_TRIGGER_MASK	(0xF << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+#define ARCH_TIMER_USR_VT_ACCESS_EN	(1 << 8) /* virtual timer registers */
+#define ARCH_TIMER_USR_PT_ACCESS_EN	(1 << 9) /* physical timer registers */
+
+#define ARCH_TIMER_EVT_STREAM_FREQ	10000	/* 100us */
 
 #ifdef CONFIG_ARM_ARCH_TIMER
 
 extern u32 arch_timer_get_rate(void);
-extern u64 arch_timer_read_counter(void);
+extern u64 (*arch_timer_read_counter)(void);
 extern struct timecounter *arch_timer_get_timecounter(void);
 
 #else
diff --git a/include/crypto/ablk_helper.h b/include/crypto/ablk_helper.h
new file mode 100644
index 000000000000..4f93df50c23e
--- /dev/null
+++ b/include/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+	struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 418d270e1806..063f8ef49301 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@ struct blkcipher_walk {
 	void *page;
 	u8 *buffer;
 	u8 *iv;
+	unsigned int ivsize;
 
 	int flags;
-	unsigned int blocksize;
+	unsigned int walk_blocksize;
+	unsigned int cipher_blocksize;
+	unsigned int alignmask;
 };
 
 struct ablkcipher_walk {
@@ -192,6 +195,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      struct blkcipher_walk *walk,
 			      unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize);
 
 int ablkcipher_walk_done(struct ablkcipher_request *req,
 			 struct ablkcipher_walk *walk, int err);
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 3744d2a642df..2cddd2b92c19 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -36,6 +36,7 @@ static inline void scatterwalk_sg_chain(struct scatterlist *sg1, int num,
 {
 	sg_set_page(&sg1[num - 1], (void *)sg2, 0, 0);
 	sg1[num - 1].page_link &= ~0x02;
+	sg1[num - 1].page_link |= 0x01;
 }
 
 static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg)
@@ -43,7 +44,7 @@ static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg)
 	if (sg_is_last(sg))
 		return NULL;
 
-	return (++sg)->length ? sg : (void *)sg_page(sg);
+	return (++sg)->length ? sg : sg_chain_ptr(sg);
 }
 
 static inline void scatterwalk_crypto_chain(struct scatterlist *head,
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index bb1bc485390b..d7b717090f2f 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -52,7 +52,6 @@
 	{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
@@ -143,8 +142,11 @@
 	{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
@@ -256,6 +258,7 @@
 	{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -559,7 +562,7 @@
 	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
-	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/dt-bindings/thermal/thermal.h b/include/dt-bindings/thermal/thermal.h
new file mode 100644
index 000000000000..59822a995858
--- /dev/null
+++ b/include/dt-bindings/thermal/thermal.h
@@ -0,0 +1,17 @@
+/*
+ * This header provides constants for most thermal bindings.
+ *
+ * Copyright (C) 2013 Texas Instruments
+ *	Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ * GPLv2 only
+ */
+
+#ifndef _DT_BINDINGS_THERMAL_THERMAL_H
+#define _DT_BINDINGS_THERMAL_THERMAL_H
+
+/* On cooling devices upper and lower limits */
+#define THERMAL_NO_LIMIT		(-1UL)
+
+#endif
+
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 43ec7e247a80..aafb89c3a3e6 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -23,6 +23,7 @@
 
 #define AMBA_NR_IRQS	2
 #define AMBA_CID	0xb105f00d
+#define CORESIGHT_CID	0xb105900d
 
 struct clk;
 
diff --git a/include/linux/arm-cci.h b/include/linux/arm-cci.h
new file mode 100644
index 000000000000..79d6edf446d5
--- /dev/null
+++ b/include/linux/arm-cci.h
@@ -0,0 +1,61 @@
+/*
+ * CCI cache coherent interconnect support
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __LINUX_ARM_CCI_H
+#define __LINUX_ARM_CCI_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device_node;
+
+#ifdef CONFIG_ARM_CCI
+extern bool cci_probed(void);
+extern int cci_ace_get_port(struct device_node *dn);
+extern int cci_disable_port_by_cpu(u64 mpidr);
+extern int __cci_control_port_by_device(struct device_node *dn, bool enable);
+extern int __cci_control_port_by_index(u32 port, bool enable);
+#else
+static inline bool cci_probed(void) { return false; }
+static inline int cci_ace_get_port(struct device_node *dn)
+{
+	return -ENODEV;
+}
+static inline int cci_disable_port_by_cpu(u64 mpidr) { return -ENODEV; }
+static inline int __cci_control_port_by_device(struct device_node *dn,
+					       bool enable)
+{
+	return -ENODEV;
+}
+static inline int __cci_control_port_by_index(u32 port, bool enable)
+{
+	return -ENODEV;
+}
+#endif
+#define cci_disable_port_by_device(dev) \
+	__cci_control_port_by_device(dev, false)
+#define cci_enable_port_by_device(dev) \
+	__cci_control_port_by_device(dev, true)
+#define cci_disable_port_by_index(dev) \
+	__cci_control_port_by_index(dev, false)
+#define cci_enable_port_by_index(dev) \
+	__cci_control_port_by_index(dev, true)
+
+#endif
diff --git a/include/linux/arm-hdlcd.h b/include/linux/arm-hdlcd.h
new file mode 100644
index 000000000000..939f3a81d56b
--- /dev/null
+++ b/include/linux/arm-hdlcd.h
@@ -0,0 +1,122 @@
+/*
+ * include/linux/arm-hdlcd.h
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller register definition
+ */
+
+#include <linux/fb.h>
+#include <linux/completion.h>
+
+/* register offsets */
+#define HDLCD_REG_VERSION		0x0000	/* ro */
+#define HDLCD_REG_INT_RAWSTAT		0x0010	/* rw */
+#define HDLCD_REG_INT_CLEAR		0x0014	/* wo */
+#define HDLCD_REG_INT_MASK		0x0018	/* rw */
+#define HDLCD_REG_INT_STATUS		0x001c	/* ro */
+#define HDLCD_REG_USER_OUT		0x0020	/* rw */
+#define HDLCD_REG_FB_BASE		0x0100	/* rw */
+#define HDLCD_REG_FB_LINE_LENGTH	0x0104	/* rw */
+#define HDLCD_REG_FB_LINE_COUNT		0x0108	/* rw */
+#define HDLCD_REG_FB_LINE_PITCH		0x010c	/* rw */
+#define HDLCD_REG_BUS_OPTIONS		0x0110	/* rw */
+#define HDLCD_REG_V_SYNC		0x0200	/* rw */
+#define HDLCD_REG_V_BACK_PORCH		0x0204	/* rw */
+#define HDLCD_REG_V_DATA		0x0208	/* rw */
+#define HDLCD_REG_V_FRONT_PORCH		0x020c	/* rw */
+#define HDLCD_REG_H_SYNC		0x0210	/* rw */
+#define HDLCD_REG_H_BACK_PORCH		0x0214	/* rw */
+#define HDLCD_REG_H_DATA		0x0218	/* rw */
+#define HDLCD_REG_H_FRONT_PORCH		0x021c	/* rw */
+#define HDLCD_REG_POLARITIES		0x0220	/* rw */
+#define HDLCD_REG_COMMAND		0x0230	/* rw */
+#define HDLCD_REG_PIXEL_FORMAT		0x0240	/* rw */
+#define HDLCD_REG_BLUE_SELECT		0x0244	/* rw */
+#define HDLCD_REG_GREEN_SELECT		0x0248	/* rw */
+#define HDLCD_REG_RED_SELECT		0x024c	/* rw */
+
+/* version */
+#define HDLCD_PRODUCT_ID		0x1CDC0000
+#define HDLCD_PRODUCT_MASK		0xFFFF0000
+#define HDLCD_VERSION_MAJOR_MASK	0x0000FF00
+#define HDLCD_VERSION_MINOR_MASK	0x000000FF
+
+/* interrupts */
+#define HDLCD_INTERRUPT_DMA_END		(1 << 0)
+#define HDLCD_INTERRUPT_BUS_ERROR	(1 << 1)
+#define HDLCD_INTERRUPT_VSYNC		(1 << 2)
+#define HDLCD_INTERRUPT_UNDERRUN	(1 << 3)
+
+/* polarity */
+#define HDLCD_POLARITY_VSYNC		(1 << 0)
+#define HDLCD_POLARITY_HSYNC		(1 << 1)
+#define HDLCD_POLARITY_DATAEN		(1 << 2)
+#define HDLCD_POLARITY_DATA		(1 << 3)
+#define HDLCD_POLARITY_PIXELCLK		(1 << 4)
+
+/* commands */
+#define HDLCD_COMMAND_DISABLE		(0 << 0)
+#define HDLCD_COMMAND_ENABLE		(1 << 0)
+
+/* pixel format */
+#define HDLCD_PIXEL_FMT_LITTLE_ENDIAN	(0 << 31)
+#define HDLCD_PIXEL_FMT_BIG_ENDIAN	(1 << 31)
+#define HDLCD_BYTES_PER_PIXEL_MASK	(3 << 3)
+
+/* bus options */
+#define HDLCD_BUS_BURST_MASK		0x01f
+#define HDLCD_BUS_MAX_OUTSTAND		0xf00
+#define HDLCD_BUS_BURST_NONE		(0 << 0)
+#define HDLCD_BUS_BURST_1		(1 << 0)
+#define HDLCD_BUS_BURST_2		(1 << 1)
+#define HDLCD_BUS_BURST_4		(1 << 2)
+#define HDLCD_BUS_BURST_8		(1 << 3)
+#define HDLCD_BUS_BURST_16		(1 << 4)
+
+/* Max resolution supported is 4096x4096, 8 bit per color component,
+   8 bit alpha, but we are going to choose the usual hardware default
+   (2048x2048, 32 bpp) and enable double buffering */
+#define HDLCD_MAX_XRES			2048
+#define HDLCD_MAX_YRES			2048
+#define HDLCD_MAX_FRAMEBUFFER_SIZE	(HDLCD_MAX_XRES * HDLCD_MAX_YRES << 2)
+
+#define HDLCD_MEM_BASE			(CONFIG_PAGE_OFFSET - 0x1000000)
+
+#define NR_PALETTE	256
+
+/* OEMs using HDLCD may wish to enable these settings if
+ * display disruption is apparent and you suspect HDLCD
+ * access to RAM may be starved.
+ */
+/* Turn HDLCD default color red instead of black so
+ * that it's easy to see pixel clock data underruns
+ * (compared to other visual disruption)
+ */
+//#define HDLCD_RED_DEFAULT_COLOUR
+/* Add a counter in the IRQ handler to count buffer underruns
+ * and /proc/hdlcd_underrun to read the counter
+ */
+//#define HDLCD_COUNT_BUFFERUNDERRUNS
+/* Restrict height to 1x screen size
+ *
+ */
+//#define HDLCD_NO_VIRTUAL_SCREEN
+
+#ifdef CONFIG_ANDROID
+#define HDLCD_NO_VIRTUAL_SCREEN
+#endif
+
+struct hdlcd_device {
+	struct fb_info		fb;
+	struct device		*dev;
+	struct clk		*clk;
+	void __iomem		*base;
+	int			irq;
+	struct completion	vsync_completion;
+	unsigned char		*edid;
+};
diff --git a/include/linux/audit.h b/include/linux/audit.h
index b20b03852f21..4fb28b23a4a4 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -103,8 +103,11 @@ extern void __audit_syscall_exit(int ret_success, long ret_value);
 extern struct filename *__audit_reusename(const __user char *uptr);
 extern void __audit_getname(struct filename *name);
 extern void audit_putname(struct filename *name);
+
+#define AUDIT_INODE_PARENT	1	/* dentry represents the parent */
+#define AUDIT_INODE_HIDDEN	2	/* audit record should be hidden */
 extern void __audit_inode(struct filename *name, const struct dentry *dentry,
-				unsigned int parent);
+				unsigned int flags);
 extern void __audit_inode_child(const struct inode *parent,
 				const struct dentry *dentry,
 				const unsigned char type);
@@ -132,7 +135,7 @@ static inline void audit_syscall_exit(void *pt_regs)
 {
 	if (unlikely(current->audit_context)) {
 		int success = is_syscall_success(pt_regs);
-		int return_code = regs_return_value(pt_regs);
+		long return_code = regs_return_value(pt_regs);
 
 		__audit_syscall_exit(success, return_code);
 	}
@@ -148,10 +151,22 @@ static inline void audit_getname(struct filename *name)
 	if (unlikely(!audit_dummy_context()))
 		__audit_getname(name);
 }
-static inline void audit_inode(struct filename *name, const struct dentry *dentry,
+static inline void audit_inode(struct filename *name,
+				const struct dentry *dentry,
 				unsigned int parent) {
+	if (unlikely(!audit_dummy_context())) {
+		unsigned int flags = 0;
+		if (parent)
+			flags |= AUDIT_INODE_PARENT;
+		__audit_inode(name, dentry, flags);
+	}
+}
+static inline void audit_inode_parent_hidden(struct filename *name,
+						const struct dentry *dentry)
+{
 	if (unlikely(!audit_dummy_context()))
-		__audit_inode(name, dentry, parent);
+		__audit_inode(name, dentry,
+				AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN);
 }
 static inline void audit_inode_child(const struct inode *parent,
 				     const struct dentry *dentry,
@@ -311,7 +326,7 @@ static inline void audit_putname(struct filename *name)
 { }
 static inline void __audit_inode(struct filename *name,
 					const struct dentry *dentry,
-					unsigned int parent)
+					unsigned int flags)
 { }
 static inline void __audit_inode_child(const struct inode *parent,
 					const struct dentry *dentry,
@@ -321,6 +336,9 @@ static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int parent)
 { }
+static inline void audit_inode_parent_hidden(struct filename *name,
+				const struct dentry *dentry)
+{ }
 static inline void audit_inode_child(const struct inode *parent,
 				     const struct dentry *dentry,
 				     const unsigned char type)
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 669fef5c745a..3e0fbe441763 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -3,6 +3,6 @@
 
 #include <uapi/linux/auxvec.h>
 
-#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c3881553f7d1..4cfdbf28fc6a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -95,7 +95,7 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects work_list */
+	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
 
 	struct list_head work_list;
 
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index f7f1d7169b11..089743ade734 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -159,6 +159,26 @@ static inline bool balloon_page_movable(struct page *page)
 }
 
 /*
+ * isolated_balloon_page - identify an isolated balloon page on private
+ *			   compaction/migration page lists.
+ *
+ * After a compaction thread isolates a balloon page for migration, it raises
+ * the page refcount to prevent concurrent compaction threads from re-isolating
+ * the same page. For that reason putback_movable_pages(), or other routines
+ * that need to identify isolated balloon pages on private pagelists, cannot
+ * rely on balloon_page_movable() to accomplish the task.
+ */
+static inline bool isolated_balloon_page(struct page *page)
+{
+	/* Already isolated balloon pages, by default, have a raised refcount */
+	if (page_flags_cleared(page) && !page_mapped(page) &&
+	    page_count(page) >= 2)
+		return __is_movable_balloon_page(page);
+
+	return false;
+}
+
+/*
  * balloon_page_insert - insert a page into the balloon's page list and make
  *		         the page->mapping assignment accordingly.
  * @page    : page to be assigned as a 'balloon page'
@@ -243,6 +263,11 @@ static inline bool balloon_page_movable(struct page *page)
 	return false;
 }
 
+static inline bool isolated_balloon_page(struct page *page)
+{
+	return false;
+}
+
 static inline bool balloon_page_isolate(struct page *page)
 {
 	return false;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 70cf138690e9..df97ca4aae52 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -99,9 +99,6 @@ extern void setup_new_exec(struct linux_binprm * bprm);
 extern void would_dump(struct linux_binprm *, struct file *);
 
 extern int suid_dumpable;
-#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
-#define SUID_DUMP_USER		1	/* Dump as user of process */
-#define SUID_DUMP_ROOT		2	/* Dump as root */
 
 /* Stack area protections */
 #define EXSTACK_DEFAULT   0	/* Whatever the arch defaults to */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3b6b82108b9..be3a228f389b 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -10,6 +10,14 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
 extern unsigned int __sw_hweight32(unsigned int w);
@@ -185,6 +193,21 @@ static inline unsigned long __ffs64(u64 word)
 
 #ifdef __KERNEL__
 
+#ifndef set_mask_bits
+#define set_mask_bits(ptr, _mask, _bits)	\
+({								\
+	const typeof(*ptr) mask = (_mask), bits = (_bits);	\
+	typeof(*ptr) old, new;					\
+								\
+	do {							\
+		old = ACCESS_ONCE(*ptr);			\
+		new = (old & ~mask) | bits;			\
+	} while (cmpxchg(ptr, old, new) != old);		\
+								\
+	new;							\
+})
+#endif
+
 #ifndef find_last_bit
 /**
  * find_last_bit - find the last set bit in a memory region
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2fdb4a451b49..494d228a91dd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1187,10 +1187,9 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = (sector << 9) & (granularity - 1);
+	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
 
-	return (granularity + lim->alignment_offset - alignment)
-		& (granularity - 1);
+	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
 
 static inline int bdev_alignment_offset(struct block_device *bdev)
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 2f0543f7510c..f9bbbb472663 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -11,7 +11,9 @@
 #define CAN_SKB_H
 
 #include <linux/types.h>
+#include <linux/skbuff.h>
 #include <linux/can.h>
+#include <net/sock.h>
 
 /*
  * The struct can_skb_priv is used to transport additional information along
@@ -42,4 +44,40 @@ static inline void can_skb_reserve(struct sk_buff *skb)
 	skb_reserve(skb, sizeof(struct can_skb_priv));
 }
 
+static inline void can_skb_destructor(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+
+static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk) {
+		sock_hold(sk);
+		skb->destructor = can_skb_destructor;
+		skb->sk = sk;
+	}
+}
+
+/*
+ * returns an unshared skb owned by the original sock to be echo'ed back
+ */
+static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
+{
+	if (skb_shared(skb)) {
+		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+		if (likely(nskb)) {
+			can_skb_set_owner(nskb, skb->sk);
+			consume_skb(skb);
+			return nskb;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
+	/* we can assume to have an unshared skb with proper owner */
+	return skb;
+}
+
 #endif /* CAN_SKB_H */
diff --git a/include/linux/capability.h b/include/linux/capability.h
index d9a4f7f40f32..9b4378af414c 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set;
 # error Fix up hand-coded capability macro initializers
 #else /* HAND-CODED capability initializers */
 
+#define CAP_LAST_U32			((_KERNEL_CAPABILITY_U32S) - 1)
+#define CAP_LAST_U32_VALID_MASK		(CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
+
 # define CAP_EMPTY_SET    ((kernel_cap_t){{ 0, 0 }})
-# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, ~0 }})
+# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
 # define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0 \
 				    | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
 				    CAP_FS_MASK_B1 } })
@@ -211,7 +214,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
 extern bool nsown_capable(int cap);
-extern bool inode_capable(const struct inode *inode, int cap);
+extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 
 /* audit system wants to get cap info from files as well */
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 7c1420bb1dce..6ade97de7a85 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -157,7 +157,7 @@ struct ceph_msg {
 	bool front_is_vmalloc;
 	bool more_to_follow;
 	bool needs_out_seq;
-	int front_max;
+	int front_alloc_len;
 	unsigned long ack_stamp;        /* tx: when we were acked */
 
 	struct ceph_msgpool *pool;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 186db0bf4951..4fb6a8938957 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -138,6 +138,7 @@ struct ceph_osd_request {
 	__le64           *r_request_pool;
 	void             *r_request_pgid;
 	__le32           *r_request_attempts;
+	bool              r_paused;
 	struct ceph_eversion *r_request_reassert_version;
 
 	int               r_result;
@@ -145,7 +146,6 @@ struct ceph_osd_request {
 	s32               r_reply_op_result[CEPH_OSD_MAX_OP];
 	int               r_got_reply;
 	int		  r_linger;
-	int		  r_completed;
 
 	struct ceph_osd_client *r_osdc;
 	struct kref       r_kref;
@@ -336,6 +336,8 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
 				  struct ceph_osd_request *req);
 extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
 
+extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
+
 extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 			       struct ceph_vino vino,
 			       struct ceph_file_layout *layout,
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 11860985fecb..89b7ceed70db 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -257,6 +257,8 @@ struct clk_div_table {
  *	Some hardware implementations gracefully handle this case and allow a
  *	zero divisor by not modifying their input clock
  *	(divide by one / bypass).
+ * CLK_DIVIDER_ROUND_CLOSEST - Makes the best calculated divider to be rounded
+ *	to the closest integer instead of the up one.
  */
 struct clk_divider {
 	struct clk_hw	hw;
@@ -271,6 +273,7 @@ struct clk_divider {
 #define CLK_DIVIDER_ONE_BASED		BIT(0)
 #define CLK_DIVIDER_POWER_OF_TWO	BIT(1)
 #define CLK_DIVIDER_ALLOW_ZERO		BIT(2)
+#define CLK_DIVIDER_ROUND_CLOSEST	BIT(4)
 
 extern const struct clk_ops clk_divider_ops;
 struct clk *clk_register_divider(struct device *dev, const char *name,
@@ -435,6 +438,7 @@ struct clk_onecell_data {
 	unsigned int clk_num;
 };
 struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data);
+int of_clk_get_parent_count(struct device_node *np);
 const char *of_clk_get_parent_name(struct device_node *np, int index);
 
 void of_clk_init(const struct of_device_id *matches);
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 963d71431388..3abe1e9a1bde 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -30,6 +30,7 @@ enum clock_event_nofitiers {
 #include <linux/notifier.h>
 
 struct clock_event_device;
+struct module;
 
 /* Clock event mode commands */
 enum clock_event_mode {
@@ -60,6 +61,11 @@ enum clock_event_mode {
  */
 #define CLOCK_EVT_FEAT_DYNIRQ		0x000020
 
+/*
+ * Clockevent device is based on a hrtimer for broadcast
+ */
+#define CLOCK_EVT_FEAT_HRTIMER		0x000080
+
 /**
  * struct clock_event_device - clock event device descriptor
  * @event_handler:	Assigned by the framework to be called by the low
@@ -81,8 +87,10 @@ enum clock_event_mode {
  * @name:		ptr to clock event name
  * @rating:		variable to rate clock event devices
  * @irq:		IRQ number (only for non CPU local devices)
+ * @bound_on:		Bound on CPU
  * @cpumask:		cpumask to indicate for which CPUs this device works
  * @list:		list head for the management code
+ * @owner:		module reference
  */
 struct clock_event_device {
 	void			(*event_handler)(struct clock_event_device *);
@@ -110,8 +118,10 @@ struct clock_event_device {
 	const char		*name;
 	int			rating;
 	int			irq;
+	int			bound_on;
 	const struct cpumask	*cpumask;
 	struct list_head	list;
+	struct module		*owner;
 } ____cacheline_aligned;
 
 /*
@@ -150,7 +160,6 @@ extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
 extern void clockevents_set_mode(struct clock_event_device *dev,
 				 enum clock_event_mode mode);
-extern int clockevents_register_notifier(struct notifier_block *nb);
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, bool force);
 
@@ -176,15 +185,17 @@ extern int tick_receive_broadcast(void);
 #endif
 
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void tick_setup_hrtimer_broadcast(void);
 extern int tick_check_broadcast_expired(void);
 #else
 static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
-extern void clockevents_notify(unsigned long reason, void *arg);
+extern int clockevents_notify(unsigned long reason, void *arg);
 #else
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
 #endif
 
 #else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
@@ -192,8 +203,9 @@ static inline void clockevents_notify(unsigned long reason, void *arg) {}
 static inline void clockevents_suspend(void) {}
 static inline void clockevents_resume(void) {}
 
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
 static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
 
 #endif
 
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7279b94c01da..91aa89e1aaa0 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -285,7 +285,7 @@ extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
-extern struct clocksource * __init __weak clocksource_default_clock(void);
+extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
 
 extern void
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ec1aee4aec9c..df7060083d85 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -326,16 +326,16 @@ asmlinkage long compat_sys_keyctl(u32 option,
 			      u32 arg2, u32 arg3, u32 arg4, u32 arg5);
 asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 
-asmlinkage ssize_t compat_sys_readv(unsigned long fd,
-		const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_writev(unsigned long fd,
-		const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
+asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
+		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
+		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_low, u32 pos_high);
-asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
+		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_low, u32 pos_high);
+		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
@@ -421,7 +421,7 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 				  compat_long_t addr, compat_long_t data);
 
-asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, size_t);
+asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
 /*
  * epoll (fs/eventpoll.c) compat bits follow ...
  */
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 24545cd90a25..02ae99e8e6d3 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -37,6 +37,9 @@
     __asm__ ("" : "=r"(__ptr) : "0"(ptr));		\
     (typeof(ptr)) (__ptr + (off)); })
 
+/* Make the optimizer believe the variable can be manipulated arbitrarily. */
+#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var))
+
 #ifdef __CHECKER__
 #define __must_be_array(arr) 0
 #else
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 842de225055f..2507fd2a1eb4 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -65,6 +65,17 @@
 #define __visible __attribute__((externally_visible))
 #endif
 
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
 
 #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
 #if GCC_VERSION >= 40400
diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 000000000000..cdd1cc202d51
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used				__attribute__((__used__))
+#define __must_check			__attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b)	__builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold			__attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased.  Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone	__attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index 973ce10c40b6..5529c5239421 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -15,6 +15,7 @@
  */
 #undef barrier
 #undef RELOC_HIDE
+#undef OPTIMIZER_HIDE_VAR
 
 #define barrier() __memory_barrier()
 
@@ -23,13 +24,17 @@
      __ptr = (unsigned long) (ptr);				\
     (typeof(ptr)) (__ptr + (off)); })
 
+/* This should act as an optimization barrier on var.
+ * Given that this compiler does not have inline assembly, a compiler barrier
+ * is the best we can do.
+ */
+#define OPTIMIZER_HIDE_VAR(var) barrier()
+
 /* Intel ECC compiler doesn't support __builtin_types_compatible_p() */
 #define __must_be_array(a) 0
 
 #endif
 
-#define uninitialized_var(x) x
-
 #ifndef __HAVE_BUILTIN_BSWAP16__
 /* icc has this, but it's called _bswap16 */
 #define __HAVE_BUILTIN_BSWAP16__
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 92669cd182a6..a2329c5e6206 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -170,6 +170,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+#ifndef OPTIMIZER_HIDE_VAR
+#define OPTIMIZER_HIDE_VAR(var) barrier()
+#endif
+
 /* Not-quite-unique ID. */
 #ifndef __UNIQUE_ID
 # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
new file mode 100644
index 000000000000..bdde4199c74a
--- /dev/null
+++ b/include/linux/coresight.h
@@ -0,0 +1,263 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_CORESIGHT_H
+#define _LINUX_CORESIGHT_H
+
+#include <linux/device.h>
+
+/* Peripheral id registers (0xFD0-0xFEC) */
+#define CORESIGHT_PERIPHIDR4	0xfd0
+#define CORESIGHT_PERIPHIDR5	0xfd4
+#define CORESIGHT_PERIPHIDR6	0xfd8
+#define CORESIGHT_PERIPHIDR7	0xfdC
+#define CORESIGHT_PERIPHIDR0	0xfe0
+#define CORESIGHT_PERIPHIDR1	0xfe4
+#define CORESIGHT_PERIPHIDR2	0xfe8
+#define CORESIGHT_PERIPHIDR3	0xfeC
+/* Component id registers (0xFF0-0xFFC) */
+#define CORESIGHT_COMPIDR0	0xff0
+#define CORESIGHT_COMPIDR1	0xff4
+#define CORESIGHT_COMPIDR2	0xff8
+#define CORESIGHT_COMPIDR3	0xffC
+
+#define ETM_ARCH_V3_3		0x23
+#define ETM_ARCH_V3_5		0x25
+#define PFT_ARCH_V1_0		0x30
+#define PFT_ARCH_V1_1		0x31
+
+#define CORESIGHT_UNLOCK	0xc5acce55
+
+extern struct bus_type coresight_bustype;
+
+enum coresight_dev_type {
+	CORESIGHT_DEV_TYPE_NONE,
+	CORESIGHT_DEV_TYPE_SINK,
+	CORESIGHT_DEV_TYPE_LINK,
+	CORESIGHT_DEV_TYPE_LINKSINK,
+	CORESIGHT_DEV_TYPE_SOURCE,
+};
+
+enum coresight_dev_subtype_sink {
+	CORESIGHT_DEV_SUBTYPE_SINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
+	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+};
+
+enum coresight_dev_subtype_link {
+	CORESIGHT_DEV_SUBTYPE_LINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_LINK_MERG,
+	CORESIGHT_DEV_SUBTYPE_LINK_SPLIT,
+	CORESIGHT_DEV_SUBTYPE_LINK_FIFO,
+};
+
+enum coresight_dev_subtype_source {
+	CORESIGHT_DEV_SUBTYPE_SOURCE_NONE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+};
+
+/**
+ * struct coresight_dev_subtype - further characterisation of a type
+ * @sink_subtype:	type of sink this component is, as defined
+			by @coresight_dev_subtype_sink.
+ * @link_subtype:	type of link this component is, as defined
+			by @coresight_dev_subtype_link.
+ * @source_subtype:	type of source this component is, as defined
+			by @coresight_dev_subtype_source.
+ */
+struct coresight_dev_subtype {
+	enum coresight_dev_subtype_sink sink_subtype;
+	enum coresight_dev_subtype_link link_subtype;
+	enum coresight_dev_subtype_source source_subtype;
+};
+
+/**
+ * struct coresight_platform_data - data harvested from the DT specification
+ * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
+ * @name:	name of the component as shown under sysfs.
+ * @nr_inport:	number of input ports for this component.
+ * @outports:	list of remote enpoint port number.
+ * @child_names:name of all child components connected to this device.
+ * @child_ports:child component port number the current component is
+		connected  to.
+ * @nr_outport:	number of output ports for this component.
+ * @clk:	The clock this component is associated to.
+ */
+struct coresight_platform_data {
+	int cpu;
+	const char *name;
+	int nr_inport;
+	int *outports;
+	const char **child_names;
+	int *child_ports;
+	int nr_outport;
+	struct clk *clk;
+};
+
+/**
+ * struct coresight_desc - description of a component required from drivers
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @pdata:	platform data collected from DT.
+ * @dev:	The device entity associated to this component.
+ * @groups	:operations specific to this component. These will end up
+		in the component's sysfs sub-directory.
+ */
+struct coresight_desc {
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct coresight_platform_data *pdata;
+	struct device *dev;
+	const struct attribute_group **groups;
+};
+
+/**
+ * struct coresight_connection - representation of a single connection
+ * @ref_count:	keeping count a port' references.
+ * @outport:	a connection's output port number.
+ * @chid_name:	remote component's name.
+ * @child_port:	remote component's port number @output is connected to.
+ * @child_dev:	a @coresight_device representation of the component
+		connected to @outport.
+ */
+struct coresight_connection {
+	int outport;
+	const char *child_name;
+	int child_port;
+	struct coresight_device *child_dev;
+};
+
+/**
+ * struct coresight_device - representation of a device as used by the framework
+ * @nr_inport:	number of input port associated to this component.
+ * @nr_outport:	number of output port associated to this component.
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @dev:	The device entity associated to this component.
+ * @refcnt:	keep track of what is in use.
+ * @path_link:	link of current component into the path being enabled.
+ * @orphan:	true if the component has connections that haven't been linked.
+ * @enable:	'true' if component is currently part of an active path.
+ * @activated:	'true' only if a _sink_ has been activated.  A sink can be
+		activated but not yet enabled.  Enabling for a _sink_
+		happens when a source has been selected for that it.
+ */
+struct coresight_device {
+	struct coresight_connection *conns;
+	int nr_inport;
+	int nr_outport;
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct device dev;
+	atomic_t *refcnt;
+	struct list_head path_link;
+	bool orphan;
+	bool enable;	/* true only if configured as part of a path */
+	bool activated;	/* true only if a sink is part of a path */
+};
+
+#define to_coresight_device(d) container_of(d, struct coresight_device, dev)
+
+#define source_ops(csdev)	csdev->ops->source_ops
+#define sink_ops(csdev)		csdev->ops->sink_ops
+#define link_ops(csdev)		csdev->ops->link_ops
+
+#define CORESIGHT_DEBUGFS_ENTRY(__name, __entry_name,			\
+				 __mode, __get, __set, __fmt)		\
+DEFINE_SIMPLE_ATTRIBUTE(__name ## _ops, __get, __set, __fmt);		\
+static const struct coresight_ops_entry __name ## _entry = {		\
+	.name = __entry_name,						\
+	.mode = __mode,							\
+	.ops  = &__name ## _ops						\
+}
+
+/**
+ * struct coresight_ops_sink - basic operations for a sink
+ * Operations available for sinks
+ * @enable:	enables the sink.
+ * @disable:	disables the sink.
+ */
+struct coresight_ops_sink {
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+/**
+ * struct coresight_ops_link - basic operations for a link
+ * Operations available for links.
+ * @enable:	enables flow between iport and oport.
+ * @disable:	disables flow between iport and oport.
+ */
+struct coresight_ops_link {
+	int (*enable)(struct coresight_device *csdev, int iport, int oport);
+	void (*disable)(struct coresight_device *csdev, int iport, int oport);
+};
+
+/**
+ * struct coresight_ops_source - basic operations for a source
+ * Operations available for sources.
+ * @trace_id:	returns the value of the component's trace ID as known
+		to the HW.
+ * @enable:	enables tracing from a source.
+ * @disable:	disables tracing for a source.
+ */
+struct coresight_ops_source {
+	int (*trace_id)(struct coresight_device *csdev);
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+struct coresight_ops {
+	const struct coresight_ops_sink *sink_ops;
+	const struct coresight_ops_link *link_ops;
+	const struct coresight_ops_source *source_ops;
+};
+
+#ifdef CONFIG_CORESIGHT
+extern struct coresight_device *
+coresight_register(struct coresight_desc *desc);
+extern void coresight_unregister(struct coresight_device *csdev);
+extern int coresight_enable(struct coresight_device *csdev);
+extern void coresight_disable(struct coresight_device *csdev);
+extern int coresight_is_bit_set(u32 val, int position, int value);
+extern int coresight_timeout(void __iomem *addr, u32 offset,
+			     int position, int value);
+#ifdef CONFIG_OF
+extern struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node);
+#endif
+#else
+static inline struct coresight_device *
+coresight_register(struct coresight_desc *desc) { return NULL; }
+static inline void coresight_unregister(struct coresight_device *csdev) {}
+static inline int
+coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
+static inline void coresight_disable(struct coresight_device *csdev) {}
+static inline int coresight_is_bit_set(u32 val, int position, int value)
+					 { return 0; }
+static inline int coresight_timeout(void __iomem *addr, u32 offset,
+				     int position, int value) { return 1; }
+#ifdef CONFIG_OF
+static inline struct coresight_platform_data *of_get_coresight_platform_data(
+	struct device *dev, struct device_node *node) { return NULL; }
+#endif
+#endif
+
+#endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 9f3c7e81270a..322e0afc8634 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -29,6 +29,7 @@ struct cpu {
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
 extern bool cpu_is_hotpluggable(unsigned cpu);
+extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id);
 
 extern int cpu_add_dev_attr(struct device_attribute *attr);
 extern void cpu_remove_dev_attr(struct device_attribute *attr);
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index a5d52eea8232..c303d383def1 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -24,6 +24,7 @@
 #ifndef __CPU_COOLING_H__
 #define __CPU_COOLING_H__
 
+#include <linux/of.h>
 #include <linux/thermal.h>
 #include <linux/cpumask.h>
 
@@ -36,6 +37,24 @@ struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus);
 
 /**
+ * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
+ * @np: a valid struct device_node to the cooling device device tree node.
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ */
+#ifdef CONFIG_THERMAL_OF
+struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+			    const struct cpumask *clip_cpus);
+#else
+static inline struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+			    const struct cpumask *clip_cpus)
+{
+	return NULL;
+}
+#endif
+
+/**
  * cpufreq_cooling_unregister - function to remove cpufreq cooling device.
  * @cdev: thermal cooling device pointer.
  */
@@ -48,6 +67,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
 	return NULL;
 }
+static inline struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+			    const struct cpumask *clip_cpus)
+{
+	return NULL;
+}
 static inline
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h
new file mode 100644
index 000000000000..c4d4eb8ac9fe
--- /dev/null
+++ b/include/linux/cpufeature.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CPUFEATURE_H
+#define __LINUX_CPUFEATURE_H
+
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+
+#include <linux/mod_devicetable.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Macros imported from <asm/cpufeature.h>:
+ * - cpu_feature(x)		ordinal value of feature called 'x'
+ * - cpu_have_feature(u32 n)	whether feature #n is available
+ * - MAX_CPU_FEATURES		upper bound for feature ordinal values
+ * Optional:
+ * - CPU_FEATURE_TYPEFMT	format string fragment for printing the cpu type
+ * - CPU_FEATURE_TYPEVAL	set of values matching the format string above
+ */
+
+#ifndef CPU_FEATURE_TYPEFMT
+#define CPU_FEATURE_TYPEFMT	"%s"
+#endif
+
+#ifndef CPU_FEATURE_TYPEVAL
+#define CPU_FEATURE_TYPEVAL	ELF_PLATFORM
+#endif
+
+/*
+ * Use module_cpu_feature_match(feature, module_init_function) to
+ * declare that
+ * a) the module shall be probed upon discovery of CPU feature 'feature'
+ *    (typically at boot time using udev)
+ * b) the module must not be loaded if CPU feature 'feature' is not present
+ *    (not even by manual insmod).
+ *
+ * For a list of legal values for 'feature', please consult the file
+ * 'asm/cpufeature.h' of your favorite architecture.
+ */
+#define module_cpu_feature_match(x, __init)			\
+static struct cpu_feature const cpu_feature_match_ ## x[] =	\
+	{ { .feature = cpu_feature(x) }, { } };			\
+MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x);		\
+								\
+static int cpu_feature_match_ ## x ## _init(void)		\
+{								\
+	if (!cpu_have_feature(cpu_feature(x)))			\
+		return -ENODEV;					\
+	return __init();					\
+}								\
+module_init(cpu_feature_match_ ## x ## _init)
+
+#endif
+#endif
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 037d36ae63e5..69cb5cc81013 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -107,6 +107,7 @@ struct cpufreq_policy {
 	unsigned int		policy; /* see above */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
+	bool			governor_enabled; /* governor start/stop flag */
 
 	struct work_struct	update; /* if update_policy() needs to be
 					 * called, but you're in IRQ context */
@@ -306,6 +307,18 @@ struct freq_attr {
 static struct freq_attr _name =			\
 __ATTR(_name, 0444, show_##_name, NULL)
 
+#ifdef CONFIG_CPU_FREQ
+void cpufreq_suspend(void);
+void cpufreq_resume(void);
+#else
+static inline void cpufreq_suspend(void) {}
+static inline void cpufreq_resume(void) {}
+#endif
+
+/*********************************************************************
+ *                     CPUFREQ NOTIFIER INTERFACE                    *
+ *********************************************************************/
+
 #define cpufreq_freq_attr_ro_perm(_name, _perm)	\
 static struct freq_attr _name =			\
 __ATTR(_name, _perm, show_##_name, NULL)
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 8f0406230a0a..1312cde68504 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -111,6 +111,7 @@ struct cpuidle_driver {
 	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
 	int			state_count;
 	int			safe_state_index;
+	struct cpumask		*cpumask;
 };
 
 #ifdef CONFIG_CPU_IDLE
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 04421e825365..6c58dd7cb9ac 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -68,6 +68,7 @@ extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern int set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
+extern bool may_setgroups(void);
 
 /* access the groups "array" with this macro */
 #define GROUP_AT(gi, i) \
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1a6bb81f0fe5..9be5ac960fd8 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -332,6 +332,7 @@ extern int d_validate(struct dentry *, struct dentry *);
  * helper function for dentry_operations.d_dname() members
  */
 extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
+extern char *simple_dname(struct dentry *, char *, int);
 
 extern char *__d_path(const struct path *, const struct path *, char *, int);
 extern char *d_absolute_path(const struct path *, char *, int);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 3cd32478f2fd..ef5bd3ff7eb4 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -405,13 +405,14 @@ int dm_noflush_suspending(struct dm_target *ti);
 union map_info *dm_get_mapinfo(struct bio *bio);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
+
 /*
  * Geometry functions.
  */
 int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo);
 int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 
-
 /*-----------------------------------------------------------------
  * Functions for manipulating device-mapper tables.
  *---------------------------------------------------------------*/
diff --git a/include/linux/device.h b/include/linux/device.h
index d98ec771de42..3425de2e07e8 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -26,6 +26,7 @@
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
 #include <linux/uidgid.h>
+#include <linux/gfp.h>
 #include <asm/device.h>
 
 struct device;
@@ -47,7 +48,11 @@ struct bus_attribute {
 };
 
 #define BUS_ATTR(_name, _mode, _show, _store)	\
-struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
+	struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define BUS_ATTR_RW(_name) \
+	struct bus_attribute bus_attr_##_name = __ATTR_RW(_name)
+#define BUS_ATTR_RO(_name) \
+	struct bus_attribute bus_attr_##_name = __ATTR_RO(_name)
 
 extern int __must_check bus_create_file(struct bus_type *,
 					struct bus_attribute *);
@@ -253,9 +258,14 @@ struct driver_attribute {
 			 size_t count);
 };
 
-#define DRIVER_ATTR(_name, _mode, _show, _store)	\
-struct driver_attribute driver_attr_##_name =		\
-	__ATTR(_name, _mode, _show, _store)
+#define DRIVER_ATTR(_name, _mode, _show, _store) \
+	struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define DRIVER_ATTR_RW(_name) \
+	struct driver_attribute driver_attr_##_name = __ATTR_RW(_name)
+#define DRIVER_ATTR_RO(_name) \
+	struct driver_attribute driver_attr_##_name = __ATTR_RO(_name)
+#define DRIVER_ATTR_WO(_name) \
+	struct driver_attribute driver_attr_##_name = __ATTR_WO(_name)
 
 extern int __must_check driver_create_file(struct device_driver *driver,
 					const struct driver_attribute *attr);
@@ -406,8 +416,12 @@ struct class_attribute {
 				 const struct class_attribute *attr);
 };
 
-#define CLASS_ATTR(_name, _mode, _show, _store)			\
-struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define CLASS_ATTR(_name, _mode, _show, _store) \
+	struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define CLASS_ATTR_RW(_name) \
+	struct class_attribute class_attr_##_name = __ATTR_RW(_name)
+#define CLASS_ATTR_RO(_name) \
+	struct class_attribute class_attr_##_name = __ATTR_RO(_name)
 
 extern int __must_check class_create_file(struct class *class,
 					  const struct class_attribute *attr);
@@ -415,7 +429,6 @@ extern void class_remove_file(struct class *class,
 			      const struct class_attribute *attr);
 
 /* Simple class attribute that is just a static string */
-
 struct class_attribute_string {
 	struct class_attribute attr;
 	char *str;
@@ -504,6 +517,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
 
 #define DEVICE_ATTR(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define DEVICE_ATTR_RW(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
+#define DEVICE_ATTR_RO(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
+#define DEVICE_ATTR_WO(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
 #define DEVICE_ULONG_ATTR(_name, _mode, _var) \
 	struct dev_ext_attribute dev_attr_##_name = \
 		{ __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) }
@@ -568,8 +587,24 @@ extern void devres_close_group(struct device *dev, void *id);
 extern void devres_remove_group(struct device *dev, void *id);
 extern int devres_release_group(struct device *dev, void *id);
 
-/* managed kzalloc/kfree for device drivers, no kmalloc, always use kzalloc */
-extern void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp);
+/* managed devm_k.alloc/kfree for device drivers */
+extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
+static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+{
+	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+static inline void *devm_kmalloc_array(struct device *dev,
+				       size_t n, size_t size, gfp_t flags)
+{
+	if (size != 0 && n > SIZE_MAX / size)
+		return NULL;
+	return devm_kmalloc(dev, n * size, flags);
+}
+static inline void *devm_kcalloc(struct device *dev,
+				 size_t n, size_t size, gfp_t flags)
+{
+	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
 extern void devm_kfree(struct device *dev, void *p);
 
 void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2bc0ad78d058..ae3426a4879c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -39,6 +39,8 @@
 typedef unsigned long efi_status_t;
 typedef u8 efi_bool_t;
 typedef u16 efi_char16_t;		/* UNICODE character */
+typedef u64 efi_physical_addr_t;
+typedef void *efi_handle_t;
 
 
 typedef struct {
@@ -96,6 +98,7 @@ typedef	struct {
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
 #define EFI_PAGE_SHIFT		12
+#define EFI_PAGE_SIZE		(1UL << EFI_PAGE_SHIFT)
 
 typedef struct {
 	u32 type;
@@ -150,6 +153,102 @@ typedef struct {
 	u8 sets_to_zero;
 } efi_time_cap_t;
 
+typedef struct {
+	efi_table_hdr_t hdr;
+	u32 raise_tpl;
+	u32 restore_tpl;
+	u32 allocate_pages;
+	u32 free_pages;
+	u32 get_memory_map;
+	u32 allocate_pool;
+	u32 free_pool;
+	u32 create_event;
+	u32 set_timer;
+	u32 wait_for_event;
+	u32 signal_event;
+	u32 close_event;
+	u32 check_event;
+	u32 install_protocol_interface;
+	u32 reinstall_protocol_interface;
+	u32 uninstall_protocol_interface;
+	u32 handle_protocol;
+	u32 __reserved;
+	u32 register_protocol_notify;
+	u32 locate_handle;
+	u32 locate_device_path;
+	u32 install_configuration_table;
+	u32 load_image;
+	u32 start_image;
+	u32 exit;
+	u32 unload_image;
+	u32 exit_boot_services;
+	u32 get_next_monotonic_count;
+	u32 stall;
+	u32 set_watchdog_timer;
+	u32 connect_controller;
+	u32 disconnect_controller;
+	u32 open_protocol;
+	u32 close_protocol;
+	u32 open_protocol_information;
+	u32 protocols_per_handle;
+	u32 locate_handle_buffer;
+	u32 locate_protocol;
+	u32 install_multiple_protocol_interfaces;
+	u32 uninstall_multiple_protocol_interfaces;
+	u32 calculate_crc32;
+	u32 copy_mem;
+	u32 set_mem;
+	u32 create_event_ex;
+} __packed efi_boot_services_32_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
+	u64 raise_tpl;
+	u64 restore_tpl;
+	u64 allocate_pages;
+	u64 free_pages;
+	u64 get_memory_map;
+	u64 allocate_pool;
+	u64 free_pool;
+	u64 create_event;
+	u64 set_timer;
+	u64 wait_for_event;
+	u64 signal_event;
+	u64 close_event;
+	u64 check_event;
+	u64 install_protocol_interface;
+	u64 reinstall_protocol_interface;
+	u64 uninstall_protocol_interface;
+	u64 handle_protocol;
+	u64 __reserved;
+	u64 register_protocol_notify;
+	u64 locate_handle;
+	u64 locate_device_path;
+	u64 install_configuration_table;
+	u64 load_image;
+	u64 start_image;
+	u64 exit;
+	u64 unload_image;
+	u64 exit_boot_services;
+	u64 get_next_monotonic_count;
+	u64 stall;
+	u64 set_watchdog_timer;
+	u64 connect_controller;
+	u64 disconnect_controller;
+	u64 open_protocol;
+	u64 close_protocol;
+	u64 open_protocol_information;
+	u64 protocols_per_handle;
+	u64 locate_handle_buffer;
+	u64 locate_protocol;
+	u64 install_multiple_protocol_interfaces;
+	u64 uninstall_multiple_protocol_interfaces;
+	u64 calculate_crc32;
+	u64 copy_mem;
+	u64 set_mem;
+	u64 create_event_ex;
+} __packed efi_boot_services_64_t;
+
 /*
  * EFI Boot Services table
  */
@@ -157,11 +256,13 @@ typedef struct {
 	efi_table_hdr_t hdr;
 	void *raise_tpl;
 	void *restore_tpl;
-	void *allocate_pages;
-	void *free_pages;
-	void *get_memory_map;
-	void *allocate_pool;
-	void *free_pool;
+	efi_status_t (*allocate_pages)(int, int, unsigned long,
+				       efi_physical_addr_t *);
+	efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long);
+	efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *,
+				       unsigned long *, u32 *);
+	efi_status_t (*allocate_pool)(int, unsigned long, void **);
+	efi_status_t (*free_pool)(void *);
 	void *create_event;
 	void *set_timer;
 	void *wait_for_event;
@@ -171,7 +272,7 @@ typedef struct {
 	void *install_protocol_interface;
 	void *reinstall_protocol_interface;
 	void *uninstall_protocol_interface;
-	void *handle_protocol;
+	efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **);
 	void *__reserved;
 	void *register_protocol_notify;
 	void *locate_handle;
@@ -181,7 +282,7 @@ typedef struct {
 	void *start_image;
 	void *exit;
 	void *unload_image;
-	void *exit_boot_services;
+	efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long);
 	void *get_next_monotonic_count;
 	void *stall;
 	void *set_watchdog_timer;
@@ -226,6 +327,15 @@ typedef enum {
     EfiPciIoAttributeOperationMaximum
 } EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION;
 
+typedef struct {
+	u32 read;
+	u32 write;
+} efi_pci_io_protocol_access_32_t;
+
+typedef struct {
+	u64 read;
+	u64 write;
+} efi_pci_io_protocol_access_64_t;
 
 typedef struct {
 	void *read;
@@ -233,6 +343,46 @@ typedef struct {
 } efi_pci_io_protocol_access_t;
 
 typedef struct {
+	u32 poll_mem;
+	u32 poll_io;
+	efi_pci_io_protocol_access_32_t mem;
+	efi_pci_io_protocol_access_32_t io;
+	efi_pci_io_protocol_access_32_t pci;
+	u32 copy_mem;
+	u32 map;
+	u32 unmap;
+	u32 allocate_buffer;
+	u32 free_buffer;
+	u32 flush;
+	u32 get_location;
+	u32 attributes;
+	u32 get_bar_attributes;
+	u32 set_bar_attributes;
+	uint64_t romsize;
+	void *romimage;
+} efi_pci_io_protocol_32;
+
+typedef struct {
+	u64 poll_mem;
+	u64 poll_io;
+	efi_pci_io_protocol_access_64_t mem;
+	efi_pci_io_protocol_access_64_t io;
+	efi_pci_io_protocol_access_64_t pci;
+	u64 copy_mem;
+	u64 map;
+	u64 unmap;
+	u64 allocate_buffer;
+	u64 free_buffer;
+	u64 flush;
+	u64 get_location;
+	u64 attributes;
+	u64 get_bar_attributes;
+	u64 set_bar_attributes;
+	uint64_t romsize;
+	void *romimage;
+} efi_pci_io_protocol_64;
+
+typedef struct {
 	void *poll_mem;
 	void *poll_io;
 	efi_pci_io_protocol_access_t mem;
@@ -287,20 +437,56 @@ typedef struct {
 
 typedef struct {
 	efi_table_hdr_t hdr;
-	unsigned long get_time;
-	unsigned long set_time;
-	unsigned long get_wakeup_time;
-	unsigned long set_wakeup_time;
-	unsigned long set_virtual_address_map;
-	unsigned long convert_pointer;
-	unsigned long get_variable;
-	unsigned long get_next_variable;
-	unsigned long set_variable;
-	unsigned long get_next_high_mono_count;
-	unsigned long reset_system;
-	unsigned long update_capsule;
-	unsigned long query_capsule_caps;
-	unsigned long query_variable_info;
+	u32 get_time;
+	u32 set_time;
+	u32 get_wakeup_time;
+	u32 set_wakeup_time;
+	u32 set_virtual_address_map;
+	u32 convert_pointer;
+	u32 get_variable;
+	u32 get_next_variable;
+	u32 set_variable;
+	u32 get_next_high_mono_count;
+	u32 reset_system;
+	u32 update_capsule;
+	u32 query_capsule_caps;
+	u32 query_variable_info;
+} efi_runtime_services_32_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
+	u64 get_time;
+	u64 set_time;
+	u64 get_wakeup_time;
+	u64 set_wakeup_time;
+	u64 set_virtual_address_map;
+	u64 convert_pointer;
+	u64 get_variable;
+	u64 get_next_variable;
+	u64 set_variable;
+	u64 get_next_high_mono_count;
+	u64 reset_system;
+	u64 update_capsule;
+	u64 query_capsule_caps;
+	u64 query_variable_info;
+} efi_runtime_services_64_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
+	void *get_time;
+	void *set_time;
+	void *get_wakeup_time;
+	void *set_wakeup_time;
+	void *set_virtual_address_map;
+	void *convert_pointer;
+	void *get_variable;
+	void *get_next_variable;
+	void *set_variable;
+	void *get_next_high_mono_count;
+	void *reset_system;
+	void *update_capsule;
+	void *query_capsule_caps;
+	void *query_variable_info;
 } efi_runtime_services_t;
 
 typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc);
@@ -389,6 +575,9 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long si
 #define EFI_FILE_SYSTEM_GUID \
     EFI_GUID(  0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
 
+#define DEVICE_TREE_GUID \
+    EFI_GUID(  0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 )
+
 typedef struct {
 	efi_guid_t guid;
 	u64 table;
@@ -404,6 +593,12 @@ typedef struct {
 	unsigned long table;
 } efi_config_table_t;
 
+typedef struct {
+	efi_guid_t guid;
+	const char *name;
+	unsigned long *ptr;
+} efi_config_table_type_t;
+
 #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL)
 
 #define EFI_2_30_SYSTEM_TABLE_REVISION  ((2 << 16) | (30))
@@ -472,6 +667,46 @@ struct efi_memory_map {
 	unsigned long desc_size;
 };
 
+struct efi_fdt_params {
+	u64 system_table;
+	u64 mmap;
+	u32 mmap_size;
+	u32 desc_size;
+	u32 desc_ver;
+};
+
+typedef struct {
+	u32 revision;
+	u32 parent_handle;
+	u32 system_table;
+	u32 device_handle;
+	u32 file_path;
+	u32 reserved;
+	u32 load_options_size;
+	u32 load_options;
+	u32 image_base;
+	__aligned_u64 image_size;
+	unsigned int image_code_type;
+	unsigned int image_data_type;
+	unsigned long unload;
+} efi_loaded_image_32_t;
+
+typedef struct {
+	u32 revision;
+	u64 parent_handle;
+	u64 system_table;
+	u64 device_handle;
+	u64 file_path;
+	u64 reserved;
+	u32 load_options_size;
+	u64 load_options;
+	u64 image_base;
+	__aligned_u64 image_size;
+	unsigned int image_code_type;
+	unsigned int image_data_type;
+	unsigned long unload;
+} efi_loaded_image_64_t;
+
 typedef struct {
 	u32 revision;
 	void *parent_handle;
@@ -488,10 +723,6 @@ typedef struct {
 	unsigned long unload;
 } efi_loaded_image_t;
 
-typedef struct {
-	u64 revision;
-	void *open_volume;
-} efi_file_io_interface_t;
 
 typedef struct {
 	u64 size;
@@ -506,18 +737,56 @@ typedef struct {
 
 typedef struct {
 	u64 revision;
-	void *open;
-	void *close;
+	u32 open;
+	u32 close;
+	u32 delete;
+	u32 read;
+	u32 write;
+	u32 get_position;
+	u32 set_position;
+	u32 get_info;
+	u32 set_info;
+	u32 flush;
+} efi_file_handle_32_t;
+
+typedef struct {
+	u64 revision;
+	u64 open;
+	u64 close;
+	u64 delete;
+	u64 read;
+	u64 write;
+	u64 get_position;
+	u64 set_position;
+	u64 get_info;
+	u64 set_info;
+	u64 flush;
+} efi_file_handle_64_t;
+
+typedef struct _efi_file_handle {
+	u64 revision;
+	efi_status_t (*open)(struct _efi_file_handle *,
+			     struct _efi_file_handle **,
+			     efi_char16_t *, u64, u64);
+	efi_status_t (*close)(struct _efi_file_handle *);
 	void *delete;
-	void *read;
+	efi_status_t (*read)(struct _efi_file_handle *, unsigned long *,
+			     void *);
 	void *write;
 	void *get_position;
 	void *set_position;
-	void *get_info;
+	efi_status_t (*get_info)(struct _efi_file_handle *, efi_guid_t *,
+			unsigned long *, void *);
 	void *set_info;
 	void *flush;
 } efi_file_handle_t;
 
+typedef struct _efi_file_io_interface {
+	u64 revision;
+	int (*open_volume)(struct _efi_file_io_interface *,
+			   efi_file_handle_t **);
+} efi_file_io_interface_t;
+
 #define EFI_FILE_MODE_READ	0x0000000000000001
 #define EFI_FILE_MODE_WRITE	0x0000000000000002
 #define EFI_FILE_MODE_CREATE	0x8000000000000000
@@ -552,6 +821,8 @@ extern struct efi {
 	efi_get_next_high_mono_count_t *get_next_high_mono_count;
 	efi_reset_system_t *reset_system;
 	efi_set_virtual_address_map_t *set_virtual_address_map;
+	struct efi_memory_map *memmap;
+	unsigned long flags;
 } efi;
 
 static inline int
@@ -587,6 +858,7 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon
 }
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
+extern int efi_config_init(efi_config_table_type_t *arch_tables);
 extern u64 efi_get_iobase (void);
 extern u32 efi_mem_type (unsigned long phys_addr);
 extern u64 efi_mem_attributes (unsigned long phys_addr);
@@ -597,8 +869,15 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource,
 extern unsigned long efi_get_time(void);
 extern int efi_set_rtc_mmss(unsigned long nowtime);
 extern void efi_reserve_boot_services(void);
+extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose);
 extern struct efi_memory_map memmap;
 
+/* Iterate through an efi_memory_map */
+#define for_each_efi_memory_desc(m, md)					   \
+	for ((md) = (m)->map;						   \
+	     (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \
+	     (md) = (void *)(md) + (m)->desc_size)
+
 /**
  * efi_range_is_wc - check the WC bit on an address range
  * @start: starting kvirt address
@@ -636,18 +915,17 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_64BIT		5	/* Is the firmware 64-bit? */
 
 #ifdef CONFIG_EFI
-# ifdef CONFIG_X86
-extern int efi_enabled(int facility);
-# else
-static inline int efi_enabled(int facility)
+/*
+ * Test whether the above EFI_* bits are enabled.
+ */
+static inline bool efi_enabled(int feature)
 {
-	return 1;
+	return test_bit(feature, &efi.flags) != 0;
 }
-# endif
 #else
-static inline int efi_enabled(int facility)
+static inline bool efi_enabled(int feature)
 {
-	return 0;
+	return false;
 }
 #endif
 
@@ -769,8 +1047,10 @@ struct efivars {
  * and we use a page for reading/writing.
  */
 
+#define EFI_VAR_NAME_LEN	1024
+
 struct efi_variable {
-	efi_char16_t  VariableName[1024/sizeof(efi_char16_t)];
+	efi_char16_t  VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)];
 	efi_guid_t    VendorGuid;
 	unsigned long DataSize;
 	__u8          Data[1024];
@@ -782,6 +1062,26 @@ struct efivar_entry {
 	struct efi_variable var;
 	struct list_head list;
 	struct kobject kobj;
+	bool scanning;
+	bool deleting;
+};
+
+struct efi_simple_text_output_protocol_32 {
+	u32 reset;
+	u32 output_string;
+	u32 test_string;
+};
+
+struct efi_simple_text_output_protocol_64 {
+	u64 reset;
+	u64 output_string;
+	u64 test_string;
+};
+
+struct efi_simple_text_output_protocol {
+	void *reset;
+	efi_status_t (*output_string)(void *, void *);
+	void *test_string;
 };
 
 extern struct list_head efivar_sysfs_list;
@@ -832,7 +1132,7 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 				       struct list_head *head, bool remove);
 
-bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len);
+bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
@@ -840,6 +1140,8 @@ void efivar_run_worker(void);
 #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
 int efivars_sysfs_init(void);
 
+#define EFIVARS_DATA_SIZE_MAX 1024
+
 #endif /* CONFIG_EFI_VARS */
 
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 217e4b42b7c8..5d838bf10cbd 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@ struct fw_device {
 	unsigned irmc:1;
 	unsigned bc_implemented:2;
 
+	work_func_t workfn;
 	struct delayed_work work;
 	struct fw_attribute_group attribute_group;
 };
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 99d0fbcbaf79..38eb5dbbf1cb 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -524,6 +524,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
+extern void ftrace_module_init(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
@@ -533,6 +534,7 @@ static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) {}
 static inline int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
@@ -609,25 +611,27 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifndef HAVE_ARCH_CALLER_ADDR
+/* All archs should have this, but we define it for consistency */
+#ifndef ftrace_return_address0
+# define ftrace_return_address0 __builtin_return_address(0)
+#endif
+
+/* Archs may use other ways for ADDR1 and beyond */
+#ifndef ftrace_return_address
 # ifdef CONFIG_FRAME_POINTER
-#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#  define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-#  define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-#  define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-#  define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-#  define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-#  define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+#  define ftrace_return_address(n) __builtin_return_address(n)
 # else
-#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#  define CALLER_ADDR1 0UL
-#  define CALLER_ADDR2 0UL
-#  define CALLER_ADDR3 0UL
-#  define CALLER_ADDR4 0UL
-#  define CALLER_ADDR5 0UL
-#  define CALLER_ADDR6 0UL
+#  define ftrace_return_address(n) 0UL
 # endif
-#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
+#endif
+
+#define CALLER_ADDR0 ((unsigned long)ftrace_return_address0)
+#define CALLER_ADDR1 ((unsigned long)ftrace_return_address(1))
+#define CALLER_ADDR2 ((unsigned long)ftrace_return_address(2))
+#define CALLER_ADDR3 ((unsigned long)ftrace_return_address(3))
+#define CALLER_ADDR4 ((unsigned long)ftrace_return_address(4))
+#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
+#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
 
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 120d57a1c3a5..b5e36017acd7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -325,10 +325,6 @@ enum {
 	FILTER_TRACE_FN,
 };
 
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b0d95cac826e..6435f46d6e13 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,7 +55,11 @@ union futex_key {
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
 extern int futex_cmpxchg_enabled;
+#endif
 #else
 static inline void exit_robust_list(struct task_struct *curr)
 {
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index bc24f34c6ecb..9e8986ae700c 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -66,8 +66,8 @@ struct gen_pool_chunk {
 	struct list_head next_chunk;	/* next chunk in pool */
 	atomic_t avail;
 	phys_addr_t phys_addr;		/* physical starting address of memory chunk */
-	unsigned long start_addr;	/* starting address of memory chunk */
-	unsigned long end_addr;		/* ending address of memory chunk */
+	unsigned long start_addr;	/* start address of memory chunk */
+	unsigned long end_addr;		/* end address of memory chunk (inclusive) */
 	unsigned long bits[0];		/* bitmap for allocating memory chunk */
 };
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index ff545cc33c3a..4f8aa4733fb6 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -746,9 +746,14 @@ struct hid_field *hidinput_get_led_field(struct hid_device *hid);
 unsigned int hidinput_count_leds(struct hid_device *hid);
 __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code);
 void hid_output_report(struct hid_report *report, __u8 *data);
+u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags);
 struct hid_device *hid_allocate_device(void);
 struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id);
 int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size);
+struct hid_report *hid_validate_values(struct hid_device *hid,
+				       unsigned int type, unsigned int id,
+				       unsigned int field_index,
+				       unsigned int report_counts);
 int hid_open_report(struct hid_device *device);
 int hid_check_keys_pressed(struct hid_device *hid);
 int hid_connect(struct hid_device *hid, unsigned int connect_mask);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 26ee56c80dc7..3d36eb0ff0d8 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -159,23 +159,6 @@ static inline int hpage_nr_pages(struct page *page)
 		return HPAGE_PMD_NR;
 	return 1;
 }
-static inline struct page *compound_trans_head(struct page *page)
-{
-	if (PageTail(page)) {
-		struct page *head;
-		head = page->first_page;
-		smp_rmb();
-		/*
-		 * head may be a dangling pointer.
-		 * __split_huge_page_refcount clears PageTail before
-		 * overwriting first_page, so if PageTail is still
-		 * there it means the head pointer isn't dangling.
-		 */
-		if (PageTail(page))
-			return head;
-	}
-	return page;
-}
 
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -205,7 +188,6 @@ static inline int split_huge_page(struct page *page)
 	do { } while (0)
 #define split_huge_page_pmd_mm(__mm, __address, __pmd)	\
 	do { } while (0)
-#define compound_trans_head(page) compound_head(page)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
 {
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 89d4fbf681e7..dca09c0cd3cc 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -31,6 +31,7 @@ struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
 int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page_head);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -102,6 +103,11 @@ static inline int PageHuge(struct page *page)
 	return 0;
 }
 
+static inline int PageHeadHuge(struct page *page_head)
+{
+	return 0;
+}
+
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c2559847d7ee..422eac8538fd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -483,15 +483,18 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi,
  * 0 . 13 (Windows Server 2008)
  * 1 . 1  (Windows 7)
  * 2 . 4  (Windows 8)
+ * 3 . 0  (Windows 8 R2)
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
 #define VERSION_WIN7    ((1 << 16) | (1))
 #define VERSION_WIN8    ((2 << 16) | (4))
+#define VERSION_WIN8_1    ((3 << 16) | (0))
+
 
 #define VERSION_INVAL -1
 
-#define VERSION_CURRENT VERSION_WIN8
+#define VERSION_CURRENT VERSION_WIN8_1
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
@@ -894,7 +897,7 @@ struct vmbus_channel_relid_released {
 struct vmbus_channel_initiate_contact {
 	struct vmbus_channel_message_header header;
 	u32 vmbus_version_requested;
-	u32 padding2;
+	u32 target_vcpu; /* The VCPU the host should respond to */
 	u64 interrupt_page;
 	u64 monitor_page1;
 	u64 monitor_page2;
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 16fae6436d0e..25b8b15197b0 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -193,6 +193,7 @@ struct team {
 	bool user_carrier_enabled;
 	bool queue_override_enabled;
 	struct list_head *qom_lists; /* array of queue override mapping lists */
+	bool port_mtu_change_allowed;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h
index 13ce220c7003..593ae7ce07c7 100644
--- a/include/linux/iio/events.h
+++ b/include/linux/iio/events.h
@@ -90,7 +90,7 @@ enum iio_event_direction {
 
 #define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF)
 
-#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF)
+#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F)
 
 #define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF)
 
diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index 3869c525b052..545deb149655 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -83,10 +83,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig)
 	put_device(&trig->dev);
 }
 
-static inline void iio_trigger_get(struct iio_trigger *trig)
+static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig)
 {
 	get_device(&trig->dev);
 	__module_get(trig->ops->owner);
+
+	return trig;
 }
 
 /**
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ea1e3b863890..770ecc90993b 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -261,7 +261,7 @@ static inline void in_dev_put(struct in_device *idev)
 static __inline__ __be32 inet_make_mask(int logmask)
 {
 	if (logmask)
-		return htonl(~((1<<(32-logmask))-1));
+		return htonl(~((1U<<(32-logmask))-1));
 	return 0;
 }
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5cd0f0949927..998f4dfedecf 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,6 +40,7 @@ extern struct fs_struct init_fs;
 
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\
@@ -213,6 +214,7 @@ extern struct task_group root_task_group;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),	\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5fa5afeeb759..6de0f2c14ec0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -239,7 +239,40 @@ static inline int check_wakeup_irqs(void) { return 0; }
 
 extern cpumask_var_t irq_default_affinity;
 
-extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+/* Internal implementation. Use the helpers below */
+extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
+			      bool force);
+
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+static inline int
+irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, false);
+}
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+static inline int
+irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, true);
+}
+
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
@@ -275,6 +308,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
 	return -EINVAL;
 }
 
+static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return 0;
+}
+
 static inline int irq_can_set_affinity(unsigned int irq)
 {
 	return 0;
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index c4d870b0d5e6..d6ad91f26038 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -22,7 +22,7 @@ struct ipc_ids {
 	int in_use;
 	unsigned short seq;
 	unsigned short seq_max;
-	struct rw_semaphore rw_mutex;
+	struct rw_semaphore rwsem;
 	struct idr ipcs_idr;
 	int next_id;
 };
@@ -34,9 +34,9 @@ struct ipc_namespace {
 	int		sem_ctls[4];
 	int		used_sems;
 
-	int		msg_ctlmax;
-	int		msg_ctlmnb;
-	int		msg_ctlmni;
+	unsigned int	msg_ctlmax;
+	unsigned int	msg_ctlmnb;
+	unsigned int	msg_ctlmni;
 	atomic_t	msg_bytes;
 	atomic_t	msg_hdrs;
 	int		auto_msgmni;
@@ -119,9 +119,7 @@ extern int mq_init_ns(struct ipc_namespace *ns);
  *     the new maximum will handle anyone else.  I may have to revisit this
  *     in the future.
  */
-#define MIN_QUEUESMAX			1
 #define DFLT_QUEUESMAX		      256
-#define HARD_QUEUESMAX		     1024
 #define MIN_MSGMAX			1
 #define DFLT_MSG		       10U
 #define DFLT_MSGMAX		       10
diff --git a/include/linux/irq.h b/include/linux/irq.h
index bc4e06611958..d591bfe1475b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -375,7 +375,8 @@ extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
 extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
-extern int __irq_set_affinity_locked(struct irq_data *data,  const struct cpumask *cpumask);
+extern int irq_set_affinity_locked(struct irq_data *data,
+				   const struct cpumask *cpumask, bool force);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
new file mode 100644
index 000000000000..03a4ea37ba86
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
+ */
+#define GICD_CTLR			0x0000
+#define GICD_TYPER			0x0004
+#define GICD_IIDR			0x0008
+#define GICD_STATUSR			0x0010
+#define GICD_SETSPI_NSR			0x0040
+#define GICD_CLRSPI_NSR			0x0048
+#define GICD_SETSPI_SR			0x0050
+#define GICD_CLRSPI_SR			0x0058
+#define GICD_SEIR			0x0068
+#define GICD_ISENABLER			0x0100
+#define GICD_ICENABLER			0x0180
+#define GICD_ISPENDR			0x0200
+#define GICD_ICPENDR			0x0280
+#define GICD_ISACTIVER			0x0300
+#define GICD_ICACTIVER			0x0380
+#define GICD_IPRIORITYR			0x0400
+#define GICD_ICFGR			0x0C00
+#define GICD_IROUTER			0x6000
+#define GICD_PIDR2			0xFFE8
+
+#define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_ARE_NS		(1U << 4)
+#define GICD_CTLR_ENABLE_G1A		(1U << 1)
+#define GICD_CTLR_ENABLE_G1		(1U << 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK		0xf0
+#define GIC_PIDR2_ARCH_GICv3		0x30
+#define GIC_PIDR2_ARCH_GICv4		0x40
+
+/*
+ * Re-Distributor registers, offsets from RD_base
+ */
+#define GICR_CTLR			GICD_CTLR
+#define GICR_IIDR			0x0004
+#define GICR_TYPER			0x0008
+#define GICR_STATUSR			GICD_STATUSR
+#define GICR_WAKER			0x0014
+#define GICR_SETLPIR			0x0040
+#define GICR_CLRLPIR			0x0048
+#define GICR_SEIR			GICD_SEIR
+#define GICR_PROPBASER			0x0070
+#define GICR_PENDBASER			0x0078
+#define GICR_INVLPIR			0x00A0
+#define GICR_INVALLR			0x00B0
+#define GICR_SYNCR			0x00C0
+#define GICR_MOVLPIR			0x0100
+#define GICR_MOVALLR			0x0110
+#define GICR_PIDR2			GICD_PIDR2
+
+#define GICR_WAKER_ProcessorSleep	(1U << 1)
+#define GICR_WAKER_ChildrenAsleep	(1U << 2)
+
+/*
+ * Re-Distributor registers, offsets from SGI_base
+ */
+#define GICR_ISENABLER0			GICD_ISENABLER
+#define GICR_ICENABLER0			GICD_ICENABLER
+#define GICR_ISPENDR0			GICD_ISPENDR
+#define GICR_ICPENDR0			GICD_ICPENDR
+#define GICR_ISACTIVER0			GICD_ISACTIVER
+#define GICR_ICACTIVER0			GICD_ICACTIVER
+#define GICR_IPRIORITYR0		GICD_IPRIORITYR
+#define GICR_ICFGR0			GICD_ICFGR
+
+#define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_LAST			(1U << 4)
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
+#define ICC_CTLR_EL1_EOImode_drop	(1U << 1)
+#define ICC_SRE_EL1_SRE			(1U << 0)
+
+/*
+ * Hypervisor interface registers (SRE only)
+ */
+#define ICH_LR_VIRTUAL_ID_MASK		((1UL << 32) - 1)
+
+#define ICH_LR_EOI			(1UL << 41)
+#define ICH_LR_GROUP			(1UL << 60)
+#define ICH_LR_STATE			(3UL << 62)
+#define ICH_LR_PENDING_BIT		(1UL << 62)
+#define ICH_LR_ACTIVE_BIT		(1UL << 63)
+
+#define ICH_MISR_EOI			(1 << 0)
+#define ICH_MISR_U			(1 << 1)
+
+#define ICH_HCR_EN			(1 << 0)
+#define ICH_HCR_UIE			(1 << 1)
+
+#define ICH_VMCR_CTLR_SHIFT		0
+#define ICH_VMCR_CTLR_MASK		(0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT		18
+#define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT		21
+#define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT		24
+#define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
+
+#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
+#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_IAR1_EL1_SPURIOUS		0x3ff
+
+#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+
+#define ICC_SRE_EL2_SRE			(1 << 0)
+#define ICC_SRE_EL2_ENABLE		(1 << 3)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2			__LR0_EL2(0)
+#define ICH_LR1_EL2			__LR0_EL2(1)
+#define ICH_LR2_EL2			__LR0_EL2(2)
+#define ICH_LR3_EL2			__LR0_EL2(3)
+#define ICH_LR4_EL2			__LR0_EL2(4)
+#define ICH_LR5_EL2			__LR0_EL2(5)
+#define ICH_LR6_EL2			__LR0_EL2(6)
+#define ICH_LR7_EL2			__LR0_EL2(7)
+#define ICH_LR8_EL2			__LR8_EL2(0)
+#define ICH_LR9_EL2			__LR8_EL2(1)
+#define ICH_LR10_EL2			__LR8_EL2(2)
+#define ICH_LR11_EL2			__LR8_EL2(3)
+#define ICH_LR12_EL2			__LR8_EL2(4)
+#define ICH_LR13_EL2			__LR8_EL2(5)
+#define ICH_LR14_EL2			__LR8_EL2(6)
+#define ICH_LR15_EL2			__LR8_EL2(7)
+
+#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+static inline void gic_write_eoir(u64 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
+	isb();
+}
+
+#endif
+
+#endif
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 4483adb61c88..1f004b16641e 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -21,6 +21,8 @@
 #define GIC_CPU_ACTIVEPRIO		0xd0
 #define GIC_CPU_IDENT			0xfc
 
+#define GICC_IAR_INT_ID_MASK		0x3ff
+
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
 #define GIC_DIST_IGROUP			0x080
@@ -34,6 +36,8 @@
 #define GIC_DIST_TARGET			0x800
 #define GIC_DIST_CONFIG			0xc00
 #define GIC_DIST_SOFTINT		0xf00
+#define GIC_DIST_SGI_PENDING_CLEAR	0xf10
+#define GIC_DIST_SGI_PENDING_SET	0xf20
 
 #define GICH_HCR			0x0
 #define GICH_VTR			0x4
@@ -78,6 +82,9 @@ extern struct irq_chip gic_arch_extn;
 void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
 		    u32 offset, struct device_node *);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
+void gic_cpu_if_down(void);
+
+void gic_cpu_if_down(void);
 
 static inline void gic_init(unsigned int nr, int start,
 			    void __iomem *dist , void __iomem *cpu)
@@ -85,6 +92,16 @@ static inline void gic_init(unsigned int nr, int start,
 	gic_init_bases(nr, start, dist, cpu, 0, NULL);
 }
 
-#endif /* __ASSEMBLY */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
+int gic_get_cpu_id(unsigned int cpu);
+void gic_migrate_target(unsigned int new_cpu_id);
+unsigned long gic_get_sgir_physaddr(void);
 
+extern const struct irq_domain_ops *gic_routable_irq_domain_ops;
+static inline void __init register_routable_domain_ops
+					(const struct irq_domain_ops *ops)
+{
+	gic_routable_irq_domain_ops = ops;
+}
+#endif /* __ASSEMBLY */
 #endif
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 623325e2ff97..a8cc2fcffcaf 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -27,6 +27,8 @@ struct irq_desc;
  * @irq_count:		stats field to detect stalled irqs
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
+ * @threads_handled:	stats field for deferred spurious detection of threaded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
  * @lock:		locking for SMP
  * @affinity_hint:	hint to user space for preferred irq affinity
  * @affinity_notify:	context for notification of affinity changes
@@ -52,6 +54,8 @@ struct irq_desc {
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
+	atomic_t		threads_handled;
+	int			threads_handled_last;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 #ifdef CONFIG_SMP
@@ -154,6 +158,14 @@ static inline int irq_balancing_disabled(unsigned int irq)
 	return desc->status_use_accessors & IRQ_NO_BALANCING_MASK;
 }
 
+static inline int irq_is_percpu(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status_use_accessors & IRQ_PER_CPU;
+}
+
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class)
 {
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 8fb8edf12417..c039fe1315eb 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after(a,b)		\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(b) - (long)(a) < 0))
+	 ((long)((b) - (a)) < 0))
 #define time_before(a,b)	time_after(b,a)
 
 #define time_after_eq(a,b)	\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(a) - (long)(b) >= 0))
+	 ((long)((a) - (b)) >= 0))
 #define time_before_eq(a,b)	time_after_eq(b,a)
 
 /*
@@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after64(a,b)	\
 	(typecheck(__u64, a) &&	\
 	 typecheck(__u64, b) && \
-	 ((__s64)(b) - (__s64)(a) < 0))
+	 ((__s64)((b) - (a)) < 0))
 #define time_before64(a,b)	time_after64(b,a)
 
 #define time_after_eq64(a,b)	\
 	(typecheck(__u64, a) && \
 	 typecheck(__u64, b) && \
-	 ((__s64)(a) - (__s64)(b) >= 0))
+	 ((__s64)((a) - (b)) >= 0))
 #define time_before_eq64(a,b)	time_after_eq64(b,a)
 
 /*
@@ -254,23 +254,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d78d28a733b1..5fd33dc1fe3a 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -198,6 +198,9 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
+/* flag to track if kexec reboot is in progress */
+extern bool kexec_in_progress;
+
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
 int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index c6e091bf39a5..bdfc95bddde9 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -283,7 +283,7 @@ struct kgdb_io {
 
 extern struct kgdb_arch		arch_kgdb_ops;
 
-extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs);
+extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
 
 #ifdef CONFIG_SERIAL_KGDB_NMI
 extern int kgdb_register_nmi_console(void);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index eae7a053dc51..cc82cfb66259 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -399,6 +399,9 @@ enum {
 	ATA_HORKAGE_BROKEN_FPDMA_AA	= (1 << 15),	/* skip AA */
 	ATA_HORKAGE_DUMP_ID	= (1 << 16),	/* dump IDENTIFY data */
 	ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17),	/* Set max sects to 65535 */
+	ATA_HORKAGE_ATAPI_DMADIR = (1 << 18),	/* device requires dmadir */
+	ATA_HORKAGE_NOLPM	= (1 << 20),	/* don't use LPM */
+	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
@@ -544,6 +547,7 @@ struct ata_host {
 	struct device 		*dev;
 	void __iomem * const	*iomap;
 	unsigned int		n_ports;
+	unsigned int		n_tags;			/* nr of NCQ tags */
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
@@ -769,6 +773,7 @@ struct ata_port {
 	unsigned long		qc_allocated;
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
+	unsigned int		last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
diff --git a/include/linux/list.h b/include/linux/list.h
index b83e5657365a..83a9576f479f 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -373,6 +373,22 @@ static inline void list_splice_tail_init(struct list_head *list,
 	(!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
 
 /**
+ * list_next_entry - get the next element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_next_entry(pos, member) \
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_prev_entry(pos, member) \
+	list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+/**
  * list_for_each	-	iterate over a list
  * @pos:	the &struct list_head to use as a loop cursor.
  * @head:	the head for your list.
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
new file mode 100644
index 000000000000..307d9cab2026
--- /dev/null
+++ b/include/linux/mailbox_client.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CLIENT_H
+#define __MAILBOX_CLIENT_H
+
+#include <linux/of.h>
+#include <linux/device.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_client - User of a mailbox
+ * @dev:		The client device
+ * @tx_block:		If the mbox_send_message should block until data is
+ *			transmitted.
+ * @tx_tout:		Max block period in ms before TX is assumed failure
+ * @knows_txdone:	If the client could run the TX state machine. Usually
+ *			if the client receives some ACK packet for transmission.
+ *			Unused if the controller already has TX_Done/RTR IRQ.
+ * @rx_callback:	Atomic callback to provide client the data received
+ * @tx_done:		Atomic callback to tell client of data transmission
+ */
+struct mbox_client {
+	struct device *dev;
+	bool tx_block;
+	unsigned long tx_tout;
+	bool knows_txdone;
+
+	void (*rx_callback)(struct mbox_client *cl, void *mssg);
+	void (*tx_done)(struct mbox_client *cl, void *mssg, int r);
+};
+
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index);
+int mbox_send_message(struct mbox_chan *chan, void *mssg);
+void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */
+bool mbox_client_peek_data(struct mbox_chan *chan); /* atomic */
+void mbox_free_channel(struct mbox_chan *chan); /* may sleep */
+
+#endif /* __MAILBOX_CLIENT_H */
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
new file mode 100644
index 000000000000..d4cf96f07cfc
--- /dev/null
+++ b/include/linux/mailbox_controller.h
@@ -0,0 +1,133 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CONTROLLER_H
+#define __MAILBOX_CONTROLLER_H
+
+#include <linux/of.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/device.h>
+#include <linux/completion.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_chan_ops - methods to control mailbox channels
+ * @send_data:	The API asks the MBOX controller driver, in atomic
+ *		context try to transmit a message on the bus. Returns 0 if
+ *		data is accepted for transmission, -EBUSY while rejecting
+ *		if the remote hasn't yet read the last data sent. Actual
+ *		transmission of data is reported by the controller via
+ *		mbox_chan_txdone (if it has some TX ACK irq). It must not
+ *		sleep.
+ * @startup:	Called when a client requests the chan. The controller
+ *		could ask clients for additional parameters of communication
+ *		to be provided via client's chan_data. This call may
+ *		block. After this call the Controller must forward any
+ *		data received on the chan by calling mbox_chan_received_data.
+ *		The controller may do stuff that need to sleep.
+ * @shutdown:	Called when a client relinquishes control of a chan.
+ *		This call may block too. The controller must not forward
+ *		any received data anymore.
+ *		The controller may do stuff that need to sleep.
+ * @last_tx_done: If the controller sets 'txdone_poll', the API calls
+ *		  this to poll status of last TX. The controller must
+ *		  give priority to IRQ method over polling and never
+ *		  set both txdone_poll and txdone_irq. Only in polling
+ *		  mode 'send_data' is expected to return -EBUSY.
+ *		  The controller may do stuff that need to sleep/block.
+ *		  Used only if txdone_poll:=true && txdone_irq:=false
+ * @peek_data: Atomic check for any received data. Return true if controller
+ *		  has some data to push to the client. False otherwise.
+ */
+struct mbox_chan_ops {
+	int (*send_data)(struct mbox_chan *chan, void *data);
+	int (*startup)(struct mbox_chan *chan);
+	void (*shutdown)(struct mbox_chan *chan);
+	bool (*last_tx_done)(struct mbox_chan *chan);
+	bool (*peek_data)(struct mbox_chan *chan);
+};
+
+/**
+ * struct mbox_controller - Controller of a class of communication channels
+ * @dev:		Device backing this controller
+ * @ops:		Operators that work on each communication chan
+ * @chans:		Array of channels
+ * @num_chans:		Number of channels in the 'chans' array.
+ * @txdone_irq:		Indicates if the controller can report to API when
+ *			the last transmitted data was read by the remote.
+ *			Eg, if it has some TX ACK irq.
+ * @txdone_poll:	If the controller can read but not report the TX
+ *			done. Ex, some register shows the TX status but
+ *			no interrupt rises. Ignored if 'txdone_irq' is set.
+ * @txpoll_period:	If 'txdone_poll' is in effect, the API polls for
+ *			last TX's status after these many millisecs
+ * @of_xlate:		Controller driver specific mapping of channel via DT
+ * @poll:		API private. Used to poll for TXDONE on all channels.
+ * @node:		API private. To hook into list of controllers.
+ */
+struct mbox_controller {
+	struct device *dev;
+	struct mbox_chan_ops *ops;
+	struct mbox_chan *chans;
+	int num_chans;
+	bool txdone_irq;
+	bool txdone_poll;
+	unsigned txpoll_period;
+	struct mbox_chan *(*of_xlate)(struct mbox_controller *mbox,
+				      const struct of_phandle_args *sp);
+	/* Internal to API */
+	struct timer_list poll;
+	struct list_head node;
+};
+
+/*
+ * The length of circular buffer for queuing messages from a client.
+ * 'msg_count' tracks the number of buffered messages while 'msg_free'
+ * is the index where the next message would be buffered.
+ * We shouldn't need it too big because every transfer is interrupt
+ * triggered and if we have lots of data to transfer, the interrupt
+ * latencies are going to be the bottleneck, not the buffer length.
+ * Besides, mbox_send_message could be called from atomic context and
+ * the client could also queue another message from the notifier 'tx_done'
+ * of the last transfer done.
+ * REVISIT: If too many platforms see the "Try increasing MBOX_TX_QUEUE_LEN"
+ * print, it needs to be taken from config option or somesuch.
+ */
+#define MBOX_TX_QUEUE_LEN	20
+
+/**
+ * struct mbox_chan - s/w representation of a communication chan
+ * @mbox:		Pointer to the parent/provider of this channel
+ * @txdone_method:	Way to detect TXDone chosen by the API
+ * @cl:			Pointer to the current owner of this channel
+ * @tx_complete:	Transmission completion
+ * @active_req:		Currently active request hook
+ * @msg_count:		No. of mssg currently queued
+ * @msg_free:		Index of next available mssg slot
+ * @msg_data:		Hook for data packet
+ * @lock:		Serialise access to the channel
+ * @con_priv:		Hook for controller driver to attach private data
+ */
+struct mbox_chan {
+	struct mbox_controller *mbox;
+	unsigned txdone_method;
+	struct mbox_client *cl;
+	struct completion tx_complete;
+	void *active_req;
+	unsigned msg_count, msg_free;
+	void *msg_data[MBOX_TX_QUEUE_LEN];
+	spinlock_t lock; /* Serialise access to the channel */
+	void *con_priv;
+};
+
+int mbox_controller_register(struct mbox_controller *mbox); /* can sleep */
+void mbox_controller_unregister(struct mbox_controller *mbox); /* can sleep */
+void mbox_chan_received_data(struct mbox_chan *chan, void *data); /* atomic */
+void mbox_chan_txdone(struct mbox_chan *chan, int r); /* atomic */
+
+#endif /* __MAILBOX_CONTROLLER_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d6183f06d8c1..a3b4812f494f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -124,6 +124,25 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
 					struct page *newpage);
 
+static inline void mem_cgroup_oom_enable(void)
+{
+	WARN_ON(current->memcg_oom.may_oom);
+	current->memcg_oom.may_oom = 1;
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+	WARN_ON(!current->memcg_oom.may_oom);
+	current->memcg_oom.may_oom = 0;
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return p->memcg_oom.memcg;
+}
+
+bool mem_cgroup_oom_synchronize(bool wait);
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -347,6 +366,24 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 {
 }
 
+static inline void mem_cgroup_oom_enable(void)
+{
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(bool wait)
+{
+	return false;
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_page_stat_item idx)
 {
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 09c2300ddb37..cb358355ef43 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -45,6 +45,7 @@
 #define MAPPER_CTRL_MINOR	236
 #define LOOP_CTRL_MINOR		237
 #define VHOST_NET_MINOR		238
+#define UHID_MINOR		239
 #define MISC_DYNAMIC_MINOR	255
 
 struct device;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f42c5baa47cc..682877729c2c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -170,6 +170,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
 #define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
 #define FAULT_FLAG_TRIED	0x40	/* second try */
+#define FAULT_FLAG_USER		0x80	/* The fault originated in userspace */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -364,8 +365,18 @@ static inline void compound_unlock_irqrestore(struct page *page,
 
 static inline struct page *compound_head(struct page *page)
 {
-	if (unlikely(PageTail(page)))
-		return page->first_page;
+	if (unlikely(PageTail(page))) {
+		struct page *head = page->first_page;
+
+		/*
+		 * page->first_page may be a dangling pointer to an old
+		 * compound page, so recheck that it is still a tail
+		 * page before returning.
+		 */
+		smp_rmb();
+		if (likely(PageTail(page)))
+			return head;
+	}
 	return page;
 }
 
@@ -769,11 +780,14 @@ static __always_inline void *lowmem_page_address(const struct page *page)
 #endif
 
 #if defined(WANT_PAGE_VIRTUAL)
-#define page_address(page) ((page)->virtual)
-#define set_page_address(page, address)			\
-	do {						\
-		(page)->virtual = (address);		\
-	} while(0)
+static inline void *page_address(const struct page *page)
+{
+	return page->virtual;
+}
+static inline void set_page_address(struct page *page, void *address)
+{
+	page->virtual = address;
+}
 #define page_address_init()  do { } while(0)
 #endif
 
@@ -994,6 +1008,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 
 extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
@@ -1618,7 +1633,7 @@ extern int expand_downwards(struct vm_area_struct *vma,
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
-  #define expand_upwards(vma, address) do { } while (0)
+  #define expand_upwards(vma, address) (0)
 #endif
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4a189ba6b128..10a9a17342fc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -437,6 +437,14 @@ struct mm_struct {
 	 */
 	int first_nid;
 #endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+	/*
+	 * An operation with batched TLB flushing is going on. Anything that
+	 * can move process memory needs to flush the TLB when moving a
+	 * PROT_NONE or PROT_NUMA mapped page.
+	 */
+	bool tlb_flush_pending;
+#endif
 	struct uprobes_state uprobes_state;
 };
 
@@ -457,4 +465,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return mm->cpu_vm_mask_var;
 }
 
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+	mm->tlb_flush_pending = true;
+
+	/*
+	 * Guarantee that the tlb_flush_pending store does not leak into the
+	 * critical section updating the page tables
+	 */
+	smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index b508016fb76d..08450a6146e1 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -456,7 +456,8 @@ enum dmi_field {
 };
 
 struct dmi_strmatch {
-	unsigned char slot;
+	unsigned char slot:7;
+	unsigned char exact_match:1;
 	char substr[79];
 };
 
@@ -474,7 +475,8 @@ struct dmi_system_id {
  */
 #define dmi_device_id dmi_system_id
 
-#define DMI_MATCH(a, b)	{ a, b }
+#define DMI_MATCH(a, b)	{ .slot = a, .substr = b }
+#define DMI_EXACT_MATCH(a, b)	{ .slot = a, .substr = b, .exact_match = 1 }
 
 #define PLATFORM_NAME_SIZE	20
 #define PLATFORM_MODULE_PREFIX	"platform:"
@@ -561,6 +563,15 @@ struct x86_cpu_id {
 #define X86_MODEL_ANY  0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
+/*
+ * Generic table type for matching CPU features.
+ * @feature:	the bit number of the feature (0 - 65535)
+ */
+
+struct cpu_feature {
+	__u16	feature;
+};
+
 #define IPACK_ANY_FORMAT 0xff
 #define IPACK_ANY_ID (~0)
 struct ipack_device_id {
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 73005f9957ea..8eeb8f6ab110 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -42,11 +42,18 @@ struct mnt_namespace;
  * flag, consider how it interacts with shared mounts.
  */
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
-#define MNT_PROPAGATION_MASK	(MNT_SHARED | MNT_UNBINDABLE)
+#define MNT_USER_SETTABLE_MASK  (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
+				 | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
+				 | MNT_READONLY)
 
+#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL	0x4000
 
+#define MNT_LOCK_ATIME		0x040000
+#define MNT_LOCK_NOEXEC		0x080000
+#define MNT_LOCK_NOSUID		0x100000
+#define MNT_LOCK_NODEV		0x200000
 #define MNT_LOCK_READONLY	0x400000
 
 struct vfsmount {
diff --git a/include/linux/msg.h b/include/linux/msg.h
index 391af8d11cce..e21f9d44307f 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -6,9 +6,9 @@
 
 /* one msg_msg structure for each message */
 struct msg_msg {
-	struct list_head m_list; 
-	long  m_type;          
-	int m_ts;           /* message text size */
+	struct list_head m_list;
+	long m_type;
+	size_t m_ts;		/* message text size */
 	struct msg_msgseg* next;
 	void *security;
 	/* the actual message follows immediately */
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 4b02512e421c..5f487d776411 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -365,7 +365,7 @@ static inline map_word map_word_load_partial(struct map_info *map, map_word orig
 			bitpos = (map_bankwidth(map)-1-i)*8;
 #endif
 			orig.x[0] &= ~(0xff << bitpos);
-			orig.x[0] |= buf[i-start] << bitpos;
+			orig.x[0] |= (unsigned long)buf[i-start] << bitpos;
 		}
 	}
 	return orig;
@@ -384,7 +384,7 @@ static inline map_word map_word_ff(struct map_info *map)
 
 	if (map_bankwidth(map) < MAP_FF_LIMIT) {
 		int bw = 8 * map_bankwidth(map);
-		r.x[0] = (1 << bw) - 1;
+		r.x[0] = (1UL << bw) - 1;
 	} else {
 		for (i=0; i<map_words(map); i++)
 			r.x[i] = ~0UL;
diff --git a/include/linux/net.h b/include/linux/net.h
index 99c9f0c103c2..65545ac6fb9c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -163,6 +163,14 @@ struct proto_ops {
 #endif
 	int		(*sendmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len);
+	/* Notes for implementing recvmsg:
+	 * ===============================
+	 * msg->msg_namelen should get updated by the recvmsg handlers
+	 * iff msg_name != NULL. It is by default 0 to prevent
+	 * returning uninitialized memory to user space.  The recvfrom
+	 * handlers can assume that msg.msg_name is either NULL or has
+	 * a minimum size of sizeof(struct sockaddr_storage).
+	 */
 	int		(*recvmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len,
 				      int flags);
@@ -172,7 +180,7 @@ struct proto_ops {
 				      int offset, size_t size, int flags);
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
-	void		(*set_peek_off)(struct sock *sk, int val);
+	int		(*set_peek_off)(struct sock *sk, int val);
 };
 
 #define DECLARE_SOCKADDR(type, dst, src)	\
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 96e4c21e15e0..4d2e0418ab5a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1772,6 +1772,15 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+static inline int dev_rebuild_header(struct sk_buff *skb)
+{
+	const struct net_device *dev = skb->dev;
+
+	if (!dev->header_ops || !dev->header_ops->rebuild)
+		return 0;
+	return dev->header_ops->rebuild(skb);
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 extern int		register_gifconf(unsigned int family, gifconf_func_t * gifconf);
 static inline int unregister_gifconf(unsigned int family)
@@ -2752,7 +2761,12 @@ void netdev_change_features(struct net_device *dev);
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
-netdev_features_t netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+	return netif_skb_dev_features(skb, skb->dev);
+}
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 6358da5eeee8..9516dad45109 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
 }
 
 enum netlink_skb_flags {
-	NETLINK_SKB_MMAPED	= 0x1,		/* Packet data is mmaped */
-	NETLINK_SKB_TX		= 0x2,		/* Packet was sent by userspace */
-	NETLINK_SKB_DELIVERED	= 0x4,		/* Packet was delivered */
+	NETLINK_SKB_MMAPED	= 0x1,	/* Packet data is mmaped */
+	NETLINK_SKB_TX		= 0x2,	/* Packet was sent by userspace */
+	NETLINK_SKB_DELIVERED	= 0x4,	/* Packet was delivered */
+	NETLINK_SKB_DST		= 0x8,	/* Dst set in sendto or sendmsg */
 };
 
 struct netlink_skb_parms {
@@ -144,4 +145,11 @@ static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	return __netlink_dump_start(ssk, skb, nlh, control);
 }
 
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			  struct user_namespace *ns, int cap);
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *ns, int cap);
+bool netlink_capable(const struct sk_buff *skb, int cap);
+bool netlink_net_capable(const struct sk_buff *skb, int cap);
+
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 104b62f23ee0..54e351aa4d2e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1184,11 +1184,22 @@ struct nfs41_free_stateid_res {
 	unsigned int			status;
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+	kfree(cinfo->buckets);
+}
+
 #else
 
 struct pnfs_ds_commit_info {
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
diff --git a/include/linux/of.h b/include/linux/of.h
index 429e16801858..078a187d518c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -252,20 +252,19 @@ extern int of_property_read_u64(const struct device_node *np,
 extern int of_property_read_string(struct device_node *np,
 				   const char *propname,
 				   const char **out_string);
-extern int of_property_read_string_index(struct device_node *np,
-					 const char *propname,
-					 int index, const char **output);
 extern int of_property_match_string(struct device_node *np,
 				    const char *propname,
 				    const char *string);
-extern int of_property_count_strings(struct device_node *np,
-				     const char *propname);
+extern int of_property_read_string_helper(struct device_node *np,
+					      const char *propname,
+					      const char **out_strs, size_t sz, int index);
 extern int of_device_is_compatible(const struct device_node *device,
 				   const char *);
 extern int of_device_is_available(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
 				const char *name,
 				int *lenp);
+extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 #define for_each_property_of_node(dn, pp) \
 	for (pp = dn->properties; pp != NULL; pp = pp->next)
 
@@ -441,15 +440,9 @@ static inline int of_property_read_string(struct device_node *np,
 	return -ENOSYS;
 }
 
-static inline int of_property_read_string_index(struct device_node *np,
-						const char *propname, int index,
-						const char **out_string)
-{
-	return -ENOSYS;
-}
-
-static inline int of_property_count_strings(struct device_node *np,
-					    const char *propname)
+static inline int of_property_read_string_helper(struct device_node *np,
+						 const char *propname,
+						 const char **out_strs, size_t sz, int index)
 {
 	return -ENOSYS;
 }
@@ -461,6 +454,12 @@ static inline const void *of_get_property(const struct device_node *node,
 	return NULL;
 }
 
+static inline struct device_node *of_get_cpu_node(int cpu,
+					unsigned int *thread)
+{
+	return NULL;
+}
+
 static inline int of_property_read_u64(const struct device_node *np,
 				       const char *propname, u64 *out_value)
 {
@@ -530,6 +529,70 @@ static inline int of_node_to_nid(struct device_node *np)
 #endif
 
 /**
+ * of_property_read_string_array() - Read an array of strings from a multiple
+ * strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_strs:	output array of string pointers.
+ * @sz:		number of array elements to read.
+ *
+ * Search for a property in a device tree node and retrieve a list of
+ * terminated string values (pointer to data, not a copy) in that property.
+ *
+ * If @out_strs is NULL, the number of strings in the property is returned.
+ */
+static inline int of_property_read_string_array(struct device_node *np,
+						const char *propname, const char **out_strs,
+						size_t sz)
+{
+	return of_property_read_string_helper(np, propname, out_strs, sz, 0);
+}
+
+/**
+ * of_property_count_strings() - Find and return the number of strings from a
+ * multiple strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device tree node and retrieve the number of null
+ * terminated string contain in it. Returns the number of strings on
+ * success, -EINVAL if the property does not exist, -ENODATA if property
+ * does not have a value, and -EILSEQ if the string is not null-terminated
+ * within the length of the property data.
+ */
+static inline int of_property_count_strings(struct device_node *np,
+					    const char *propname)
+{
+	return of_property_read_string_helper(np, propname, NULL, 0, 0);
+}
+
+/**
+ * of_property_read_string_index() - Find and read a string from a multiple
+ * strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @index:	index of the string in the list of strings
+ * @out_string:	pointer to null terminated return string, modified only if
+ *		return value is 0.
+ *
+ * Search for a property in a device tree node and retrieve a null
+ * terminated string value (pointer to data, not a copy) in the list of strings
+ * contained in that property.
+ * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
+ * property does not have a value, and -EILSEQ if the string is not
+ * null-terminated within the length of the property data.
+ *
+ * The out_string pointer is modified only if a valid string can be decoded.
+ */
+static inline int of_property_read_string_index(struct device_node *np,
+						const char *propname,
+						int index, const char **output)
+{
+	int rc = of_property_read_string_helper(np, propname, output, 1, index);
+	return rc < 0 ? rc : 0;
+}
+
+/**
  * of_property_read_bool - Findfrom a property
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 901b7435e890..192c783c2ec6 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
+#include <linux/cpu.h>
 #include <linux/platform_device.h>
 #include <linux/of_platform.h> /* temporary until merge */
 
@@ -43,6 +44,15 @@ static inline void of_device_node_put(struct device *dev)
 	of_node_put(dev->of_node);
 }
 
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+	struct device *cpu_dev;
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return NULL;
+	return of_node_get(cpu_dev->of_node);
+}
+
 #else /* CONFIG_OF_DEVICE */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -67,6 +77,11 @@ static inline const struct of_device_id *of_match_device(
 {
 	return NULL;
 }
+
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+	return NULL;
+}
 #endif /* CONFIG_OF_DEVICE */
 
 #endif /* _LINUX_OF_DEVICE_H */
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
new file mode 100644
index 000000000000..56e0507a0d58
--- /dev/null
+++ b/include/linux/of_graph.h
@@ -0,0 +1,65 @@
+/*
+ * OF graph binding parsing helpers
+ *
+ * Copyright (C) 2012 - 2013 Samsung Electronics Co., Ltd.
+ * Author: Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * Copyright (C) 2012 Renesas Electronics Corp.
+ * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_OF_GRAPH_H
+#define __LINUX_OF_GRAPH_H
+
+/**
+ * struct of_endpoint - the OF graph endpoint data structure
+ * @port: identifier (value of reg property) of a port this endpoint belongs to
+ * @id: identifier (value of reg property) of this endpoint
+ * @local_node: pointer to device_node of this endpoint
+ */
+struct of_endpoint {
+	unsigned int port;
+	unsigned int id;
+	const struct device_node *local_node;
+};
+
+#ifdef CONFIG_OF
+int of_graph_parse_endpoint(const struct device_node *node,
+				struct of_endpoint *endpoint);
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *previous);
+struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node);
+struct device_node *of_graph_get_remote_port(const struct device_node *node);
+#else
+
+static inline int of_graph_parse_endpoint(const struct device_node *node,
+					struct of_endpoint *endpoint)
+{
+	return -ENOSYS;
+}
+static inline struct device_node *of_graph_get_next_endpoint(
+					const struct device_node *parent,
+					struct device_node *previous)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_OF */
+
+#endif /* __LINUX_OF_GRAPH_H */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index da60007075b5..297cda528855 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+
+extern int oom_kills_count(void);
+extern void note_oom_kill(void);
 extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			     unsigned int points, unsigned long totalpages,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 3a24e4ff3248..102136ab1a5f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -310,6 +310,7 @@ struct pci_dev {
 	unsigned int	is_added:1;
 	unsigned int	is_busmaster:1; /* device is busmaster */
 	unsigned int	no_msi:1;	/* device may not use msi */
+	unsigned int	no_64bit_msi:1; /* device may only use 32-bit MSIs */
 	unsigned int	block_cfg_access:1;	/* config space access is blocked */
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int	irq_reroute_variant:2;	/* device needs IRQ rerouting variant */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c5b6dbf9c2fc..229a757e1c13 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -695,10 +695,17 @@ static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
+extern int sysctl_perf_cpu_time_max_percent;
+
+extern void perf_sample_event_took(u64 sample_len_ns);
 
 extern int perf_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
+extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
 
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h
index 4aad3cea69ae..04c760d56bb8 100644
--- a/include/linux/pinctrl/consumer.h
+++ b/include/linux/pinctrl/consumer.h
@@ -158,47 +158,4 @@ static inline struct pinctrl * __must_check devm_pinctrl_get_select_default(
 	return devm_pinctrl_get_select(dev, PINCTRL_STATE_DEFAULT);
 }
 
-#ifdef CONFIG_PINCONF
-
-extern int pin_config_get(const char *dev_name, const char *name,
-			  unsigned long *config);
-extern int pin_config_set(const char *dev_name, const char *name,
-			  unsigned long config);
-extern int pin_config_group_get(const char *dev_name,
-				const char *pin_group,
-				unsigned long *config);
-extern int pin_config_group_set(const char *dev_name,
-				const char *pin_group,
-				unsigned long config);
-
-#else
-
-static inline int pin_config_get(const char *dev_name, const char *name,
-				 unsigned long *config)
-{
-	return 0;
-}
-
-static inline int pin_config_set(const char *dev_name, const char *name,
-				 unsigned long config)
-{
-	return 0;
-}
-
-static inline int pin_config_group_get(const char *dev_name,
-				       const char *pin_group,
-				       unsigned long *config)
-{
-	return 0;
-}
-
-static inline int pin_config_group_set(const char *dev_name,
-				       const char *pin_group,
-				       unsigned long config)
-{
-	return 0;
-}
-
-#endif
-
 #endif /* __LINUX_PINCTRL_CONSUMER_H */
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index 6aa238096622..201e68de2d11 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -29,12 +29,21 @@
  *	if for example some other pin is going to drive the signal connected
  *	to it for a while. Pins used for input are usually always high
  *	impedance.
+ * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it
+ *	weakly drives the last value on a tristate bus, also known as a "bus
+ *	holder", "bus keeper" or "repeater". This allows another device on the
+ *	bus to change the value by driving the bus high or low and switching to
+ *	tristate. The argument is ignored.
  * @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high
  *	impedance to VDD). If the argument is != 0 pull-up is enabled,
  *	if it is 0, pull-up is disabled.
  * @PIN_CONFIG_BIAS_PULL_DOWN: the pin will be pulled down (usually with high
  *	impedance to GROUND). If the argument is != 0 pull-down is enabled,
  *	if it is 0, pull-down is disabled.
+ * @PIN_CONFIG_BIAS_PULL_PIN_DEFAULT: the pin will be pulled up or down based
+ *	on embedded knowledge of the controller, like current mux function.
+ *	If the argument is != 0 pull up/down is enabled, if it is 0,
+ *	the pull is disabled.
  * @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and
  *	low, this is the most typical case and is typically achieved with two
  *	active transistors on the output. Setting this config will enable
@@ -48,6 +57,9 @@
  *	argument is ignored.
  * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current
  *	passed as argument. The argument is in mA.
+ * @PIN_CONFIG_INPUT_ENABLE: enable the pin's input.  Note that this does not
+ *	affect the pin's ability to drive output.  1 enables input, 0 disables
+ *	input.
  * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin.
  *      If the argument != 0, schmitt-trigger mode is enabled. If it's 0,
  *      schmitt-trigger mode is disabled.
@@ -57,7 +69,7 @@
  *	setting pins to this mode.
  * @PIN_CONFIG_INPUT_DEBOUNCE: this will configure the pin to debounce mode,
  *	which means it will wait for signals to settle when reading inputs. The
- *	argument gives the debounce time on a custom format. Setting the
+ *	argument gives the debounce time in usecs. Setting the
  *	argument to zero turns debouncing off.
  * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power
  *	supplies, the argument to this parameter (on a custom format) tells
@@ -78,12 +90,15 @@
 enum pin_config_param {
 	PIN_CONFIG_BIAS_DISABLE,
 	PIN_CONFIG_BIAS_HIGH_IMPEDANCE,
+	PIN_CONFIG_BIAS_BUS_HOLD,
 	PIN_CONFIG_BIAS_PULL_UP,
 	PIN_CONFIG_BIAS_PULL_DOWN,
+	PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
 	PIN_CONFIG_DRIVE_PUSH_PULL,
 	PIN_CONFIG_DRIVE_OPEN_DRAIN,
 	PIN_CONFIG_DRIVE_OPEN_SOURCE,
 	PIN_CONFIG_DRIVE_STRENGTH,
+	PIN_CONFIG_INPUT_ENABLE,
 	PIN_CONFIG_INPUT_SCHMITT_ENABLE,
 	PIN_CONFIG_INPUT_SCHMITT,
 	PIN_CONFIG_INPUT_DEBOUNCE,
@@ -122,6 +137,58 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param
 	return PIN_CONF_PACKED(param, argument);
 }
 
+#ifdef CONFIG_OF
+
+#include <linux/device.h>
+#include <linux/pinctrl/machine.h>
+struct pinctrl_dev;
+struct pinctrl_map;
+
+int pinconf_generic_dt_subnode_to_map_new(struct pinctrl_dev *pctldev,
+		struct device_node *np, struct pinctrl_map **map,
+		unsigned *reserved_maps, unsigned *num_maps,
+		enum pinctrl_map_type type);
+int pinconf_generic_dt_node_to_map_new(struct pinctrl_dev *pctldev,
+		struct device_node *np_config, struct pinctrl_map **map,
+		unsigned *num_maps, enum pinctrl_map_type type);
+
+static inline int pinconf_generic_dt_node_to_map_group(
+		struct pinctrl_dev *pctldev, struct device_node *np_config,
+		struct pinctrl_map **map, unsigned *num_maps)
+{
+	return pinconf_generic_dt_node_to_map_new(pctldev, np_config, map, num_maps,
+			PIN_MAP_TYPE_CONFIGS_GROUP);
+}
+
+static inline int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
+		struct device_node *np, struct pinctrl_map **map,
+		unsigned *reserved_maps, unsigned *num_maps)
+{
+	return pinconf_generic_dt_subnode_to_map_new(pctldev, np, map,
+						     reserved_maps, num_maps,
+						     PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+static inline int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
+		struct device_node *np_config, struct pinctrl_map **map,
+		unsigned *num_maps)
+{
+	return pinconf_generic_dt_node_to_map_new(pctldev, np_config,
+						  map, num_maps,
+						  PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+
+static inline int pinconf_generic_dt_node_to_map_pin(
+		struct pinctrl_dev *pctldev, struct device_node *np_config,
+		struct pinctrl_map **map, unsigned *num_maps)
+{
+	return pinconf_generic_dt_node_to_map_new(pctldev, np_config, map, num_maps,
+						  PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+#endif
+
 #endif /* CONFIG_GENERIC_PINCONF */
 
 #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index 1ad4f31ef6b8..e6a68e476aef 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -48,12 +48,20 @@ struct pinconf_ops {
 	int (*pin_config_set) (struct pinctrl_dev *pctldev,
 			       unsigned pin,
 			       unsigned long config);
+	int (*pin_config_set_bulk) (struct pinctrl_dev *pctldev,
+				    unsigned pin,
+				    unsigned long *configs,
+				    unsigned num_configs);
 	int (*pin_config_group_get) (struct pinctrl_dev *pctldev,
 				     unsigned selector,
 				     unsigned long *config);
 	int (*pin_config_group_set) (struct pinctrl_dev *pctldev,
 				     unsigned selector,
 				     unsigned long config);
+	int (*pin_config_group_set_bulk) (struct pinctrl_dev *pctldev,
+					  unsigned selector,
+					  unsigned long *configs,
+					  unsigned num_configs);
 	int (*pin_config_dbg_parse_modify) (struct pinctrl_dev *pctldev,
 					   const char *arg,
 					   unsigned long *config);
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 2c2a9e8d8578..9adb1067af71 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -32,10 +32,12 @@ struct device_node;
  * pins, pads or other muxable units in this struct
  * @number: unique pin number from the global pin number space
  * @name: a name for this pin
+ * @drv_data: driver-defined per-pin data. pinctrl core does not touch this
  */
 struct pinctrl_pin_desc {
 	unsigned number;
 	const char *name;
+	void *drv_data;
 };
 
 /* Convenience macro to define a single named or anonymous pin descriptor */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index b8809fef61f5..ab5752692113 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -157,6 +157,8 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
+extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
+
 /* for F_SETPIPE_SZ and F_GETPIPE_SZ */
 long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
 struct pipe_inode_info *get_pipe_info(struct file *file);
diff --git a/include/linux/mailbox.h b/include/linux/pl320-ipc.h
index 5161f63ec1c8..5161f63ec1c8 100644
--- a/include/linux/mailbox.h
+++ b/include/linux/pl320-ipc.h
diff --git a/include/linux/pm.h b/include/linux/pm.h
index a224c7f5c377..b8760601ecbe 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -575,6 +575,7 @@ extern int dev_pm_put_subsys_data(struct device *dev);
  */
 struct dev_pm_domain {
 	struct dev_pm_ops	ops;
+	void (*detach)(struct device *dev, bool power_off);
 };
 
 /*
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 7c1d252b20c0..66cfa1a39d81 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -310,4 +310,56 @@ static inline void pm_genpd_syscore_poweron(struct device *dev)
 	pm_genpd_syscore_switch(dev, false);
 }
 
+/* OF PM domain providers */
+struct of_device_id;
+
+struct genpd_onecell_data {
+	struct generic_pm_domain **domains;
+	unsigned int num_domains;
+};
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+						void *data);
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data);
+void of_genpd_del_provider(struct device_node *np);
+
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data);
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data);
+
+int genpd_dev_pm_attach(struct device *dev);
+#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
+static inline int __of_genpd_add_provider(struct device_node *np,
+					genpd_xlate_t xlate, void *data)
+{
+	return 0;
+}
+static inline void of_genpd_del_provider(struct device_node *np) {}
+
+#define __of_genpd_xlate_simple		NULL
+#define __of_genpd_xlate_onecell	NULL
+
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+					struct generic_pm_domain *genpd)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+}
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+					struct genpd_onecell_data *data)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
+}
+
 #endif /* _LINUX_PM_DOMAIN_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 22c7052e9372..708b8a84f6c0 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -124,9 +124,9 @@ asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
 /*
- * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
  */
-__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -161,7 +161,7 @@ int printk(const char *s, ...)
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk_sched(const char *s, ...)
+int printk_deferred(const char *s, ...)
 {
 	return 0;
 }
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9974975d40db..4af3fdc85b01 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -53,7 +53,8 @@ struct persistent_ram_zone {
 };
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info);
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
@@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
 struct ramoops_platform_data {
 	unsigned long	mem_size;
 	unsigned long	mem_address;
+	unsigned int	mem_type;
 	unsigned long	record_size;
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 89573a33ab3c..bb980ae6d9d3 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>		/* For struct task_struct.  */
 #include <linux/err.h>			/* for IS_ERR_VALUE */
 #include <linux/bug.h>			/* For BUG_ON.  */
+#include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
 #include <uapi/linux/ptrace.h>
 
 /*
@@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message)
 }
 
 /**
+ * ptrace_event_pid - possibly stop for a ptrace event notification
+ * @event:	%PTRACE_EVENT_* value to report
+ * @pid:	process identifier for %PTRACE_GETEVENTMSG to return
+ *
+ * Check whether @event is enabled and, if so, report @event and @pid
+ * to the ptrace parent.  @pid is reported as the pid_t seen from the
+ * the ptrace parent's pid namespace.
+ *
+ * Called without locks.
+ */
+static inline void ptrace_event_pid(int event, struct pid *pid)
+{
+	/*
+	 * FIXME: There's a potential race if a ptracer in a different pid
+	 * namespace than parent attaches between computing message below and
+	 * when we acquire tasklist_lock in ptrace_stop().  If this happens,
+	 * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG.
+	 */
+	unsigned long message = 0;
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = task_active_pid_ns(rcu_dereference(current->parent));
+	if (ns)
+		message = pid_nr_ns(pid, ns);
+	rcu_read_unlock();
+
+	ptrace_event(event, message);
+}
+
+/**
  * ptrace_init_task - initialize ptrace state for a new child
  * @child:		new child task
  * @ptrace:		true if child should be ptrace'd by parent's tracer
@@ -305,6 +337,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
  * calling arch_ptrace_stop() when it would be superfluous.  For example,
  * if the thread has not been back to user mode since the last stop, the
  * thread state might indicate that nothing needs to be done.
+ *
+ * This is guaranteed to be invoked once before a task stops for ptrace and
+ * may include arch-specific operations necessary prior to a ptrace stop.
  */
 #define arch_ptrace_stop_needed(code, info)	(0)
 #endif
diff --git a/include/linux/random.h b/include/linux/random.h
index 3b9377d6b7a5..bf9085e89fb5 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -17,6 +17,7 @@ extern void add_interrupt_randomness(int irq, int irq_flags);
 extern void get_random_bytes(void *buf, int nbytes);
 extern void get_random_bytes_arch(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);
+extern int random_int_secret_init(void);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
@@ -49,9 +50,9 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 {
 	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
 
-	state->s1 = __seed(i, 1);
-	state->s2 = __seed(i, 7);
-	state->s3 = __seed(i, 15);
+	state->s1 = __seed(i, 2);
+	state->s2 = __seed(i, 8);
+	state->s3 = __seed(i, 16);
 }
 
 #ifdef CONFIG_ARCH_RANDOM
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d69cf637a15a..49a4d6f59108 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu);
 int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 178a8d909f14..6ca9630fde2d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -332,6 +332,10 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
 
+#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
+#define SUID_DUMP_USER		1	/* Dump as user of process */
+#define SUID_DUMP_ROOT		2	/* Dump as root */
+
 /* mm flags */
 /* dumpable bits */
 #define MMF_DUMPABLE      0  /* core dump is permitted */
@@ -476,6 +480,7 @@ struct signal_struct {
 	atomic_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 
@@ -885,6 +890,13 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
+#ifdef CONFIG_SCHED_HMP
+struct hmp_domain {
+	struct cpumask cpus;
+	struct cpumask possible_cpus;
+	struct list_head hmp_domains;
+};
+#endif /* CONFIG_SCHED_HMP */
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -931,8 +943,22 @@ struct sched_avg {
 	u64 last_runnable_update;
 	s64 decay_count;
 	unsigned long load_avg_contrib;
+	unsigned long load_avg_ratio;
+#ifdef CONFIG_SCHED_HMP
+	u64 hmp_last_up_migration;
+	u64 hmp_last_down_migration;
+#endif
+	u32 usage_avg_sum;
 };
 
+#ifdef CONFIG_SCHED_HMP
+/*
+ * We want to avoid boosting any processes forked from init (PID 1)
+ * and kthreadd (assumed to be PID 2).
+ */
+#define hmp_task_should_forkboost(task) ((task->parent && task->parent->pid > 2))
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
 	u64			wait_start;
@@ -1156,6 +1182,7 @@ struct task_struct {
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
+	struct list_head thread_node;
 
 	struct completion *vfork_done;		/* for vfork() */
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
@@ -1405,6 +1432,12 @@ struct task_struct {
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
 	unsigned int memcg_kmem_skip_account;
+	struct memcg_oom_info {
+		struct mem_cgroup *memcg;
+		gfp_t gfp_mask;
+		int order;
+		unsigned int may_oom:1;
+	} memcg_oom;
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	atomic_t ptrace_bp_refcnt;
@@ -1664,11 +1697,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
 static inline gfp_t memalloc_noio_flags(gfp_t flags)
 {
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~__GFP_IO;
+		flags &= ~(__GFP_IO | __GFP_FS);
 	return flags;
 }
 
@@ -2163,6 +2198,16 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
 static inline int get_nr_threads(struct task_struct *tsk)
 {
 	return tsk->signal->nr_threads;
@@ -2469,34 +2514,98 @@ static inline int tsk_is_polling(struct task_struct *p)
 {
 	return task_thread_info(p)->status & TS_POLLING;
 }
-static inline void current_set_polling(void)
+static inline void __current_set_polling(void)
 {
 	current_thread_info()->status |= TS_POLLING;
 }
 
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
 {
 	current_thread_info()->status &= ~TS_POLLING;
-	smp_mb__after_clear_bit();
+}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb();
+
+	return unlikely(tif_need_resched());
 }
 #elif defined(TIF_POLLING_NRFLAG)
 static inline int tsk_is_polling(struct task_struct *p)
 {
 	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
 }
-static inline void current_set_polling(void)
+
+static inline void __current_set_polling(void)
 {
 	set_thread_flag(TIF_POLLING_NRFLAG);
 }
 
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 *
+	 * XXX: assumes set/clear bit are identical barrier wise.
+	 */
+	smp_mb__after_clear_bit();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
 {
 	clear_thread_flag(TIF_POLLING_NRFLAG);
 }
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb__after_clear_bit();
+
+	return unlikely(tif_need_resched());
+}
+
 #else
 static inline int tsk_is_polling(struct task_struct *p) { return 0; }
-static inline void current_set_polling(void) { }
-static inline void current_clr_polling(void) { }
+static inline void __current_set_polling(void) { }
+static inline void __current_clr_polling(void) { }
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
 #endif
 
 /*
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 53d42650b193..976ce3a19f1b 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -12,10 +12,12 @@ struct task_struct;
 struct sem_array {
 	struct kern_ipc_perm	____cacheline_aligned_in_smp
 				sem_perm;	/* permissions .. see ipc.h */
-	time_t			sem_otime;	/* last semop time */
 	time_t			sem_ctime;	/* last change time */
 	struct sem		*sem_base;	/* ptr to first semaphore in array */
-	struct list_head	sem_pending;	/* pending operations to be processed */
+	struct list_head	pending_alter;	/* pending operations */
+						/* that alter the array */
+	struct list_head	pending_const;	/* pending complex operations */
+						/* that do not alter semvals */
 	struct list_head	list_id;	/* undo requests on this array */
 	int			sem_nsems;	/* no. of semaphores in array */
 	int			complex_count;	/* pending complex operations */
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 87d4bbc773fc..c2b355fd921a 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -279,6 +279,22 @@ static inline int uart_poll_timeout(struct uart_port *port)
 /*
  * Console helpers.
  */
+struct earlycon_device {
+	struct console *con;
+	struct uart_port port;
+	char options[16];		/* e.g., 115200n8 */
+	unsigned int baud;
+};
+int setup_earlycon(char *buf, const char *match,
+		   int (*setup)(struct earlycon_device *, const char *));
+
+#define EARLYCON_DECLARE(name, func) \
+static int __init name ## _setup_earlycon(char *buf) \
+{ \
+	return setup_earlycon(buf, __stringify(name), func); \
+} \
+early_param("earlycon", name ## _setup_earlycon);
+
 struct uart_port *uart_get_console(struct uart_port *ports, int nr,
 				   struct console *c);
 void uart_parse_options(char *options, int *baud, int *parity, int *bits,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index dec1748cd002..478120ae34e5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -331,11 +331,6 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
-#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
-    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
-#endif
-
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
@@ -368,7 +363,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
  *	@nfct: Associated connection, if any
- *	@nfct_reasm: netfilter conntrack re-assembly pointer
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
@@ -455,9 +449,6 @@ struct sk_buff {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	struct sk_buff		*nfct_reasm;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif
@@ -1308,6 +1299,11 @@ static inline int skb_pagelen(const struct sk_buff *skb)
 	return len + skb_headlen(skb);
 }
 
+static inline bool skb_has_frags(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->nr_frags;
+}
+
 /**
  * __skb_fill_page_desc - initialise a paged fragment in an skb
  * @skb: buffer containing fragment to be initialised
@@ -1745,6 +1741,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
 }
 #endif /* NET_SKBUFF_DATA_USES_OFFSET */
 
+static inline void skb_pop_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = skb->network_header;
+}
+
 static inline void skb_probe_transport_header(struct sk_buff *skb,
 					      const int offset_hint)
 {
@@ -2487,6 +2488,8 @@ extern int	       skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
 extern struct sk_buff *skb_segment(struct sk_buff *skb,
 				   netdev_features_t features);
 
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
+
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
 {
@@ -2695,18 +2698,6 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 		atomic_inc(&nfct->use);
 }
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		atomic_inc(&skb->users);
-}
-static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		kfree_skb(skb);
-}
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {
@@ -2725,10 +2716,6 @@ static inline void nf_reset(struct sk_buff *skb)
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-	skb->nfct_reasm = NULL;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;
@@ -2750,10 +2737,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	dst->nfct_reasm = src->nfct_reasm;
-	nf_conntrack_get_reasm(src->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
@@ -2765,9 +2748,6 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(dst->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(dst->nf_bridge);
 #endif
@@ -2933,5 +2913,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb)
 {
 	return !skb->head_frag || skb_cloned(skb);
 }
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) -
+			       skb_network_header(skb);
+	return hdr_len + skb_gso_transport_seglen(skb);
+}
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 54f91d35e5fd..46cca4c06848 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie);
 void sock_diag_save_cookie(void *sk, __u32 *cookie);
 
 int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype);
 
 #endif
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 7d537ced949a..75f34949d9ab 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -117,9 +117,17 @@ do {								\
 #endif /*arch_spin_is_contended*/
 #endif
 
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
+/*
+ * Despite its name it doesn't necessarily has to be a full barrier.
+ * It should only guarantee that a STORE before the critical section
+ * can not be reordered with a LOAD inside this section.
+ * spin_lock() is the one-way barrier, this LOAD can not escape out
+ * of the region. So the default implementation simply ensures that
+ * a STORE can not move into the critical section, smp_wmb() should
+ * serialize it with another STORE done by spin_lock().
+ */
+#ifndef smp_mb__before_spinlock
+#define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
 /**
diff --git a/include/linux/string.h b/include/linux/string.h
index ac889c5ea11b..0ed878d0465c 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
 #endif
 
 extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
-			const void *from, size_t available);
+				       const void *from, size_t available);
 
 /**
  * strstarts - does @str start with @prefix?
@@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix)
 	return strncmp(str, prefix, strlen(prefix)) == 0;
 }
 
-extern size_t memweight(const void *ptr, size_t bytes);
+size_t memweight(const void *ptr, size_t bytes);
+void memzero_explicit(void *s, size_t count);
 
 /**
  * kbasename - return the last part of a pathname.
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b05963f09ebf..f5bfb1a80abe 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -32,6 +32,7 @@ struct svc_xprt_class {
 	struct svc_xprt_ops	*xcl_ops;
 	struct list_head	xcl_list;
 	u32			xcl_max_payload;
+	int			xcl_ident;
 };
 
 /*
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 62fd1b756e99..947009ed5996 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -56,6 +56,7 @@ int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);
 void		svc_sock_update_bufs(struct svc_serv *serv);
+bool		svc_alien_sock(struct net *net, int fd);
 int		svc_addsock(struct svc_serv *serv, const int fd,
 					char *name_return, const size_t len);
 void		svc_init_xprt_sock(void);
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index e2cee22f578a..7dd65cbfcdb3 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -17,6 +17,7 @@
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/kobject_ns.h>
+#include <linux/stat.h>
 #include <linux/atomic.h>
 
 struct kobject;
@@ -68,17 +69,25 @@ struct attribute_group {
  * for examples..
  */
 
-#define __ATTR(_name,_mode,_show,_store) { \
-	.attr = {.name = __stringify(_name), .mode = _mode },	\
-	.show	= _show,					\
-	.store	= _store,					\
+#define __ATTR(_name,_mode,_show,_store) { 				\
+	.attr = {.name = __stringify(_name), .mode = _mode },		\
+	.show	= _show,						\
+	.store	= _store,						\
 }
 
-#define __ATTR_RO(_name) { \
-	.attr	= { .name = __stringify(_name), .mode = 0444 },	\
-	.show	= _name##_show,					\
+#define __ATTR_RO(_name) {						\
+	.attr	= { .name = __stringify(_name), .mode = S_IRUGO },	\
+	.show	= _name##_show,						\
 }
 
+#define __ATTR_WO(_name) {						\
+	.attr	= { .name = __stringify(_name), .mode = S_IWUSR },	\
+	.store	= _name##_store,					\
+}
+
+#define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO),		\
+			 _name##_show, _name##_store)
+
 #define __ATTR_NULL { .attr = { .name = NULL } }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -92,6 +101,18 @@ struct attribute_group {
 #define __ATTR_IGNORE_LOCKDEP	__ATTR
 #endif
 
+#define __ATTRIBUTE_GROUPS(_name)				\
+static const struct attribute_group *_name##_groups[] = {	\
+	&_name##_group,						\
+	NULL,							\
+}
+
+#define ATTRIBUTE_GROUPS(_name)					\
+static const struct attribute_group _name##_group = {		\
+	.attrs = _name##_attrs,					\
+};								\
+__ATTRIBUTE_GROUPS(_name)
+
 #define attr_name(_attr) (_attr).attr.name
 
 struct file;
@@ -121,6 +142,36 @@ struct bin_attribute {
  */
 #define sysfs_bin_attr_init(bin_attr) sysfs_attr_init(&(bin_attr)->attr)
 
+/* macros to create static binary attributes easier */
+#define __BIN_ATTR(_name, _mode, _read, _write, _size) {		\
+	.attr = { .name = __stringify(_name), .mode = _mode },		\
+	.read	= _read,						\
+	.write	= _write,						\
+	.size	= _size,						\
+}
+
+#define __BIN_ATTR_RO(_name, _size) {					\
+	.attr	= { .name = __stringify(_name), .mode = S_IRUGO },	\
+	.read	= _name##_read,						\
+	.size	= _size,						\
+}
+
+#define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name,			\
+				   (S_IWUSR | S_IRUGO), _name##_read,	\
+				   _name##_write)
+
+#define __BIN_ATTR_NULL __ATTR_NULL
+
+#define BIN_ATTR(_name, _mode, _read, _write, _size)			\
+struct bin_attribute bin_attr_##_name = __BIN_ATTR(_name, _mode, _read,	\
+					_write, _size)
+
+#define BIN_ATTR_RO(_name, _size)					\
+struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size)
+
+#define BIN_ATTR_RW(_name, _size)					\
+struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size)
+
 struct sysfs_ops {
 	ssize_t	(*show)(struct kobject *, struct attribute *,char *);
 	ssize_t	(*store)(struct kobject *,struct attribute *,const char *, size_t);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a386a1cbb6e1..55fce47b0095 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -25,6 +25,7 @@
 #ifndef __THERMAL_H__
 #define __THERMAL_H__
 
+#include <linux/of.h>
 #include <linux/idr.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
@@ -143,6 +144,7 @@ struct thermal_cooling_device {
 	int id;
 	char type[THERMAL_NAME_LENGTH];
 	struct device device;
+	struct device_node *np;
 	void *devdata;
 	const struct thermal_cooling_device_ops *ops;
 	bool updated; /* true if the cooling device does not need update */
@@ -172,7 +174,7 @@ struct thermal_zone_device {
 	int emul_temperature;
 	int passive;
 	unsigned int forced_passive;
-	const struct thermal_zone_device_ops *ops;
+	struct thermal_zone_device_ops *ops;
 	const struct thermal_zone_params *tzp;
 	struct thermal_governor *governor;
 	struct list_head thermal_instances;
@@ -214,6 +216,14 @@ struct thermal_bind_params {
 /* Structure to define Thermal Zone parameters */
 struct thermal_zone_params {
 	char governor_name[THERMAL_NAME_LENGTH];
+
+	/*
+	 * a boolean to indicate if the thermal to hwmon sysfs interface
+	 * is required. when no_hwmon == false, a hwmon sysfs interface
+	 * will be created. when no_hwmon == true, nothing will be done
+	 */
+	bool no_hwmon;
+
 	int num_tbps;	/* Number of tbp entries */
 	struct thermal_bind_params *tbp;
 };
@@ -224,8 +234,31 @@ struct thermal_genl_event {
 };
 
 /* Function declarations */
+#ifdef CONFIG_THERMAL_OF
+struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int id,
+				void *data, int (*get_temp)(void *, long *),
+				int (*get_trend)(void *, long *));
+void thermal_zone_of_sensor_unregister(struct device *dev,
+				       struct thermal_zone_device *tz);
+#else
+static inline struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int id,
+				void *data, int (*get_temp)(void *, long *),
+				int (*get_trend)(void *, long *))
+{
+	return NULL;
+}
+
+static inline
+void thermal_zone_of_sensor_unregister(struct device *dev,
+				       struct thermal_zone_device *tz)
+{
+}
+
+#endif
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
-		void *, const struct thermal_zone_device_ops *,
+		void *, struct thermal_zone_device_ops *,
 		const struct thermal_zone_params *, int, int);
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
@@ -238,6 +271,9 @@ void thermal_zone_device_update(struct thermal_zone_device *);
 
 struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
 		const struct thermal_cooling_device_ops *);
+struct thermal_cooling_device *
+thermal_of_cooling_device_register(struct device_node *np, char *, void *,
+				   const struct thermal_cooling_device_ops *);
 void thermal_cooling_device_unregister(struct thermal_cooling_device *);
 struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name);
 int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp);
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e7e04736802f..4ae6f32c8033 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -107,6 +107,8 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define set_need_resched()	set_thread_flag(TIF_NEED_RESCHED)
 #define clear_need_resched()	clear_thread_flag(TIF_NEED_RESCHED)
 
+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*
  * An arch can define its own version of set_restore_sigmask() to get the
diff --git a/include/linux/timex.h b/include/linux/timex.h
index b3726e61368e..dd3edd7dfc94 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -141,6 +141,7 @@ extern int do_adjtimex(struct timex *);
 extern void hardpps(const struct timespec *, const struct timespec *);
 
 int read_current_timer(unsigned long *timer_val);
+void ntp_notify_cmos_timer(void);
 
 /* The clock frequency of the i8253/i8254 PIT */
 #define PIT_TICK_RATE 1193182ul
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index f8e084d0fc77..ba605015c4d8 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@ struct tp_module {
 	unsigned int num_tracepoints;
 	struct tracepoint * const *tracepoints_ptrs;
 };
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+	return false;
+}
 #endif /* CONFIG_MODULES */
 
 struct tracepoint_iter {
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 52f944dfe2fd..49587dc22f5d 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -30,4 +30,7 @@
    descriptor */
 #define USB_QUIRK_DELAY_INIT		0x00000040
 
+/* device generates spurious wakeup, ignore remote wakeup capability */
+#define USB_QUIRK_IGNORE_REMOTE_WAKEUP	0x00000200
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index f18d64129f99..123b21bef1b4 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -30,7 +30,7 @@ struct usbnet {
 	struct driver_info	*driver_info;
 	const char		*driver_name;
 	void			*driver_priv;
-	wait_queue_head_t	*wait;
+	wait_queue_head_t	wait;
 	struct mutex		phy_mutex;
 	unsigned char		suspend_count;
 	unsigned char		pkt_cnt, pkt_err;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index bf99cd01be20..630356866030 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -66,7 +66,9 @@
 	US_FLAG(INITIAL_READ10,	0x00100000)			\
 		/* Initial READ(10) (and others) must be retried */	\
 	US_FLAG(WRITE_CACHE,	0x00200000)			\
-		/* Write Cache status is not available */
+		/* Write Cache status is not available */	\
+	US_FLAG(NEEDS_CAP16,	0x00400000)
+		/* cannot handle READ_CAPACITY_10 */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 14105c26a836..a37081cf59da 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -17,6 +17,10 @@ struct uid_gid_map {	/* 64 bytes -- 1 cache line */
 	} extent[UID_GID_MAP_MAX_EXTENTS];
 };
 
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -27,6 +31,7 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	unsigned long		flags;
 	bool			may_mount_sysfs;
 	bool			may_mount_proc;
 };
@@ -59,6 +64,9 @@ extern struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
+extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -83,6 +91,10 @@ static inline void put_user_ns(struct user_namespace *ns)
 {
 }
 
+static inline bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	return true;
+}
 #endif
 
 void update_mnt_policy(struct user_namespace *userns);
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
index ea7168a68081..c1191ab4cb98 100644
--- a/include/linux/vexpress.h
+++ b/include/linux/vexpress.h
@@ -68,7 +68,8 @@
  */
 struct vexpress_config_bridge_info {
 	const char *name;
-	void *(*func_get)(struct device *dev, struct device_node *node);
+	void *(*func_get)(struct device *dev, struct device_node *node,
+			  const char *id);
 	void (*func_put)(void *func);
 	int (*func_exec)(void *func, int offset, bool write, u32 *data);
 };
@@ -87,12 +88,17 @@ void vexpress_config_complete(struct vexpress_config_bridge *bridge,
 
 struct vexpress_config_func;
 
-struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
-		struct device_node *node);
+struct vexpress_config_func *__vexpress_config_func_get(
+		struct vexpress_config_bridge *bridge,
+		struct device *dev,
+		struct device_node *node,
+		const char *id);
+#define vexpress_config_func_get(bridge, id) \
+		__vexpress_config_func_get(bridge, NULL, NULL, id)
 #define vexpress_config_func_get_by_dev(dev) \
-		__vexpress_config_func_get(dev, NULL)
+		__vexpress_config_func_get(NULL, dev, NULL, NULL)
 #define vexpress_config_func_get_by_node(node) \
-		__vexpress_config_func_get(NULL, node)
+		__vexpress_config_func_get(NULL, NULL, node, NULL)
 void vexpress_config_func_put(struct vexpress_config_func *func);
 
 /* Both may sleep! */
@@ -120,7 +126,53 @@ void vexpress_sysreg_of_early_init(void);
 struct clk *vexpress_osc_setup(struct device *dev);
 void vexpress_osc_of_setup(struct device_node *node);
 
+struct clk *vexpress_clk_register_spc(const char *name, int cluster_id);
+void vexpress_clk_of_register_spc(void);
+
 void vexpress_clk_init(void __iomem *sp810_base);
 void vexpress_clk_of_init(void);
 
+/* SPC */
+
+#define	VEXPRESS_SPC_WAKE_INTR_IRQ(cluster, cpu) \
+			(1 << (4 * (cluster) + (cpu)))
+#define	VEXPRESS_SPC_WAKE_INTR_FIQ(cluster, cpu) \
+			(1 << (7 * (cluster) + (cpu)))
+#define	VEXPRESS_SPC_WAKE_INTR_SWDOG		(1 << 10)
+#define	VEXPRESS_SPC_WAKE_INTR_GTIMER		(1 << 11)
+#define	VEXPRESS_SPC_WAKE_INTR_MASK		0xFFF
+
+#ifdef CONFIG_VEXPRESS_SPC
+extern bool vexpress_spc_check_loaded(void);
+extern void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster, bool set);
+extern void vexpress_spc_set_global_wakeup_intr(bool set);
+extern int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr);
+extern int vexpress_spc_get_performance(u32 cluster, u32 *freq);
+extern int vexpress_spc_set_performance(u32 cluster, u32 freq);
+extern void vexpress_spc_write_resume_reg(u32 cluster, u32 cpu, u32 addr);
+extern int vexpress_spc_get_nb_cpus(u32 cluster);
+extern void vexpress_spc_powerdown_enable(u32 cluster, bool enable);
+#else
+static inline bool vexpress_spc_check_loaded(void) { return false; }
+static inline void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster,
+						   bool set) { }
+static inline void vexpress_spc_set_global_wakeup_intr(bool set) { }
+static inline int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr)
+{
+	return -ENODEV;
+}
+static inline int vexpress_spc_get_performance(u32 cluster, u32 *freq)
+{
+	return -ENODEV;
+}
+static inline int vexpress_spc_set_performance(u32 cluster, u32 freq)
+{
+	return -ENODEV;
+}
+static inline void vexpress_spc_write_resume_reg(u32 cluster,
+						 u32 cpu, u32 addr) { }
+static inline int vexpress_spc_get_nb_cpus(u32 cluster) { return -ENODEV; }
+static inline void vexpress_spc_powerdown_enable(u32 cluster, bool enable) { }
+#endif
+
 #endif
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index bd6cf61142be..8c0f6cb2a603 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -39,6 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
+		NUMA_HUGE_PTE_UPDATES,
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index c586679b6fef..2d4e3d793f79 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -142,9 +142,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 	return x;
 }
 
-extern unsigned long global_reclaimable_pages(void);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
-
 #ifdef CONFIG_NUMA
 /*
  * Determine the per node value of a stat item. This function
@@ -198,7 +195,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item);
 extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
-void refresh_cpu_vm_stats(int);
+bool refresh_cpu_vm_stats(int);
 void refresh_zone_stat_thresholds(void);
 
 void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 623488fdc1f5..ef4df5b86e85 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -303,6 +303,33 @@ enum {
 	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
 	WQ_SYSFS		= 1 << 6, /* visible in sysfs, see wq_sysfs_register() */
 
+	/*
+	 * Per-cpu workqueues are generally preferred because they tend to
+	 * show better performance thanks to cache locality.  Per-cpu
+	 * workqueues exclude the scheduler from choosing the CPU to
+	 * execute the worker threads, which has an unfortunate side effect
+	 * of increasing power consumption.
+	 *
+	 * The scheduler considers a CPU idle if it doesn't have any task
+	 * to execute and tries to keep idle cores idle to conserve power;
+	 * however, for example, a per-cpu work item scheduled from an
+	 * interrupt handler on an idle CPU will force the scheduler to
+	 * excute the work item on that CPU breaking the idleness, which in
+	 * turn may lead to more scheduling choices which are sub-optimal
+	 * in terms of power consumption.
+	 *
+	 * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default
+	 * but become unbound if workqueue.power_efficient kernel param is
+	 * specified.  Per-cpu workqueues which are identified to
+	 * contribute significantly to power-consumption are identified and
+	 * marked with this flag and enabling the power_efficient mode
+	 * leads to noticeable power saving at the cost of small
+	 * performance disadvantage.
+	 *
+	 * http://thread.gmane.org/gmane.linux.kernel/1480396
+	 */
+	WQ_POWER_EFFICIENT	= 1 << 7,
+
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 
@@ -333,11 +360,19 @@ enum {
  *
  * system_freezable_wq is equivalent to system_wq except that it's
  * freezable.
+ *
+ * *_power_efficient_wq are inclined towards saving power and converted
+ * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
+ * they are same as their non-power-efficient counterparts - e.g.
+ * system_power_efficient_wq is identical to system_wq if
+ * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
+extern struct workqueue_struct *system_power_efficient_wq;
+extern struct workqueue_struct *system_freezable_power_efficient_wq;
 
 static inline struct workqueue_struct * __deprecated __system_nrt_wq(void)
 {
@@ -414,7 +449,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 #define create_freezable_workqueue(name)				\
 	alloc_workqueue((name), WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
 #define create_singlethread_workqueue(name)				\
-	alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
+	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index d88a098d1aff..2cc4e0df9c5d 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -318,6 +318,9 @@ struct v4l2_fh;
  * @done_wq:	waitqueue for processes waiting for buffers ready to be dequeued
  * @alloc_ctx:	memory type/allocator-specific contexts for each plane
  * @streaming:	current streaming state
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ *		buffers. Only set for capture queues if qbuf has not yet been
+ *		called since poll() needs to return POLLERR in that situation.
  * @fileio:	file io emulator internal data, used only if emulator is active
  */
 struct vb2_queue {
@@ -350,6 +353,7 @@ struct vb2_queue {
 	unsigned int			plane_sizes[VIDEO_MAX_PLANES];
 
 	unsigned int			streaming:1;
+	unsigned int			waiting_for_buffers:1;
 
 	struct vb2_fileio_data		*fileio;
 };
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 01b1a1ad77d2..25100687babb 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -73,6 +73,10 @@ extern int			ipv6_chk_home_addr(struct net *net,
 						   const struct in6_addr *addr);
 #endif
 
+bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
+				   const unsigned int prefix_len,
+				   struct net_device *dev);
+
 extern int			ipv6_chk_prefix(const struct in6_addr *addr,
 						struct net_device *dev);
 
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e0512aaef4b8..0ef00066dae8 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -104,6 +104,7 @@ enum {
 enum {
 	HCI_SETUP,
 	HCI_AUTO_OFF,
+	HCI_RFKILLED,
 	HCI_MGMT,
 	HCI_PAIRABLE,
 	HCI_SERVICE_CACHE,
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index a7a683e30b64..a8c2ef6d3b93 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -290,6 +290,7 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	unsigned char err_offset = 0;
 	u8 opt_len = opt[1];
 	u8 opt_iter;
+	u8 tag_len;
 
 	if (opt_len < 8) {
 		err_offset = 1;
@@ -302,11 +303,12 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
-		if (opt[opt_iter + 1] > (opt_len - opt_iter)) {
+		tag_len = opt[opt_iter + 1];
+		if ((tag_len == 0) || (opt[opt_iter + 1] > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;
 			goto out;
 		}
-		opt_iter += opt[opt_iter + 1];
+		opt_iter += tag_len;
 	}
 
 out:
diff --git a/include/net/dst.h b/include/net/dst.h
index 1f8fd109e225..e0c97f5a57cf 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -477,10 +477,22 @@ static inline struct dst_entry *xfrm_lookup(struct net *net,
 {
 	return dst_orig;
 } 
+
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
+{
+	return NULL;
+}
+
 #else
 extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 				     const struct flowi *fl, struct sock *sk,
 				     int flags);
+
+/* skb attached with this dst needs transformation if dst->xfrm is valid */
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
+{
+	return dst->xfrm;
+}
 #endif
 
 #endif /* _NET_DST_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index de2c78529afa..0a8f6f961baa 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -62,6 +62,7 @@ struct inet_connection_sock_af_ops {
 	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
 	int	    (*bind_conflict)(const struct sock *sk,
 				     const struct inet_bind_bucket *tb, bool relax);
+	void	    (*mtu_reduced)(struct sock *sk);
 };
 
 /** inet_connection_sock - INET connection oriented sock
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 53f464d7cddc..bb06fd26a7bd 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@ struct inet_peer {
 		struct rcu_head     gc_rcu;
 	};
 	/*
-	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count
+	 * Once inet_peer is queued for deletion (refcnt == -1), following field
+	 * is not available: rid
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
-			atomic_t			ip_id_count;	/* IP ID for the next packet */
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
@@ -166,7 +165,7 @@ extern void inetpeer_invalidate_tree(struct inet_peer_base *);
 extern void inetpeer_invalidate_family(int family);
 
 /*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
  * tcp_ts_stamp if no refcount is taken on inet_peer
  */
 static inline void inet_peer_refcheck(const struct inet_peer *p)
@@ -174,20 +173,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p)
 	WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
 }
 
-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
-	int old, new;
-	more++;
-	inet_peer_refcheck(p);
-	do {
-		old = atomic_read(&p->ip_id_count);
-		new = old + more;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&p->ip_id_count, old, new) != old);
-	return new;
-}
-
 #endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index a68f838a132c..8695359982d1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -252,32 +252,33 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
 		 !(dst_metric_locked(dst, RTAX_MTU)));
 }
 
-extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);
 
-static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
 {
-	if (iph->frag_off & htons(IP_DF)) {
+	struct iphdr *iph = ip_hdr(skb);
+
+	if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
 		/* This is only to work around buggy Windows95/2000
 		 * VJ compression implementations.  If the ID field
 		 * does not change, they drop every other packet in
 		 * a TCP stream using header compression.
 		 */
-		iph->id = (sk && inet_sk(sk)->inet_daddr) ?
-					htons(inet_sk(sk)->inet_id++) : 0;
-	} else
-		__ip_select_ident(iph, dst, 0);
-}
-
-static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more)
-{
-	if (iph->frag_off & htons(IP_DF)) {
 		if (sk && inet_sk(sk)->inet_daddr) {
 			iph->id = htons(inet_sk(sk)->inet_id);
-			inet_sk(sk)->inet_id += 1 + more;
-		} else
+			inet_sk(sk)->inet_id += segs;
+		} else {
 			iph->id = 0;
-	} else
-		__ip_select_ident(iph, dst, more);
+		}
+	} else {
+		__ip_select_ident(iph, segs);
+	}
+}
+
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
+{
+	ip_select_ident_segs(skb, sk, 1);
 }
 
 /*
@@ -450,7 +451,7 @@ extern int	compat_ip_getsockopt(struct sock *sk, int level,
 			int optname, char __user *optval, int __user *optlen);
 extern int	ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *));
 
-extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
+extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len);
 extern void	ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
 			      __be16 port, u32 info, u8 *payload);
 extern void	ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 2a601e7da1bf..665e0cee59bd 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -165,6 +165,7 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 static inline void rt6_clean_expires(struct rt6_info *rt)
 {
 	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.expires = 0;
 }
 
 static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 260f83f16bcf..8d977b343647 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,11 @@ struct route_info {
 #define RT6_LOOKUP_F_SRCPREF_PUBLIC	0x00000010
 #define RT6_LOOKUP_F_SRCPREF_COA	0x00000020
 
+/* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
+ * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
+ */
+#define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr))
+
 /*
  * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate
  * between IPV6_ADDR_PREFERENCES socket option values
@@ -194,11 +199,9 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
 }
 
-static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, struct in6_addr *dest)
+static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
 {
-	if (rt->rt6i_flags & RTF_GATEWAY)
-		return &rt->rt6i_gateway;
-	return dest;
+	return &rt->rt6i_gateway;
 }
 
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a9942e1faefb..7ac7f91f0242 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -113,7 +113,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 key);
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
-		  const struct tnl_ptk_info *tpi, bool log_ecn_error);
+		  const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 			 struct ip_tunnel_parm *p);
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4c062ccff9aa..f0c13a386bf3 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -109,7 +109,6 @@ extern int ip_vs_conn_tab_size;
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
 			   IPv6 where L4 Transport Header starts */
-	__u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;
@@ -117,34 +116,12 @@ struct ip_vs_iphdr {
 	union nf_inet_addr daddr;
 };
 
-/* Dependency to module: nf_defrag_ipv6 */
-#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return skb->nfct_reasm;
-}
-static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
-				      int len, void *buffer,
-				      const struct ip_vs_iphdr *ipvsh)
-{
-	if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
-		return skb_header_pointer(skb_nfct_reasm(skb),
-					  ipvsh->thoff_reasm, len, buffer);
-
-	return skb_header_pointer(skb, offset, len, buffer);
-}
-#else
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return NULL;
-}
 static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
 				      int len, void *buffer,
 				      const struct ip_vs_iphdr *ipvsh)
 {
 	return skb_header_pointer(skb, offset, len, buffer);
 }
-#endif
 
 static inline void
 ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
@@ -171,19 +148,12 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
 			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
-		/* ipv6_find_hdr() updates len, flags, thoff_reasm */
-		iphdr->thoff_reasm = 0;
+		/* ipv6_find_hdr() updates len, flags */
 		iphdr->len	 = 0;
 		iphdr->flags	 = 0;
 		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
 						 &iphdr->fragoffs,
 						 &iphdr->flags);
-		/* get proto from re-assembled packet and it's offset */
-		if (skb_nfct_reasm(skb))
-			iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
-							&iphdr->thoff_reasm,
-							-1, NULL, NULL);
-
 	} else
 #endif
 	{
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0810aa57c780..087370ff05f1 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -530,14 +530,19 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a)
 }
 
 /* more secured version of ipv6_addr_hash() */
-static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval)
 {
 	u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
 
 	return jhash_3words(v,
 			    (__force u32)a->s6_addr32[2],
 			    (__force u32)a->s6_addr32[3],
-			    ipv6_hash_secret);
+			    initval);
+}
+
+static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+{
+	return __ipv6_addr_jhash(a, ipv6_hash_secret);
 }
 
 static inline bool ipv6_addr_loopback(const struct in6_addr *a)
@@ -649,8 +654,6 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-extern void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
-
 /*
  *	Header manipulation
  */
@@ -793,8 +796,10 @@ extern int			compat_ipv6_getsockopt(struct sock *sk,
 extern int			ip6_datagram_connect(struct sock *sk, 
 						     struct sockaddr *addr, int addr_len);
 
-extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
-extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
+extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
+						int *addr_len);
+extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+						 int *addr_len);
 extern void			ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 						u32 info, u8 *payload);
 extern void			ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index fd79c9a1779d..17920d847b40 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -6,10 +6,7 @@ extern void nf_defrag_ipv6_enable(void);
 extern int nf_ct_frag6_init(void);
 extern void nf_ct_frag6_cleanup(void);
 extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			       struct net_device *in,
-			       struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
+extern void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;
 
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 977bc8a46444..86dd7dd3d617 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -41,8 +41,8 @@ enum nf_ct_ext_id {
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
 	struct rcu_head rcu;
-	u8 offset[NF_CT_EXT_NUM];
-	u8 len;
+	u16 offset[NF_CT_EXT_NUM];
+	u16 len;
 	char data[0];
 };
 
@@ -80,7 +80,7 @@ static inline void nf_ct_ext_destroy(struct nf_conn *ct)
 static inline void nf_ct_ext_free(struct nf_conn *ct)
 {
 	if (ct->ext)
-		kfree(ct->ext);
+		kfree_rcu(ct->ext, rcu);
 }
 
 /* Add this type, returns pointer to data or NULL. */
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 35247271e557..5f39c1cc0766 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -118,7 +118,7 @@ typedef enum {
  * analysis of the state functions, but in reality just taken from
  * thin air in the hopes othat we don't trigger a kernel panic.
  */
-#define SCTP_MAX_NUM_COMMANDS 14
+#define SCTP_MAX_NUM_COMMANDS 20
 
 typedef union {
 	__s32 i32;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index cd89510eab2a..845ab6decc45 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -540,6 +540,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat
 	asoc->pmtu_pending = 0;
 }
 
+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+	return !list_empty(&chunk->list);
+}
+
 /* Walk through a list of TLV parameters.  Don't trust the
  * individual parameter lengths and instead depend on
  * the chunk length to indicate when to stop.  Make sure
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2a82d1384706..c4c9458f37cd 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -255,9 +255,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *,
 					      int, __be16);
 struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
 					     union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp);
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf);
 int sctp_process_asconf_ack(struct sctp_association *asoc,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 1bd4c4144fe8..da6b9a01ff75 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1252,6 +1252,7 @@ struct sctp_endpoint {
 	/* SCTP-AUTH: endpoint shared keys */
 	struct list_head endpoint_shared_keys;
 	__u16 active_key_id;
+	__u8  auth_enable;
 };
 
 /* Recover the outter endpoint structure. */
@@ -1280,7 +1281,8 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *,
 int sctp_has_association(struct net *net, const union sctp_addr *laddr,
 			 const union sctp_addr *paddr);
 
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+		     const struct sctp_association *asoc,
 		     sctp_cid_t, sctp_init_chunk_t *peer_init,
 		     struct sctp_chunk *chunk, struct sctp_chunk **err_chunk);
 int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 6ca975bebd37..b1c3d1c63c4e 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,9 +3,6 @@
 
 #include <linux/types.h>
 
-extern void net_secret_init(void);
-extern __u32 secure_ip_id(__be32 daddr);
-extern __u32 secure_ipv6_id(const __be32 daddr[4]);
 extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 				      __be16 dport);
diff --git a/include/net/sock.h b/include/net/sock.h
index 66772cf8c3c5..c0aad07160ef 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -230,6 +230,7 @@ struct cg_proto;
   *	@sk_wmem_queued: persistent queue size
   *	@sk_forward_alloc: space allocated forward
   *	@sk_allocation: allocation mode
+  *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
   *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
@@ -355,6 +356,7 @@ struct sock {
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
 	gfp_t			sk_allocation;
+	u32			sk_pacing_rate; /* bytes per second */
 	netdev_features_t	sk_route_caps;
 	netdev_features_t	sk_route_nocaps;
 	int			sk_gso_type;
@@ -930,7 +932,6 @@ struct proto {
 						struct sk_buff *skb);
 
 	void		(*release_cb)(struct sock *sk);
-	void		(*mtu_reduced)(struct sock *sk);
 
 	/* Keeping track of sk's, looking them up, and port selection methods. */
 	void			(*hash)(struct sock *sk);
@@ -1435,6 +1436,11 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
  */
 #define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
 
+static inline void sock_release_ownership(struct sock *sk)
+{
+	sk->sk_lock.owned = 0;
+}
+
 /*
  * Macro so as to not evaluate some arguments when
  * lockdep is not enabled.
@@ -1720,8 +1726,8 @@ sk_dst_get(struct sock *sk)
 
 	rcu_read_lock();
 	dst = rcu_dereference(sk->sk_dst_cache);
-	if (dst)
-		dst_hold(dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	rcu_read_unlock();
 	return dst;
 }
@@ -1760,9 +1766,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 static inline void
 sk_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_set(sk, dst);
-	spin_unlock(&sk->sk_dst_lock);
+	struct dst_entry *old_dst;
+
+	sk_tx_queue_clear(sk);
+	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	dst_release(old_dst);
 }
 
 static inline void
@@ -1774,9 +1782,7 @@ __sk_dst_reset(struct sock *sk)
 static inline void
 sk_dst_reset(struct sock *sk)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_reset(sk);
-	spin_unlock(&sk->sk_dst_lock);
+	sk_dst_set(sk, NULL);
 }
 
 extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
@@ -2241,6 +2247,11 @@ extern void sock_enable_timestamp(struct sock *sk, int flag);
 extern int sock_get_timestamp(struct sock *, struct timeval __user *);
 extern int sock_get_timestampns(struct sock *, struct timespec __user *);
 
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
+
 /*
  *	Enable debug/info messages
  */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5bba80fbd1d9..29a1a63cd303 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -287,6 +287,7 @@ extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
 extern int sysctl_tcp_limit_output_bytes;
 extern int sysctl_tcp_challenge_ack_limit;
+extern int sysctl_tcp_min_tso_segs;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -459,6 +460,7 @@ extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
  */
 
 extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
+void tcp_v4_mtu_reduced(struct sock *sk);
 extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 extern struct sock * tcp_create_openreq_child(struct sock *sk,
 					      struct request_sock *req,
@@ -1307,7 +1309,8 @@ struct tcp_fastopen_request {
 	/* Fast Open cookie. Size 0 means a cookie request */
 	struct tcp_fastopen_cookie	cookie;
 	struct msghdr			*data;  /* data in MSG_FASTOPEN */
-	u16				copied;	/* queued in tcp_connect() */
+	size_t				size;
+	int				copied;	/* queued in tcp_connect() */
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
 
diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h
index a5f9b960dfc8..6ca3265a4dca 100644
--- a/include/scsi/osd_ore.h
+++ b/include/scsi/osd_ore.h
@@ -102,6 +102,7 @@ struct ore_striping_info {
 	unsigned unit_off;
 	unsigned cur_pg;
 	unsigned cur_comp;
+	unsigned maxdevUnits;
 };
 
 struct ore_io_state;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index cc645876d147..cc92ef3df62e 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -248,7 +248,7 @@ struct scsi_target {
 	struct list_head	siblings;
 	struct list_head	devices;
 	struct device		dev;
-	unsigned int		reap_ref; /* protected by the host lock */
+	struct kref		reap_ref; /* last put renders target invisible */
 	unsigned int		channel;
 	unsigned int		id; /* target id ... replace
 				     * scsi_device.id eventually */
@@ -272,7 +272,6 @@ struct scsi_target {
 #define SCSI_DEFAULT_TARGET_BLOCKED	3
 
 	char			scsi_level;
-	struct execute_work	ew;
 	enum scsi_target_state	state;
 	void 			*hostdata; /* available to low-level driver */
 	unsigned long		starget_data[0]; /* for the transport */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 755243572219..50769a72166b 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -475,6 +475,9 @@ struct scsi_host_template {
 	 */
 	unsigned ordered_tag:1;
 
+	/* True if the controller does not support WRITE SAME */
+	unsigned no_write_same:1;
+
 	/*
 	 * Countdown for host blocking with no commands outstanding.
 	 */
@@ -674,6 +677,9 @@ struct Scsi_Host {
 	/* Don't resume host in EH */
 	unsigned eh_noresume:1;
 
+	/* The controller does not support WRITE SAME */
+	unsigned no_write_same:1;
+
 	/*
 	 * Optional work queue to be utilized by the transport
 	 */
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 9031a26249b5..ae6c3b8ed2f5 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -171,4 +171,13 @@ static inline void snd_compr_fragment_elapsed(struct snd_compr_stream *stream)
 	wake_up(&stream->runtime->sleep);
 }
 
+static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
+{
+	if (snd_BUG_ON(!stream))
+		return;
+
+	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	wake_up(&stream->runtime->sleep);
+}
+
 #endif
diff --git a/include/sound/core.h b/include/sound/core.h
index 5bfe5136441c..97cd9c3592f7 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -120,6 +120,8 @@ struct snd_card {
 	int user_ctl_count;		/* count of all user controls */
 	struct list_head controls;	/* all controls for this card */
 	struct list_head ctl_files;	/* active control files */
+	struct mutex user_ctl_lock;	/* protects user controls against
+					   concurrent access */
 
 	struct snd_info_entry *proc_root;	/* root for soundcard specific files */
 	struct snd_info_entry *proc_id;	/* the card id */
diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index cf15b8213df7..54aff2d73150 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -103,7 +103,7 @@ static inline dma_addr_t snd_sgbuf_get_addr(struct snd_dma_buffer *dmab,
 {
 	struct snd_sg_buf *sgbuf = dmab->private_data;
 	dma_addr_t addr = sgbuf->table[offset >> PAGE_SHIFT].addr;
-	addr &= PAGE_MASK;
+	addr &= ~((dma_addr_t)PAGE_SIZE - 1);
 	return addr + offset % PAGE_SIZE;
 }
 
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index 04598f1efd77..a2e15cad76a0 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -11,6 +11,7 @@
 #ifndef __LINUX_SND_SOC_DPCM_H
 #define __LINUX_SND_SOC_DPCM_H
 
+#include <linux/slab.h>
 #include <linux/list.h>
 #include <sound/pcm.h>
 
@@ -135,4 +136,25 @@ int soc_dpcm_be_digital_mute(struct snd_soc_pcm_runtime *fe, int mute);
 int soc_dpcm_debugfs_add(struct snd_soc_pcm_runtime *rtd);
 int soc_dpcm_runtime_update(struct snd_soc_dapm_widget *);
 
+int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
+	int stream, struct snd_soc_dapm_widget_list **list_);
+int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
+	int stream, struct snd_soc_dapm_widget_list **list, int new);
+int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream);
+void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream);
+void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int tream);
+int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream, int cmd);
+int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
+	int event);
+
+static inline void dpcm_path_put(struct snd_soc_dapm_widget_list **list)
+{
+	kfree(*list);
+}
+
+
 #endif
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 85c15226103b..5bbdc653a826 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1063,6 +1063,7 @@ struct snd_soc_pcm_runtime {
 
 	/* Dynamic PCM BE runtime data */
 	struct snd_soc_dpcm_runtime dpcm[2];
+	int fe_compr;
 
 	long pmdown_time;
 	unsigned char pop_wait:1;
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index c5aade523863..4a5f00e2e6cd 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -11,6 +11,7 @@ struct iscsit_transport {
 	int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
 	int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
 	void (*iscsit_free_np)(struct iscsi_np *);
+	void (*iscsit_wait_conn)(struct iscsi_conn *);
 	void (*iscsit_free_conn)(struct iscsi_conn *);
 	struct iscsi_cmd *(*iscsit_alloc_cmd)(struct iscsi_conn *, gfp_t);
 	int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index ffa2696d64dc..a63529ab9fd7 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -50,6 +50,7 @@ int	transport_subsystem_register(struct se_subsystem_api *);
 void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
+void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
 
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 4ea4f985f394..7d99c0b5b789 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -614,6 +614,7 @@ struct se_dev_attrib {
 	u32		unmap_granularity;
 	u32		unmap_granularity_alignment;
 	u32		max_write_same_len;
+	u32		max_bytes_per_io;
 	struct se_device *da_dev;
 	struct config_group da_group;
 };
diff --git a/include/trace/events/arm-ipi.h b/include/trace/events/arm-ipi.h
new file mode 100644
index 000000000000..5d3bd21827be
--- /dev/null
+++ b/include/trace/events/arm-ipi.h
@@ -0,0 +1,100 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM arm-ipi
+
+#if !defined(_TRACE_ARM_IPI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM_IPI_H
+
+#include <linux/tracepoint.h>
+
+#define show_arm_ipi_name(val)				\
+	__print_symbolic(val,				\
+			 { 0, "IPI_WAKEUP" },		\
+			 { 1, "IPI_TIMER" },		\
+			 { 2, "IPI_RESCHEDULE" },		\
+			 { 3, "IPI_CALL_FUNC" },		\
+			 { 4, "IPI_CALL_FUNC_SINGLE" },		\
+			 { 5, "IPI_CPU_STOP" },	\
+			 { 6, "IPI_COMPLETION" },		\
+			 { 7, "IPI_CPU_BACKTRACE" })
+
+DECLARE_EVENT_CLASS(arm_ipi,
+
+	TP_PROTO(unsigned int ipi_nr),
+
+	TP_ARGS(ipi_nr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	ipi	)
+	),
+
+	TP_fast_assign(
+		__entry->ipi = ipi_nr;
+	),
+
+	TP_printk("ipi=%u [action=%s]", __entry->ipi,
+		show_arm_ipi_name(__entry->ipi))
+);
+
+/**
+ * arm_ipi_entry - called in the arm-generic ipi handler immediately before
+ *                 entering ipi-type handler
+ * @ipi_nr:  ipi number
+ *
+ * When used in combination with the arm_ipi_exit tracepoint
+ * we can determine the ipi handler runtine.
+ */
+DEFINE_EVENT(arm_ipi, arm_ipi_entry,
+
+	TP_PROTO(unsigned int ipi_nr),
+
+	TP_ARGS(ipi_nr)
+);
+
+/**
+ * arm_ipi_exit - called in the arm-generic ipi handler immediately
+ *                after the ipi-type handler returns
+ * @ipi_nr:  ipi number
+ *
+ * When used in combination with the arm_ipi_entry tracepoint
+ * we can determine the ipi handler runtine.
+ */
+DEFINE_EVENT(arm_ipi, arm_ipi_exit,
+
+	TP_PROTO(unsigned int ipi_nr),
+
+	TP_ARGS(ipi_nr)
+);
+
+/**
+ * arm_ipi_send - called as the ipi target mask is built, immediately
+ *                before the register is written
+ * @ipi_nr:  ipi number
+ * @dest:    cpu to send to
+ *
+ * When used in combination with the arm_ipi_entry tracepoint
+ * we can determine the ipi raise to run latency.
+ */
+TRACE_EVENT(arm_ipi_send,
+
+	TP_PROTO(unsigned int ipi_nr, int dest),
+
+	TP_ARGS(ipi_nr, dest),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	ipi	)
+		__field(	int			,	dest )
+	),
+
+	TP_fast_assign(
+		__entry->ipi = ipi_nr;
+		__entry->dest = dest;
+	),
+
+	TP_printk("dest=%d ipi=%u [action=%s]", __entry->dest,
+			__entry->ipi, show_arm_ipi_name(__entry->ipi))
+);
+
+#endif /*  _TRACE_ARM_IPI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 60ae7c3db912..2e96e2bb1529 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -132,6 +132,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * block_rq_complete - block IO operation completed by device driver
  * @q: queue containing the block operation request
  * @rq: block operations request
+ * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
  * of operation request has been completed by the device driver.  If
@@ -139,11 +140,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * do for the request. If @rq->bio is non-NULL then there is
  * additional work required to complete the request.
  */
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request_queue *q, struct request *rq,
+		 unsigned int nr_bytes),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(q, rq, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
 );
 
 DECLARE_EVENT_CLASS(block_rq,
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 161932737416..ca298c7157ae 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -78,7 +78,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
diff --git a/include/trace/events/power_cpu_migrate.h b/include/trace/events/power_cpu_migrate.h
new file mode 100644
index 000000000000..f76dd4de625e
--- /dev/null
+++ b/include/trace/events/power_cpu_migrate.h
@@ -0,0 +1,67 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_CPU_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_CPU_MIGRATE_H
+
+#include <linux/tracepoint.h>
+
+#define __cpu_migrate_proto			\
+	TP_PROTO(u64 timestamp,			\
+		 u32 cpu_hwid)
+#define __cpu_migrate_args			\
+	TP_ARGS(timestamp,			\
+		cpu_hwid)
+
+DECLARE_EVENT_CLASS(cpu_migrate,
+
+	__cpu_migrate_proto,
+	__cpu_migrate_args,
+
+	TP_STRUCT__entry(
+		__field(u64,	timestamp		)
+		__field(u32,	cpu_hwid		)
+	),
+
+	TP_fast_assign(
+		__entry->timestamp = timestamp;
+		__entry->cpu_hwid = cpu_hwid;
+	),
+
+	TP_printk("timestamp=%llu cpu_hwid=0x%08lX",
+		(unsigned long long)__entry->timestamp,
+		(unsigned long)__entry->cpu_hwid
+	)
+);
+
+#define __define_cpu_migrate_event(name)		\
+	DEFINE_EVENT(cpu_migrate, cpu_migrate_##name,	\
+		__cpu_migrate_proto,			\
+		__cpu_migrate_args			\
+	)
+
+__define_cpu_migrate_event(begin);
+__define_cpu_migrate_event(finish);
+__define_cpu_migrate_event(current);
+
+#undef __define_cpu_migrate
+#undef __cpu_migrate_proto
+#undef __cpu_migrate_args
+
+/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
+#ifndef _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+#define _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+
+/*
+ * Set from_phys_cpu and to_phys_cpu to CPU_MIGRATE_ALL_CPUS to indicate
+ * a whole-cluster migration:
+ */
+#define CPU_MIGRATE_ALL_CPUS 0x80000000U
+#endif
+
+#endif /* _TRACE_POWER_CPU_MIGRATE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE power_cpu_migrate
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e5586caff67a..2afcb71857fd 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -430,6 +430,280 @@ TRACE_EVENT(sched_pi_setprio,
 			__entry->oldprio, __entry->newprio)
 );
 
+/*
+ * Tracepoint for showing tracked load contribution.
+ */
+TRACE_EVENT(sched_task_load_contrib,
+
+	TP_PROTO(struct task_struct *tsk, unsigned long load_contrib),
+
+	TP_ARGS(tsk, load_contrib),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(pid_t, pid)
+		__field(unsigned long, load_contrib)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid            = tsk->pid;
+		__entry->load_contrib   = load_contrib;
+	),
+
+	TP_printk("comm=%s pid=%d load_contrib=%lu",
+			__entry->comm, __entry->pid,
+			__entry->load_contrib)
+);
+
+/*
+ * Tracepoint for showing tracked task runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_runnable_ratio,
+
+	TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+	TP_ARGS(tsk, ratio),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(pid_t, pid)
+		__field(unsigned long, ratio)
+	),
+
+	TP_fast_assign(
+	memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid   = tsk->pid;
+		__entry->ratio = ratio;
+	),
+
+	TP_printk("comm=%s pid=%d ratio=%lu",
+			__entry->comm, __entry->pid,
+			__entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_rq_runnable_ratio,
+
+	TP_PROTO(int cpu, unsigned long ratio),
+
+	TP_ARGS(cpu, ratio),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(unsigned long, ratio)
+	),
+
+	TP_fast_assign(
+		__entry->cpu   = cpu;
+		__entry->ratio = ratio;
+	),
+
+	TP_printk("cpu=%d ratio=%lu",
+			__entry->cpu,
+			__entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable load.
+ */
+TRACE_EVENT(sched_rq_runnable_load,
+
+	TP_PROTO(int cpu, u64 load),
+
+	TP_ARGS(cpu, load),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(u64, load)
+	),
+
+	TP_fast_assign(
+		__entry->cpu  = cpu;
+		__entry->load = load;
+	),
+
+	TP_printk("cpu=%d load=%llu",
+			__entry->cpu,
+			__entry->load)
+);
+
+TRACE_EVENT(sched_rq_nr_running,
+
+	TP_PROTO(int cpu, unsigned int nr_running, int nr_iowait),
+
+	TP_ARGS(cpu, nr_running, nr_iowait),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(unsigned int, nr_running)
+		__field(int, nr_iowait)
+	),
+
+	TP_fast_assign(
+		__entry->cpu  = cpu;
+		__entry->nr_running = nr_running;
+		__entry->nr_iowait = nr_iowait;
+	),
+
+	TP_printk("cpu=%d nr_running=%u nr_iowait=%d",
+			__entry->cpu,
+			__entry->nr_running, __entry->nr_iowait)
+);
+
+/*
+ * Tracepoint for showing tracked task cpu usage ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_usage_ratio,
+
+	TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+	TP_ARGS(tsk, ratio),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(pid_t, pid)
+		__field(unsigned long, ratio)
+	),
+
+	TP_fast_assign(
+	memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid   = tsk->pid;
+		__entry->ratio = ratio;
+	),
+
+	TP_printk("comm=%s pid=%d ratio=%lu",
+			__entry->comm, __entry->pid,
+			__entry->ratio)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running tasks.
+ */
+TRACE_EVENT(sched_hmp_migrate_force_running,
+
+	TP_PROTO(struct task_struct *tsk, int running),
+
+	TP_ARGS(tsk, running),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(int, running)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->running = running;
+	),
+
+	TP_printk("running=%d comm=%s",
+		__entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running
+ * tasks when a task is about to go idle.
+ */
+TRACE_EVENT(sched_hmp_migrate_idle_running,
+
+	TP_PROTO(struct task_struct *tsk, int running),
+
+	TP_ARGS(tsk, running),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(int, running)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->running = running;
+	),
+
+	TP_printk("running=%d comm=%s",
+		__entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations.
+ */
+#define HMP_MIGRATE_WAKEUP 0
+#define HMP_MIGRATE_FORCE  1
+#define HMP_MIGRATE_OFFLOAD 2
+#define HMP_MIGRATE_IDLE_PULL 3
+TRACE_EVENT(sched_hmp_migrate,
+
+	TP_PROTO(struct task_struct *tsk, int dest, int force),
+
+	TP_ARGS(tsk, dest, force),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(pid_t, pid)
+		__field(int,  dest)
+		__field(int,  force)
+	),
+
+	TP_fast_assign(
+	memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid   = tsk->pid;
+		__entry->dest  = dest;
+		__entry->force = force;
+	),
+
+	TP_printk("comm=%s pid=%d dest=%d force=%d",
+			__entry->comm, __entry->pid,
+			__entry->dest, __entry->force)
+);
+
+TRACE_EVENT(sched_hmp_offload_abort,
+
+	TP_PROTO(int cpu, int data, char *label),
+
+	TP_ARGS(cpu,data,label),
+
+	TP_STRUCT__entry(
+		__array(char, label, 64)
+		__field(int, cpu)
+		__field(int, data)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->label, label, 64);
+		__entry->cpu   = cpu;
+		__entry->data = data;
+	),
+
+	TP_printk("cpu=%d data=%d label=%63s",
+			__entry->cpu, __entry->data,
+			__entry->label)
+);
+
+TRACE_EVENT(sched_hmp_offload_succeed,
+
+	TP_PROTO(int cpu, int dest_cpu),
+
+	TP_ARGS(cpu,dest_cpu),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(int, dest_cpu)
+	),
+
+	TP_fast_assign(
+		__entry->cpu   = cpu;
+		__entry->dest_cpu = dest_cpu;
+	),
+
+	TP_printk("cpu=%d dest=%d",
+			__entry->cpu,
+			__entry->dest_cpu)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/smp.h b/include/trace/events/smp.h
new file mode 100644
index 000000000000..da0baf27a39a
--- /dev/null
+++ b/include/trace/events/smp.h
@@ -0,0 +1,90 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM smp
+
+#if !defined(_TRACE_SMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SMP_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(smp_call_class,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc),
+
+	TP_STRUCT__entry(
+		__field( void *, func )
+	),
+
+	TP_fast_assign(
+		__entry->func = fnc;
+	),
+
+	TP_printk("func=%pf", __entry->func)
+);
+
+/**
+ * smp_call_func_entry - called in the generic smp-cross-call-handler
+ * 						 immediately before calling the destination
+ * 						 function
+ * @func:  function pointer
+ *
+ * When used in combination with the smp_call_func_exit tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_entry,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_exit - called in the generic smp-cross-call-handler
+ * 						immediately after the destination function
+ * 						returns
+ * @func:  function pointer
+ *
+ * When used in combination with the smp_call_entry tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_exit,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_send - called as destination function is set
+ * 						in the per-cpu storage
+ * @func:  function pointer
+ * @dest:  cpu to send to
+ *
+ * When used in combination with the smp_cross_call_entry tracepoint
+ * we can determine the call-to-run latency.
+ */
+TRACE_EVENT(smp_call_func_send,
+
+	TP_PROTO(void * func, int dest),
+
+	TP_ARGS(func, dest),
+
+	TP_STRUCT__entry(
+		__field(	void * 	,	func )
+		__field(	int		,	dest )
+	),
+
+	TP_fast_assign(
+		__entry->func = func;
+		__entry->dest = dest;
+	),
+
+	TP_printk("dest=%d func=%pf", __entry->dest,
+			__entry->func)
+);
+
+#endif /*  _TRACE_SMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 19edd7facaa1..dbb47418df81 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -299,15 +299,12 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
-		mutex_lock(&event_storage_mutex);			\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), FILTER_OTHER);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
@@ -368,7 +365,8 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 	__data_size += (len) * sizeof(type);
 
 #undef __string
-#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)
+#define __string(item, src) __dynamic_array(char, item,			\
+		    strlen((src) ? (const char *)(src) : "(null)") + 1)
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -498,7 +496,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
 
 #undef __assign_str
 #define __assign_str(dst, src)						\
-	strcpy(__get_str(dst), src);
+	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
 
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 84bc4197e736..0a5b4952aa30 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -4,6 +4,7 @@
 #include <linux/tracepoint.h>
 #include <linux/unistd.h>
 #include <linux/ftrace_event.h>
+#include <linux/thread_info.h>
 
 #include <asm/ptrace.h>
 
@@ -31,4 +32,18 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	else
+		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
 #endif /* _TRACE_SYSCALL_H */
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 090e5331ab7e..cc2e00eac2f1 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -223,6 +223,8 @@ struct drm_mode_get_connector {
 	__u32 connection;
 	__u32 mm_width, mm_height; /**< HxW in millimeters */
 	__u32 subpixel;
+
+	__u32 pad;
 };
 
 #define DRM_MODE_PROP_PENDING	(1<<0)
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 321d4ac5c512..fa8b3adf9ffb 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -979,6 +979,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_RING_WORKING	0x15
 /* SI tile mode array */
 #define RADEON_INFO_SI_TILE_MODE_ARRAY	0x16
+/* query if CP DMA is supported on the compute ring */
+#define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
 
 
 struct drm_radeon_info {
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 6e132a2f7420..86b1f9942d0a 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -103,7 +103,6 @@ struct drm_tegra_submit {
 	__u32 num_waitchks;
 	__u32 waitchk_mask;
 	__u32 timeout;
-	__u32 pad;
 	__u64 syncpts;
 	__u64 cmdbufs;
 	__u64 relocs;
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index 5dda450eb55b..2ec9fbcd06f9 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -6,6 +6,8 @@
 
 #define XT_BPF_MAX_NUM_INSTR	64
 
+struct sk_filter;
+
 struct xt_bpf_info {
 	__u16 bpf_program_num_elem;
 	struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index fb104e51496e..9e59950f55cf 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -425,13 +425,15 @@ struct perf_event_mmap_page {
 	/*
 	 * Control data for the mmap() data buffer.
 	 *
-	 * User-space reading the @data_head value should issue an rmb(), on
-	 * SMP capable platforms, after reading this value -- see
-	 * perf_event_wakeup().
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
 	 *
 	 * When the mapping is PROT_WRITE the @data_tail value should be
-	 * written by userspace to reflect the last read data. In this case
-	 * the kernel will not over-write unread data.
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
 	 */
 	__u64   data_head;		/* head in the data section */
 	__u64	data_tail;		/* user-space written tail */
diff --git a/include/uapi/linux/usb/Kbuild b/include/uapi/linux/usb/Kbuild
index 6cb4ea826834..4cc4d6e7e523 100644
--- a/include/uapi/linux/usb/Kbuild
+++ b/include/uapi/linux/usb/Kbuild
@@ -1,6 +1,7 @@
 # UAPI Header export list
 header-y += audio.h
 header-y += cdc.h
+header-y += cdc-wdm.h
 header-y += ch11.h
 header-y += ch9.h
 header-y += functionfs.h
diff --git a/include/uapi/linux/usb/cdc-wdm.h b/include/uapi/linux/usb/cdc-wdm.h
index f03134feebd6..0dc132e75030 100644
--- a/include/uapi/linux/usb/cdc-wdm.h
+++ b/include/uapi/linux/usb/cdc-wdm.h
@@ -9,6 +9,8 @@
 #ifndef _UAPI__LINUX_USB_CDC_WDM_H
 #define _UAPI__LINUX_USB_CDC_WDM_H
 
+#include <linux/types.h>
+
 /*
  * This IOCTL is used to retrieve the wMaxCommand for the device,
  * defining the message limit for both reading and writing.
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index d630163b9a2e..21eed488783f 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -30,7 +30,7 @@
 #include <sound/compress_params.h>
 
 
-#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 1)
+#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 2)
 /**
  * struct snd_compressed_buffer: compressed buffer
  * @fragment_size: size of buffer fragment in bytes
@@ -67,8 +67,8 @@ struct snd_compr_params {
 struct snd_compr_tstamp {
 	__u32 byte_offset;
 	__u32 copied_total;
-	snd_pcm_uframes_t pcm_frames;
-	snd_pcm_uframes_t pcm_io_frames;
+	__u32 pcm_frames;
+	__u32 pcm_io_frames;
 	__u32 sampling_rate;
 };
 
@@ -80,7 +80,7 @@ struct snd_compr_tstamp {
 struct snd_compr_avail {
 	__u64 avail;
 	struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed));
 
 enum snd_compr_direction {
 	SND_COMPRESS_PLAYBACK = 0,
diff --git a/init/Kconfig b/init/Kconfig
index 2d9b83104dcf..8fa4f758821a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1365,6 +1365,14 @@ config FUTEX
 	  support for "fast userspace mutexes".  The resulting kernel may not
 	  run glibc-based applications correctly.
 
+config HAVE_FUTEX_CMPXCHG
+	bool
+	depends on FUTEX
+	help
+	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
+	  is implemented and always working. This removes a couple of runtime
+	  checks.
+
 config EPOLL
 	bool "Enable eventpoll support" if EXPERT
 	default y
diff --git a/init/main.c b/init/main.c
index 9484f4ba88d0..2132ffd5e031 100644
--- a/init/main.c
+++ b/init/main.c
@@ -74,6 +74,7 @@
 #include <linux/ptrace.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/random.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -605,6 +606,10 @@ asmlinkage void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
+#ifdef CONFIG_X86_ESPFIX64
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
@@ -777,6 +782,7 @@ static void __init do_basic_setup(void)
 	do_ctors();
 	usermodehelper_enable();
 	do_initcalls();
+	random_int_secret_init();
 }
 
 static void __init do_pre_smp_initcalls(void)
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 130dfece27ac..a0f0ab2ac2a8 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,7 +62,7 @@ static int proc_ipc_dointvec_minmax_orphans(ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_callback_dointvec(ctl_table *table, int write,
+static int proc_ipc_callback_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
@@ -72,7 +72,7 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write,
 	memcpy(&ipc_table, table, sizeof(ipc_table));
 	ipc_table.data = get_ipc(table);
 
-	rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
+	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
 	if (write && !rc && lenp_bef == *lenp)
 		/*
@@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
 	int oldval;
 	int rc;
 
@@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 
 	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
-	if (write && !rc && lenp_bef == *lenp) {
+	if (write && !rc) {
 		int newval = *((int *)(ipc_table.data));
 		/*
 		 * The file "auto_msgmni" has correctly been set.
@@ -152,15 +151,13 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 #define proc_ipc_dointvec	   NULL
 #define proc_ipc_dointvec_minmax   NULL
 #define proc_ipc_dointvec_minmax_orphans   NULL
-#define proc_ipc_callback_dointvec NULL
+#define proc_ipc_callback_dointvec_minmax  NULL
 #define proc_ipcauto_dointvec_minmax NULL
 #endif
 
 static int zero;
 static int one = 1;
-#ifdef CONFIG_CHECKPOINT_RESTORE
 static int int_max = INT_MAX;
-#endif
 
 static struct ctl_table ipc_kern_table[] = {
 	{
@@ -198,21 +195,27 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmax,
 		.maxlen		= sizeof (init_ipc_ns.msg_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
 		.procname	= "msgmni",
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof (init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec,
+		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof (init_ipc_ns.msg_ctlmnb),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
 		.procname	= "sem",
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638340b8..5bb8bfe67149 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@ static void *get_mq(ctl_table *table)
 	return which;
 }
 
+static int proc_mq_dointvec(ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table mq_table;
+	memcpy(&mq_table, table, sizeof(mq_table));
+	mq_table.data = get_mq(table);
+
+	return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
 static int proc_mq_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -33,12 +43,10 @@ static int proc_mq_dointvec_minmax(ctl_table *table, int write,
 					lenp, ppos);
 }
 #else
+#define proc_mq_dointvec NULL
 #define proc_mq_dointvec_minmax NULL
 #endif
 
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
 static int msg_max_limit_min = MIN_MSGMAX;
 static int msg_max_limit_max = HARD_MSGMAX;
 
@@ -51,9 +59,7 @@ static ctl_table mq_sysctls[] = {
 		.data		= &init_ipc_ns.mq_queues_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
-		.extra1		= &msg_queues_limit_min,
-		.extra2		= &msg_queues_limit_max,
+		.proc_handler	= proc_mq_dointvec,
 	},
 	{
 		.procname	= "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index e4e47f647446..bb0248fc5187 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry,
 		error = -EACCES;
 		goto out_unlock;
 	}
-	if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
-	    (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
-	     !capable(CAP_SYS_RESOURCE))) {
+
+	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+	    !capable(CAP_SYS_RESOURCE)) {
 		error = -ENOSPC;
 		goto out_unlock;
 	}
@@ -823,6 +823,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
 				error = ro;
 				goto out;
 			}
+			audit_inode_parent_hidden(name, root);
 			filp = do_create(ipc_ns, root->d_inode,
 						&path, oflag, mode,
 						u_attr ? &attr : NULL);
@@ -868,6 +869,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
+	audit_inode_parent_hidden(name, mnt->mnt_root);
 	err = mnt_want_write(mnt);
 	if (err)
 		goto out_name;
diff --git a/ipc/msg.c b/ipc/msg.c
index f8fbe2c095ce..52770bfde2a5 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -70,8 +70,6 @@ struct msg_sender {
 
 #define msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])
 
-#define msg_unlock(msq)		ipc_unlock(&(msq)->q_perm)
-
 static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
 static int newque(struct ipc_namespace *, struct ipc_params *);
 #ifdef CONFIG_PROC_FS
@@ -141,27 +139,23 @@ void __init msg_init(void)
 				IPC_MSG_IDS, sysvipc_msg_proc_show);
 }
 
-/*
- * msg_lock_(check_) routines are called in the paths where the rw_mutex
- * is not held.
- */
-static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
 
 	if (IS_ERR(ipcp))
-		return (struct msg_queue *)ipcp;
+		return ERR_CAST(ipcp);
 
 	return container_of(ipcp, struct msg_queue, q_perm);
 }
 
-static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
-						int id)
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+							int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
 
 	if (IS_ERR(ipcp))
-		return (struct msg_queue *)ipcp;
+		return ERR_CAST(ipcp);
 
 	return container_of(ipcp, struct msg_queue, q_perm);
 }
@@ -171,12 +165,21 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
 	ipc_rmid(&msg_ids(ns), &s->q_perm);
 }
 
+static void msg_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct msg_queue *msq = ipc_rcu_to_struct(p);
+
+	security_msg_queue_free(msq);
+	ipc_rcu_free(head);
+}
+
 /**
  * newque - Create a new msg queue
  * @ns: namespace
  * @params: ptr to the structure that contains the key and msgflg
  *
- * Called with msg_ids.rw_mutex held (writer)
+ * Called with msg_ids.rwsem held (writer)
  */
 static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 {
@@ -195,17 +198,14 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	msq->q_perm.security = NULL;
 	retval = security_msg_queue_alloc(msq);
 	if (retval) {
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, ipc_rcu_free);
 		return retval;
 	}
 
-	/*
-	 * ipc_addid() locks msq
-	 */
+	/* ipc_addid() locks msq upon success. */
 	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
 	if (id < 0) {
-		security_msg_queue_free(msq);
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, msg_rcu_free);
 		return id;
 	}
 
@@ -218,7 +218,8 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	INIT_LIST_HEAD(&msq->q_receivers);
 	INIT_LIST_HEAD(&msq->q_senders);
 
-	msg_unlock(msq);
+	ipc_unlock_object(&msq->q_perm);
+	rcu_read_unlock();
 
 	return msq->q_perm.id;
 }
@@ -264,8 +265,8 @@ static void expunge_all(struct msg_queue *msq, int res)
  * removes the message queue from message queue ID IDR, and cleans up all the
  * messages associated with this queue.
  *
- * msg_ids.rw_mutex (writer) and the spinlock for this message queue are held
- * before freeque() is called. msg_ids.rw_mutex remains locked on exit.
+ * msg_ids.rwsem (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rwsem remains locked on exit.
  */
 static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 {
@@ -275,19 +276,19 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	expunge_all(msq, -EIDRM);
 	ss_wakeup(&msq->q_senders, 1);
 	msg_rmid(ns, msq);
-	msg_unlock(msq);
+	ipc_unlock_object(&msq->q_perm);
+	rcu_read_unlock();
 
 	list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
 		atomic_dec(&ns->msg_hdrs);
 		free_msg(msg);
 	}
 	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
-	security_msg_queue_free(msq);
-	ipc_rcu_putref(msq);
+	ipc_rcu_putref(msq, msg_rcu_free);
 }
 
 /*
- * Called with msg_ids.rw_mutex and ipcp locked.
+ * Called with msg_ids.rwsem and ipcp locked.
  */
 static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
 {
@@ -391,9 +392,9 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
 }
 
 /*
- * This function handles some msgctl commands which require the rw_mutex
+ * This function handles some msgctl commands which require the rwsem
  * to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
  */
 static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 		       struct msqid_ds __user *buf, int version)
@@ -408,31 +409,39 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 			return -EFAULT;
 	}
 
-	ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
-			       &msqid64.msg_perm, msqid64.msg_qbytes);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	down_write(&msg_ids(ns).rwsem);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+				      &msqid64.msg_perm, msqid64.msg_qbytes);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
 
 	msq = container_of(ipcp, struct msg_queue, q_perm);
 
 	err = security_msg_queue_msgctl(msq, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock1;
 
 	switch (cmd) {
 	case IPC_RMID:
+		ipc_lock_object(&msq->q_perm);
+		/* freeque unlocks the ipc object and rcu */
 		freeque(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EPERM;
-			goto out_unlock;
+			goto out_unlock1;
 		}
 
+		ipc_lock_object(&msq->q_perm);
 		err = ipc_update_perm(&msqid64.msg_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 
 		msq->q_qbytes = msqid64.msg_qbytes;
 
@@ -448,25 +457,23 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 		break;
 	default:
 		err = -EINVAL;
+		goto out_unlock1;
 	}
-out_unlock:
-	msg_unlock(msq);
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
-	up_write(&msg_ids(ns).rw_mutex);
+	up_write(&msg_ids(ns).rwsem);
 	return err;
 }
 
-SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+			 int cmd, int version, void __user *buf)
 {
+	int err;
 	struct msg_queue *msq;
-	int err, version;
-	struct ipc_namespace *ns;
-
-	if (msqid < 0 || cmd < 0)
-		return -EINVAL;
-
-	version = ipc_parse_version(&cmd);
-	ns = current->nsproxy->ipc_ns;
 
 	switch (cmd) {
 	case IPC_INFO:
@@ -477,6 +484,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 
 		if (!buf)
 			return -EFAULT;
+
 		/*
 		 * We must not return kernel stack data.
 		 * due to padding, it's not enough
@@ -492,7 +500,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		msginfo.msgmnb = ns->msg_ctlmnb;
 		msginfo.msgssz = MSGSSZ;
 		msginfo.msgseg = MSGSEG;
-		down_read(&msg_ids(ns).rw_mutex);
+		down_read(&msg_ids(ns).rwsem);
 		if (cmd == MSG_INFO) {
 			msginfo.msgpool = msg_ids(ns).in_use;
 			msginfo.msgmap = atomic_read(&ns->msg_hdrs);
@@ -503,12 +511,13 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 			msginfo.msgtql = MSGTQL;
 		}
 		max_id = ipc_get_maxid(&msg_ids(ns));
-		up_read(&msg_ids(ns).rw_mutex);
+		up_read(&msg_ids(ns).rwsem);
 		if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
 			return -EFAULT;
 		return (max_id < 0) ? 0 : max_id;
 	}
-	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+
+	case MSG_STAT:
 	case IPC_STAT:
 	{
 		struct msqid64_ds tbuf;
@@ -517,17 +526,25 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		if (!buf)
 			return -EFAULT;
 
+		memset(&tbuf, 0, sizeof(tbuf));
+
+		rcu_read_lock();
 		if (cmd == MSG_STAT) {
-			msq = msg_lock(ns, msqid);
-			if (IS_ERR(msq))
-				return PTR_ERR(msq);
+			msq = msq_obtain_object(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
 			success_return = msq->q_perm.id;
 		} else {
-			msq = msg_lock_check(ns, msqid);
-			if (IS_ERR(msq))
-				return PTR_ERR(msq);
+			msq = msq_obtain_object_check(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
 			success_return = 0;
 		}
+
 		err = -EACCES;
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
 			goto out_unlock;
@@ -536,8 +553,6 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		if (err)
 			goto out_unlock;
 
-		memset(&tbuf, 0, sizeof(tbuf));
-
 		kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
 		tbuf.msg_stime  = msq->q_stime;
 		tbuf.msg_rtime  = msq->q_rtime;
@@ -547,24 +562,48 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		tbuf.msg_qbytes = msq->q_qbytes;
 		tbuf.msg_lspid  = msq->q_lspid;
 		tbuf.msg_lrpid  = msq->q_lrpid;
-		msg_unlock(msq);
+		rcu_read_unlock();
+
 		if (copy_msqid_to_user(buf, &tbuf, version))
 			return -EFAULT;
 		return success_return;
 	}
-	case IPC_SET:
-	case IPC_RMID:
-		err = msgctl_down(ns, msqid, cmd, buf, version);
-		return err;
+
 	default:
-		return  -EINVAL;
+		return -EINVAL;
 	}
 
+	return err;
 out_unlock:
-	msg_unlock(msq);
+	rcu_read_unlock();
 	return err;
 }
 
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+	int version;
+	struct ipc_namespace *ns;
+
+	if (msqid < 0 || cmd < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case MSG_INFO:
+	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+	case IPC_STAT:
+		return msgctl_nolock(ns, msqid, cmd, version, buf);
+	case IPC_SET:
+	case IPC_RMID:
+		return msgctl_down(ns, msqid, cmd, buf, version);
+	default:
+		return  -EINVAL;
+	}
+}
+
 static int testmsg(struct msg_msg *msg, long type, int mode)
 {
 	switch(mode)
@@ -640,22 +679,31 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	msg->m_type = mtype;
 	msg->m_ts = msgsz;
 
-	msq = msg_lock_check(ns, msqid);
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
 	if (IS_ERR(msq)) {
 		err = PTR_ERR(msq);
-		goto out_free;
+		goto out_unlock1;
 	}
 
+	ipc_lock_object(&msq->q_perm);
+
 	for (;;) {
 		struct msg_sender s;
 
 		err = -EACCES;
 		if (ipcperms(ns, &msq->q_perm, S_IWUGO))
-			goto out_unlock_free;
+			goto out_unlock0;
+
+		/* raced with RMID? */
+		if (msq->q_perm.deleted) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
 
 		err = security_msg_queue_msgsnd(msq, msg, msgflg);
 		if (err)
-			goto out_unlock_free;
+			goto out_unlock0;
 
 		if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
 				1 + msq->q_qnum <= msq->q_qbytes) {
@@ -665,32 +713,37 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		/* queue full, wait: */
 		if (msgflg & IPC_NOWAIT) {
 			err = -EAGAIN;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
+
 		ss_add(msq, &s);
 
 		if (!ipc_rcu_getref(msq)) {
 			err = -EIDRM;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
 
-		msg_unlock(msq);
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
 		schedule();
 
-		ipc_lock_by_ptr(&msq->q_perm);
-		ipc_rcu_putref(msq);
+		rcu_read_lock();
+		ipc_lock_object(&msq->q_perm);
+
+		ipc_rcu_putref(msq, ipc_rcu_free);
 		if (msq->q_perm.deleted) {
 			err = -EIDRM;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
+
 		ss_del(&s);
 
 		if (signal_pending(current)) {
 			err = -ERESTARTNOHAND;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
-	}
 
+	}
 	msq->q_lspid = task_tgid_vnr(current);
 	msq->q_stime = get_seconds();
 
@@ -706,9 +759,10 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	err = 0;
 	msg = NULL;
 
-out_unlock_free:
-	msg_unlock(msq);
-out_free:
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 	if (msg != NULL)
 		free_msg(msg);
 	return err;
@@ -817,30 +871,32 @@ static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
 	return found ?: ERR_PTR(-EAGAIN);
 }
 
-
-long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
-	       int msgflg,
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
 	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
 {
-	struct msg_queue *msq;
-	struct msg_msg *msg;
 	int mode;
+	struct msg_queue *msq;
 	struct ipc_namespace *ns;
-	struct msg_msg *copy = NULL;
+	struct msg_msg *msg, *copy = NULL;
 
 	ns = current->nsproxy->ipc_ns;
 
 	if (msqid < 0 || (long) bufsz < 0)
 		return -EINVAL;
+
 	if (msgflg & MSG_COPY) {
+		if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+			return -EINVAL;
 		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
 		if (IS_ERR(copy))
 			return PTR_ERR(copy);
 	}
 	mode = convert_mode(&msgtyp, msgflg);
 
-	msq = msg_lock_check(ns, msqid);
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
 	if (IS_ERR(msq)) {
+		rcu_read_unlock();
 		free_copy(copy);
 		return PTR_ERR(msq);
 	}
@@ -850,10 +906,17 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 
 		msg = ERR_PTR(-EACCES);
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
-			goto out_unlock;
+			goto out_unlock1;
 
-		msg = find_msg(msq, &msgtyp, mode);
+		ipc_lock_object(&msq->q_perm);
+
+		/* raced with RMID? */
+		if (msq->q_perm.deleted) {
+			msg = ERR_PTR(-EIDRM);
+			goto out_unlock0;
+		}
 
+		msg = find_msg(msq, &msgtyp, mode);
 		if (!IS_ERR(msg)) {
 			/*
 			 * Found a suitable message.
@@ -861,7 +924,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			 */
 			if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
 				msg = ERR_PTR(-E2BIG);
-				goto out_unlock;
+				goto out_unlock0;
 			}
 			/*
 			 * If we are copying, then do not unlink message and do
@@ -869,8 +932,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			 */
 			if (msgflg & MSG_COPY) {
 				msg = copy_msg(msg, copy);
-				goto out_unlock;
+				goto out_unlock0;
 			}
+
 			list_del(&msg->m_list);
 			msq->q_qnum--;
 			msq->q_rtime = get_seconds();
@@ -879,14 +943,16 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			atomic_sub(msg->m_ts, &ns->msg_bytes);
 			atomic_dec(&ns->msg_hdrs);
 			ss_wakeup(&msq->q_senders, 0);
-			msg_unlock(msq);
-			break;
+
+			goto out_unlock0;
 		}
+
 		/* No message waiting. Wait for a message */
 		if (msgflg & IPC_NOWAIT) {
 			msg = ERR_PTR(-ENOMSG);
-			goto out_unlock;
+			goto out_unlock0;
 		}
+
 		list_add_tail(&msr_d.r_list, &msq->q_receivers);
 		msr_d.r_tsk = current;
 		msr_d.r_msgtype = msgtyp;
@@ -897,8 +963,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			msr_d.r_maxsize = bufsz;
 		msr_d.r_msg = ERR_PTR(-EAGAIN);
 		current->state = TASK_INTERRUPTIBLE;
-		msg_unlock(msq);
 
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
 		schedule();
 
 		/* Lockless receive, part 1:
@@ -909,7 +976,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 		 * Prior to destruction, expunge_all(-EIRDM) changes r_msg.
 		 * Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
 		 * rcu_read_lock() prevents preemption between reading r_msg
-		 * and the spin_lock() inside ipc_lock_by_ptr().
+		 * and acquiring the q_perm.lock in ipc_lock_object().
 		 */
 		rcu_read_lock();
 
@@ -928,32 +995,34 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 		 * If there is a message or an error then accept it without
 		 * locking.
 		 */
-		if (msg != ERR_PTR(-EAGAIN)) {
-			rcu_read_unlock();
-			break;
-		}
+		if (msg != ERR_PTR(-EAGAIN))
+			goto out_unlock1;
 
 		/* Lockless receive, part 3:
 		 * Acquire the queue spinlock.
 		 */
-		ipc_lock_by_ptr(&msq->q_perm);
-		rcu_read_unlock();
+		ipc_lock_object(&msq->q_perm);
 
 		/* Lockless receive, part 4:
 		 * Repeat test after acquiring the spinlock.
 		 */
 		msg = (struct msg_msg*)msr_d.r_msg;
 		if (msg != ERR_PTR(-EAGAIN))
-			goto out_unlock;
+			goto out_unlock0;
 
 		list_del(&msr_d.r_list);
 		if (signal_pending(current)) {
 			msg = ERR_PTR(-ERESTARTNOHAND);
-out_unlock:
-			msg_unlock(msq);
-			break;
+			goto out_unlock0;
 		}
+
+		ipc_unlock_object(&msq->q_perm);
 	}
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 	if (IS_ERR(msg)) {
 		free_copy(copy);
 		return PTR_ERR(msg);
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 491e71f2a1b8..7e7095974d54 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -41,15 +41,15 @@ struct msg_msgseg {
 	/* the next part of the message follows immediately */
 };
 
-#define DATALEN_MSG	(int)(PAGE_SIZE-sizeof(struct msg_msg))
-#define DATALEN_SEG	(int)(PAGE_SIZE-sizeof(struct msg_msgseg))
+#define DATALEN_MSG	((size_t)PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG	((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
 
 
-static struct msg_msg *alloc_msg(int len)
+static struct msg_msg *alloc_msg(size_t len)
 {
 	struct msg_msg *msg;
 	struct msg_msgseg **pseg;
-	int alen;
+	size_t alen;
 
 	alen = min(len, DATALEN_MSG);
 	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
@@ -80,12 +80,12 @@ out_err:
 	return NULL;
 }
 
-struct msg_msg *load_msg(const void __user *src, int len)
+struct msg_msg *load_msg(const void __user *src, size_t len)
 {
 	struct msg_msg *msg;
 	struct msg_msgseg *seg;
 	int err = -EFAULT;
-	int alen;
+	size_t alen;
 
 	msg = alloc_msg(len);
 	if (msg == NULL)
@@ -117,8 +117,8 @@ out_err:
 struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
 {
 	struct msg_msgseg *dst_pseg, *src_pseg;
-	int len = src->m_ts;
-	int alen;
+	size_t len = src->m_ts;
+	size_t alen;
 
 	BUG_ON(dst == NULL);
 	if (src->m_ts > dst->m_ts)
@@ -147,9 +147,9 @@ struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
 	return ERR_PTR(-ENOSYS);
 }
 #endif
-int store_msg(void __user *dest, struct msg_msg *msg, int len)
+int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
 {
-	int alen;
+	size_t alen;
 	struct msg_msgseg *seg;
 
 	alen = min(len, DATALEN_MSG);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 7ee61bf44933..aba9a586c667 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -81,7 +81,7 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 	int next_id;
 	int total, in_use;
 
-	down_write(&ids->rw_mutex);
+	down_write(&ids->rwsem);
 
 	in_use = ids->in_use;
 
@@ -89,11 +89,12 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 		perm = idr_find(&ids->ipcs_idr, next_id);
 		if (perm == NULL)
 			continue;
-		ipc_lock_by_ptr(perm);
+		rcu_read_lock();
+		ipc_lock_object(perm);
 		free(ns, perm);
 		total++;
 	}
-	up_write(&ids->rw_mutex);
+	up_write(&ids->rwsem);
 }
 
 static void free_ipc_ns(struct ipc_namespace *ns)
diff --git a/ipc/sem.c b/ipc/sem.c
index 70480a3aa698..db9d241af133 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -95,8 +95,12 @@ struct sem {
 	int	semval;		/* current value */
 	int	sempid;		/* pid of last operation */
 	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
-	struct list_head sem_pending; /* pending single-sop operations */
-};
+	struct list_head pending_alter; /* pending single-sop operations */
+					/* that alter the semaphore */
+	struct list_head pending_const; /* pending single-sop operations */
+					/* that do not alter the semaphore*/
+	time_t	sem_otime;	/* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
 
 /* One queue for each sleeping process in the system. */
 struct sem_queue {
@@ -150,12 +154,15 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
 #define SEMOPM_FAST	64  /* ~ 372 bytes on stack */
 
 /*
- * linked list protection:
+ * Locking:
  *	sem_undo.id_next,
- *	sem_array.sem_pending{,last},
- *	sem_array.sem_undo: sem_lock() for read/write
+ *	sem_array.complex_count,
+ *	sem_array.pending{_alter,_cont},
+ *	sem_array.sem_undo: global sem_lock() for read/write
  *	sem_undo.proc_next: only "current" is allowed to read/write that field.
  *	
+ *	sem_array.sem_base[i].pending_{const,alter}:
+ *		global or semaphore sem_lock() for read/write
  */
 
 #define sc_semmsl	sem_ctls[0]
@@ -189,77 +196,176 @@ void __init sem_init (void)
 				IPC_SEM_IDS, sysvipc_sem_proc_show);
 }
 
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+	struct sem_queue *q, *tq;
+
+	/* complex operations still around? */
+	if (sma->complex_count)
+		return;
+	/*
+	 * We will switch back to simple mode.
+	 * Move all pending operation back into the per-semaphore
+	 * queues.
+	 */
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+		struct sem *curr;
+		curr = &sma->sem_base[q->sops[0].sem_num];
+
+		list_add_tail(&q->list, &curr->pending_alter);
+	}
+	INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - Merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+	int i;
+	for (i = 0; i < sma->sem_nsems; i++) {
+		struct sem *sem = sma->sem_base + i;
+
+		list_splice_init(&sem->pending_alter, &sma->pending_alter);
+	}
+}
+
+static void sem_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct sem_array *sma = ipc_rcu_to_struct(p);
+
+	security_sem_free(sma);
+	ipc_rcu_free(head);
+}
+
+/*
+ * Wait until all currently ongoing simple ops have completed.
+ * Caller must own sem_perm.lock.
+ * New simple ops cannot start, because simple ops first check
+ * that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
+ */
+static void sem_wait_array(struct sem_array *sma)
+{
+	int i;
+	struct sem *sem;
+
+	if (sma->complex_count)  {
+		/* The thread that increased sma->complex_count waited on
+		 * all sem->lock locks. Thus we don't need to wait again.
+		 */
+		return;
+	}
+
+	for (i = 0; i < sma->sem_nsems; i++) {
+		sem = sma->sem_base + i;
+		spin_unlock_wait(&sem->lock);
+	}
+}
+
 /*
  * If the request contains only one semaphore operation, and there are
  * no complex transactions pending, lock only the semaphore involved.
  * Otherwise, lock the entire semaphore array, since we either have
  * multiple semaphores in our own semops, or we need to look at
  * semaphores from other pending complex operations.
- *
- * Carefully guard against sma->complex_count changing between zero
- * and non-zero while we are spinning for the lock. The value of
- * sma->complex_count cannot change while we are holding the lock,
- * so sem_unlock should be fine.
- *
- * The global lock path checks that all the local locks have been released,
- * checking each local lock once. This means that the local lock paths
- * cannot start their critical sections while the global lock is held.
  */
 static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 			      int nsops)
 {
-	int locknum;
- again:
-	if (nsops == 1 && !sma->complex_count) {
-		struct sem *sem = sma->sem_base + sops->sem_num;
+	struct sem *sem;
 
-		/* Lock just the semaphore we are interested in. */
-		spin_lock(&sem->lock);
+	if (nsops != 1) {
+		/* Complex operation - acquire a full lock */
+		ipc_lock_object(&sma->sem_perm);
 
-		/*
-		 * If sma->complex_count was set while we were spinning,
-		 * we may need to look at things we did not lock here.
+		/* And wait until all simple ops that are processed
+		 * right now have dropped their locks.
 		 */
-		if (unlikely(sma->complex_count)) {
-			spin_unlock(&sem->lock);
-			goto lock_array;
-		}
+		sem_wait_array(sma);
+		return -1;
+	}
 
+	/*
+	 * Only one semaphore affected - try to optimize locking.
+	 * The rules are:
+	 * - optimized locking is possible if no complex operation
+	 *   is either enqueued or processed right now.
+	 * - The test for enqueued complex ops is simple:
+	 *      sma->complex_count != 0
+	 * - Testing for complex ops that are processed right now is
+	 *   a bit more difficult. Complex ops acquire the full lock
+	 *   and first wait that the running simple ops have completed.
+	 *   (see above)
+	 *   Thus: If we own a simple lock and the global lock is free
+	 *	and complex_count is now 0, then it will stay 0 and
+	 *	thus just locking sem->lock is sufficient.
+	 */
+	sem = sma->sem_base + sops->sem_num;
+
+	if (sma->complex_count == 0) {
 		/*
-		 * Another process is holding the global lock on the
-		 * sem_array; we cannot enter our critical section,
-		 * but have to wait for the global lock to be released.
+		 * It appears that no complex operation is around.
+		 * Acquire the per-semaphore lock.
 		 */
-		if (unlikely(spin_is_locked(&sma->sem_perm.lock))) {
-			spin_unlock(&sem->lock);
-			spin_unlock_wait(&sma->sem_perm.lock);
-			goto again;
+		spin_lock(&sem->lock);
+
+		/* Then check that the global lock is free */
+		if (!spin_is_locked(&sma->sem_perm.lock)) {
+			/* spin_is_locked() is not a memory barrier */
+			smp_mb();
+
+			/* Now repeat the test of complex_count:
+			 * It can't change anymore until we drop sem->lock.
+			 * Thus: if is now 0, then it will stay 0.
+			 */
+			if (sma->complex_count == 0) {
+				/* fast path successful! */
+				return sops->sem_num;
+			}
 		}
+		spin_unlock(&sem->lock);
+	}
 
-		locknum = sops->sem_num;
+	/* slow path: acquire the full lock */
+	ipc_lock_object(&sma->sem_perm);
+
+	if (sma->complex_count == 0) {
+		/* False alarm:
+		 * There is no complex operation, thus we can switch
+		 * back to the fast path.
+		 */
+		spin_lock(&sem->lock);
+		ipc_unlock_object(&sma->sem_perm);
+		return sops->sem_num;
 	} else {
-		int i;
-		/*
-		 * Lock the semaphore array, and wait for all of the
-		 * individual semaphore locks to go away.  The code
-		 * above ensures no new single-lock holders will enter
-		 * their critical section while the array lock is held.
+		/* Not a false alarm, thus complete the sequence for a
+		 * full lock.
 		 */
- lock_array:
-		spin_lock(&sma->sem_perm.lock);
-		for (i = 0; i < sma->sem_nsems; i++) {
-			struct sem *sem = sma->sem_base + i;
-			spin_unlock_wait(&sem->lock);
-		}
-		locknum = -1;
+		sem_wait_array(sma);
+		return -1;
 	}
-	return locknum;
 }
 
 static inline void sem_unlock(struct sem_array *sma, int locknum)
 {
 	if (locknum == -1) {
-		spin_unlock(&sma->sem_perm.lock);
+		unmerge_queues(sma);
+		ipc_unlock_object(&sma->sem_perm);
 	} else {
 		struct sem *sem = sma->sem_base + locknum;
 		spin_unlock(&sem->lock);
@@ -267,7 +373,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum)
 }
 
 /*
- * sem_lock_(check_) routines are called in the paths where the rw_mutex
+ * sem_lock_(check_) routines are called in the paths where the rwsem
  * is not held.
  *
  * The caller holds the RCU read lock.
@@ -319,12 +425,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
 static inline void sem_lock_and_putref(struct sem_array *sma)
 {
 	sem_lock(sma, NULL, -1);
-	ipc_rcu_putref(sma);
-}
-
-static inline void sem_putref(struct sem_array *sma)
-{
-	ipc_rcu_putref(sma);
+	ipc_rcu_putref(sma, ipc_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -337,7 +438,7 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
  * Without the check/retry algorithm a lockless wakeup is possible:
  * - queue.status is initialized to -EINTR before blocking.
  * - wakeup is performed by
- *	* unlinking the queue entry from sma->sem_pending
+ *	* unlinking the queue entry from the pending list
  *	* setting queue.status to IN_WAKEUP
  *	  This is the notification for the blocked thread that a
  *	  result value is imminent.
@@ -371,7 +472,7 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
  * @ns: namespace
  * @params: ptr to the structure that contains key, semflg and nsems
  *
- * Called with sem_ids.rw_mutex held (as a writer)
+ * Called with sem_ids.rwsem held (as a writer)
  */
 
 static int newary(struct ipc_namespace *ns, struct ipc_params *params)
@@ -403,14 +504,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	sma->sem_perm.security = NULL;
 	retval = security_sem_alloc(sma);
 	if (retval) {
-		ipc_rcu_putref(sma);
+		ipc_rcu_putref(sma, ipc_rcu_free);
 		return retval;
 	}
 
 	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
 	if (id < 0) {
-		security_sem_free(sma);
-		ipc_rcu_putref(sma);
+		ipc_rcu_putref(sma, sem_rcu_free);
 		return id;
 	}
 	ns->used_sems += nsems;
@@ -418,12 +518,14 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	sma->sem_base = (struct sem *) &sma[1];
 
 	for (i = 0; i < nsems; i++) {
-		INIT_LIST_HEAD(&sma->sem_base[i].sem_pending);
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
 		spin_lock_init(&sma->sem_base[i].lock);
 	}
 
 	sma->complex_count = 0;
-	INIT_LIST_HEAD(&sma->sem_pending);
+	INIT_LIST_HEAD(&sma->pending_alter);
+	INIT_LIST_HEAD(&sma->pending_const);
 	INIT_LIST_HEAD(&sma->list_id);
 	sma->sem_nsems = nsems;
 	sma->sem_ctime = get_seconds();
@@ -435,7 +537,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 
 
 /*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
  */
 static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
 {
@@ -446,7 +548,7 @@ static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
 }
 
 /*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
  */
 static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
 				struct ipc_params *params)
@@ -482,12 +584,19 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
 	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
 }
 
-/*
- * Determine whether a sequence of semaphore operations would succeed
- * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
+/** perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @sops: array with operations that should be checked
+ * @nsems: number of sops
+ * @un: undo array
+ * @pid: pid that did the change
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
  */
 
-static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
+static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
 			     int nsops, struct sem_undo *un, int pid)
 {
 	int result, sem_op;
@@ -609,60 +718,132 @@ static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
  * update_queue is O(N^2) when it restarts scanning the whole queue of
  * waiting operations. Therefore this function checks if the restart is
  * really necessary. It is called after a previously waiting operation
- * was completed.
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
  */
 static int check_restart(struct sem_array *sma, struct sem_queue *q)
 {
-	struct sem *curr;
-	struct sem_queue *h;
-
-	/* if the operation didn't modify the array, then no restart */
-	if (q->alter == 0)
-		return 0;
-
-	/* pending complex operations are too difficult to analyse */
-	if (sma->complex_count)
+	/* pending complex alter operations are too difficult to analyse */
+	if (!list_empty(&sma->pending_alter))
 		return 1;
 
 	/* we were a sleeping complex operation. Too difficult */
 	if (q->nsops > 1)
 		return 1;
 
-	curr = sma->sem_base + q->sops[0].sem_num;
+	/* It is impossible that someone waits for the new value:
+	 * - complex operations always restart.
+	 * - wait-for-zero are handled seperately.
+	 * - q is a previously sleeping simple operation that
+	 *   altered the array. It must be a decrement, because
+	 *   simple increments never sleep.
+	 * - If there are older (higher priority) decrements
+	 *   in the queue, then they have observed the original
+	 *   semval value and couldn't proceed. The operation
+	 *   decremented to value - thus they won't proceed either.
+	 */
+	return 0;
+}
 
-	/* No-one waits on this queue */
-	if (list_empty(&curr->sem_pending))
-		return 0;
+/**
+ * wake_const_ops(sma, semnum, pt) - Wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+				struct list_head *pt)
+{
+	struct sem_queue *q;
+	struct list_head *walk;
+	struct list_head *pending_list;
+	int semop_completed = 0;
+
+	if (semnum == -1)
+		pending_list = &sma->pending_const;
+	else
+		pending_list = &sma->sem_base[semnum].pending_const;
+
+	walk = pending_list->next;
+	while (walk != pending_list) {
+		int error;
+
+		q = container_of(walk, struct sem_queue, list);
+		walk = walk->next;
+
+		error = perform_atomic_semop(sma, q->sops, q->nsops,
+						 q->undo, q->pid);
+
+		if (error <= 0) {
+			/* operation completed, remove from queue & wakeup */
+
+			unlink_queue(sma, q);
+
+			wake_up_sem_queue_prepare(pt, q, error);
+			if (error == 0)
+				semop_completed = 1;
+		}
+	}
+	return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero(sma, sops, nsops, pt) - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_wakeup_zero() checks all required queue for wait-for-zero
+ * operations, based on the actual changes that were performed on the
+ * semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+					int nsops, struct list_head *pt)
+{
+	int i;
+	int semop_completed = 0;
+	int got_zero = 0;
+
+	/* first: the per-semaphore queues, if known */
+	if (sops) {
+		for (i = 0; i < nsops; i++) {
+			int num = sops[i].sem_num;
 
-	/* the new semaphore value */
-	if (curr->semval) {
-		/* It is impossible that someone waits for the new value:
-		 * - q is a previously sleeping simple operation that
-		 *   altered the array. It must be a decrement, because
-		 *   simple increments never sleep.
-		 * - The value is not 0, thus wait-for-zero won't proceed.
-		 * - If there are older (higher priority) decrements
-		 *   in the queue, then they have observed the original
-		 *   semval value and couldn't proceed. The operation
-		 *   decremented to value - thus they won't proceed either.
+			if (sma->sem_base[num].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, num, pt);
+			}
+		}
+	} else {
+		/*
+		 * No sops means modified semaphores not known.
+		 * Assume all were changed.
 		 */
-		BUG_ON(q->sops[0].sem_op >= 0);
-		return 0;
+		for (i = 0; i < sma->sem_nsems; i++) {
+			if (sma->sem_base[i].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, i, pt);
+			}
+		}
 	}
 	/*
-	 * semval is 0. Check if there are wait-for-zero semops.
-	 * They must be the first entries in the per-semaphore queue
+	 * If one of the modified semaphores got 0,
+	 * then check the global queue, too.
 	 */
-	h = list_first_entry(&curr->sem_pending, struct sem_queue, list);
-	BUG_ON(h->nsops != 1);
-	BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num);
-
-	/* Yes, there is a wait-for-zero semop. Restart */
-	if (h->sops[0].sem_op == 0)
-		return 1;
+	if (got_zero)
+		semop_completed |= wake_const_ops(sma, -1, pt);
 
-	/* Again - no-one is waiting for the new value. */
-	return 0;
+	return semop_completed;
 }
 
 
@@ -678,6 +859,8 @@ static int check_restart(struct sem_array *sma, struct sem_queue *q)
  * semaphore.
  * The tasks that must be woken up are added to @pt. The return code
  * is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
  * The function return 1 if at least one semop was completed successfully.
  */
 static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
@@ -688,9 +871,9 @@ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
 	int semop_completed = 0;
 
 	if (semnum == -1)
-		pending_list = &sma->sem_pending;
+		pending_list = &sma->pending_alter;
 	else
-		pending_list = &sma->sem_base[semnum].sem_pending;
+		pending_list = &sma->sem_base[semnum].pending_alter;
 
 again:
 	walk = pending_list->next;
@@ -702,16 +885,15 @@ again:
 
 		/* If we are scanning the single sop, per-semaphore list of
 		 * one semaphore and that semaphore is 0, then it is not
-		 * necessary to scan the "alter" entries: simple increments
+		 * necessary to scan further: simple increments
 		 * that affect only one entry succeed immediately and cannot
 		 * be in the  per semaphore pending queue, and decrements
 		 * cannot be successful if the value is already 0.
 		 */
-		if (semnum != -1 && sma->sem_base[semnum].semval == 0 &&
-				q->alter)
+		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
 			break;
 
-		error = try_atomic_semop(sma, q->sops, q->nsops,
+		error = perform_atomic_semop(sma, q->sops, q->nsops,
 					 q->undo, q->pid);
 
 		/* Does q->sleeper still need to sleep? */
@@ -724,6 +906,7 @@ again:
 			restart = 0;
 		} else {
 			semop_completed = 1;
+			do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
 			restart = check_restart(sma, q);
 		}
 
@@ -735,6 +918,24 @@ again:
 }
 
 /**
+ * set_semotime(sma, sops) - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+	if (sops == NULL) {
+		sma->sem_base[0].sem_otime = get_seconds();
+	} else {
+		sma->sem_base[sops[0].sem_num].sem_otime =
+							get_seconds();
+	}
+}
+
+/**
  * do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue
  * @sma: semaphore array
  * @sops: operations that were performed
@@ -742,8 +943,8 @@ again:
  * @otime: force setting otime
  * @pt: list head of the tasks that must be woken up.
  *
- * do_smart_update() does the required called to update_queue, based on the
- * actual changes that were performed on the semaphore array.
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
  * Note that the function does not do the actual wake-up: the caller is
  * responsible for calling wake_up_sem_queue_do(@pt).
  * It is safe to perform this call after dropping all locks.
@@ -752,52 +953,42 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			int otime, struct list_head *pt)
 {
 	int i;
-	int progress;
-
-	progress = 1;
-retry_global:
-	if (sma->complex_count) {
-		if (update_queue(sma, -1, pt)) {
-			progress = 1;
-			otime = 1;
-			sops = NULL;
-		}
-	}
-	if (!progress)
-		goto done;
 
-	if (!sops) {
-		/* No semops; something special is going on. */
-		for (i = 0; i < sma->sem_nsems; i++) {
-			if (update_queue(sma, i, pt)) {
-				otime = 1;
-				progress = 1;
-			}
-		}
-		goto done_checkretry;
-	}
+	otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
 
-	/* Check the semaphores that were modified. */
-	for (i = 0; i < nsops; i++) {
-		if (sops[i].sem_op > 0 ||
-			(sops[i].sem_op < 0 &&
-				sma->sem_base[sops[i].sem_num].semval == 0))
-			if (update_queue(sma, sops[i].sem_num, pt)) {
-				otime = 1;
-				progress = 1;
+	if (!list_empty(&sma->pending_alter)) {
+		/* semaphore array uses the global queue - just process it. */
+		otime |= update_queue(sma, -1, pt);
+	} else {
+		if (!sops) {
+			/*
+			 * No sops, thus the modified semaphores are not
+			 * known. Check all.
+			 */
+			for (i = 0; i < sma->sem_nsems; i++)
+				otime |= update_queue(sma, i, pt);
+		} else {
+			/*
+			 * Check the semaphores that were increased:
+			 * - No complex ops, thus all sleeping ops are
+			 *   decrease.
+			 * - if we decreased the value, then any sleeping
+			 *   semaphore ops wont be able to run: If the
+			 *   previous value was too small, then the new
+			 *   value will be too small, too.
+			 */
+			for (i = 0; i < nsops; i++) {
+				if (sops[i].sem_op > 0) {
+					otime |= update_queue(sma,
+							sops[i].sem_num, pt);
+				}
 			}
+		}
 	}
-done_checkretry:
-	if (progress) {
-		progress = 0;
-		goto retry_global;
-	}
-done:
 	if (otime)
-		sma->sem_otime = get_seconds();
+		set_semotime(sma, sops);
 }
 
-
 /* The following counts are associated to each semaphore:
  *   semncnt        number of tasks waiting on semval being nonzero
  *   semzcnt        number of tasks waiting on semval being zero
@@ -813,14 +1004,14 @@ static int count_semncnt (struct sem_array * sma, ushort semnum)
 	struct sem_queue * q;
 
 	semncnt = 0;
-	list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+	list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
 		struct sembuf * sops = q->sops;
 		BUG_ON(sops->sem_num != semnum);
 		if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
 			semncnt++;
 	}
 
-	list_for_each_entry(q, &sma->sem_pending, list) {
+	list_for_each_entry(q, &sma->pending_alter, list) {
 		struct sembuf * sops = q->sops;
 		int nsops = q->nsops;
 		int i;
@@ -839,14 +1030,14 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
 	struct sem_queue * q;
 
 	semzcnt = 0;
-	list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+	list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
 		struct sembuf * sops = q->sops;
 		BUG_ON(sops->sem_num != semnum);
 		if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
 			semzcnt++;
 	}
 
-	list_for_each_entry(q, &sma->sem_pending, list) {
+	list_for_each_entry(q, &sma->pending_const, list) {
 		struct sembuf * sops = q->sops;
 		int nsops = q->nsops;
 		int i;
@@ -859,8 +1050,8 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
 	return semzcnt;
 }
 
-/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
- * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
+/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
+ * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
  * remains locked on exit.
  */
 static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
@@ -872,7 +1063,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	int i;
 
 	/* Free the existing undo structures for this semaphore set.  */
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
 		list_del(&un->list_id);
 		spin_lock(&un->ulp->lock);
@@ -884,13 +1075,22 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	/* Wake up all pending processes and let them fail with EIDRM. */
 	INIT_LIST_HEAD(&tasks);
-	list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+		unlink_queue(sma, q);
+		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+	}
+
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
 		unlink_queue(sma, q);
 		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
 	}
 	for (i = 0; i < sma->sem_nsems; i++) {
 		struct sem *sem = sma->sem_base + i;
-		list_for_each_entry_safe(q, tq, &sem->sem_pending, list) {
+		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+			unlink_queue(sma, q);
+			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		}
+		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
 			unlink_queue(sma, q);
 			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
 		}
@@ -903,8 +1103,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	wake_up_sem_queue_do(&tasks);
 	ns->used_sems -= sma->sem_nsems;
-	security_sem_free(sma);
-	ipc_rcu_putref(sma);
+	ipc_rcu_putref(sma, sem_rcu_free);
 }
 
 static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
@@ -931,6 +1130,21 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in,
 	}
 }
 
+static time_t get_semotime(struct sem_array *sma)
+{
+	int i;
+	time_t res;
+
+	res = sma->sem_base[0].sem_otime;
+	for (i = 1; i < sma->sem_nsems; i++) {
+		time_t to = sma->sem_base[i].sem_otime;
+
+		if (to > res)
+			res = to;
+	}
+	return res;
+}
+
 static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			 int cmd, int version, void __user *p)
 {
@@ -957,7 +1171,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
 		seminfo.semmnu = SEMMNU;
 		seminfo.semmap = SEMMAP;
 		seminfo.semume = SEMUME;
-		down_read(&sem_ids(ns).rw_mutex);
+		down_read(&sem_ids(ns).rwsem);
 		if (cmd == SEM_INFO) {
 			seminfo.semusz = sem_ids(ns).in_use;
 			seminfo.semaem = ns->used_sems;
@@ -966,7 +1180,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			seminfo.semaem = SEMAEM;
 		}
 		max_id = ipc_get_maxid(&sem_ids(ns));
-		up_read(&sem_ids(ns).rw_mutex);
+		up_read(&sem_ids(ns).rwsem);
 		if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) 
 			return -EFAULT;
 		return (max_id < 0) ? 0: max_id;
@@ -1004,9 +1218,9 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			goto out_unlock;
 
 		kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
-		tbuf.sem_otime  = sma->sem_otime;
-		tbuf.sem_ctime  = sma->sem_ctime;
-		tbuf.sem_nsems  = sma->sem_nsems;
+		tbuf.sem_otime = get_semotime(sma);
+		tbuf.sem_ctime = sma->sem_ctime;
+		tbuf.sem_nsems = sma->sem_nsems;
 		rcu_read_unlock();
 		if (copy_semid_to_user(p, &tbuf, version))
 			return -EFAULT;
@@ -1068,9 +1282,15 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 
 	sem_lock(sma, NULL, -1);
 
+	if (sma->sem_perm.deleted) {
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		return -EIDRM;
+	}
+
 	curr = &sma->sem_base[semnum];
 
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry(un, &sma->list_id, list_id)
 		un->semadj[semnum] = 0;
 
@@ -1122,28 +1342,28 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 
 		sem_lock(sma, NULL, -1);
+		if (sma->sem_perm.deleted) {
+			err = -EIDRM;
+			goto out_unlock;
+		}
 		if(nsems > SEMMSL_FAST) {
 			if (!ipc_rcu_getref(sma)) {
-				sem_unlock(sma, -1);
-				rcu_read_unlock();
 				err = -EIDRM;
-				goto out_free;
+				goto out_unlock;
 			}
 			sem_unlock(sma, -1);
 			rcu_read_unlock();
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				return -ENOMEM;
 			}
 
 			rcu_read_lock();
 			sem_lock_and_putref(sma);
 			if (sma->sem_perm.deleted) {
-				sem_unlock(sma, -1);
-				rcu_read_unlock();
 				err = -EIDRM;
-				goto out_free;
+				goto out_unlock;
 			}
 		}
 		for (i = 0; i < sma->sem_nsems; i++)
@@ -1161,28 +1381,28 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		struct sem_undo *un;
 
 		if (!ipc_rcu_getref(sma)) {
-			rcu_read_unlock();
-			return -EIDRM;
+			err = -EIDRM;
+			goto out_rcu_wakeup;
 		}
 		rcu_read_unlock();
 
 		if(nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) {
-			sem_putref(sma);
+			ipc_rcu_putref(sma, ipc_rcu_free);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1190,16 +1410,14 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		rcu_read_lock();
 		sem_lock_and_putref(sma);
 		if (sma->sem_perm.deleted) {
-			sem_unlock(sma, -1);
-			rcu_read_unlock();
 			err = -EIDRM;
-			goto out_free;
+			goto out_unlock;
 		}
 
 		for (i = 0; i < nsems; i++)
 			sma->sem_base[i].semval = sem_io[i];
 
-		assert_spin_locked(&sma->sem_perm.lock);
+		ipc_assert_locked_object(&sma->sem_perm);
 		list_for_each_entry(un, &sma->list_id, list_id) {
 			for (i = 0; i < nsems; i++)
 				un->semadj[i] = 0;
@@ -1217,6 +1435,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		goto out_rcu_wakeup;
 
 	sem_lock(sma, NULL, -1);
+	if (sma->sem_perm.deleted) {
+		err = -EIDRM;
+		goto out_unlock;
+	}
 	curr = &sma->sem_base[semnum];
 
 	switch (cmd) {
@@ -1272,9 +1494,9 @@ copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version)
 }
 
 /*
- * This function handles some semctl commands which require the rw_mutex
+ * This function handles some semctl commands which require the rwsem
  * to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
  */
 static int semctl_down(struct ipc_namespace *ns, int semid,
 		       int cmd, int version, void __user *p)
@@ -1289,42 +1511,46 @@ static int semctl_down(struct ipc_namespace *ns, int semid,
 			return -EFAULT;
 	}
 
+	down_write(&sem_ids(ns).rwsem);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
 				      &semid64.sem_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
 
 	sma = container_of(ipcp, struct sem_array, sem_perm);
 
 	err = security_sem_semctl(sma, cmd);
-	if (err) {
-		rcu_read_unlock();
-		goto out_up;
-	}
+	if (err)
+		goto out_unlock1;
 
-	switch(cmd){
+	switch (cmd) {
 	case IPC_RMID:
 		sem_lock(sma, NULL, -1);
+		/* freeary unlocks the ipc object and rcu */
 		freeary(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		sem_lock(sma, NULL, -1);
 		err = ipc_update_perm(&semid64.sem_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		sma->sem_ctime = get_seconds();
 		break;
 	default:
-		rcu_read_unlock();
 		err = -EINVAL;
-		goto out_up;
+		goto out_unlock1;
 	}
 
-out_unlock:
+out_unlock0:
 	sem_unlock(sma, -1);
+out_unlock1:
 	rcu_read_unlock();
 out_up:
-	up_write(&sem_ids(ns).rw_mutex);
+	up_write(&sem_ids(ns).rwsem);
 	return err;
 }
 
@@ -1466,7 +1692,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	/* step 2: allocate new undo structure */
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		sem_putref(sma);
+		ipc_rcu_putref(sma, ipc_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1496,7 +1722,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	new->semid = semid;
 	assert_spin_locked(&ulp->lock);
 	list_add_rcu(&new->list_proc, &ulp->list_proc);
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_add(&new->list_id, &sma->list_id);
 	un = new;
 
@@ -1533,7 +1759,6 @@ static int get_queue_result(struct sem_queue *q)
 	return error;
 }
 
-
 SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		unsigned, nsops, const struct timespec __user *, timeout)
 {
@@ -1619,6 +1844,10 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	if (error)
 		goto out_rcu_wakeup;
 
+	error = -EIDRM;
+	locknum = sem_lock(sma, sops, nsops);
+	if (sma->sem_perm.deleted)
+		goto out_unlock_free;
 	/*
 	 * semid identifiers are not unique - find_alloc_undo may have
 	 * allocated an undo structure, it was invalidated by an RMID
@@ -1626,18 +1855,22 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	 * This case can be detected checking un->semid. The existence of
 	 * "un" itself is guaranteed by rcu.
 	 */
-	error = -EIDRM;
-	locknum = sem_lock(sma, sops, nsops);
 	if (un && un->semid == -1)
 		goto out_unlock_free;
 
-	error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
-	if (error <= 0) {
-		if (alter && error == 0)
+	error = perform_atomic_semop(sma, sops, nsops, un,
+					task_tgid_vnr(current));
+	if (error == 0) {
+		/* If the operation was successful, then do
+		 * the required updates.
+		 */
+		if (alter)
 			do_smart_update(sma, sops, nsops, 1, &tasks);
-
-		goto out_unlock_free;
+		else
+			set_semotime(sma, sops);
 	}
+	if (error <= 0)
+		goto out_unlock_free;
 
 	/* We need to sleep on this operation, so we put the current
 	 * task into the pending queue and go to sleep.
@@ -1653,15 +1886,27 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		struct sem *curr;
 		curr = &sma->sem_base[sops->sem_num];
 
-		if (alter)
-			list_add_tail(&queue.list, &curr->sem_pending);
-		else
-			list_add(&queue.list, &curr->sem_pending);
+		if (alter) {
+			if (sma->complex_count) {
+				list_add_tail(&queue.list,
+						&sma->pending_alter);
+			} else {
+
+				list_add_tail(&queue.list,
+						&curr->pending_alter);
+			}
+		} else {
+			list_add_tail(&queue.list, &curr->pending_const);
+		}
 	} else {
+		if (!sma->complex_count)
+			merge_queues(sma);
+
 		if (alter)
-			list_add_tail(&queue.list, &sma->sem_pending);
+			list_add_tail(&queue.list, &sma->pending_alter);
 		else
-			list_add(&queue.list, &sma->sem_pending);
+			list_add_tail(&queue.list, &sma->pending_const);
+
 		sma->complex_count++;
 	}
 
@@ -1822,6 +2067,12 @@ void exit_sem(struct task_struct *tsk)
 		}
 
 		sem_lock(sma, NULL, -1);
+		/* exit_sem raced with IPC_RMID, nothing to do */
+		if (sma->sem_perm.deleted) {
+			sem_unlock(sma, -1);
+			rcu_read_unlock();
+			continue;
+		}
 		un = __lookup_undo(ulp, semid);
 		if (un == NULL) {
 			/* exit_sem raced with IPC_RMID+semget() that created
@@ -1833,7 +2084,7 @@ void exit_sem(struct task_struct *tsk)
 		}
 
 		/* remove un from the linked lists */
-		assert_spin_locked(&sma->sem_perm.lock);
+		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
 		spin_lock(&ulp->lock);
@@ -1882,6 +2133,17 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 {
 	struct user_namespace *user_ns = seq_user_ns(s);
 	struct sem_array *sma = it;
+	time_t sem_otime;
+
+	/*
+	 * The proc interface isn't aware of sem_lock(), it calls
+	 * ipc_lock_object() directly (in sysvipc_find_ipc).
+	 * In order to stay compatible with sem_lock(), we must wait until
+	 * all simple semop() calls have left their critical regions.
+	 */
+	sem_wait_array(sma);
+
+	sem_otime = get_semotime(sma);
 
 	return seq_printf(s,
 			  "%10d %10d  %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
@@ -1893,7 +2155,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 			  from_kgid_munged(user_ns, sma->sem_perm.gid),
 			  from_kuid_munged(user_ns, sma->sem_perm.cuid),
 			  from_kgid_munged(user_ns, sma->sem_perm.cgid),
-			  sma->sem_otime,
+			  sem_otime,
 			  sma->sem_ctime);
 }
 #endif
diff --git a/ipc/shm.c b/ipc/shm.c
index 7e199fa1960f..6dc55af8a29b 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -19,6 +19,9 @@
  * namespaces support
  * OpenVZ, SWsoft Inc.
  * Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
  */
 
 #include <linux/slab.h>
@@ -80,8 +83,8 @@ void shm_init_ns(struct ipc_namespace *ns)
 }
 
 /*
- * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
- * Only shm_ids.rw_mutex remains locked on exit.
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
  */
 static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 {
@@ -124,8 +127,28 @@ void __init shm_init (void)
 				IPC_SHM_IDS, sysvipc_shm_proc_show);
 }
 
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
 /*
- * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * shm_lock_(check_) routines are called in the paths where the rwsem
  * is not necessarily held.
  */
 static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
@@ -141,18 +164,16 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
 static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
 {
 	rcu_read_lock();
-	spin_lock(&ipcp->shm_perm.lock);
+	ipc_lock_object(&ipcp->shm_perm);
 }
 
-static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
-						int id)
+static void shm_rcu_free(struct rcu_head *head)
 {
-	struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id);
-
-	if (IS_ERR(ipcp))
-		return (struct shmid_kernel *)ipcp;
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct shmid_kernel *shp = ipc_rcu_to_struct(p);
 
-	return container_of(ipcp, struct shmid_kernel, shm_perm);
+	security_shm_free(shp);
+	ipc_rcu_free(head);
 }
 
 static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
@@ -182,22 +203,24 @@ static void shm_open(struct vm_area_struct *vma)
  * @ns: namespace
  * @shp: struct to free
  *
- * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
  * but returns with shp unlocked and freed.
  */
 static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 {
+	struct file *shm_file;
+
+	shm_file = shp->shm_file;
+	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	shm_rmid(ns, shp);
 	shm_unlock(shp);
-	if (!is_file_hugepages(shp->shm_file))
-		shmem_lock(shp->shm_file, 0, shp->mlock_user);
+	if (!is_file_hugepages(shm_file))
+		shmem_lock(shm_file, 0, shp->mlock_user);
 	else if (shp->mlock_user)
-		user_shm_unlock(file_inode(shp->shm_file)->i_size,
-						shp->mlock_user);
-	fput (shp->shm_file);
-	security_shm_free(shp);
-	ipc_rcu_putref(shp);
+		user_shm_unlock(file_inode(shm_file)->i_size, shp->mlock_user);
+	fput(shm_file);
+	ipc_rcu_putref(shp, shm_rcu_free);
 }
 
 /*
@@ -230,7 +253,7 @@ static void shm_close(struct vm_area_struct *vma)
 	struct shmid_kernel *shp;
 	struct ipc_namespace *ns = sfd->ns;
 
-	down_write(&shm_ids(ns).rw_mutex);
+	down_write(&shm_ids(ns).rwsem);
 	/* remove from the list of attaches of the shm segment */
 	shp = shm_lock(ns, sfd->id);
 	BUG_ON(IS_ERR(shp));
@@ -241,10 +264,10 @@ static void shm_close(struct vm_area_struct *vma)
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
-	up_write(&shm_ids(ns).rw_mutex);
+	up_write(&shm_ids(ns).rwsem);
 }
 
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
 static int shm_try_destroy_current(int id, void *p, void *data)
 {
 	struct ipc_namespace *ns = data;
@@ -275,7 +298,7 @@ static int shm_try_destroy_current(int id, void *p, void *data)
 	return 0;
 }
 
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
 static int shm_try_destroy_orphaned(int id, void *p, void *data)
 {
 	struct ipc_namespace *ns = data;
@@ -286,7 +309,7 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 * We want to destroy segments without users and with already
 	 * exit'ed originating process.
 	 *
-	 * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
+	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
 	if (shp->shm_creator != NULL)
 		return 0;
@@ -300,10 +323,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 
 void shm_destroy_orphaned(struct ipc_namespace *ns)
 {
-	down_write(&shm_ids(ns).rw_mutex);
+	down_write(&shm_ids(ns).rwsem);
 	if (shm_ids(ns).in_use)
 		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
-	up_write(&shm_ids(ns).rw_mutex);
+	up_write(&shm_ids(ns).rwsem);
 }
 
 
@@ -315,10 +338,10 @@ void exit_shm(struct task_struct *task)
 		return;
 
 	/* Destroy all already created segments, but not mapped yet */
-	down_write(&shm_ids(ns).rw_mutex);
+	down_write(&shm_ids(ns).rwsem);
 	if (shm_ids(ns).in_use)
 		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
-	up_write(&shm_ids(ns).rw_mutex);
+	up_write(&shm_ids(ns).rwsem);
 }
 
 static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -452,7 +475,7 @@ static const struct vm_operations_struct shm_vm_ops = {
  * @ns: namespace
  * @params: ptr to the structure that contains key, size and shmflg
  *
- * Called with shm_ids.rw_mutex held as a writer.
+ * Called with shm_ids.rwsem held as a writer.
  */
 
 static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
@@ -485,7 +508,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_perm.security = NULL;
 	error = security_shm_alloc(shp);
 	if (error) {
-		ipc_rcu_putref(shp);
+		ipc_rcu_putref(shp, ipc_rcu_free);
 		return error;
 	}
 
@@ -535,6 +558,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_nattch = 0;
 	shp->shm_file = file;
 	shp->shm_creator = current;
+
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
 	 * proc-ps tools use this. Changing this will break them.
@@ -543,7 +567,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	ns->shm_tot += numpages;
 	error = shp->shm_perm.id;
-	shm_unlock(shp);
+
+	ipc_unlock_object(&shp->shm_perm);
+	rcu_read_unlock();
 	return error;
 
 no_id:
@@ -551,13 +577,12 @@ no_id:
 		user_shm_unlock(size, shp->mlock_user);
 	fput(file);
 no_file:
-	security_shm_free(shp);
-	ipc_rcu_putref(shp);
+	ipc_rcu_putref(shp, shm_rcu_free);
 	return error;
 }
 
 /*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
  */
 static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
 {
@@ -568,7 +593,7 @@ static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
 }
 
 /*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
  */
 static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
 				struct ipc_params *params)
@@ -681,7 +706,7 @@ static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminf
 
 /*
  * Calculate and add used RSS and swap pages of a shm.
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
  */
 static void shm_add_rss_swap(struct shmid_kernel *shp,
 	unsigned long *rss_add, unsigned long *swp_add)
@@ -708,7 +733,7 @@ static void shm_add_rss_swap(struct shmid_kernel *shp,
 }
 
 /*
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
  */
 static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
 		unsigned long *swp)
@@ -737,9 +762,9 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
 }
 
 /*
- * This function handles some shmctl commands which require the rw_mutex
+ * This function handles some shmctl commands which require the rwsem
  * to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
  */
 static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
 		       struct shmid_ds __user *buf, int version)
@@ -754,59 +779,67 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
 			return -EFAULT;
 	}
 
-	ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
-			       &shmid64.shm_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	down_write(&shm_ids(ns).rwsem);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+				      &shmid64.shm_perm, 0);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
 
 	err = security_shm_shmctl(shp, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock1;
+
 	switch (cmd) {
 	case IPC_RMID:
+		ipc_lock_object(&shp->shm_perm);
+		/* do_shm_rmid unlocks the ipc object and rcu */
 		do_shm_rmid(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
+		ipc_lock_object(&shp->shm_perm);
 		err = ipc_update_perm(&shmid64.shm_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		shp->shm_ctim = get_seconds();
 		break;
 	default:
 		err = -EINVAL;
+		goto out_unlock1;
 	}
-out_unlock:
-	shm_unlock(shp);
+
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
-	up_write(&shm_ids(ns).rw_mutex);
+	up_write(&shm_ids(ns).rwsem);
 	return err;
 }
 
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+			 int cmd, int version, void __user *buf)
 {
+	int err;
 	struct shmid_kernel *shp;
-	int err, version;
-	struct ipc_namespace *ns;
 
-	if (cmd < 0 || shmid < 0) {
-		err = -EINVAL;
-		goto out;
+	/* preliminary security checks for *_INFO */
+	if (cmd == IPC_INFO || cmd == SHM_INFO) {
+		err = security_shm_shmctl(NULL, cmd);
+		if (err)
+			return err;
 	}
 
-	version = ipc_parse_version(&cmd);
-	ns = current->nsproxy->ipc_ns;
-
-	switch (cmd) { /* replace with proc interface ? */
+	switch (cmd) {
 	case IPC_INFO:
 	{
 		struct shminfo64 shminfo;
 
-		err = security_shm_shmctl(NULL, cmd);
-		if (err)
-			return err;
-
 		memset(&shminfo, 0, sizeof(shminfo));
 		shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
 		shminfo.shmmax = ns->shm_ctlmax;
@@ -816,9 +849,9 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 		if(copy_shminfo_to_user (buf, &shminfo, version))
 			return -EFAULT;
 
-		down_read(&shm_ids(ns).rw_mutex);
+		down_read(&shm_ids(ns).rwsem);
 		err = ipc_get_maxid(&shm_ids(ns));
-		up_read(&shm_ids(ns).rw_mutex);
+		up_read(&shm_ids(ns).rwsem);
 
 		if(err<0)
 			err = 0;
@@ -828,19 +861,15 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 	{
 		struct shm_info shm_info;
 
-		err = security_shm_shmctl(NULL, cmd);
-		if (err)
-			return err;
-
 		memset(&shm_info, 0, sizeof(shm_info));
-		down_read(&shm_ids(ns).rw_mutex);
+		down_read(&shm_ids(ns).rwsem);
 		shm_info.used_ids = shm_ids(ns).in_use;
 		shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp);
 		shm_info.shm_tot = ns->shm_tot;
 		shm_info.swap_attempts = 0;
 		shm_info.swap_successes = 0;
 		err = ipc_get_maxid(&shm_ids(ns));
-		up_read(&shm_ids(ns).rw_mutex);
+		up_read(&shm_ids(ns).rwsem);
 		if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
 			err = -EFAULT;
 			goto out;
@@ -855,27 +884,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 		struct shmid64_ds tbuf;
 		int result;
 
+		rcu_read_lock();
 		if (cmd == SHM_STAT) {
-			shp = shm_lock(ns, shmid);
+			shp = shm_obtain_object(ns, shmid);
 			if (IS_ERR(shp)) {
 				err = PTR_ERR(shp);
-				goto out;
+				goto out_unlock;
 			}
 			result = shp->shm_perm.id;
 		} else {
-			shp = shm_lock_check(ns, shmid);
+			shp = shm_obtain_object_check(ns, shmid);
 			if (IS_ERR(shp)) {
 				err = PTR_ERR(shp);
-				goto out;
+				goto out_unlock;
 			}
 			result = 0;
 		}
+
 		err = -EACCES;
 		if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
 			goto out_unlock;
+
 		err = security_shm_shmctl(shp, cmd);
 		if (err)
 			goto out_unlock;
+
 		memset(&tbuf, 0, sizeof(tbuf));
 		kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
 		tbuf.shm_segsz	= shp->shm_segsz;
@@ -885,43 +918,86 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 		tbuf.shm_cpid	= shp->shm_cprid;
 		tbuf.shm_lpid	= shp->shm_lprid;
 		tbuf.shm_nattch	= shp->shm_nattch;
-		shm_unlock(shp);
-		if(copy_shmid_to_user (buf, &tbuf, version))
+		rcu_read_unlock();
+
+		if (copy_shmid_to_user(buf, &tbuf, version))
 			err = -EFAULT;
 		else
 			err = result;
 		goto out;
 	}
+	default:
+		return -EINVAL;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+	struct shmid_kernel *shp;
+	int err, version;
+	struct ipc_namespace *ns;
+
+	if (cmd < 0 || shmid < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SHM_INFO:
+	case SHM_STAT:
+	case IPC_STAT:
+		return shmctl_nolock(ns, shmid, cmd, version, buf);
+	case IPC_RMID:
+	case IPC_SET:
+		return shmctl_down(ns, shmid, cmd, buf, version);
 	case SHM_LOCK:
 	case SHM_UNLOCK:
 	{
 		struct file *shm_file;
 
-		shp = shm_lock_check(ns, shmid);
+		rcu_read_lock();
+		shp = shm_obtain_object_check(ns, shmid);
 		if (IS_ERR(shp)) {
 			err = PTR_ERR(shp);
-			goto out;
+			goto out_unlock1;
 		}
 
 		audit_ipc_obj(&(shp->shm_perm));
+		err = security_shm_shmctl(shp, cmd);
+		if (err)
+			goto out_unlock1;
 
+		ipc_lock_object(&shp->shm_perm);
 		if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
 			kuid_t euid = current_euid();
-			err = -EPERM;
 			if (!uid_eq(euid, shp->shm_perm.uid) &&
-			    !uid_eq(euid, shp->shm_perm.cuid))
-				goto out_unlock;
-			if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
-				goto out_unlock;
+			    !uid_eq(euid, shp->shm_perm.cuid)) {
+				err = -EPERM;
+				goto out_unlock0;
+			}
+			if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
+				err = -EPERM;
+				goto out_unlock0;
+			}
 		}
 
-		err = security_shm_shmctl(shp, cmd);
-		if (err)
-			goto out_unlock;
-
 		shm_file = shp->shm_file;
+
+		/* check if shm_destroy() is tearing down shp */
+		if (shm_file == NULL) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
+
 		if (is_file_hugepages(shm_file))
-			goto out_unlock;
+			goto out_unlock0;
 
 		if (cmd == SHM_LOCK) {
 			struct user_struct *user = current_user();
@@ -930,32 +1006,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 				shp->shm_perm.mode |= SHM_LOCKED;
 				shp->mlock_user = user;
 			}
-			goto out_unlock;
+			goto out_unlock0;
 		}
 
 		/* SHM_UNLOCK */
 		if (!(shp->shm_perm.mode & SHM_LOCKED))
-			goto out_unlock;
+			goto out_unlock0;
 		shmem_lock(shm_file, 0, shp->mlock_user);
 		shp->shm_perm.mode &= ~SHM_LOCKED;
 		shp->mlock_user = NULL;
 		get_file(shm_file);
-		shm_unlock(shp);
+		ipc_unlock_object(&shp->shm_perm);
+		rcu_read_unlock();
 		shmem_unlock_mapping(shm_file->f_mapping);
+
 		fput(shm_file);
-		goto out;
-	}
-	case IPC_RMID:
-	case IPC_SET:
-		err = shmctl_down(ns, shmid, cmd, buf, version);
 		return err;
+	}
 	default:
 		return -EINVAL;
 	}
 
-out_unlock:
-	shm_unlock(shp);
-out:
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
 	return err;
 }
 
@@ -1023,10 +1098,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 	 * additional creator id...
 	 */
 	ns = current->nsproxy->ipc_ns;
-	shp = shm_lock_check(ns, shmid);
+	rcu_read_lock();
+	shp = shm_obtain_object_check(ns, shmid);
 	if (IS_ERR(shp)) {
 		err = PTR_ERR(shp);
-		goto out;
+		goto out_unlock;
 	}
 
 	err = -EACCES;
@@ -1037,24 +1113,39 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 	if (err)
 		goto out_unlock;
 
+	ipc_lock_object(&shp->shm_perm);
+
+	/* check if shm_destroy() is tearing down shp */
+	if (shp->shm_file == NULL) {
+		ipc_unlock_object(&shp->shm_perm);
+		err = -EIDRM;
+		goto out_unlock;
+	}
+
 	path = shp->shm_file->f_path;
 	path_get(&path);
 	shp->shm_nattch++;
 	size = i_size_read(path.dentry->d_inode);
-	shm_unlock(shp);
+	ipc_unlock_object(&shp->shm_perm);
+	rcu_read_unlock();
 
 	err = -ENOMEM;
 	sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
-	if (!sfd)
-		goto out_put_dentry;
+	if (!sfd) {
+		path_put(&path);
+		goto out_nattch;
+	}
 
 	file = alloc_file(&path, f_mode,
 			  is_file_hugepages(shp->shm_file) ?
 				&shm_file_operations_huge :
 				&shm_file_operations);
 	err = PTR_ERR(file);
-	if (IS_ERR(file))
-		goto out_free;
+	if (IS_ERR(file)) {
+		kfree(sfd);
+		path_put(&path);
+		goto out_nattch;
+	}
 
 	file->private_data = sfd;
 	file->f_mapping = shp->shm_file->f_mapping;
@@ -1080,7 +1171,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 		    addr > current->mm->start_stack - size - PAGE_SIZE * 5)
 			goto invalid;
 	}
-		
+
 	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
 	*raddr = addr;
 	err = 0;
@@ -1095,7 +1186,7 @@ out_fput:
 	fput(file);
 
 out_nattch:
-	down_write(&shm_ids(ns).rw_mutex);
+	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	BUG_ON(IS_ERR(shp));
 	shp->shm_nattch--;
@@ -1103,20 +1194,13 @@ out_nattch:
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
-	up_write(&shm_ids(ns).rw_mutex);
-
-out:
+	up_write(&shm_ids(ns).rwsem);
 	return err;
 
 out_unlock:
-	shm_unlock(shp);
-	goto out;
-
-out_free:
-	kfree(sfd);
-out_put_dentry:
-	path_put(&path);
-	goto out_nattch;
+	rcu_read_unlock();
+out:
+	return err;
 }
 
 SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
@@ -1221,8 +1305,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 #else /* CONFIG_MMU */
 	/* under NOMMU conditions, the exact address to be destroyed must be
 	 * given */
-	retval = -EINVAL;
-	if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+	if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
 		do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
 		retval = 0;
 	}
diff --git a/ipc/util.c b/ipc/util.c
index 809ec5ec8122..7684f41bce76 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -15,6 +15,29 @@
  * Jun 2006 - namespaces ssupport
  *            OpenVZ, SWsoft Inc.
  *            Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ *	rcu_read_lock()
+ *          obtain the ipc object (kern_ipc_perm) by looking up the id in an idr
+ *	    tree.
+ *	    - perform initial checks (capabilities, auditing and permission,
+ *	      etc).
+ *	    - perform read-only operations, such as STAT, INFO commands.
+ *	      acquire the ipc lock (kern_ipc_perm.lock) through
+ *	      ipc_lock_object()
+ *		- perform data updates, such as SET, RMID commands and
+ *		  mechanism-specific operations (semop/semtimedop,
+ *		  msgsnd/msgrcv, shmat/shmdt).
+ *	    drop the ipc lock, through ipc_unlock_object().
+ *	rcu_read_unlock()
+ *
+ *  The ids->rwsem must be taken when:
+ *	- creating, removing and iterating the existing entries in ipc
+ *	  identifier sets.
+ *	- iterating through files under /proc/sysvipc/
+ *
+ *  Note that sems have a special fast path that avoids kern_ipc_perm.lock -
+ *  see sem_lock().
  */
 
 #include <linux/mm.h>
@@ -119,7 +142,7 @@ __initcall(ipc_init);
  
 void ipc_init_ids(struct ipc_ids *ids)
 {
-	init_rwsem(&ids->rw_mutex);
+	init_rwsem(&ids->rwsem);
 
 	ids->in_use = 0;
 	ids->seq = 0;
@@ -174,7 +197,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
  *	@ids: Identifier set
  *	@key: The key to find
  *	
- *	Requires ipc_ids.rw_mutex locked.
+ *	Requires ipc_ids.rwsem locked.
  *	Returns the LOCKED pointer to the ipc structure if found or NULL
  *	if not.
  *	If key is found ipc points to the owning ipc structure
@@ -197,7 +220,8 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
 			continue;
 		}
 
-		ipc_lock_by_ptr(ipc);
+		rcu_read_lock();
+		ipc_lock_object(ipc);
 		return ipc;
 	}
 
@@ -208,7 +232,7 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
  *	ipc_get_maxid 	-	get the last assigned id
  *	@ids: IPC identifier set
  *
- *	Called with ipc_ids.rw_mutex held.
+ *	Called with ipc_ids.rwsem held.
  */
 
 int ipc_get_maxid(struct ipc_ids *ids)
@@ -246,9 +270,8 @@ int ipc_get_maxid(struct ipc_ids *ids)
  *	is returned. The 'new' entry is returned in a locked state on success.
  *	On failure the entry is not locked and a negative err-code is returned.
  *
- *	Called with ipc_ids.rw_mutex held as a writer.
+ *	Called with writer ipc_ids.rwsem held.
  */
- 
 int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 {
 	kuid_t euid;
@@ -313,9 +336,9 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
 {
 	int err;
 
-	down_write(&ids->rw_mutex);
+	down_write(&ids->rwsem);
 	err = ops->getnew(ns, params);
-	up_write(&ids->rw_mutex);
+	up_write(&ids->rwsem);
 	return err;
 }
 
@@ -332,7 +355,7 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
  *
  *	On success, the IPC id is returned.
  *
- *	It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ *	It is called with ipc_ids.rwsem and ipcp->lock held.
  */
 static int ipc_check_perms(struct ipc_namespace *ns,
 			   struct kern_ipc_perm *ipcp,
@@ -377,7 +400,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 	 * Take the lock as a writer since we are potentially going to add
 	 * a new entry + read locks are not "upgradable"
 	 */
-	down_write(&ids->rw_mutex);
+	down_write(&ids->rwsem);
 	ipcp = ipc_findkey(ids, params->key);
 	if (ipcp == NULL) {
 		/* key not used */
@@ -403,7 +426,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 		}
 		ipc_unlock(ipcp);
 	}
-	up_write(&ids->rw_mutex);
+	up_write(&ids->rwsem);
 
 	return err;
 }
@@ -414,7 +437,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
  *	@ids: IPC identifier set
  *	@ipcp: ipc perm structure containing the identifier to remove
  *
- *	ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ *	ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
  *	before this function is called, and remain locked on the exit.
  */
  
@@ -466,13 +489,6 @@ void ipc_free(void* ptr, int size)
 		kfree(ptr);
 }
 
-struct ipc_rcu {
-	struct rcu_head rcu;
-	atomic_t refcount;
-	/* "void *" makes sure alignment of following data is sane. */
-	void *data[0];
-};
-
 /**
  *	ipc_rcu_alloc	-	allocate ipc and rcu space 
  *	@size: size desired
@@ -489,35 +505,34 @@ void *ipc_rcu_alloc(int size)
 	if (unlikely(!out))
 		return NULL;
 	atomic_set(&out->refcount, 1);
-	return out->data;
+	return out + 1;
 }
 
 int ipc_rcu_getref(void *ptr)
 {
-	return atomic_inc_not_zero(&container_of(ptr, struct ipc_rcu, data)->refcount);
-}
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
 
-/**
- * ipc_schedule_free - free ipc + rcu space
- * @head: RCU callback structure for queued work
- */
-static void ipc_schedule_free(struct rcu_head *head)
-{
-	vfree(container_of(head, struct ipc_rcu, rcu));
+	return atomic_inc_not_zero(&p->refcount);
 }
 
-void ipc_rcu_putref(void *ptr)
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
 {
-	struct ipc_rcu *p = container_of(ptr, struct ipc_rcu, data);
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
 
 	if (!atomic_dec_and_test(&p->refcount))
 		return;
 
-	if (is_vmalloc_addr(ptr)) {
-		call_rcu(&p->rcu, ipc_schedule_free);
-	} else {
-		kfree_rcu(p, rcu);
-	}
+	call_rcu(&p->rcu, func);
+}
+
+void ipc_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+
+	if (is_vmalloc_addr(p))
+		vfree(p);
+	else
+		kfree(p);
 }
 
 /**
@@ -622,7 +637,7 @@ struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id)
 }
 
 /**
- * ipc_lock - Lock an ipc structure without rw_mutex held
+ * ipc_lock - Lock an ipc structure without rwsem held
  * @ids: IPC identifier set
  * @id: ipc id to look for
  *
@@ -678,22 +693,6 @@ out:
 	return out;
 }
 
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
-{
-	struct kern_ipc_perm *out;
-
-	out = ipc_lock(ids, id);
-	if (IS_ERR(out))
-		return out;
-
-	if (ipc_checkid(out, id)) {
-		ipc_unlock(out);
-		return ERR_PTR(-EIDRM);
-	}
-
-	return out;
-}
-
 /**
  * ipcget - Common sys_*get() code
  * @ns : namsepace
@@ -734,7 +733,7 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
 }
 
 /**
- * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
  * @ns:  the ipc namespace
  * @ids:  the table of ids where to look for the ipc
  * @id:   the id of the ipc to retrieve
@@ -747,39 +746,22 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  * It must be called without any lock held and
  *  - retrieves the ipc with the given id in the given table.
  *  - performs some audit and permission check, depending on the given cmd
- *  - returns the ipc with both ipc and rw_mutex locks held in case of success
- *    or an err-code without any lock held otherwise.
+ *  - returns a pointer to the ipc object or otherwise, the corresponding error.
+ *
+ * Call holding the both the rwsem and the rcu read lock.
  */
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
-				      struct ipc_ids *ids, int id, int cmd,
-				      struct ipc64_perm *perm, int extra_perm)
-{
-	struct kern_ipc_perm *ipcp;
-
-	ipcp = ipcctl_pre_down_nolock(ns, ids, id, cmd, perm, extra_perm);
-	if (IS_ERR(ipcp))
-		goto out;
-
-	spin_lock(&ipcp->lock);
-out:
-	return ipcp;
-}
-
 struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
-					     struct ipc_ids *ids, int id, int cmd,
-					     struct ipc64_perm *perm, int extra_perm)
+					struct ipc_ids *ids, int id, int cmd,
+					struct ipc64_perm *perm, int extra_perm)
 {
 	kuid_t euid;
 	int err = -EPERM;
 	struct kern_ipc_perm *ipcp;
 
-	down_write(&ids->rw_mutex);
-	rcu_read_lock();
-
 	ipcp = ipc_obtain_object_check(ids, id);
 	if (IS_ERR(ipcp)) {
 		err = PTR_ERR(ipcp);
-		goto out_up;
+		goto err;
 	}
 
 	audit_ipc_obj(ipcp);
@@ -790,16 +772,8 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 	euid = current_euid();
 	if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)  ||
 	    ns_capable(ns->user_ns, CAP_SYS_ADMIN))
-		return ipcp;
-
-out_up:
-	/*
-	 * Unsuccessful lookup, unlock and return
-	 * the corresponding error.
-	 */
-	rcu_read_unlock();
-	up_write(&ids->rw_mutex);
-
+		return ipcp; /* successful lookup */
+err:
 	return ERR_PTR(err);
 }
 
@@ -856,7 +830,8 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
 		ipc = idr_find(&ids->ipcs_idr, pos);
 		if (ipc != NULL) {
 			*new_pos = pos + 1;
-			ipc_lock_by_ptr(ipc);
+			rcu_read_lock();
+			ipc_lock_object(ipc);
 			return ipc;
 		}
 	}
@@ -894,7 +869,7 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
 	 * Take the lock - this will be released by the corresponding
 	 * call to stop().
 	 */
-	down_read(&ids->rw_mutex);
+	down_read(&ids->rwsem);
 
 	/* pos < 0 is invalid */
 	if (*pos < 0)
@@ -921,7 +896,7 @@ static void sysvipc_proc_stop(struct seq_file *s, void *it)
 
 	ids = &iter->ns->ids[iface->ids];
 	/* Release the lock we took in start() */
-	up_read(&ids->rw_mutex);
+	up_read(&ids->rwsem);
 }
 
 static int sysvipc_proc_show(struct seq_file *s, void *it)
diff --git a/ipc/util.h b/ipc/util.h
index 2b0bdd5d92ce..59d78aa94987 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -47,6 +47,13 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { }
 static inline void shm_exit_ns(struct ipc_namespace *ns) { }
 #endif
 
+struct ipc_rcu {
+	struct rcu_head rcu;
+	atomic_t refcount;
+} ____cacheline_aligned_in_smp;
+
+#define ipc_rcu_to_struct(p)  ((void *)(p+1))
+
 /*
  * Structure that holds the parameters needed by the ipc operations
  * (see after)
@@ -94,10 +101,10 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
 #define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
 #define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
 
-/* must be called with ids->rw_mutex acquired for writing */
+/* must be called with ids->rwsem acquired for writing */
 int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
 
-/* must be called with ids->rw_mutex acquired for reading */
+/* must be called with ids->rwsem acquired for reading */
 int ipc_get_maxid(struct ipc_ids *);
 
 /* must be called with both locks acquired. */
@@ -120,7 +127,8 @@ void ipc_free(void* ptr, int size);
  */
 void* ipc_rcu_alloc(int size);
 int ipc_rcu_getref(void *ptr);
-void ipc_rcu_putref(void *ptr);
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *head);
 
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
@@ -131,9 +139,6 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
 struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 					     struct ipc_ids *ids, int id, int cmd,
 					     struct ipc64_perm *perm, int extra_perm);
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
-				      struct ipc_ids *ids, int id, int cmd,
-				      struct ipc64_perm *perm, int extra_perm);
 
 #ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
   /* On IA-64, we always use the "64-bit version" of the IPC structures.  */ 
@@ -143,9 +148,9 @@ int ipc_parse_version (int *cmd);
 #endif
 
 extern void free_msg(struct msg_msg *msg);
-extern struct msg_msg *load_msg(const void __user *src, int len);
+extern struct msg_msg *load_msg(const void __user *src, size_t len);
 extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
-extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
 
 extern void recompute_msgmni(struct ipc_namespace *);
 
@@ -159,24 +164,27 @@ static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
 	return uid / SEQ_MULTIPLIER != ipcp->seq;
 }
 
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+static inline void ipc_lock_object(struct kern_ipc_perm *perm)
 {
-	rcu_read_lock();
 	spin_lock(&perm->lock);
 }
 
-static inline void ipc_unlock(struct kern_ipc_perm *perm)
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
 {
 	spin_unlock(&perm->lock);
-	rcu_read_unlock();
 }
 
-static inline void ipc_lock_object(struct kern_ipc_perm *perm)
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
 {
-	spin_lock(&perm->lock);
+	assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+	ipc_unlock_object(perm);
+	rcu_read_unlock();
 }
 
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
 struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
 int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
 			struct ipc_ops *ops, struct ipc_params *params);
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 44511d100eaa..e4d30533c562 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,6 +220,9 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
 
 endif
 
+config ARCH_SUPPORTS_ATOMIC_RMW
+	bool
+
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d04b6a9..4dd7529b0845 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -103,7 +103,8 @@ static int	audit_rate_limit;
 
 /* Number of outstanding audit_buffers allowed. */
 static int	audit_backlog_limit = 64;
-static int	audit_backlog_wait_time = 60 * HZ;
+#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static int	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
 static int	audit_backlog_wait_overflow = 0;
 
 /* The identity of the user shutting down the audit system. */
@@ -592,13 +593,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 	case AUDIT_TTY_SET:
 	case AUDIT_TRIM:
 	case AUDIT_MAKE_EQUIV:
-		if (!capable(CAP_AUDIT_CONTROL))
+		if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
 			err = -EPERM;
 		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
-		if (!capable(CAP_AUDIT_WRITE))
+		if (!netlink_capable(skb, CAP_AUDIT_WRITE))
 			err = -EPERM;
 		break;
 	default:  /* bad msg */
@@ -613,7 +614,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
 	int rc = 0;
 	uid_t uid = from_kuid(&init_user_ns, current_uid());
 
-	if (!audit_enabled) {
+	if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
 		*ab = NULL;
 		return rc;
 	}
@@ -659,6 +660,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	switch (msg_type) {
 	case AUDIT_GET:
+		status_set.mask		 = 0;
 		status_set.enabled	 = audit_enabled;
 		status_set.failure	 = audit_failure;
 		status_set.pid		 = audit_pid;
@@ -670,7 +672,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				 &status_set, sizeof(status_set));
 		break;
 	case AUDIT_SET:
-		if (nlh->nlmsg_len < sizeof(struct audit_status))
+		if (nlmsg_len(nlh) < sizeof(struct audit_status))
 			return -EINVAL;
 		status_get   = (struct audit_status *)data;
 		if (status_get->mask & AUDIT_STATUS_ENABLED) {
@@ -832,7 +834,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
-		memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
 		if ((s.enabled != 0 && s.enabled != 1) ||
 		    (s.log_passwd != 0 && s.log_passwd != 1))
 			return -EINVAL;
@@ -1117,9 +1119,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING
@@ -1133,6 +1136,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 		return NULL;
 	}
 
+	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+
 	ab = audit_buffer_alloc(ctx, gfp_mask, type);
 	if (!ab) {
 		audit_log_lost("out of memory in audit_log_start");
@@ -1407,7 +1412,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
 	audit_log_format(ab, " %s=", prefix);
 	CAP_FOR_EACH_U32(i) {
 		audit_log_format(ab, "%08x",
-				 cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+				 cap->cap[CAP_LAST_U32 - i]);
 	}
 }
 
@@ -1535,6 +1540,26 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
 		}
 	}
 
+	/* log the audit_names record type */
+	audit_log_format(ab, " nametype=");
+	switch(n->type) {
+	case AUDIT_TYPE_NORMAL:
+		audit_log_format(ab, "NORMAL");
+		break;
+	case AUDIT_TYPE_PARENT:
+		audit_log_format(ab, "PARENT");
+		break;
+	case AUDIT_TYPE_CHILD_DELETE:
+		audit_log_format(ab, "DELETE");
+		break;
+	case AUDIT_TYPE_CHILD_CREATE:
+		audit_log_format(ab, "CREATE");
+		break;
+	default:
+		audit_log_format(ab, "UNKNOWN");
+		break;
+	}
+
 	audit_log_fcaps(ab, n);
 	audit_log_end(ab);
 }
diff --git a/kernel/audit.h b/kernel/audit.h
index 1c95131ef760..123c9b7c3979 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -85,6 +85,7 @@ struct audit_names {
 
 	struct filename		*name;
 	int			name_len;	/* number of chars to log */
+	bool			hidden;		/* don't log this record */
 	bool			name_put;	/* call __putname()? */
 
 	unsigned long		ino;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307dc9453..00c4459f76df 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
 		chunk->owners[i].index = i;
 	}
 	fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+	chunk->mark.mask = FS_IN_IGNORED;
 	return chunk;
 }
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 6bd4a90d1991..4d230eafd5e8 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -423,7 +423,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		f->lsm_rule = NULL;
 
 		/* Support legacy tests for a valid loginuid */
-		if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) {
+		if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
 		}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3c8a601324a2..03a3af8538bd 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -733,6 +733,22 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
 	return AUDIT_BUILD_CONTEXT;
 }
 
+static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
+{
+	int word, bit;
+
+	if (val > 0xffffffff)
+		return false;
+
+	word = AUDIT_WORD(val);
+	if (word >= AUDIT_BITMASK_SIZE)
+		return false;
+
+	bit = AUDIT_BIT(val);
+
+	return rule->mask[word] & bit;
+}
+
 /* At syscall entry and exit time, this filter is called if the
  * audit_state is not low enough that auditing cannot take place, but is
  * also not high enough that we already know we have to write an audit
@@ -750,11 +766,8 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 
 	rcu_read_lock();
 	if (!list_empty(list)) {
-		int word = AUDIT_WORD(ctx->major);
-		int bit  = AUDIT_BIT(ctx->major);
-
 		list_for_each_entry_rcu(e, list, list) {
-			if ((e->rule.mask[word] & bit) == bit &&
+			if (audit_in_mask(&e->rule, ctx->major) &&
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state, false)) {
 				rcu_read_unlock();
@@ -774,20 +787,16 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 static int audit_filter_inode_name(struct task_struct *tsk,
 				   struct audit_names *n,
 				   struct audit_context *ctx) {
-	int word, bit;
 	int h = audit_hash_ino((u32)n->ino);
 	struct list_head *list = &audit_inode_hash[h];
 	struct audit_entry *e;
 	enum audit_state state;
 
-	word = AUDIT_WORD(ctx->major);
-	bit  = AUDIT_BIT(ctx->major);
-
 	if (list_empty(list))
 		return 0;
 
 	list_for_each_entry_rcu(e, list, list) {
-		if ((e->rule.mask[word] & bit) == bit &&
+		if (audit_in_mask(&e->rule, ctx->major) &&
 		    audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
 			ctx->current_state = state;
 			return 1;
@@ -1399,8 +1408,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	}
 
 	i = 0;
-	list_for_each_entry(n, &context->names_list, list)
+	list_for_each_entry(n, &context->names_list, list) {
+		if (n->hidden)
+			continue;
 		audit_log_name(context, n, NULL, i++, &call_panic);
+	}
 
 	/* Send end of event record to help user space know we are finished */
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
@@ -1769,14 +1781,15 @@ void audit_putname(struct filename *name)
  * __audit_inode - store the inode and device from a lookup
  * @name: name being audited
  * @dentry: dentry being audited
- * @parent: does this dentry represent the parent?
+ * @flags: attributes for this particular entry
  */
 void __audit_inode(struct filename *name, const struct dentry *dentry,
-		   unsigned int parent)
+		   unsigned int flags)
 {
 	struct audit_context *context = current->audit_context;
 	const struct inode *inode = dentry->d_inode;
 	struct audit_names *n;
+	bool parent = flags & AUDIT_INODE_PARENT;
 
 	if (!context->in_syscall)
 		return;
@@ -1831,6 +1844,8 @@ out:
 	if (parent) {
 		n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_PARENT;
+		if (flags & AUDIT_INODE_HIDDEN)
+			n->hidden = true;
 	} else {
 		n->name_len = AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_NORMAL;
diff --git a/kernel/capability.c b/kernel/capability.c
index f6c2ce5701e1..1339806a8731 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -268,6 +268,10 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 		i++;
 	}
 
+	effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
@@ -445,22 +449,18 @@ bool nsown_capable(int cap)
 }
 
 /**
- * inode_capable - Check superior capability over inode
+ * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
  *
- * Return true if the current task has the given superior capability
- * targeted at it's own user namespace and that the given inode is owned
- * by the current user namespace or a child namespace.
- *
- * Currently we check to see if an inode is owned by the current
- * user namespace by seeing if the inode's owner maps into the
- * current user namespace.
- *
+ * Return true if the current task has the given capability targeted at
+ * its own user namespace and that the given inode's uid and gid are
+ * mapped into the current user namespace.
  */
-bool inode_capable(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
 {
 	struct user_namespace *ns = current_user_ns();
 
-	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
+		kgid_has_mapping(ns, inode->i_gid);
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2e9b387971d1..d0def7fc2848 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -92,6 +92,14 @@ static DEFINE_MUTEX(cgroup_mutex);
 static DEFINE_MUTEX(cgroup_root_mutex);
 
 /*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions.  Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
+/*
  * Generate an array of cgroup subsystem pointers. At boot time, this is
  * populated with the built in subsystems, and modular subsystems are
  * registered after that. The mutable section of this array is protected by
@@ -873,7 +881,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
 {
 	struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
 
-	schedule_work(&cgrp->free_work);
+	queue_work(cgroup_destroy_wq, &cgrp->free_work);
 }
 
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -1995,7 +2003,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 
 		/* @tsk either already exited or can't exit until the end */
 		if (tsk->flags & PF_EXITING)
-			continue;
+			goto next;
 
 		/* as per above, nr_threads may decrease, but not increase. */
 		BUG_ON(i >= group_size);
@@ -2003,7 +2011,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 		ent.cgrp = task_cgroup_from_root(tsk, root);
 		/* nothing to do if this task is already in the cgroup */
 		if (ent.cgrp == cgrp)
-			continue;
+			goto next;
 		/*
 		 * saying GFP_ATOMIC has no effect here because we did prealloc
 		 * earlier, but it's good form to communicate our expectations.
@@ -2011,7 +2019,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
 		BUG_ON(retval != 0);
 		i++;
-
+	next:
 		if (!threadgroup)
 			break;
 	} while_each_thread(leader, tsk);
@@ -4686,6 +4694,22 @@ out:
 	return err;
 }
 
+static int __init cgroup_wq_init(void)
+{
+	/*
+	 * There isn't much point in executing destruction path in
+	 * parallel.  Good chunk is serialized with cgroup_mutex anyway.
+	 * Use 1 for @max_active.
+	 *
+	 * We would prefer to do this in cgroup_init() above, but that
+	 * is called before init_workqueues(): so leave this until after.
+	 */
+	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+	BUG_ON(!cgroup_destroy_wq);
+	return 0;
+}
+core_initcall(cgroup_wq_init);
+
 /*
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
@@ -4996,7 +5020,7 @@ void __css_put(struct cgroup_subsys_state *css)
 
 	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
 	if (v == 0)
-		schedule_work(&css->dput_work);
+		queue_work(cgroup_destroy_wq, &css->dput_work);
 }
 EXPORT_SYMBOL_GPL(__css_put);
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 198a38883e64..bc255e25d5dd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -698,10 +698,12 @@ void set_cpu_present(unsigned int cpu, bool present)
 
 void set_cpu_online(unsigned int cpu, bool online)
 {
-	if (online)
+	if (online) {
 		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-	else
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	} else {
 		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+	}
 }
 
 void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a0bcb5..c261409500e4 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!need_resched())
+	while (!tif_need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
 			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
-				current_clr_polling();
-				if (!need_resched()) {
+				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
 					arch_cpu_idle();
@@ -103,7 +102,7 @@ static void cpu_idle_loop(void)
 				} else {
 					local_irq_enable();
 				}
-				current_set_polling();
+				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
 		}
@@ -129,7 +128,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	current_set_polling();
+	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6948e9476b42..067750bbdad8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -984,8 +984,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop)
+	if (need_loop) {
+		local_irq_disable();
 		write_seqcount_begin(&tsk->mems_allowed_seq);
+	}
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -993,8 +995,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop)
+	if (need_loop) {
 		write_seqcount_end(&tsk->mems_allowed_seq);
+		local_irq_enable();
+	}
 
 	task_unlock(tsk);
 }
@@ -1149,7 +1153,13 @@ done:
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
@@ -2418,9 +2428,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 
 	task_lock(current);
 	cs = nearest_hardwall_ancestor(task_cs(current));
+	allowed = node_isset(node, cs->mems_allowed);
 	task_unlock(current);
 
-	allowed = node_isset(node, cs->mems_allowed);
 	mutex_unlock(&callback_mutex);
 	return allowed;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e76e4959908c..7bf4d519c20f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -39,6 +39,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
+#include <linux/compat.h>
 
 #include "internal.h"
 
@@ -165,25 +166,109 @@ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free'
 /*
  * max perf event sample rate
  */
-#define DEFAULT_MAX_SAMPLE_RATE 100000
-int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
-static int max_samples_per_tick __read_mostly =
-	DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+#define DEFAULT_MAX_SAMPLE_RATE		100000
+#define DEFAULT_SAMPLE_PERIOD_NS	(NSEC_PER_SEC / DEFAULT_MAX_SAMPLE_RATE)
+#define DEFAULT_CPU_TIME_MAX_PERCENT	25
+
+int sysctl_perf_event_sample_rate __read_mostly	= DEFAULT_MAX_SAMPLE_RATE;
+
+static int max_samples_per_tick __read_mostly	= DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+static int perf_sample_period_ns __read_mostly	= DEFAULT_SAMPLE_PERIOD_NS;
+
+static atomic_t perf_sample_allowed_ns __read_mostly =
+	ATOMIC_INIT( DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100);
+
+void update_perf_cpu_limits(void)
+{
+	u64 tmp = perf_sample_period_ns;
+
+	tmp *= sysctl_perf_cpu_time_max_percent;
+	do_div(tmp, 100);
+	atomic_set(&perf_sample_allowed_ns, tmp);
+}
 
 int perf_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (ret || !write)
 		return ret;
 
 	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
+	update_perf_cpu_limits();
 
 	return 0;
 }
 
+int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
+
+int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	update_perf_cpu_limits();
+
+	return 0;
+}
+
+/*
+ * perf samples are done in some very critical code paths (NMIs).
+ * If they take too much CPU time, the system can lock up and not
+ * get any real work done.  This will drop the sample rate when
+ * we detect that events are taking too long.
+ */
+#define NR_ACCUMULATED_SAMPLES 128
+DEFINE_PER_CPU(u64, running_sample_length);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
+	u64 avg_local_sample_len;
+	u64 local_samples_len;
+
+	if (atomic_read(&perf_sample_allowed_ns) == 0)
+		return;
+
+	/* decay the counter by 1 average sample */
+	local_samples_len = __get_cpu_var(running_sample_length);
+	local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
+	local_samples_len += sample_len_ns;
+	__get_cpu_var(running_sample_length) = local_samples_len;
+
+	/*
+	 * note: this will be biased artifically low until we have
+	 * seen NR_ACCUMULATED_SAMPLES.  Doing it this way keeps us
+	 * from having to maintain a count.
+	 */
+	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+	if (avg_local_sample_len <= atomic_read(&perf_sample_allowed_ns))
+		return;
+
+	if (max_samples_per_tick <= 1)
+		return;
+
+	max_samples_per_tick = DIV_ROUND_UP(max_samples_per_tick, 2);
+	sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
+	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
+
+	printk_ratelimited(KERN_WARNING
+			"perf samples too long (%lld > %d), lowering "
+			"kernel.perf_event_max_sample_rate to %d\n",
+			avg_local_sample_len,
+			atomic_read(&perf_sample_allowed_ns),
+			sysctl_perf_event_sample_rate);
+
+	update_perf_cpu_limits();
+}
+
 static atomic64_t perf_event_id;
 
 static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
@@ -1237,6 +1322,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1245,12 +1335,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1275,10 +1368,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1287,12 +1384,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1302,6 +1399,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -1309,6 +1411,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -1731,6 +1835,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -2016,9 +2125,6 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	perf_event_update_userpage(next_event);
 }
 
-#define list_next_entry(pos, member) \
-	list_entry(pos->member.next, typeof(*pos), member)
-
 static void perf_event_sync_stat(struct perf_event_context *ctx,
 				   struct perf_event_context *next_ctx)
 {
@@ -3018,10 +3124,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 *     to trigger the AB-BA case.
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
+	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
 	free_event(event);
@@ -3388,6 +3491,25 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+			cmd &= ~IOCSIZE_MASK;
+			cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+		}
+		break;
+	}
+	return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
 int perf_event_task_enable(void)
 {
 	struct perf_event *event;
@@ -3859,7 +3981,7 @@ static const struct file_operations perf_fops = {
 	.read			= perf_read,
 	.poll			= perf_poll,
 	.unlocked_ioctl		= perf_ioctl,
-	.compat_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_compat_ioctl,
 	.mmap			= perf_mmap,
 	.fasync			= perf_fasync,
 };
@@ -5047,6 +5169,9 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
+
+	/* Keeps track of cpu being initialized/exited */
+	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5293,8 +5418,14 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (WARN_ON_ONCE(!head))
+	if (!head) {
+		/*
+		 * We can race with cpu hotplug code. Do not
+		 * WARN if the cpu just got unplugged.
+		 */
+		WARN_ON_ONCE(swhash->online);
 		return -EINVAL;
+	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 
@@ -6584,6 +6715,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
+	} else {
+		if (attr.sample_period & (1ULL << 63))
+			return -EINVAL;
 	}
 
 	/*
@@ -6730,7 +6864,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -6740,7 +6874,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -6753,11 +6887,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		synchronize_rcu();
-		perf_install_in_context(ctx, group_leader, event->cpu);
+		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_install_in_context(ctx, sibling, event->cpu);
+			perf_install_in_context(ctx, sibling, sibling->cpu);
 			get_ctx(ctx);
 		}
 	}
@@ -6870,7 +7004,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		put_ctx(src_ctx);
 		list_add(&event->event_entry, &events);
 	}
@@ -6930,13 +7064,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7374,8 +7502,10 @@ int perf_event_init_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
-		if (ret)
+		if (ret) {
+			perf_event_free_task(child);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -7398,6 +7528,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -7420,15 +7551,15 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_remove_from_context(event);
+	rcu_read_lock();
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7452,11 +7583,12 @@ static void perf_event_exit_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = false;
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index cd55144270b5..9c2ddfbf4525 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -87,10 +87,31 @@ again:
 		goto out;
 
 	/*
-	 * Publish the known good head. Rely on the full barrier implied
-	 * by atomic_dec_and_test() order the rb->head read and this
-	 * write.
+	 * Since the mmap() consumer (userspace) can run on a different CPU:
+	 *
+	 *   kernel				user
+	 *
+	 *   READ ->data_tail			READ ->data_head
+	 *   smp_mb()	(A)			smp_rmb()	(C)
+	 *   WRITE $data			READ $data
+	 *   smp_wmb()	(B)			smp_mb()	(D)
+	 *   STORE ->data_head			WRITE ->data_tail
+	 *
+	 * Where A pairs with D, and B pairs with C.
+	 *
+	 * I don't think A needs to be a full barrier because we won't in fact
+	 * write data until we see the store from userspace. So we simply don't
+	 * issue the data WRITE until we observe it. Be conservative for now.
+	 *
+	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * from the tail WRITE.
+	 *
+	 * For B a WMB is sufficient since it separates two WRITEs, and for C
+	 * an RMB is sufficient since it separates two READs.
+	 *
+	 * See perf_output_begin().
 	 */
+	smp_wmb();
 	rb->user_page->data_head = head;
 
 	/*
@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * Userspace could choose to issue a mb() before updating the
 		 * tail pointer. So that all reads will be completed before the
 		 * write is issued.
+		 *
+		 * See perf_output_put_handle().
 		 */
 		tail = ACCESS_ONCE(rb->user_page->data_tail);
-		smp_rmb();
+		smp_mb();
 		offset = head = local_read(&rb->head);
 		head += size;
 		if (unlikely(!perf_output_space(rb, tail, offset, head)))
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ad8e1bdca70e..8176caf6efd9 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1511,7 +1511,6 @@ bool uprobe_deny_signal(void)
 		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
 			utask->state = UTASK_SSTEP_TRAPPED;
 			set_tsk_thread_flag(t, TIF_UPROBE);
-			set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
 		}
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 7bb73f9d09db..717efbd7cb72 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		__this_cpu_dec(process_counts);
 	}
 	list_del_rcu(&p->thread_group);
+	list_del_rcu(&p->thread_node);
 }
 
 /*
@@ -570,9 +571,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.
@@ -580,9 +578,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/*
+	 * We don't want people slaying init.
+	 *
+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+	 * state, do_notify_parent() was already called and ->exit_signal
+	 * doesn't matter.
+	 */
 	p->exit_signal = SIGCHLD;
 
+	if (p->exit_state == EXIT_DEAD)
+		return;
+
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
@@ -794,6 +802,8 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	if (group_dead)
+		disassociate_ctty(1);
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	check_stack_usage();
@@ -809,13 +819,9 @@ void do_exit(long code)
 
 	cgroup_exit(tsk, 1);
 
-	if (group_dead)
-		disassociate_ctty(1);
-
 	module_put(task_thread_info(tsk)->exec_domain->module);
 
 	proc_exit_connector(tsk);
-
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
diff --git a/kernel/fork.c b/kernel/fork.c
index 80d92e987f21..514dbc40f98f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -544,6 +544,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	clear_tlb_flush_pending(mm);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
@@ -1044,6 +1045,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
+
+	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
@@ -1318,7 +1324,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_policy;
 	retval = audit_alloc(p);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_cleanup_perf;
 	/* copy all the process information */
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
@@ -1447,14 +1453,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_free_pid;
 	}
 
-	if (clone_flags & CLONE_THREAD) {
-		current->signal->nr_threads++;
-		atomic_inc(&current->signal->live);
-		atomic_inc(&current->signal->sigcnt);
-		p->group_leader = current->group_leader;
-		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-	}
-
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
@@ -1471,6 +1469,15 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
 			__this_cpu_inc(process_counts);
+		} else {
+			current->signal->nr_threads++;
+			atomic_inc(&current->signal->live);
+			atomic_inc(&current->signal->sigcnt);
+			p->group_leader = current->group_leader;
+			list_add_tail_rcu(&p->thread_group,
+					  &p->group_leader->thread_group);
+			list_add_tail_rcu(&p->thread_node,
+					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID, pid);
 		nr_threads++;
@@ -1478,7 +1485,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
+	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
+
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	if (clone_flags & CLONE_THREAD)
@@ -1513,8 +1522,9 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
@@ -1606,10 +1616,12 @@ long do_fork(unsigned long clone_flags,
 	 */
 	if (!IS_ERR(p)) {
 		struct completion vfork;
+		struct pid *pid;
 
 		trace_sched_process_fork(current, p);
 
-		nr = task_pid_vnr(p);
+		pid = get_task_pid(p, PIDTYPE_PID);
+		nr = pid_vnr(pid);
 
 		if (clone_flags & CLONE_PARENT_SETTID)
 			put_user(nr, parent_tidptr);
@@ -1624,12 +1636,14 @@ long do_fork(unsigned long clone_flags,
 
 		/* forking complete and child started to run, tell ptracer */
 		if (unlikely(trace))
-			ptrace_event(trace, nr);
+			ptrace_event_pid(trace, pid);
 
 		if (clone_flags & CLONE_VFORK) {
 			if (!wait_for_vfork_done(p, &vfork))
-				ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+				ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
 		}
+
+		put_pid(pid);
 	} else {
 		nr = PTR_ERR(p);
 	}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c38893b0efba..bd733f6e610d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt);
 bool pm_freezing;
 bool pm_nosig_freezing;
 
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
 /* protects freezing and frozen transitions */
 static DEFINE_SPINLOCK(freezer_lock);
 
@@ -36,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p)
 	if (p->flags & PF_NOFREEZE)
 		return false;
 
+	if (test_thread_flag(TIF_MEMDIE))
+		return false;
+
 	if (pm_nosig_freezing || cgroup_freezing(p))
 		return true;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 49dacfb45745..625a4e659e7a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -67,7 +67,9 @@
 
 #include "rtmutex_common.h"
 
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 int __read_mostly futex_cmpxchg_enabled;
+#endif
 
 #define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
 
@@ -287,7 +289,7 @@ again:
 		put_page(page);
 		/* serialize against __split_huge_page_splitting() */
 		local_irq_disable();
-		if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+		if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
 			page_head = compound_head(page);
 			/*
 			 * page_head is valid pointer but we must pin
@@ -590,6 +592,55 @@ void exit_pi_state_list(struct task_struct *curr)
 	raw_spin_unlock_irq(&curr->pi_lock);
 }
 
+/*
+ * We need to check the following states:
+ *
+ *      Waiter | pi_state | pi->owner | uTID      | uODIED | ?
+ *
+ * [1]  NULL   | ---      | ---       | 0         | 0/1    | Valid
+ * [2]  NULL   | ---      | ---       | >0        | 0/1    | Valid
+ *
+ * [3]  Found  | NULL     | --        | Any       | 0/1    | Invalid
+ *
+ * [4]  Found  | Found    | NULL      | 0         | 1      | Valid
+ * [5]  Found  | Found    | NULL      | >0        | 1      | Invalid
+ *
+ * [6]  Found  | Found    | task      | 0         | 1      | Valid
+ *
+ * [7]  Found  | Found    | NULL      | Any       | 0      | Invalid
+ *
+ * [8]  Found  | Found    | task      | ==taskTID | 0/1    | Valid
+ * [9]  Found  | Found    | task      | 0         | 0      | Invalid
+ * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
+ *
+ * [1]	Indicates that the kernel can acquire the futex atomically. We
+ *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *
+ * [2]	Valid, if TID does not belong to a kernel thread. If no matching
+ *      thread is found then it indicates that the owner TID has died.
+ *
+ * [3]	Invalid. The waiter is queued on a non PI futex
+ *
+ * [4]	Valid state after exit_robust_list(), which sets the user space
+ *	value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
+ *
+ * [5]	The user space value got manipulated between exit_robust_list()
+ *	and exit_pi_state_list()
+ *
+ * [6]	Valid state after exit_pi_state_list() which sets the new owner in
+ *	the pi_state but cannot access the user space value.
+ *
+ * [7]	pi_state->owner can only be NULL when the OWNER_DIED bit is set.
+ *
+ * [8]	Owner and user space value match
+ *
+ * [9]	There is no transient state which sets the user space TID to 0
+ *	except exit_robust_list(), but this is indicated by the
+ *	FUTEX_OWNER_DIED bit. See [4]
+ *
+ * [10] There is no transient state which leaves owner and user space
+ *	TID out of sync.
+ */
 static int
 lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 		union futex_key *key, struct futex_pi_state **ps)
@@ -605,12 +656,13 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex(&this->key, key)) {
 			/*
-			 * Another waiter already exists - bump up
-			 * the refcount and return its pi_state:
+			 * Sanity check the waiter before increasing
+			 * the refcount and attaching to it.
 			 */
 			pi_state = this->pi_state;
 			/*
-			 * Userspace might have messed up non-PI and PI futexes
+			 * Userspace might have messed up non-PI and
+			 * PI futexes [3]
 			 */
 			if (unlikely(!pi_state))
 				return -EINVAL;
@@ -618,34 +670,70 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 			WARN_ON(!atomic_read(&pi_state->refcount));
 
 			/*
-			 * When pi_state->owner is NULL then the owner died
-			 * and another waiter is on the fly. pi_state->owner
-			 * is fixed up by the task which acquires
-			 * pi_state->rt_mutex.
-			 *
-			 * We do not check for pid == 0 which can happen when
-			 * the owner died and robust_list_exit() cleared the
-			 * TID.
+			 * Handle the owner died case:
 			 */
-			if (pid && pi_state->owner) {
+			if (uval & FUTEX_OWNER_DIED) {
 				/*
-				 * Bail out if user space manipulated the
-				 * futex value.
+				 * exit_pi_state_list sets owner to NULL and
+				 * wakes the topmost waiter. The task which
+				 * acquires the pi_state->rt_mutex will fixup
+				 * owner.
 				 */
-				if (pid != task_pid_vnr(pi_state->owner))
+				if (!pi_state->owner) {
+					/*
+					 * No pi state owner, but the user
+					 * space TID is not 0. Inconsistent
+					 * state. [5]
+					 */
+					if (pid)
+						return -EINVAL;
+					/*
+					 * Take a ref on the state and
+					 * return. [4]
+					 */
+					goto out_state;
+				}
+
+				/*
+				 * If TID is 0, then either the dying owner
+				 * has not yet executed exit_pi_state_list()
+				 * or some waiter acquired the rtmutex in the
+				 * pi state, but did not yet fixup the TID in
+				 * user space.
+				 *
+				 * Take a ref on the state and return. [6]
+				 */
+				if (!pid)
+					goto out_state;
+			} else {
+				/*
+				 * If the owner died bit is not set,
+				 * then the pi_state must have an
+				 * owner. [7]
+				 */
+				if (!pi_state->owner)
 					return -EINVAL;
 			}
 
+			/*
+			 * Bail out if user space manipulated the
+			 * futex value. If pi state exists then the
+			 * owner TID must be the same as the user
+			 * space TID. [9/10]
+			 */
+			if (pid != task_pid_vnr(pi_state->owner))
+				return -EINVAL;
+
+		out_state:
 			atomic_inc(&pi_state->refcount);
 			*ps = pi_state;
-
 			return 0;
 		}
 	}
 
 	/*
 	 * We are the first waiter - try to look up the real owner and attach
-	 * the new pi_state to it, but bail out when TID = 0
+	 * the new pi_state to it, but bail out when TID = 0 [1]
 	 */
 	if (!pid)
 		return -ESRCH;
@@ -653,6 +741,11 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	if (!p)
 		return -ESRCH;
 
+	if (!p->mm) {
+		put_task_struct(p);
+		return -EPERM;
+	}
+
 	/*
 	 * We need to look at the task state flags to figure out,
 	 * whether the task is exiting. To protect against the do_exit
@@ -673,6 +766,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 		return ret;
 	}
 
+	/*
+	 * No existing pi state. First waiter. [2]
+	 */
 	pi_state = alloc_pi_state();
 
 	/*
@@ -744,10 +840,18 @@ retry:
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock. Just return to userspace:
+	 * Surprise - we got the lock, but we do not trust user space at all.
 	 */
-	if (unlikely(!curval))
-		return 1;
+	if (unlikely(!curval)) {
+		/*
+		 * We verify whether there is kernel state for this
+		 * futex. If not, we can safely assume, that the 0 ->
+		 * TID transition is correct. If state exists, we do
+		 * not bother to fixup the user space state as it was
+		 * corrupted already.
+		 */
+		return futex_top_waiter(hb, key) ? -EINVAL : 1;
+	}
 
 	uval = curval;
 
@@ -877,6 +981,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	struct task_struct *new_owner;
 	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
+	int ret = 0;
 
 	if (!pi_state)
 		return -EINVAL;
@@ -900,23 +1005,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 		new_owner = this->task;
 
 	/*
-	 * We pass it to the next owner. (The WAITERS bit is always
-	 * kept enabled while there is PI state around. We must also
-	 * preserve the owner died bit.)
+	 * We pass it to the next owner. The WAITERS bit is always
+	 * kept enabled while there is PI state around. We cleanup the
+	 * owner died bit, because we are the owner.
 	 */
-	if (!(uval & FUTEX_OWNER_DIED)) {
-		int ret = 0;
-
-		newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
+	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			ret = -EFAULT;
-		else if (curval != uval)
-			ret = -EINVAL;
-		if (ret) {
-			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
-			return ret;
-		}
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+		ret = -EFAULT;
+	else if (curval != uval)
+		ret = -EINVAL;
+	if (ret) {
+		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+		return ret;
 	}
 
 	raw_spin_lock_irq(&pi_state->owner->pi_lock);
@@ -1195,7 +1296,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  *
  * Return:
  *  0 - failed to acquire the lock atomically;
- *  1 - acquired the lock;
+ * >0 - acquired the lock, return value is vpid of the top_waiter
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1206,7 +1307,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
-	int ret;
+	int ret, vpid;
 
 	if (get_futex_value_locked(&curval, pifutex))
 		return -EFAULT;
@@ -1234,11 +1335,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
 	 * in ps in contended cases.
 	 */
+	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   set_waiters);
-	if (ret == 1)
+	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+		return vpid;
+	}
 	return ret;
 }
 
@@ -1270,10 +1373,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
-	u32 curval2;
 
 	if (requeue_pi) {
 		/*
+		 * Requeue PI only works on two distinct uaddrs. This
+		 * check is only valid for private futexes. See below.
+		 */
+		if (uaddr1 == uaddr2)
+			return -EINVAL;
+
+		/*
 		 * requeue_pi requires a pi_state, try to allocate it now
 		 * without any locks in case it fails.
 		 */
@@ -1311,6 +1420,15 @@ retry:
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
+	/*
+	 * The check above which compares uaddrs is not sufficient for
+	 * shared futexes. We need to compare the keys:
+	 */
+	if (requeue_pi && match_futex(&key1, &key2)) {
+		ret = -EINVAL;
+		goto out_put_keys;
+	}
+
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
 
@@ -1356,16 +1474,25 @@ retry_private:
 		 * At this point the top_waiter has either taken uaddr2 or is
 		 * waiting on it.  If the former, then the pi_state will not
 		 * exist yet, look it up one more time to ensure we have a
-		 * reference to it.
+		 * reference to it. If the lock was taken, ret contains the
+		 * vpid of the top waiter task.
 		 */
-		if (ret == 1) {
+		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
-			ret = get_futex_value_locked(&curval2, uaddr2);
-			if (!ret)
-				ret = lookup_pi_state(curval2, hb2, &key2,
-						      &pi_state);
+			/*
+			 * If we acquired the lock, then the user
+			 * space value of uaddr2 should be vpid. It
+			 * cannot be changed by the top waiter as it
+			 * is blocked on hb2 lock if it tries to do
+			 * so. If something fiddled with it behind our
+			 * back the pi state lookup might unearth
+			 * it. So we rather use the known value than
+			 * rereading and handing potential crap to
+			 * lookup_pi_state.
+			 */
+			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
@@ -2135,9 +2262,10 @@ retry:
 	/*
 	 * To avoid races, try to do the TID -> 0 atomic transition
 	 * again. If it succeeds then we can return without waking
-	 * anyone else up:
+	 * anyone else up. We only try this if neither the waiters nor
+	 * the owner died bit are set.
 	 */
-	if (!(uval & FUTEX_OWNER_DIED) &&
+	if (!(uval & ~FUTEX_TID_MASK) &&
 	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
 		goto pi_faulted;
 	/*
@@ -2169,11 +2297,9 @@ retry:
 	/*
 	 * No waiters - kernel unlocks the futex:
 	 */
-	if (!(uval & FUTEX_OWNER_DIED)) {
-		ret = unlock_futex_pi(uaddr, uval);
-		if (ret == -EFAULT)
-			goto pi_faulted;
-	}
+	ret = unlock_futex_pi(uaddr, uval);
+	if (ret == -EFAULT)
+		goto pi_faulted;
 
 out_unlock:
 	spin_unlock(&hb->lock);
@@ -2332,6 +2458,15 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	if (ret)
 		goto out_key2;
 
+	/*
+	 * The check above which compares uaddrs is not sufficient for
+	 * shared futexes. We need to compare the keys:
+	 */
+	if (match_futex(&q.key, &key2)) {
+		ret = -EINVAL;
+		goto out_put_keys;
+	}
+
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
 	futex_wait_queue_me(hb, &q, to);
 
@@ -2729,10 +2864,10 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
 {
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 	u32 curval;
-	int i;
 
 	/*
 	 * This will fail and we want it. Some arch implementations do
@@ -2746,6 +2881,14 @@ static int __init futex_init(void)
 	 */
 	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
+	int i;
+
+	futex_detect_cmpxchg();
 
 	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
 		plist_head_init(&futex_queues[i].chain);
diff --git a/kernel/groups.c b/kernel/groups.c
index 6b2588dd04ff..67b4ba30475f 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
 /* init to 2 - one for init_task, one to ensure it is never freed */
@@ -223,6 +224,14 @@ out:
 	return i;
 }
 
+bool may_setgroups(void)
+{
+	struct user_namespace *user_ns = current_user_ns();
+
+	return ns_capable(user_ns, CAP_SETGID) &&
+		userns_may_setgroups(user_ns);
+}
+
 /*
  *	SMP: Our groups are copy-on-write. We can set them safely
  *	without another task interfering.
@@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!nsown_capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2288fbdada16..aadf4b7a607c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -245,6 +245,11 @@ again:
 			goto again;
 		}
 		timer->base = new_base;
+	} else {
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			goto again;
+		}
 	}
 	return new_base;
 }
@@ -580,6 +585,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	cpu_base->expires_next.tv64 = expires_next.tv64;
 
+	/*
+	 * If a hang was detected in the last timer interrupt then we
+	 * leave the hang delay active in the hardware. We want the
+	 * system to make progress. That also prevents the following
+	 * scenario:
+	 * T1 expires 50ms from now
+	 * T2 expires 5s from now
+	 *
+	 * T1 is removed, so this code is called and would reprogram
+	 * the hardware to 5s from now. Any hrtimer_start after that
+	 * will not reprogram the hardware due to hang_detected being
+	 * set. So we'd effectivly block all timers until the T2 event
+	 * fires.
+	 */
+	if (cpu_base->hang_detected)
+		return;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }
@@ -977,11 +999,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -996,6 +1015,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302d6cfd..3fcb6faa5fa6 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -23,10 +23,35 @@
 static struct lock_class_key irq_desc_lock_class;
 
 #if defined(CONFIG_SMP)
+static int __init irq_affinity_setup(char *str)
+{
+	zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	cpulist_parse(str, irq_default_affinity);
+	/*
+	 * Set at least the boot cpu. We don't want to end up with
+	 * bugreports caused by random comandline masks
+	 */
+	cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
+	return 1;
+}
+__setup("irqaffinity=", irq_affinity_setup);
+
+extern struct cpumask hmp_slow_cpu_mask;
+
 static void __init init_irq_default_affinity(void)
 {
-	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-	cpumask_setall(irq_default_affinity);
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!irq_default_affinity)
+		zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+#endif
+#ifdef CONFIG_SCHED_HMP
+	if (!cpumask_empty(&hmp_slow_cpu_mask)) {
+		cpumask_copy(irq_default_affinity, &hmp_slow_cpu_mask);
+		return;
+	}
+#endif
+	if (cpumask_empty(irq_default_affinity))
+		cpumask_setall(irq_default_affinity);
 }
 #else
 static void __init init_irq_default_affinity(void)
@@ -274,6 +299,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
+EXPORT_SYMBOL(irq_to_desc);
 
 static void free_desc(unsigned int irq)
 {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index dc4db3228dcd..a79d267b64ec 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -150,7 +150,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
-	ret = chip->irq_set_affinity(data, mask, false);
+	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 		cpumask_copy(data->affinity, mask);
@@ -162,7 +162,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+			    bool force)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	struct irq_desc *desc = irq_data_to_desc(data);
@@ -172,7 +173,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = irq_do_set_affinity(data, mask, false);
+		ret = irq_do_set_affinity(data, mask, force);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
@@ -187,13 +188,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 	return ret;
 }
 
-/**
- *	irq_set_affinity - Set the irq affinity of a given irq
- *	@irq:		Interrupt to set affinity
- *	@mask:		cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -203,7 +198,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret =  __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }
@@ -802,8 +797,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
 
 static void wake_threads_waitq(struct irq_desc *desc)
 {
-	if (atomic_dec_and_test(&desc->threads_active) &&
-	    waitqueue_active(&desc->wait_for_threads))
+	if (atomic_dec_and_test(&desc->threads_active))
 		wake_up(&desc->wait_for_threads);
 }
 
@@ -867,8 +861,8 @@ static int irq_thread(void *data)
 		irq_thread_check_affinity(desc, action);
 
 		action_ret = handler_fn(desc, action);
-		if (!noirqdebug)
-			note_interrupt(action->irq, desc, action_ret);
+		if (action_ret == IRQ_HANDLED)
+			atomic_inc(&desc->threads_handled);
 
 		wake_threads_waitq(desc);
 	}
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index cb228bf21760..abcd6ca86cb7 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@ static void resume_irqs(bool want_early)
 		bool is_early = desc->action &&
 			desc->action->flags & IRQF_EARLY_RESUME;
 
-		if (is_early != want_early)
+		if (!is_early && want_early)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7b5f012bde9d..febcee3c2aa9 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -265,21 +265,119 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 	return action && (action->flags & IRQF_IRQPOLL);
 }
 
+#define SPURIOUS_DEFERRED	0x80000000
+
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
 	if (desc->istate & IRQS_POLL_INPROGRESS)
 		return;
 
-	/* we get here again via the threaded handler */
-	if (action_ret == IRQ_WAKE_THREAD)
-		return;
-
 	if (bad_action_ret(action_ret)) {
 		report_bad_irq(irq, desc, action_ret);
 		return;
 	}
 
+	/*
+	 * We cannot call note_interrupt from the threaded handler
+	 * because we need to look at the compound of all handlers
+	 * (primary and threaded). Aside of that in the threaded
+	 * shared case we have no serialization against an incoming
+	 * hardware interrupt while we are dealing with a threaded
+	 * result.
+	 *
+	 * So in case a thread is woken, we just note the fact and
+	 * defer the analysis to the next hardware interrupt.
+	 *
+	 * The threaded handlers store whether they sucessfully
+	 * handled an interrupt and we check whether that number
+	 * changed versus the last invocation.
+	 *
+	 * We could handle all interrupts with the delayed by one
+	 * mechanism, but for the non forced threaded case we'd just
+	 * add pointless overhead to the straight hardirq interrupts
+	 * for the sake of a few lines less code.
+	 */
+	if (action_ret & IRQ_WAKE_THREAD) {
+		/*
+		 * There is a thread woken. Check whether one of the
+		 * shared primary handlers returned IRQ_HANDLED. If
+		 * not we defer the spurious detection to the next
+		 * interrupt.
+		 */
+		if (action_ret == IRQ_WAKE_THREAD) {
+			int handled;
+			/*
+			 * We use bit 31 of thread_handled_last to
+			 * denote the deferred spurious detection
+			 * active. No locking necessary as
+			 * thread_handled_last is only accessed here
+			 * and we have the guarantee that hard
+			 * interrupts are not reentrant.
+			 */
+			if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
+				desc->threads_handled_last |= SPURIOUS_DEFERRED;
+				return;
+			}
+			/*
+			 * Check whether one of the threaded handlers
+			 * returned IRQ_HANDLED since the last
+			 * interrupt happened.
+			 *
+			 * For simplicity we just set bit 31, as it is
+			 * set in threads_handled_last as well. So we
+			 * avoid extra masking. And we really do not
+			 * care about the high bits of the handled
+			 * count. We just care about the count being
+			 * different than the one we saw before.
+			 */
+			handled = atomic_read(&desc->threads_handled);
+			handled |= SPURIOUS_DEFERRED;
+			if (handled != desc->threads_handled_last) {
+				action_ret = IRQ_HANDLED;
+				/*
+				 * Note: We keep the SPURIOUS_DEFERRED
+				 * bit set. We are handling the
+				 * previous invocation right now.
+				 * Keep it for the current one, so the
+				 * next hardware interrupt will
+				 * account for it.
+				 */
+				desc->threads_handled_last = handled;
+			} else {
+				/*
+				 * None of the threaded handlers felt
+				 * responsible for the last interrupt
+				 *
+				 * We keep the SPURIOUS_DEFERRED bit
+				 * set in threads_handled_last as we
+				 * need to account for the current
+				 * interrupt as well.
+				 */
+				action_ret = IRQ_NONE;
+			}
+		} else {
+			/*
+			 * One of the primary handlers returned
+			 * IRQ_HANDLED. So we don't care about the
+			 * threaded handlers on the same line. Clear
+			 * the deferred detection bit.
+			 *
+			 * In theory we could/should check whether the
+			 * deferred bit is set and take the result of
+			 * the previous run into account here as
+			 * well. But it's really not worth the
+			 * trouble. If every other interrupt is
+			 * handled we never trigger the spurious
+			 * detector. And if this is just the one out
+			 * of 100k unhandled ones which is handled
+			 * then we merily delay the spurious detection
+			 * by one hard interrupt. Not a real problem.
+			 */
+			desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
+		}
+	}
+
 	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0fe61c3..0aa69ea1d8fd 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type)
  */
 static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
 {
-	long ret;
+	long t1, t2;
 
-	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+	t1 = kptr_obfuscate((long)v1, type);
+	t2 = kptr_obfuscate((long)v2, type);
 
-	return (ret < 0) | ((ret > 0) << 1);
+	return (t1 < t2) | ((t1 > t2) << 1);
 }
 
 /* The caller must have pinned the task */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 59f7b55ba745..1f8d9382dbac 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
 
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
 /* Location of the reserved area for the crash kernel */
 struct resource crashk_res = {
 	.name  = "Crash kernel",
@@ -1678,6 +1681,7 @@ int kernel_kexec(void)
 	} else
 #endif
 	{
+		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
diff --git a/kernel/module.c b/kernel/module.c
index fa53db8aadeb..61fb677211cb 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1866,7 +1866,9 @@ static void free_module(struct module *mod)
 
 	/* We leave it in list to prevent duplicate loads, but make sure
 	 * that noone uses it while it's being deconstructed. */
+	mutex_lock(&module_mutex);
 	mod->state = MODULE_STATE_UNFORMED;
+	mutex_unlock(&module_mutex);
 
 	/* Remove dynamic debug info */
 	ddebug_remove_module(mod->name);
@@ -3279,6 +3281,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	dynamic_debug_setup(info->debug, info->num_debug);
 
+	/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+	ftrace_module_init(mod);
+
 	/* Finally it's fully formed, ready to start executing. */
 	err = complete_formation(mod, info);
 	if (err)
diff --git a/kernel/pid.c b/kernel/pid.c
index 0eb6d8e8b1da..3cdba5173600 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -335,6 +335,8 @@ out:
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	put_pid_ns(ns);
+
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 6917e8edb48e..e32703d5e0ab 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -312,7 +312,9 @@ static void *pidns_get(struct task_struct *task)
 	struct pid_namespace *ns;
 
 	rcu_read_lock();
-	ns = get_pid_ns(task_active_pid_ns(task));
+	ns = task_active_pid_ns(task);
+	if (ns)
+		get_pid_ns(ns);
 	rcu_read_unlock();
 
 	return ns;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 424c2d4265c9..77e6b83c0431 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -634,6 +634,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 			goto out;
 		}
 	} else {
+		memset(&event.sigev_value, 0, sizeof(event.sigev_value));
 		event.sigev_notify = SIGEV_SIGNAL;
 		event.sigev_signo = SIGALRM;
 		event.sigev_value.sival_int = new_timer->it_id;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 5dfdc9ea180b..52423b5d7ae9 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -263,6 +263,26 @@ config PM_GENERIC_DOMAINS
 	bool
 	depends on PM
 
+config WQ_POWER_EFFICIENT_DEFAULT
+	bool "Enable workqueue power-efficient mode by default"
+	depends on PM
+	default n
+	help
+	  Per-cpu workqueues are generally preferred because they show
+	  better performance thanks to cache locality; unfortunately,
+	  per-cpu workqueues tend to be more power hungry than unbound
+	  workqueues.
+
+	  Enabling workqueue.power_efficient kernel parameter makes the
+	  per-cpu workqueues which were observed to contribute
+	  significantly to power consumption unbound, leading to measurably
+	  lower power usage at the cost of small performance overhead.
+
+	  This config option determines whether workqueue.power_efficient
+	  is enabled by default.
+
+	  If in doubt, say N.
+
 config PM_GENERIC_DOMAINS_SLEEP
 	def_bool y
 	depends on PM_SLEEP && PM_GENERIC_DOMAINS
@@ -271,6 +291,10 @@ config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
 
+config PM_GENERIC_DOMAINS_OF
+	def_bool y
+	depends on PM_GENERIC_DOMAINS && OF && !ARCH_EXYNOS
+
 config CPU_PM
 	bool
 	depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b26f5f1e773e..1634dc6e2fe7 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -491,8 +491,14 @@ int hibernation_restore(int platform_mode)
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
-		dpm_resume_end(PMSG_RECOVER);
+		/*
+		 * The above should either succeed and jump to the new kernel,
+		 * or return with an error. Otherwise things are just
+		 * undefined, so let's be paranoid.
+		 */
+		BUG_ON(!error);
 	}
+	dpm_resume_end(PMSG_RECOVER);
 	pm_restore_gfp_mask();
 	ftrace_start();
 	resume_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d77663bfedeb..312c1b2c725d 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -293,12 +293,12 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	char *s = buf;
 #ifdef CONFIG_SUSPEND
-	int i;
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (pm_states[i].state)
+			s += sprintf(s,"%s ", pm_states[i].label);
 
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (pm_states[i] && valid_state(i))
-			s += sprintf(s,"%s ", pm_states[i]);
-	}
 #endif
 #ifdef CONFIG_HIBERNATION
 	s += sprintf(s, "%s\n", "disk");
@@ -314,7 +314,7 @@ static suspend_state_t decode_state(const char *buf, size_t n)
 {
 #ifdef CONFIG_SUSPEND
 	suspend_state_t state = PM_SUSPEND_MIN;
-	const char * const *s;
+	struct pm_sleep_state *s;
 #endif
 	char *p;
 	int len;
@@ -328,8 +328,9 @@ static suspend_state_t decode_state(const char *buf, size_t n)
 
 #ifdef CONFIG_SUSPEND
 	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
-		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
-			return state;
+		if (s->state && len == strlen(s->label)
+		    && !strncmp(buf, s->label, len))
+			return s->state;
 #endif
 
 	return PM_SUSPEND_ON;
@@ -445,8 +446,8 @@ static ssize_t autosleep_show(struct kobject *kobj,
 
 #ifdef CONFIG_SUSPEND
 	if (state < PM_SUSPEND_MAX)
-		return sprintf(buf, "%s\n", valid_state(state) ?
-						pm_states[state] : "error");
+		return sprintf(buf, "%s\n", pm_states[state].state ?
+					pm_states[state].label : "error");
 #endif
 #ifdef CONFIG_HIBERNATION
 	return sprintf(buf, "disk\n");
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7d4b7ffb3c1d..f770cad3666c 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,17 +175,20 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
 				unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
+struct pm_sleep_state {
+	const char *label;
+	suspend_state_t state;
+};
+
 /* kernel/power/suspend.c */
-extern const char *const pm_states[];
+extern struct pm_sleep_state pm_states[];
 
-extern bool valid_state(suspend_state_t state);
 extern int suspend_devices_and_enter(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
 }
-static inline bool valid_state(suspend_state_t state) { return false; }
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM_TEST_SUSPEND
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 98088e0e71e8..0695319b5fde 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -103,6 +103,28 @@ static int try_to_freeze_tasks(bool user_only)
 	return todo ? -EBUSY : 0;
 }
 
+/*
+ * Returns true if all freezable tasks (except for current) are frozen already
+ */
+static bool check_frozen_processes(void)
+{
+	struct task_struct *g, *p;
+	bool ret = true;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		if (p != current && !freezer_should_skip(p) &&
+		    !frozen(p)) {
+			ret = false;
+			goto done;
+		}
+	}
+done:
+	read_unlock(&tasklist_lock);
+
+	return ret;
+}
+
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
  *
@@ -111,6 +133,7 @@ static int try_to_freeze_tasks(bool user_only)
 int freeze_processes(void)
 {
 	int error;
+	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -121,12 +144,27 @@ int freeze_processes(void)
 
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
+	oom_kills_saved = oom_kills_count();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
-		printk("done.");
 		__usermodehelper_set_disable_depth(UMH_DISABLED);
 		oom_killer_disable();
+
+		/*
+		 * There might have been an OOM kill while we were
+		 * freezing tasks and the killed task might be still
+		 * on the way out so we have to double check for race.
+		 */
+		if (oom_kills_count() != oom_kills_saved &&
+				!check_frozen_processes()) {
+			__usermodehelper_set_disable_depth(UMH_ENABLED);
+			printk("OOM in progress.");
+			error = -EBUSY;
+			goto done;
+		}
+		printk("done.");
 	}
+done:
 	printk("\n");
 	BUG_ON(in_atomic());
 
@@ -174,6 +212,7 @@ void thaw_processes(void)
 
 	printk("Restarting tasks ... ");
 
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0de28576807d..91c04f16e79c 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1398,7 +1398,11 @@ int hibernate_preallocate_memory(void)
 	 * highmem and non-highmem zones separately.
 	 */
 	pages_highmem = preallocate_image_highmem(highmem / 2);
-	alloc = (count - max_size) - pages_highmem;
+	alloc = count - max_size;
+	if (alloc > pages_highmem)
+		alloc -= pages_highmem;
+	else
+		alloc = 0;
 	pages = preallocate_image_memory(alloc, avail_normal);
 	if (pages < alloc) {
 		/* We have exhausted non-highmem pages, try highmem. */
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index bef86d121eb2..903c517b14da 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -29,10 +29,10 @@
 
 #include "power.h"
 
-const char *const pm_states[PM_SUSPEND_MAX] = {
-	[PM_SUSPEND_FREEZE]	= "freeze",
-	[PM_SUSPEND_STANDBY]	= "standby",
-	[PM_SUSPEND_MEM]	= "mem",
+struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE },
+	[PM_SUSPEND_STANDBY] = { .label = "standby", },
+	[PM_SUSPEND_MEM] = { .label = "mem", },
 };
 
 static const struct platform_suspend_ops *suspend_ops;
@@ -62,42 +62,34 @@ void freeze_wake(void)
 }
 EXPORT_SYMBOL_GPL(freeze_wake);
 
+static bool valid_state(suspend_state_t state)
+{
+	/*
+	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
+	 * support and need to be valid to the low level
+	 * implementation, no valid callback implies that none are valid.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
 /**
  * suspend_set_ops - Set the global suspend method table.
  * @ops: Suspend operations to use.
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
+	suspend_state_t i;
+
 	lock_system_sleep();
+
 	suspend_ops = ops;
+	for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++)
+		pm_states[i].state = valid_state(i) ? i : 0;
+
 	unlock_system_sleep();
 }
 EXPORT_SYMBOL_GPL(suspend_set_ops);
 
-bool valid_state(suspend_state_t state)
-{
-	if (state == PM_SUSPEND_FREEZE) {
-#ifdef CONFIG_PM_DEBUG
-		if (pm_test_level != TEST_NONE &&
-		    pm_test_level != TEST_FREEZER &&
-		    pm_test_level != TEST_DEVICES &&
-		    pm_test_level != TEST_PLATFORM) {
-			printk(KERN_WARNING "Unsupported pm_test mode for "
-					"freeze state, please choose "
-					"none/freezer/devices/platform.\n");
-			return false;
-		}
-#endif
-			return true;
-	}
-	/*
-	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel
-	 * support and need to be valid to the lowlevel
-	 * implementation, no valid callback implies that none are valid.
-	 */
-	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
-}
-
 /**
  * suspend_valid_only_mem - Generic memory-only valid callback.
  *
@@ -324,9 +316,17 @@ static int enter_state(suspend_state_t state)
 {
 	int error;
 
-	if (!valid_state(state))
-		return -ENODEV;
-
+	if (state == PM_SUSPEND_FREEZE) {
+#ifdef CONFIG_PM_DEBUG
+		if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
+			pr_warning("PM: Unsupported test mode for freeze state,"
+				   "please choose none/freezer/devices/platform.\n");
+			return -EAGAIN;
+		}
+#endif
+	} else if (!valid_state(state)) {
+		return -EINVAL;
+	}
 	if (!mutex_trylock(&pm_mutex))
 		return -EBUSY;
 
@@ -337,7 +337,7 @@ static int enter_state(suspend_state_t state)
 	sys_sync();
 	printk("done.\n");
 
-	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
 	error = suspend_prepare(state);
 	if (error)
 		goto Unlock;
@@ -345,7 +345,7 @@ static int enter_state(suspend_state_t state)
 	if (suspend_test(TEST_FREEZER))
 		goto Finish;
 
-	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
 	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
 	pm_restore_gfp_mask();
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 9b2a1d58558d..269b097e78ea 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -92,13 +92,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	}
 
 	if (state == PM_SUSPEND_MEM) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 		if (status == -ENODEV)
 			state = PM_SUSPEND_STANDBY;
 	}
 	if (state == PM_SUSPEND_STANDBY) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 	}
 	if (status < 0)
@@ -136,18 +136,16 @@ static char warn_bad_state[] __initdata =
 
 static int __init setup_test_suspend(char *value)
 {
-	unsigned i;
+	suspend_state_t i;
 
 	/* "=mem" ==> "mem" */
 	value++;
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (!pm_states[i])
-			continue;
-		if (strcmp(pm_states[i], value) != 0)
-			continue;
-		test_state = (__force suspend_state_t) i;
-		return 0;
-	}
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (!strcmp(pm_states[i].label, value)) {
+			test_state = pm_states[i].state;
+			return 0;
+		}
+
 	printk(warn_bad_state, value);
 	return 0;
 }
@@ -164,8 +162,8 @@ static int __init test_suspend(void)
 	/* PM is initialized by now; is that state testable? */
 	if (test_state == PM_SUSPEND_ON)
 		goto done;
-	if (!valid_state(test_state)) {
-		printk(warn_bad_state, pm_states[test_state]);
+	if (!pm_states[test_state].state) {
+		printk(warn_bad_state, pm_states[test_state].label);
 		goto done;
 	}
 
diff --git a/kernel/printk.c b/kernel/printk.c
index d37d45c90ae6..f7aff4bd5454 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -2485,7 +2485,7 @@ void wake_up_klogd(void)
 	preempt_enable();
 }
 
-int printk_sched(const char *fmt, ...)
+int printk_deferred(const char *fmt, ...)
 {
 	unsigned long flags;
 	va_list args;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 335a7ae697f5..afadcf7b4a22 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -257,7 +257,8 @@ ok:
 	if (task->mm)
 		dumpable = get_dumpable(task->mm);
 	rcu_read_lock();
-	if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+	if (dumpable != SUID_DUMP_USER &&
+	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h
index 14193d596d78..ab29b6a22669 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/rtmutex-debug.h
@@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 1e09308bf2a1..d9ca207cec0c 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -82,6 +82,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -89,6 +130,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 /*
@@ -142,6 +194,11 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
@@ -150,6 +207,7 @@ int max_lock_depth = 1024;
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
@@ -183,7 +241,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
  retry:
 	/*
@@ -208,13 +266,32 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
 	 */
-	if (top_waiter && (!task_has_pi_waiters(task) ||
-			   top_waiter != task_top_pi_waiter(task)))
-		goto out_unlock_pi;
+	if (top_waiter) {
+		if (!task_has_pi_waiters(task))
+			goto out_unlock_pi;
+		/*
+		 * If deadlock detection is off, we stop here if we
+		 * are not the top pi waiter of the task.
+		 */
+		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
+			goto out_unlock_pi;
+	}
 
 	/*
 	 * When deadlock detection is off then we check, if further
@@ -230,11 +307,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto retry;
 	}
 
-	/* Deadlock detection */
+	/*
+	 * Deadlock detection. If the lock is the same as the original
+	 * lock which caused us to walk the lock chain or if the
+	 * current lock is owned by the task which initiated the chain
+	 * walk, we detected a deadlock.
+	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
@@ -281,11 +363,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
+	/*
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -396,8 +493,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
+
+	/*
+	 * Early deadlock detection. We really don't want the task to
+	 * enqueue on itself just to untangle the mess later. It's not
+	 * only an optimization. We drop the locks, so another waiter
+	 * can come in before the chain walk detects the deadlock. So
+	 * the other will detect the deadlock and return -EDEADLOCK,
+	 * which is wrong, as the other waiter is not in a deadlock
+	 * situation.
+	 */
+	if (owner == task)
+		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 	__rt_mutex_adjust_prio(task);
@@ -418,20 +528,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
 		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
 		chain_walk = 1;
+	}
+
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
 
-	if (!chain_walk)
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -443,8 +561,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -454,7 +572,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -475,10 +594,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 */
 	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -493,8 +625,8 @@ static void remove_waiter(struct rt_mutex *lock,
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
@@ -518,15 +650,15 @@ static void remove_waiter(struct rt_mutex *lock,
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+		/* Store the lock on which owner is blocked or NULL */
+		next_lock = task_blocked_on_lock(owner);
 
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
-	if (!chain_walk)
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -534,7 +666,7 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -547,6 +679,7 @@ static void remove_waiter(struct rt_mutex *lock,
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -556,12 +689,13 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
 }
 
 /**
@@ -613,6 +747,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
@@ -650,8 +804,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -707,12 +863,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
@@ -959,7 +1152,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
index a1a1dd06421d..f6a1f3c133b1 100644
--- a/kernel/rtmutex.h
+++ b/kernel/rtmutex.h
@@ -24,3 +24,8 @@
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
 #define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 64de5f8b0c9e..4a073539c58e 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -77,8 +77,6 @@ static inline struct autogroup *autogroup_create(void)
 	if (IS_ERR(tg))
 		goto out_free;
 
-	sched_online_group(tg, &root_task_group);
-
 	kref_init(&ag->kref);
 	init_rwsem(&ag->lock);
 	ag->id = atomic_inc_return(&autogroup_seq_nr);
@@ -98,6 +96,7 @@ static inline struct autogroup *autogroup_create(void)
 #endif
 	tg->autogroup = ag;
 
+	sched_online_group(tg, &root_task_group);
 	return ag;
 
 out_free:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e8b335016c52..aa08f6419beb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1235,7 +1235,7 @@ out:
 		 * leave kernel.
 		 */
 		if (p->mm && printk_ratelimit()) {
-			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, cpu);
 		}
 	}
@@ -1407,7 +1407,11 @@ void scheduler_ipi(void)
 {
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
-			&& !got_nohz_idle_kick())
+			&& !got_nohz_idle_kick()
+#ifdef CONFIG_SCHED_HMP
+			&& !this_rq()->wake_for_idle_pull
+#endif
+			)
 		return;
 
 	/*
@@ -1434,6 +1438,11 @@ void scheduler_ipi(void)
 		this_rq()->idle_balance = 1;
 		raise_softirq_irqoff(SCHED_SOFTIRQ);
 	}
+#ifdef CONFIG_SCHED_HMP
+	else if (unlikely(this_rq()->wake_for_idle_pull))
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+#endif
+
 	irq_exit();
 }
 
@@ -1487,7 +1496,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	unsigned long flags;
 	int cpu, success = 0;
 
-	smp_wmb();
+	/*
+	 * If we are going to wake up a thread waiting for CONDITION we
+	 * need to ensure that CONDITION=1 done by the caller can not be
+	 * reordered with p->state check below. This pairs with mb() in
+	 * set_current_state() the waiting thread does.
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	if (!(p->state & state))
 		goto out;
@@ -1617,6 +1632,20 @@ static void __sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
 	p->se.avg.runnable_avg_period = 0;
 	p->se.avg.runnable_avg_sum = 0;
+#ifdef CONFIG_SCHED_HMP
+	/* keep LOAD_AVG_MAX in sync with fair.c if load avg series is changed */
+#define LOAD_AVG_MAX 47742
+	p->se.avg.hmp_last_up_migration = 0;
+	p->se.avg.hmp_last_down_migration = 0;
+	if (hmp_task_should_forkboost(p)) {
+		p->se.avg.load_avg_ratio = 1023;
+		p->se.avg.load_avg_contrib =
+				(1023 * scale_load_down(p->se.load.weight));
+		p->se.avg.runnable_avg_period = LOAD_AVG_MAX;
+		p->se.avg.runnable_avg_sum = LOAD_AVG_MAX;
+		p->se.avg.usage_avg_sum = LOAD_AVG_MAX;
+	}
+#endif
 #endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2966,6 +2995,12 @@ need_resched:
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	/*
+	 * Make sure that signal_pending_state()->signal_pending() below
+	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+	 * done by the caller to avoid the race with signal_wake_up().
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irq(&rq->lock);
 
 	switch_count = &prev->nivcsw;
@@ -3813,6 +3848,8 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
+extern struct cpumask hmp_slow_cpu_mask;
+
 /* Actually do priority change: must hold rq lock. */
 static void
 __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
@@ -3822,8 +3859,17 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 	p->normal_prio = normal_prio(p);
 	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
-	if (rt_prio(p->prio))
+	if (rt_prio(p->prio)) {
 		p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_HMP
+		if (!cpumask_empty(&hmp_slow_cpu_mask))
+			if (cpumask_equal(&p->cpus_allowed, cpu_all_mask)) {
+				p->nr_cpus_allowed =
+					cpumask_weight(&hmp_slow_cpu_mask);
+				do_set_cpus_allowed(p, &hmp_slow_cpu_mask);
+			}
+#endif
+	}
 	else
 		p->sched_class = &fair_sched_class;
 	set_load_weight(p);
@@ -5258,7 +5304,6 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
@@ -7800,7 +7845,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	runtime_enabled = quota != RUNTIME_INF;
 	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
-	account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled);
+	/*
+	 * If we need to toggle cfs_bandwidth_used, off->on must occur
+	 * before making related changes, and on->off must occur afterwards
+	 */
+	if (runtime_enabled && !runtime_was_enabled)
+		cfs_bandwidth_usage_inc();
 	raw_spin_lock_irq(&cfs_b->lock);
 	cfs_b->period = ns_to_ktime(period);
 	cfs_b->quota = quota;
@@ -7826,6 +7876,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 			unthrottle_cfs_rq(cfs_rq);
 		raw_spin_unlock_irq(&rq->lock);
 	}
+	if (runtime_was_enabled && !runtime_enabled)
+		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 1095e878a46f..b3f0a2783369 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
 
-	if (task_pri >= MAX_RT_PRIO)
-		return 0;
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index b5ccba22603b..c23a8fd36149 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -326,50 +326,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq)
+					 struct rq *rq, int ticks)
 {
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
 	if (steal_account_process_tick())
 		return;
 
+	cputime *= ticks;
+	scaled *= ticks;
+
 	if (irqtime_account_hi_update()) {
-		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_IRQ] += cputime;
 	} else if (irqtime_account_si_update()) {
-		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
 	} else if (this_cpu_ksoftirqd() == p) {
 		/*
 		 * ksoftirqd time do not get accounted in cpu_softirq_time.
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SOFTIRQ);
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime, scaled);
 	} else if (p == rq->idle) {
-		account_idle_time(cputime_one_jiffy);
+		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_guest_time(p, cputime, scaled);
 	} else {
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SYSTEM);
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
 	}
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	int i;
 	struct rq *rq = this_rq();
 
-	for (i = 0; i < ticks; i++)
-		irqtime_account_process_tick(current, 0, rq);
+	irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq) {}
+						struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
+		irqtime_account_process_tick(p, user_tick, rq, 1);
 		return;
 	}
 
@@ -558,7 +558,7 @@ static void cputime_adjust(struct task_cputime *curr,
 			   struct cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, stime, utime, total;
+	cputime_t rtime, stime, utime;
 
 	if (vtime_accounting_enabled()) {
 		*ut = curr->utime;
@@ -566,9 +566,6 @@ static void cputime_adjust(struct task_cputime *curr,
 		return;
 	}
 
-	stime = curr->stime;
-	total = stime + curr->utime;
-
 	/*
 	 * Tick based cputime accounting depend on random scheduling
 	 * timeslices of a task to be interrupted or not by the timer.
@@ -589,13 +586,19 @@ static void cputime_adjust(struct task_cputime *curr,
 	if (prev->stime + prev->utime >= rtime)
 		goto out;
 
-	if (total) {
+	stime = curr->stime;
+	utime = curr->utime;
+
+	if (utime == 0) {
+		stime = rtime;
+	} else if (stime == 0) {
+		utime = rtime;
+	} else {
+		cputime_t total = stime + utime;
+
 		stime = scale_stime((__force u64)stime,
 				    (__force u64)rtime, (__force u64)total);
 		utime = rtime - stime;
-	} else {
-		stime = rtime;
-		utime = 0;
 	}
 
 	/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 75024a673520..1e23284fd692 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -94,6 +94,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 #ifdef CONFIG_SMP
 	P(se->avg.runnable_avg_sum);
 	P(se->avg.runnable_avg_period);
+	P(se->avg.usage_avg_sum);
 	P(se->avg.load_avg_contrib);
 	P(se->avg.decay_count);
 #endif
@@ -223,6 +224,16 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->tg_runnable_contrib);
 	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
 			atomic_read(&cfs_rq->tg->runnable_avg));
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->usage_avg",
+			atomic_read(&cfs_rq->tg->usage_avg));
+#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+			cfs_rq->tg->cfs_bandwidth.timer_active);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
+			cfs_rq->throttled);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
+			cfs_rq->throttle_count);
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
@@ -543,7 +554,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
-			do_div(avg_atom, nr_switches);
+			avg_atom = div64_ul(avg_atom, nr_switches);
 		else
 			avg_atom = -1LL;
 
@@ -566,6 +577,12 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		   "nr_involuntary_switches", (long long)p->nivcsw);
 
 	P(se.load.weight);
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+	P(se.avg.runnable_avg_sum);
+	P(se.avg.runnable_avg_period);
+	P(se.avg.load_avg_contrib);
+	P(se.avg.decay_count);
+#endif
 	P(policy);
 	P(prio);
 #undef PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 03b73bea33d6..41d0cbda605d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -31,9 +31,21 @@
 #include <linux/task_work.h>
 
 #include <trace/events/sched.h>
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Include cpufreq header to add a notifier so that cpu frequency
+ * scaling can track the current CPU frequency
+ */
+#include <linux/cpufreq.h>
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#ifdef CONFIG_SCHED_HMP
+#include <linux/cpuidle.h>
+#endif
 
 #include "sched.h"
 
+
 /*
  * Targeted preemption latency for CPU-bound tasks:
  * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
@@ -936,6 +948,13 @@ void task_numa_work(struct callback_head *work)
 		if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 			continue;
 
+		/*
+		 * Skip inaccessible VMAs to avoid any confusion between
+		 * PROT_NONE and NUMA hinting ptes
+		 */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
@@ -1201,8 +1220,91 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
-/*
- * We can represent the historical contribution to runnable average as the
+#ifdef CONFIG_SCHED_HMP
+#define HMP_VARIABLE_SCALE_SHIFT 16ULL
+struct hmp_global_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct kobject *kobj,
+			struct attribute *attr, char *buf);
+	ssize_t (*store)(struct kobject *a, struct attribute *b,
+			const char *c, size_t count);
+	int *value;
+	int (*to_sysfs)(int);
+	int (*from_sysfs)(int);
+	ssize_t (*to_sysfs_text)(char *buf, int buf_size);
+};
+
+#define HMP_DATA_SYSFS_MAX 8
+
+struct hmp_data_struct {
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	int freqinvar_load_scale_enabled;
+#endif
+	int multiplier; /* used to scale the time delta */
+	struct attribute_group attr_group;
+	struct attribute *attributes[HMP_DATA_SYSFS_MAX + 1];
+	struct hmp_global_attr attr[HMP_DATA_SYSFS_MAX];
+} hmp_data;
+
+static u64 hmp_variable_scale_convert(u64 delta);
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Frequency-Invariant Load Modification:
+ * Loads are calculated as in PJT's patch however we also scale the current
+ * contribution in line with the frequency of the CPU that the task was
+ * executed on.
+ * In this version, we use a simple linear scale derived from the maximum
+ * frequency reported by CPUFreq. As an example:
+ *
+ * Consider that we ran a task for 100% of the previous interval.
+ *
+ * Our CPU was under asynchronous frequency control through one of the
+ * CPUFreq governors.
+ *
+ * The CPUFreq governor reports that it is able to scale the CPU between
+ * 500MHz and 1GHz.
+ *
+ * During the period, the CPU was running at 1GHz.
+ *
+ * In this case, our load contribution for that period is calculated as
+ * 1 * (number_of_active_microseconds)
+ *
+ * This results in our task being able to accumulate maximum load as normal.
+ *
+ *
+ * Consider now that our CPU was executing at 500MHz.
+ *
+ * We now scale the load contribution such that it is calculated as
+ * 0.5 * (number_of_active_microseconds)
+ *
+ * Our task can only record 50% maximum load during this period.
+ *
+ * This represents the task consuming 50% of the CPU's *possible* compute
+ * capacity. However the task did consume 100% of the CPU's *available*
+ * compute capacity which is the value seen by the CPUFreq governor and
+ * user-side CPU Utilization tools.
+ *
+ * Restricting tracked load to be scaled by the CPU's frequency accurately
+ * represents the consumption of possible compute capacity and allows the
+ * HMP migration's simple threshold migration strategy to interact more
+ * predictably with CPUFreq's asynchronous compute capacity changes.
+ */
+#define SCHED_FREQSCALE_SHIFT 10
+struct cpufreq_extents {
+	u32 curr_scale;
+	u32 min;
+	u32 max;
+	u32 flags;
+};
+/* Flag set when the governor in use only allows one frequency.
+ * Disables scaling.
+ */
+#define SCHED_LOAD_FREQINVAR_SINGLEFREQ 0x01
+
+static struct cpufreq_extents freq_scale[CONFIG_NR_CPUS];
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#endif /* CONFIG_SCHED_HMP */
+
+/* We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
  * history into segments of approximately 1ms (1024us); label the segment that
  * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
@@ -1231,13 +1333,24 @@ static u32 __compute_runnable_contrib(u64 n)
  */
 static __always_inline int __update_entity_runnable_avg(u64 now,
 							struct sched_avg *sa,
-							int runnable)
+							int runnable,
+							int running,
+							int cpu)
 {
 	u64 delta, periods;
 	u32 runnable_contrib;
 	int delta_w, decayed = 0;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	u64 scaled_delta;
+	u32 scaled_runnable_contrib;
+	int scaled_delta_w;
+	u32 curr_scale = 1024;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 
 	delta = now - sa->last_runnable_update;
+#ifdef CONFIG_SCHED_HMP
+	delta = hmp_variable_scale_convert(delta);
+#endif
 	/*
 	 * This should only happen when time goes backwards, which it
 	 * unfortunately does during sched clock init when we swap over to TSC.
@@ -1256,6 +1369,12 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		return 0;
 	sa->last_runnable_update = now;
 
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	/* retrieve scale factor for load */
+	if (hmp_data.freqinvar_load_scale_enabled)
+		curr_scale = freq_scale[cpu].curr_scale;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+
 	/* delta_w is the amount already accumulated against our next period */
 	delta_w = sa->runnable_avg_period % 1024;
 	if (delta + delta_w >= 1024) {
@@ -1268,8 +1387,20 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		 * period and accrue it.
 		 */
 		delta_w = 1024 - delta_w;
+		/* scale runnable time if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+		scaled_delta_w = (delta_w * curr_scale)
+				>> SCHED_FREQSCALE_SHIFT;
+		if (runnable)
+			sa->runnable_avg_sum += scaled_delta_w;
+		if (running)
+			sa->usage_avg_sum += scaled_delta_w;
+#else
 		if (runnable)
 			sa->runnable_avg_sum += delta_w;
+		if (running)
+			sa->usage_avg_sum += delta_w;
+#endif /* #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 		sa->runnable_avg_period += delta_w;
 
 		delta -= delta_w;
@@ -1277,22 +1408,49 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		/* Figure out how many additional periods this update spans */
 		periods = delta / 1024;
 		delta %= 1024;
-
+		/* decay the load we have accumulated so far */
 		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
 						  periods + 1);
 		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
 						     periods + 1);
-
+		sa->usage_avg_sum = decay_load(sa->usage_avg_sum, periods + 1);
+		/* add the contribution from this period */
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		runnable_contrib = __compute_runnable_contrib(periods);
+		/* Apply load scaling if necessary.
+		 * Note that multiplying the whole series is same as
+		 * multiplying all terms
+		 */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+		scaled_runnable_contrib = (runnable_contrib * curr_scale)
+				>> SCHED_FREQSCALE_SHIFT;
+		if (runnable)
+			sa->runnable_avg_sum += scaled_runnable_contrib;
+		if (running)
+			sa->usage_avg_sum += scaled_runnable_contrib;
+#else
 		if (runnable)
 			sa->runnable_avg_sum += runnable_contrib;
+		if (running)
+			sa->usage_avg_sum += runnable_contrib;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 		sa->runnable_avg_period += runnable_contrib;
 	}
 
 	/* Remainder of delta accrued against u_0` */
+	/* scale if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	scaled_delta = ((delta * curr_scale) >> SCHED_FREQSCALE_SHIFT);
+	if (runnable)
+		sa->runnable_avg_sum += scaled_delta;
+	if (running)
+		sa->usage_avg_sum += scaled_delta;
+#else
 	if (runnable)
 		sa->runnable_avg_sum += delta;
+	if (running)
+		sa->usage_avg_sum += delta;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 	sa->runnable_avg_period += delta;
 
 	return decayed;
@@ -1305,12 +1463,9 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
 	u64 decays = atomic64_read(&cfs_rq->decay_counter);
 
 	decays -= se->avg.decay_count;
-	if (!decays)
-		return 0;
-
-	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	if (decays)
+		se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
 	se->avg.decay_count = 0;
-
 	return decays;
 }
 
@@ -1338,16 +1493,28 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 						  struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg = cfs_rq->tg;
-	long contrib;
+	long contrib, usage_contrib;
 
 	/* The fraction of a cpu used by this cfs_rq */
 	contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT,
 			  sa->runnable_avg_period + 1);
 	contrib -= cfs_rq->tg_runnable_contrib;
 
-	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
+	usage_contrib = div_u64(sa->usage_avg_sum << NICE_0_SHIFT,
+			        sa->runnable_avg_period + 1);
+	usage_contrib -= cfs_rq->tg_usage_contrib;
+
+	/*
+	 * contrib/usage at this point represent deltas, only update if they
+	 * are substantive.
+	 */
+	if ((abs(contrib) > cfs_rq->tg_runnable_contrib / 64) ||
+	    (abs(usage_contrib) > cfs_rq->tg_usage_contrib / 64)) {
 		atomic_add(contrib, &tg->runnable_avg);
 		cfs_rq->tg_runnable_contrib += contrib;
+
+		atomic_add(usage_contrib, &tg->usage_avg);
+		cfs_rq->tg_usage_contrib += usage_contrib;
 	}
 }
 
@@ -1408,12 +1575,18 @@ static inline void __update_task_entity_contrib(struct sched_entity *se)
 	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
 	contrib /= (se->avg.runnable_avg_period + 1);
 	se->avg.load_avg_contrib = scale_load(contrib);
+	trace_sched_task_load_contrib(task_of(se), se->avg.load_avg_contrib);
+	contrib = se->avg.runnable_avg_sum * scale_load_down(NICE_0_LOAD);
+	contrib /= (se->avg.runnable_avg_period + 1);
+	se->avg.load_avg_ratio = scale_load(contrib);
+	trace_sched_task_runnable_ratio(task_of(se), se->avg.load_avg_ratio);
 }
 
 /* Compute the current contribution to load_avg by se, return any delta */
-static long __update_entity_load_avg_contrib(struct sched_entity *se)
+static long __update_entity_load_avg_contrib(struct sched_entity *se, long *ratio)
 {
 	long old_contrib = se->avg.load_avg_contrib;
+	long old_ratio   = se->avg.load_avg_ratio;
 
 	if (entity_is_task(se)) {
 		__update_task_entity_contrib(se);
@@ -1422,6 +1595,8 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
 		__update_group_entity_contrib(se);
 	}
 
+	if (ratio)
+		*ratio = se->avg.load_avg_ratio - old_ratio;
 	return se->avg.load_avg_contrib - old_contrib;
 }
 
@@ -1441,9 +1616,13 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	long contrib_delta;
+	long contrib_delta, ratio_delta;
 	u64 now;
+	int cpu = -1;   /* not used in normal case */
 
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	cpu = cfs_rq->rq->cpu;
+#endif
 	/*
 	 * For a group entity we need to use their owned cfs_rq_clock_task() in
 	 * case they are the parent of a throttled hierarchy.
@@ -1453,18 +1632,21 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 	else
 		now = cfs_rq_clock_task(group_cfs_rq(se));
 
-	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
+			cfs_rq->curr == se, cpu))
 		return;
 
-	contrib_delta = __update_entity_load_avg_contrib(se);
+	contrib_delta = __update_entity_load_avg_contrib(se, &ratio_delta);
 
 	if (!update_cfs_rq)
 		return;
 
-	if (se->on_rq)
+	if (se->on_rq) {
 		cfs_rq->runnable_load_avg += contrib_delta;
-	else
+		rq_of(cfs_rq)->avg.load_avg_ratio += ratio_delta;
+	} else {
 		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+	}
 }
 
 /*
@@ -1497,8 +1679,17 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+	int cpu = -1;	/* not used in normal case */
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	cpu = rq->cpu;
+#endif
+	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable,
+				     runnable, cpu);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
+	trace_sched_rq_runnable_ratio(cpu_of(rq), rq->avg.load_avg_ratio);
+	trace_sched_rq_runnable_load(cpu_of(rq), rq->cfs.runnable_load_avg);
+	trace_sched_rq_nr_running(cpu_of(rq), rq->nr_running, rq->nr_iowait.counter);
 }
 
 /* Add the load generated by se into cfs_rq's child load-average */
@@ -1540,6 +1731,8 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	}
 
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+	rq_of(cfs_rq)->avg.load_avg_ratio += se->avg.load_avg_ratio;
+
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
 }
@@ -1558,6 +1751,8 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 	update_cfs_rq_blocked_load(cfs_rq, !sleep);
 
 	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+	rq_of(cfs_rq)->avg.load_avg_ratio -= se->avg.load_avg_ratio;
+
 	if (sleep) {
 		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -1886,6 +2081,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
+		update_entity_load_avg(se, 1);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -2022,13 +2218,14 @@ static inline bool cfs_bandwidth_used(void)
 	return static_key_false(&__cfs_bandwidth_used);
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled)
+void cfs_bandwidth_usage_inc(void)
 {
-	/* only need to count groups transitioning between enabled/!enabled */
-	if (enabled && !was_enabled)
-		static_key_slow_inc(&__cfs_bandwidth_used);
-	else if (!enabled && was_enabled)
-		static_key_slow_dec(&__cfs_bandwidth_used);
+	static_key_slow_inc(&__cfs_bandwidth_used);
+}
+
+void cfs_bandwidth_usage_dec(void)
+{
+	static_key_slow_dec(&__cfs_bandwidth_used);
 }
 #else /* HAVE_JUMP_LABEL */
 static bool cfs_bandwidth_used(void)
@@ -2036,7 +2233,8 @@ static bool cfs_bandwidth_used(void)
 	return true;
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
+void cfs_bandwidth_usage_inc(void) {}
+void cfs_bandwidth_usage_dec(void) {}
 #endif /* HAVE_JUMP_LABEL */
 
 /*
@@ -2288,6 +2486,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled_clock = rq->clock;
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (!cfs_b->timer_active)
+		__start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -2399,6 +2599,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (idle)
 		goto out_unlock;
 
+	/*
+	 * if we have relooped after returning idle once, we need to update our
+	 * status as actually running, so that other cpus doing
+	 * __start_cfs_bandwidth will stop trying to cancel us.
+	 */
+	cfs_b->timer_active = 1;
+
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -2459,7 +2666,13 @@ static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
 /* how long we wait to gather additional slack before distributing */
 static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
 
-/* are we near the end of the current quota period? */
+/*
+ * Are we near the end of the current quota period?
+ *
+ * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
+ * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * migrate_hrtimers, base is never cleared, so we are fine.
+ */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 {
 	struct hrtimer *refresh_timer = &cfs_b->period_timer;
@@ -2535,10 +2748,12 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	u64 expires;
 
 	/* confirm we're still not at a refresh boundary */
-	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
+	raw_spin_lock(&cfs_b->lock);
+	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
+		raw_spin_unlock(&cfs_b->lock);
 		return;
+	}
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
 		runtime = cfs_b->runtime;
 		cfs_b->runtime = 0;
@@ -2663,11 +2878,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	 * (timer_active==0 becomes visible before the hrtimer call-back
 	 * terminates).  In either case we ensure that it's re-programmed
 	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+		/* bounce the lock to allow do_sched_cfs_period_timer to run */
 		raw_spin_unlock(&cfs_b->lock);
-		/* ensure cfs_b->lock is available while we wait */
-		hrtimer_cancel(&cfs_b->period_timer);
-
+		cpu_relax();
 		raw_spin_lock(&cfs_b->lock);
 		/* if someone else restarted the timer then we're done */
 		if (cfs_b->timer_active)
@@ -3315,6 +3530,835 @@ done:
 	return target;
 }
 
+#ifdef CONFIG_SCHED_HMP
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * The cpu types are distinguished using a list of hmp_domains
+ * which each represent one cpu type using a cpumask.
+ * The list is assumed ordered by compute capacity with the
+ * fastest domain first.
+ */
+DEFINE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+static const int hmp_max_tasks = 5;
+
+extern void __init arch_get_hmp_domains(struct list_head *hmp_domains_list);
+
+#ifdef CONFIG_CPU_IDLE
+/*
+ * hmp_idle_pull:
+ *
+ * In this version we have stopped using forced up migrations when we
+ * detect that a task running on a little CPU should be moved to a bigger
+ * CPU. In most cases, the bigger CPU is in a deep sleep state and a forced
+ * migration means we stop the task immediately but need to wait for the
+ * target CPU to wake up before we can restart the task which is being
+ * moved. Instead, we now wake a big CPU with an IPI and ask it to pull
+ * a task when ready. This allows the task to continue executing on its
+ * current CPU, reducing the amount of time that the task is stalled for.
+ *
+ * keepalive timers:
+ *
+ * The keepalive timer is used as a way to keep a CPU engaged in an
+ * idle pull operation out of idle while waiting for the source
+ * CPU to stop and move the task. Ideally this would not be necessary
+ * and we could impose a temporary zero-latency requirement on the
+ * current CPU, but in the current QoS framework this will result in
+ * all CPUs in the system being unable to enter idle states which is
+ * not desirable. The timer does not perform any work when it expires.
+ */
+struct hmp_keepalive {
+	bool init;
+	ktime_t delay;	/* if zero, no need for timer */
+	struct hrtimer timer;
+};
+DEFINE_PER_CPU(struct hmp_keepalive, hmp_cpu_keepalive);
+
+/* setup per-cpu keepalive timers */
+static enum hrtimer_restart hmp_cpu_keepalive_notify(struct hrtimer *hrtimer)
+{
+	return HRTIMER_NORESTART;
+}
+
+/*
+ * Work out if any of the idle states have an exit latency too high for us.
+ * ns_delay is passed in containing the max we are willing to tolerate.
+ * If there are none, set ns_delay to zero.
+ * If there are any, set ns_delay to
+ * ('target_residency of state with shortest too-big latency' - 1) * 1000.
+ */
+static void hmp_keepalive_delay(int cpu, unsigned int *ns_delay)
+{
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+	struct cpuidle_driver *drv;
+
+	drv = cpuidle_get_cpu_driver(dev);
+	if (drv) {
+		unsigned int us_delay = UINT_MAX;
+		unsigned int us_max_delay = *ns_delay / 1000;
+		int idx;
+		/* if cpuidle states are guaranteed to be sorted we
+		 * could stop at the first match.
+		 */
+		for (idx = 0; idx < drv->state_count; idx++) {
+			if (drv->states[idx].exit_latency > us_max_delay &&
+				drv->states[idx].target_residency < us_delay) {
+				us_delay = drv->states[idx].target_residency;
+			}
+		}
+		if (us_delay == UINT_MAX)
+			*ns_delay = 0; /* no timer required */
+		else
+			*ns_delay = 1000 * (us_delay - 1);
+	}
+}
+
+static void hmp_cpu_keepalive_trigger(void)
+{
+	int cpu = smp_processor_id();
+	struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+	if (!keepalive->init) {
+		unsigned int ns_delay = 100000; /* tolerate 100usec delay */
+
+		hrtimer_init(&keepalive->timer,
+				CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+		keepalive->timer.function = hmp_cpu_keepalive_notify;
+
+		hmp_keepalive_delay(cpu, &ns_delay);
+		keepalive->delay = ns_to_ktime(ns_delay);
+		keepalive->init = true;
+	}
+	if (ktime_to_ns(keepalive->delay))
+		hrtimer_start(&keepalive->timer,
+			keepalive->delay, HRTIMER_MODE_REL_PINNED);
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+	struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+	if (keepalive->init)
+		hrtimer_cancel(&keepalive->timer);
+}
+#else /* !CONFIG_CPU_IDLE */
+static void hmp_cpu_keepalive_trigger(void)
+{
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+}
+#endif
+
+/* Setup hmp_domains */
+static int __init hmp_cpu_mask_setup(void)
+{
+	char buf[64];
+	struct hmp_domain *domain;
+	struct list_head *pos;
+	int dc, cpu;
+
+	pr_debug("Initializing HMP scheduler:\n");
+
+	/* Initialize hmp_domains using platform code */
+	arch_get_hmp_domains(&hmp_domains);
+	if (list_empty(&hmp_domains)) {
+		pr_debug("HMP domain list is empty!\n");
+		return 0;
+	}
+
+	/* Print hmp_domains */
+	dc = 0;
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		cpulist_scnprintf(buf, 64, &domain->possible_cpus);
+		pr_debug("  HMP domain %d: %s\n", dc, buf);
+
+		for_each_cpu_mask(cpu, domain->possible_cpus) {
+			per_cpu(hmp_cpu_domain, cpu) = domain;
+		}
+		dc++;
+	}
+
+	return 1;
+}
+
+static struct hmp_domain *hmp_get_hmp_domain_for_cpu(int cpu)
+{
+	struct hmp_domain *domain;
+	struct list_head *pos;
+
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		if(cpumask_test_cpu(cpu, &domain->possible_cpus))
+			return domain;
+	}
+	return NULL;
+}
+
+static void hmp_online_cpu(int cpu)
+{
+	struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+	if(domain)
+		cpumask_set_cpu(cpu, &domain->cpus);
+}
+
+static void hmp_offline_cpu(int cpu)
+{
+	struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+	if(domain)
+		cpumask_clear_cpu(cpu, &domain->cpus);
+
+	hmp_cpu_keepalive_cancel(cpu);
+}
+/*
+ * Needed to determine heaviest tasks etc.
+ */
+static inline unsigned int hmp_cpu_is_fastest(int cpu);
+static inline unsigned int hmp_cpu_is_slowest(int cpu);
+static inline struct hmp_domain *hmp_slower_domain(int cpu);
+static inline struct hmp_domain *hmp_faster_domain(int cpu);
+
+/* must hold runqueue lock for queue se is currently on */
+static struct sched_entity *hmp_get_heaviest_task(
+				struct sched_entity *se, int target_cpu)
+{
+	int num_tasks = hmp_max_tasks;
+	struct sched_entity *max_se = se;
+	unsigned long int max_ratio = se->avg.load_avg_ratio;
+	const struct cpumask *hmp_target_mask = NULL;
+	struct hmp_domain *hmp;
+
+	if (hmp_cpu_is_fastest(cpu_of(se->cfs_rq->rq)))
+		return max_se;
+
+	hmp = hmp_faster_domain(cpu_of(se->cfs_rq->rq));
+	hmp_target_mask = &hmp->cpus;
+	if (target_cpu >= 0) {
+		/* idle_balance gets run on a CPU while
+		 * it is in the middle of being hotplugged
+		 * out. Bail early in that case.
+		 */
+		if(!cpumask_test_cpu(target_cpu, hmp_target_mask))
+			return NULL;
+		hmp_target_mask = cpumask_of(target_cpu);
+	}
+	/* The currently running task is not on the runqueue */
+	se = __pick_first_entity(cfs_rq_of(se));
+
+	while (num_tasks && se) {
+		if (entity_is_task(se) &&
+			se->avg.load_avg_ratio > max_ratio &&
+			cpumask_intersects(hmp_target_mask,
+				tsk_cpus_allowed(task_of(se)))) {
+			max_se = se;
+			max_ratio = se->avg.load_avg_ratio;
+		}
+		se = __pick_next_entity(se);
+		num_tasks--;
+	}
+	return max_se;
+}
+
+static struct sched_entity *hmp_get_lightest_task(
+				struct sched_entity *se, int migrate_down)
+{
+	int num_tasks = hmp_max_tasks;
+	struct sched_entity *min_se = se;
+	unsigned long int min_ratio = se->avg.load_avg_ratio;
+	const struct cpumask *hmp_target_mask = NULL;
+
+	if (migrate_down) {
+		struct hmp_domain *hmp;
+		if (hmp_cpu_is_slowest(cpu_of(se->cfs_rq->rq)))
+			return min_se;
+		hmp = hmp_slower_domain(cpu_of(se->cfs_rq->rq));
+		hmp_target_mask = &hmp->cpus;
+	}
+	/* The currently running task is not on the runqueue */
+	se = __pick_first_entity(cfs_rq_of(se));
+
+	while (num_tasks && se) {
+		if (entity_is_task(se) &&
+			(se->avg.load_avg_ratio < min_ratio &&
+			hmp_target_mask &&
+				cpumask_intersects(hmp_target_mask,
+				tsk_cpus_allowed(task_of(se))))) {
+			min_se = se;
+			min_ratio = se->avg.load_avg_ratio;
+		}
+		se = __pick_next_entity(se);
+		num_tasks--;
+	}
+	return min_se;
+}
+
+/*
+ * Migration thresholds should be in the range [0..1023]
+ * hmp_up_threshold: min. load required for migrating tasks to a faster cpu
+ * hmp_down_threshold: max. load allowed for tasks migrating to a slower cpu
+ *
+ * hmp_up_prio: Only up migrate task with high priority (<hmp_up_prio)
+ * hmp_next_up_threshold: Delay before next up migration (1024 ~= 1 ms)
+ * hmp_next_down_threshold: Delay before next down migration (1024 ~= 1 ms)
+ *
+ * Small Task Packing:
+ * We can choose to fill the littlest CPUs in an HMP system rather than
+ * the typical spreading mechanic. This behavior is controllable using
+ * two variables.
+ * hmp_packing_enabled: runtime control over pack/spread
+ * hmp_full_threshold: Consider a CPU with this much unweighted load full
+ */
+unsigned int hmp_up_threshold = 700;
+unsigned int hmp_down_threshold = 512;
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+unsigned int hmp_up_prio = NICE_TO_PRIO(CONFIG_SCHED_HMP_PRIO_FILTER_VAL);
+#endif
+unsigned int hmp_next_up_threshold = 4096;
+unsigned int hmp_next_down_threshold = 4096;
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Set the default packing threshold to try to keep little
+ * CPUs at no more than 80% of their maximum frequency if only
+ * packing a small number of small tasks. Bigger tasks will
+ * raise frequency as normal.
+ * In order to pack a task onto a CPU, the sum of the
+ * unweighted runnable_avg load of existing tasks plus the
+ * load of the new task must be less than hmp_full_threshold.
+ *
+ * This works in conjunction with frequency-invariant load
+ * and DVFS governors. Since most DVFS governors aim for 80%
+ * utilisation, we arrive at (0.8*0.8*(max_load=1024))=655
+ * and use a value slightly lower to give a little headroom
+ * in the decision.
+ * Note that the most efficient frequency is different for
+ * each system so /sys/kernel/hmp/packing_limit should be
+ * configured at runtime for any given platform to achieve
+ * optimal energy usage. Some systems may not benefit from
+ * packing, so this feature can also be disabled at runtime
+ * with /sys/kernel/hmp/packing_enable
+ */
+unsigned int hmp_packing_enabled = 1;
+unsigned int hmp_full_threshold = 650;
+#endif
+
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se);
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se);
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+						int *min_cpu, struct cpumask *affinity);
+
+static inline struct hmp_domain *hmp_smallest_domain(void)
+{
+	return list_entry(hmp_domains.prev, struct hmp_domain, hmp_domains);
+}
+
+/* Check if cpu is in fastest hmp_domain */
+static inline unsigned int hmp_cpu_is_fastest(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return pos == hmp_domains.next;
+}
+
+/* Check if cpu is in slowest hmp_domain */
+static inline unsigned int hmp_cpu_is_slowest(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_is_last(pos, &hmp_domains);
+}
+
+/* Next (slower) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_slower_domain(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_entry(pos->next, struct hmp_domain, hmp_domains);
+}
+
+/* Previous (faster) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_faster_domain(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_entry(pos->prev, struct hmp_domain, hmp_domains);
+}
+
+/*
+ * Selects a cpu in previous (faster) hmp_domain
+ */
+static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk,
+							int cpu)
+{
+	int lowest_cpu=NR_CPUS;
+	__always_unused int lowest_ratio;
+	struct hmp_domain *hmp;
+
+	if (hmp_cpu_is_fastest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_faster_domain(cpu);
+
+	lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+			tsk_cpus_allowed(tsk));
+
+	return lowest_cpu;
+}
+
+/*
+ * Selects a cpu in next (slower) hmp_domain
+ * Note that cpumask_any_and() returns the first cpu in the cpumask
+ */
+static inline unsigned int hmp_select_slower_cpu(struct task_struct *tsk,
+							int cpu)
+{
+	int lowest_cpu=NR_CPUS;
+	struct hmp_domain *hmp;
+	__always_unused int lowest_ratio;
+
+	if (hmp_cpu_is_slowest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_slower_domain(cpu);
+
+	lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+			tsk_cpus_allowed(tsk));
+
+	return lowest_cpu;
+}
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Select the 'best' candidate little CPU to wake up on.
+ * Implements a packing strategy which examines CPU in
+ * logical CPU order, and selects the first which will
+ * be loaded less than hmp_full_threshold according to
+ * the sum of the tracked load of the runqueue and the task.
+ */
+static inline unsigned int hmp_best_little_cpu(struct task_struct *tsk,
+		int cpu) {
+	int tmp_cpu;
+	unsigned long estimated_load;
+	struct hmp_domain *hmp;
+	struct sched_avg *avg;
+	struct cpumask allowed_hmp_cpus;
+
+	if(!hmp_packing_enabled ||
+			tsk->se.avg.load_avg_ratio > ((NICE_0_LOAD * 90)/100))
+		return hmp_select_slower_cpu(tsk, cpu);
+
+	if (hmp_cpu_is_slowest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_slower_domain(cpu);
+
+	/* respect affinity */
+	cpumask_and(&allowed_hmp_cpus, &hmp->cpus,
+			tsk_cpus_allowed(tsk));
+
+	for_each_cpu_mask(tmp_cpu, allowed_hmp_cpus) {
+		avg = &cpu_rq(tmp_cpu)->avg;
+		/* estimate new rq load if we add this task */
+		estimated_load = avg->load_avg_ratio +
+				tsk->se.avg.load_avg_ratio;
+		if (estimated_load <= hmp_full_threshold) {
+			cpu = tmp_cpu;
+			break;
+		}
+	}
+	/* if no match was found, the task uses the initial value */
+	return cpu;
+}
+#endif
+static inline void hmp_next_up_delay(struct sched_entity *se, int cpu)
+{
+	/* hack - always use clock from first online CPU */
+	u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	se->avg.hmp_last_up_migration = now;
+	se->avg.hmp_last_down_migration = 0;
+	cpu_rq(cpu)->avg.hmp_last_up_migration = now;
+	cpu_rq(cpu)->avg.hmp_last_down_migration = 0;
+}
+
+static inline void hmp_next_down_delay(struct sched_entity *se, int cpu)
+{
+	/* hack - always use clock from first online CPU */
+	u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	se->avg.hmp_last_down_migration = now;
+	se->avg.hmp_last_up_migration = 0;
+	cpu_rq(cpu)->avg.hmp_last_down_migration = now;
+	cpu_rq(cpu)->avg.hmp_last_up_migration = 0;
+}
+
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * These functions allow to change the growing speed of the load_avg_ratio
+ * by default it goes from 0 to 0.5 in LOAD_AVG_PERIOD = 32ms
+ * This can now be changed with /sys/kernel/hmp/load_avg_period_ms.
+ *
+ * These functions also allow to change the up and down threshold of HMP
+ * using /sys/kernel/hmp/{up,down}_threshold.
+ * Both must be between 0 and 1023. The threshold that is compared
+ * to the load_avg_ratio is up_threshold/1024 and down_threshold/1024.
+ *
+ * For instance, if load_avg_period = 64 and up_threshold = 512, an idle
+ * task with a load of 0 will reach the threshold after 64ms of busy loop.
+ *
+ * Changing load_avg_periods_ms has the same effect than changing the
+ * default scaling factor Y=1002/1024 in the load_avg_ratio computation to
+ * (1002/1024.0)^(LOAD_AVG_PERIOD/load_avg_period_ms), but the last one
+ * could trigger overflows.
+ * For instance, with Y = 1023/1024 in __update_task_entity_contrib()
+ * "contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);"
+ * could be overflowed for a weight > 2^12 even is the load_avg_contrib
+ * should still be a 32bits result. This would not happen by multiplicating
+ * delta time by 1/22 and setting load_avg_period_ms = 706.
+ */
+
+/*
+ * By scaling the delta time it end-up increasing or decrease the
+ * growing speed of the per entity load_avg_ratio
+ * The scale factor hmp_data.multiplier is a fixed point
+ * number: (32-HMP_VARIABLE_SCALE_SHIFT).HMP_VARIABLE_SCALE_SHIFT
+ */
+static inline u64 hmp_variable_scale_convert(u64 delta)
+{
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+	u64 high = delta >> 32ULL;
+	u64 low = delta & 0xffffffffULL;
+	low *= hmp_data.multiplier;
+	high *= hmp_data.multiplier;
+	return (low >> HMP_VARIABLE_SCALE_SHIFT)
+			+ (high << (32ULL - HMP_VARIABLE_SCALE_SHIFT));
+#else
+	return delta;
+#endif
+}
+
+static ssize_t hmp_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct hmp_global_attr *hmp_attr =
+		container_of(attr, struct hmp_global_attr, attr);
+	int temp;
+
+	if (hmp_attr->to_sysfs_text != NULL)
+		return hmp_attr->to_sysfs_text(buf, PAGE_SIZE);
+
+	temp = *(hmp_attr->value);
+	if (hmp_attr->to_sysfs != NULL)
+		temp = hmp_attr->to_sysfs(temp);
+
+	return (ssize_t)sprintf(buf, "%d\n", temp);
+}
+
+static ssize_t hmp_store(struct kobject *a, struct attribute *attr,
+				const char *buf, size_t count)
+{
+	int temp;
+	ssize_t ret = count;
+	struct hmp_global_attr *hmp_attr =
+		container_of(attr, struct hmp_global_attr, attr);
+	char *str = vmalloc(count + 1);
+	if (str == NULL)
+		return -ENOMEM;
+	memcpy(str, buf, count);
+	str[count] = 0;
+	if (sscanf(str, "%d", &temp) < 1)
+		ret = -EINVAL;
+	else {
+		if (hmp_attr->from_sysfs != NULL)
+			temp = hmp_attr->from_sysfs(temp);
+		if (temp < 0)
+			ret = -EINVAL;
+		else
+			*(hmp_attr->value) = temp;
+	}
+	vfree(str);
+	return ret;
+}
+
+static ssize_t hmp_print_domains(char *outbuf, int outbufsize)
+{
+	char buf[64];
+	const char nospace[] = "%s", space[] = " %s";
+	const char *fmt = nospace;
+	struct hmp_domain *domain;
+	struct list_head *pos;
+	int outpos = 0;
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		if (cpumask_scnprintf(buf, 64, &domain->possible_cpus)) {
+			outpos += sprintf(outbuf+outpos, fmt, buf);
+			fmt = space;
+		}
+	}
+	strcat(outbuf, "\n");
+	return outpos+1;
+}
+
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+static int hmp_period_tofrom_sysfs(int value)
+{
+	return (LOAD_AVG_PERIOD << HMP_VARIABLE_SCALE_SHIFT) / value;
+}
+#endif
+/* max value for threshold is 1024 */
+static int hmp_theshold_from_sysfs(int value)
+{
+	if (value > 1024)
+		return -1;
+	return value;
+}
+#if defined(CONFIG_SCHED_HMP_LITTLE_PACKING) || \
+		defined(CONFIG_HMP_FREQUENCY_INVARIANT_SCALE)
+/* toggle control is only 0,1 off/on */
+static int hmp_toggle_from_sysfs(int value)
+{
+	if (value < 0 || value > 1)
+		return -1;
+	return value;
+}
+#endif
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/* packing value must be non-negative */
+static int hmp_packing_from_sysfs(int value)
+{
+	if (value < 0)
+		return -1;
+	return value;
+}
+#endif
+static void hmp_attr_add(
+	const char *name,
+	int *value,
+	int (*to_sysfs)(int),
+	int (*from_sysfs)(int),
+	ssize_t (*to_sysfs_text)(char *, int),
+	umode_t mode)
+{
+	int i = 0;
+	while (hmp_data.attributes[i] != NULL) {
+		i++;
+		if (i >= HMP_DATA_SYSFS_MAX)
+			return;
+	}
+	if (mode)
+		hmp_data.attr[i].attr.mode = mode;
+	else
+		hmp_data.attr[i].attr.mode = 0644;
+	hmp_data.attr[i].show = hmp_show;
+	hmp_data.attr[i].store = hmp_store;
+	hmp_data.attr[i].attr.name = name;
+	hmp_data.attr[i].value = value;
+	hmp_data.attr[i].to_sysfs = to_sysfs;
+	hmp_data.attr[i].from_sysfs = from_sysfs;
+	hmp_data.attr[i].to_sysfs_text = to_sysfs_text;
+	hmp_data.attributes[i] = &hmp_data.attr[i].attr;
+	hmp_data.attributes[i + 1] = NULL;
+}
+
+static int hmp_attr_init(void)
+{
+	int ret;
+	memset(&hmp_data, sizeof(hmp_data), 0);
+	hmp_attr_add("hmp_domains",
+		NULL,
+		NULL,
+		NULL,
+		hmp_print_domains,
+		0444);
+	hmp_attr_add("up_threshold",
+		&hmp_up_threshold,
+		NULL,
+		hmp_theshold_from_sysfs,
+		NULL,
+		0);
+	hmp_attr_add("down_threshold",
+		&hmp_down_threshold,
+		NULL,
+		hmp_theshold_from_sysfs,
+		NULL,
+		0);
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+	/* by default load_avg_period_ms == LOAD_AVG_PERIOD
+	 * meaning no change
+	 */
+	hmp_data.multiplier = hmp_period_tofrom_sysfs(LOAD_AVG_PERIOD);
+	hmp_attr_add("load_avg_period_ms",
+		&hmp_data.multiplier,
+		hmp_period_tofrom_sysfs,
+		hmp_period_tofrom_sysfs,
+		NULL,
+		0);
+#endif
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	/* default frequency-invariant scaling ON */
+	hmp_data.freqinvar_load_scale_enabled = 1;
+	hmp_attr_add("frequency_invariant_load_scale",
+		&hmp_data.freqinvar_load_scale_enabled,
+		NULL,
+		hmp_toggle_from_sysfs,
+		NULL,
+		0);
+#endif
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+	hmp_attr_add("packing_enable",
+		&hmp_packing_enabled,
+		NULL,
+		hmp_toggle_from_sysfs,
+		NULL,
+		0);
+	hmp_attr_add("packing_limit",
+		&hmp_full_threshold,
+		NULL,
+		hmp_packing_from_sysfs,
+		NULL,
+		0);
+#endif
+	hmp_data.attr_group.name = "hmp";
+	hmp_data.attr_group.attrs = hmp_data.attributes;
+	ret = sysfs_create_group(kernel_kobj,
+		&hmp_data.attr_group);
+	return 0;
+}
+late_initcall(hmp_attr_init);
+/*
+ * return the load of the lowest-loaded CPU in a given HMP domain
+ * min_cpu optionally points to an int to receive the CPU.
+ * affinity optionally points to a cpumask containing the
+ * CPUs to be considered. note:
+ *   + min_cpu = NR_CPUS only if no CPUs are in the set of
+ *     affinity && hmp_domain cpus
+ *   + min_cpu will always otherwise equal one of the CPUs in
+ *     the hmp domain
+ *   + when more than one CPU has the same load, the one which
+ *     is least-recently-disturbed by an HMP migration will be
+ *     selected
+ *   + if all CPUs are equally loaded or idle and the times are
+ *     all the same, the first in the set will be used
+ *   + if affinity is not set, cpu_online_mask is used
+ */
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+						int *min_cpu, struct cpumask *affinity)
+{
+	int cpu;
+	int min_cpu_runnable_temp = NR_CPUS;
+	u64 min_target_last_migration = ULLONG_MAX;
+	u64 curr_last_migration;
+	unsigned long min_runnable_load = INT_MAX;
+	unsigned long contrib;
+	struct sched_avg *avg;
+	struct cpumask temp_cpumask;
+	/*
+	 * only look at CPUs allowed if specified,
+	 * otherwise look at all online CPUs in the
+	 * right HMP domain
+	 */
+	cpumask_and(&temp_cpumask, &hmpd->cpus, affinity ? affinity : cpu_online_mask);
+
+	for_each_cpu_mask(cpu, temp_cpumask) {
+		avg = &cpu_rq(cpu)->avg;
+		/* used for both up and down migration */
+		curr_last_migration = avg->hmp_last_up_migration ?
+			avg->hmp_last_up_migration : avg->hmp_last_down_migration;
+
+		contrib = avg->load_avg_ratio;
+		/*
+		 * Consider a runqueue completely busy if there is any load
+		 * on it. Definitely not the best for overall fairness, but
+		 * does well in typical Android use cases.
+		 */
+		if (contrib)
+			contrib = 1023;
+
+		if ((contrib < min_runnable_load) ||
+			(contrib == min_runnable_load &&
+			 curr_last_migration < min_target_last_migration)) {
+			/*
+			 * if the load is the same target the CPU with
+			 * the longest time since a migration.
+			 * This is to spread migration load between
+			 * members of a domain more evenly when the
+			 * domain is fully loaded
+			 */
+			min_runnable_load = contrib;
+			min_cpu_runnable_temp = cpu;
+			min_target_last_migration = curr_last_migration;
+		}
+	}
+
+	if (min_cpu)
+		*min_cpu = min_cpu_runnable_temp;
+
+	return min_runnable_load;
+}
+
+/*
+ * Calculate the task starvation
+ * This is the ratio of actually running time vs. runnable time.
+ * If the two are equal the task is getting the cpu time it needs or
+ * it is alone on the cpu and the cpu is fully utilized.
+ */
+static inline unsigned int hmp_task_starvation(struct sched_entity *se)
+{
+	u32 starvation;
+
+	starvation = se->avg.usage_avg_sum * scale_load_down(NICE_0_LOAD);
+	starvation /= (se->avg.runnable_avg_sum + 1);
+
+	return scale_load(starvation);
+}
+
+static inline unsigned int hmp_offload_down(int cpu, struct sched_entity *se)
+{
+	int min_usage;
+	int dest_cpu = NR_CPUS;
+
+	if (hmp_cpu_is_slowest(cpu))
+		return NR_CPUS;
+
+	/* Is there an idle CPU in the current domain */
+	min_usage = hmp_domain_min_load(hmp_cpu_domain(cpu), NULL, NULL);
+	if (min_usage == 0) {
+		trace_sched_hmp_offload_abort(cpu, min_usage, "load");
+		return NR_CPUS;
+	}
+
+	/* Is the task alone on the cpu? */
+	if (cpu_rq(cpu)->cfs.h_nr_running < 2) {
+		trace_sched_hmp_offload_abort(cpu,
+			cpu_rq(cpu)->cfs.h_nr_running, "nr_running");
+		return NR_CPUS;
+	}
+
+	/* Is the task actually starving? */
+	/* >=25% ratio running/runnable = starving */
+	if (hmp_task_starvation(se) > 768) {
+		trace_sched_hmp_offload_abort(cpu, hmp_task_starvation(se),
+			"starvation");
+		return NR_CPUS;
+	}
+
+	/* Does the slower domain have any idle CPUs? */
+	min_usage = hmp_domain_min_load(hmp_slower_domain(cpu), &dest_cpu,
+			tsk_cpus_allowed(task_of(se)));
+
+	if (min_usage == 0) {
+		trace_sched_hmp_offload_succeed(cpu, dest_cpu);
+		return dest_cpu;
+	} else
+		trace_sched_hmp_offload_abort(cpu,min_usage,"slowdomain");
+	return NR_CPUS;
+}
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
@@ -3339,6 +4383,19 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 	if (p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
+#ifdef CONFIG_SCHED_HMP
+	/* always put non-kernel forking tasks on a big domain */
+	if (unlikely(sd_flag & SD_BALANCE_FORK) && hmp_task_should_forkboost(p)) {
+		new_cpu = hmp_select_faster_cpu(p, prev_cpu);
+		if (new_cpu != NR_CPUS) {
+			hmp_next_up_delay(&p->se, new_cpu);
+			return new_cpu;
+		}
+		/* failed to perform HMP fork balance, use normal balance */
+		new_cpu = cpu;
+	}
+#endif
+
 	if (sd_flag & SD_BALANCE_WAKE) {
 		if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
 			want_affine = 1;
@@ -3413,6 +4470,35 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 unlock:
 	rcu_read_unlock();
 
+#ifdef CONFIG_SCHED_HMP
+	prev_cpu = task_cpu(p);
+
+	if (hmp_up_migration(prev_cpu, &new_cpu, &p->se)) {
+		hmp_next_up_delay(&p->se, new_cpu);
+		trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+		return new_cpu;
+	}
+	if (hmp_down_migration(prev_cpu, &p->se)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+		new_cpu = hmp_best_little_cpu(p, prev_cpu);
+#else
+		new_cpu = hmp_select_slower_cpu(p, prev_cpu);
+#endif
+		/*
+		 * we might have no suitable CPU
+		 * in which case new_cpu == NR_CPUS
+		 */
+		if (new_cpu < NR_CPUS && new_cpu != prev_cpu) {
+			hmp_next_down_delay(&p->se, new_cpu);
+			trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+			return new_cpu;
+		}
+	}
+	/* Make sure that the task stays in its previous hmp domain */
+	if (!cpumask_test_cpu(new_cpu, &hmp_cpu_domain(prev_cpu)->cpus))
+		return prev_cpu;
+#endif
+
 	return new_cpu;
 }
 
@@ -3422,6 +4508,16 @@ unlock:
  * load-balance).
  */
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+#ifdef CONFIG_NO_HZ_COMMON
+static int nohz_test_cpu(int cpu);
+#else
+static inline int nohz_test_cpu(int cpu)
+{
+	return 0;
+}
+#endif
+
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -3441,6 +4537,25 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	 * be negative here since on-rq tasks have decay-count == 0.
 	 */
 	if (se->avg.decay_count) {
+		/*
+		 * If we migrate a sleeping task away from a CPU
+		 * which has the tick stopped, then both the clock_task
+		 * and decay_counter will be out of date for that CPU
+		 * and we will not decay load correctly.
+		 */
+		if (!se->on_rq && nohz_test_cpu(task_cpu(p))) {
+			struct rq *rq = cpu_rq(task_cpu(p));
+			unsigned long flags;
+			/*
+			 * Current CPU cannot be holding rq->lock in this
+			 * circumstance, but another might be. We must hold
+			 * rq->lock before we go poking around in its clocks
+			 */
+			raw_spin_lock_irqsave(&rq->lock, flags);
+			update_rq_clock(rq);
+			update_cfs_rq_blocked_load(cfs_rq, 0);
+			raw_spin_unlock_irqrestore(&rq->lock, flags);
+		}
 		se->avg.decay_count = -__synchronize_entity_decay(se);
 		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
 	}
@@ -3946,7 +5061,6 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 1) task is cache cold, or
 	 * 2) too many balance attempts have failed.
 	 */
-
 	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
@@ -5232,6 +6346,16 @@ out:
 	return ld_moved;
 }
 
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_idle_pull(int this_cpu);
+static int move_specific_task(struct lb_env *env, struct task_struct *pm);
+#else
+static int move_specific_task(struct lb_env *env, struct task_struct *pm)
+{
+	return 0;
+}
+#endif
+
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
@@ -5276,7 +6400,10 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 		}
 	}
 	rcu_read_unlock();
-
+#ifdef CONFIG_SCHED_HMP
+	if (!pulled_task)
+		pulled_task = hmp_idle_pull(this_cpu);
+#endif
 	raw_spin_lock(&this_rq->lock);
 
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
@@ -5288,22 +6415,19 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	}
 }
 
-/*
- * active_load_balance_cpu_stop is run by cpu stopper. It pushes
- * running tasks off the busiest CPU onto idle CPUs. It requires at
- * least 1 task to be running on each physical CPU where possible, and
- * avoids physical / logical imbalances.
- */
-static int active_load_balance_cpu_stop(void *data)
+static int __do_active_load_balance_cpu_stop(void *data, bool check_sd_lb_flag)
 {
 	struct rq *busiest_rq = data;
 	int busiest_cpu = cpu_of(busiest_rq);
 	int target_cpu = busiest_rq->push_cpu;
 	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
+	struct task_struct *p = NULL;
 
 	raw_spin_lock_irq(&busiest_rq->lock);
-
+#ifdef CONFIG_SCHED_HMP
+	p = busiest_rq->migrate_task;
+#endif
 	/* make sure the requested cpu hasn't gone down in the meantime */
 	if (unlikely(busiest_cpu != smp_processor_id() ||
 		     !busiest_rq->active_balance))
@@ -5313,6 +6437,11 @@ static int active_load_balance_cpu_stop(void *data)
 	if (busiest_rq->nr_running <= 1)
 		goto out_unlock;
 
+	if (!check_sd_lb_flag) {
+		/* Task has migrated meanwhile, abort forced migration */
+		if (task_rq(p) != busiest_rq)
+			goto out_unlock;
+	}
 	/*
 	 * This condition is "impossible", if it occurs
 	 * we need to fix it. Originally reported by
@@ -5326,12 +6455,14 @@ static int active_load_balance_cpu_stop(void *data)
 	/* Search for an sd spanning us and the target CPU. */
 	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+		if (((check_sd_lb_flag && sd->flags & SD_LOAD_BALANCE) ||
+			!check_sd_lb_flag) &&
+			cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
 				break;
 	}
 
 	if (likely(sd)) {
+		bool success = false;
 		struct lb_env env = {
 			.sd		= sd,
 			.dst_cpu	= target_cpu,
@@ -5343,7 +6474,14 @@ static int active_load_balance_cpu_stop(void *data)
 
 		schedstat_inc(sd, alb_count);
 
-		if (move_one_task(&env))
+		if (check_sd_lb_flag) {
+			if (move_one_task(&env))
+				success = true;
+		} else {
+			if (move_specific_task(&env, p))
+				success = true;
+		}
+		if (success)
 			schedstat_inc(sd, alb_pushed);
 		else
 			schedstat_inc(sd, alb_failed);
@@ -5351,11 +6489,24 @@ static int active_load_balance_cpu_stop(void *data)
 	rcu_read_unlock();
 	double_unlock_balance(busiest_rq, target_rq);
 out_unlock:
+	if (!check_sd_lb_flag)
+		put_task_struct(p);
 	busiest_rq->active_balance = 0;
 	raw_spin_unlock_irq(&busiest_rq->lock);
 	return 0;
 }
 
+/*
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
+ */
+static int active_load_balance_cpu_stop(void *data)
+{
+	return __do_active_load_balance_cpu_stop(data, true);
+}
+
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
@@ -5369,12 +6520,80 @@ static struct {
 	unsigned long next_balance;     /* in jiffy units */
 } nohz ____cacheline_aligned;
 
+/*
+ * nohz_test_cpu used when load tracking is enabled. FAIR_GROUP_SCHED
+ * dependency below may be removed when load tracking guards are
+ * removed.
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int nohz_test_cpu(int cpu)
+{
+	return cpumask_test_cpu(cpu, nohz.idle_cpus_mask);
+}
+#endif
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Decide if the tasks on the busy CPUs in the
+ * littlest domain would benefit from an idle balance
+ */
+static int hmp_packing_ilb_needed(int cpu, int ilb_needed)
+{
+	struct hmp_domain *hmp;
+	/* allow previous decision on non-slowest domain */
+	if (!hmp_cpu_is_slowest(cpu))
+		return ilb_needed;
+
+	/* if disabled, use normal ILB behaviour */
+	if (!hmp_packing_enabled)
+		return ilb_needed;
+
+	hmp = hmp_cpu_domain(cpu);
+	for_each_cpu_and(cpu, &hmp->cpus, nohz.idle_cpus_mask) {
+		/* only idle balance if a CPU is loaded over threshold */
+		if (cpu_rq(cpu)->avg.load_avg_ratio > hmp_full_threshold)
+			return 1;
+	}
+	return 0;
+}
+#endif
+
+DEFINE_PER_CPU(cpumask_var_t, ilb_tmpmask);
+
 static inline int find_new_ilb(int call_cpu)
 {
 	int ilb = cpumask_first(nohz.idle_cpus_mask);
+#ifdef CONFIG_SCHED_HMP
+	int ilb_needed = 0;
+	int cpu;
+	struct cpumask* tmp = per_cpu(ilb_tmpmask, smp_processor_id());
+
+	/* restrict nohz balancing to occur in the same hmp domain */
+	ilb = cpumask_first_and(nohz.idle_cpus_mask,
+			&((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus);
+
+	/* check to see if it's necessary within this domain */
+	cpumask_andnot(tmp,
+			&((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus,
+			nohz.idle_cpus_mask);
+	for_each_cpu(cpu, tmp) {
+		if (cpu_rq(cpu)->nr_running > 1) {
+			ilb_needed = 1;
+			break;
+		}
+	}
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+	if (ilb < nr_cpu_ids)
+		ilb_needed = hmp_packing_ilb_needed(ilb, ilb_needed);
+#endif
 
+	if (ilb_needed && ilb < nr_cpu_ids && idle_cpu(ilb))
+		return ilb;
+#else
 	if (ilb < nr_cpu_ids && idle_cpu(ilb))
 		return ilb;
+#endif
 
 	return nr_cpu_ids;
 }
@@ -5651,6 +6870,18 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
+#ifdef CONFIG_SCHED_HMP
+	/*
+	 * Bail out if there are no nohz CPUs in our
+	 * HMP domain, since we will move tasks between
+	 * domains through wakeup and force balancing
+	 * as necessary based upon task load.
+	 */
+	if (cpumask_first_and(nohz.idle_cpus_mask,
+			&((struct hmp_domain *)hmp_cpu_domain(cpu))->cpus) >= nr_cpu_ids)
+		return 0;
+#endif
+
 	if (rq->nr_running >= 2)
 		goto need_kick;
 
@@ -5683,6 +6914,442 @@ need_kick:
 static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
 #endif
 
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_task_eligible_for_up_migration(struct sched_entity *se)
+{
+	/* below hmp_up_threshold, never eligible */
+	if (se->avg.load_avg_ratio < hmp_up_threshold)
+		return 0;
+	return 1;
+}
+
+/* Check if task should migrate to a faster cpu */
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se)
+{
+	struct task_struct *p = task_of(se);
+	int temp_target_cpu;
+	u64 now;
+
+	if (hmp_cpu_is_fastest(cpu))
+		return 0;
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+	/* Filter by task priority */
+	if (p->prio >= hmp_up_prio)
+		return 0;
+#endif
+	if (!hmp_task_eligible_for_up_migration(se))
+		return 0;
+
+	/* Let the task load settle before doing another up migration */
+	/* hack - always use clock from first online CPU */
+	now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	if (((now - se->avg.hmp_last_up_migration) >> 10)
+					< hmp_next_up_threshold)
+		return 0;
+
+	/* hmp_domain_min_load only returns 0 for an
+	 * idle CPU or 1023 for any partly-busy one.
+	 * Be explicit about requirement for an idle CPU.
+	 */
+	if (hmp_domain_min_load(hmp_faster_domain(cpu), &temp_target_cpu,
+			tsk_cpus_allowed(p)) == 0 && temp_target_cpu != NR_CPUS) {
+		if(target_cpu)
+			*target_cpu = temp_target_cpu;
+		return 1;
+	}
+	return 0;
+}
+
+/* Check if task should migrate to a slower cpu */
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se)
+{
+	struct task_struct *p = task_of(se);
+	u64 now;
+
+	if (hmp_cpu_is_slowest(cpu)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+		if(hmp_packing_enabled)
+			return 1;
+		else
+#endif
+		return 0;
+	}
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+	/* Filter by task priority */
+	if ((p->prio >= hmp_up_prio) &&
+		cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+					tsk_cpus_allowed(p))) {
+		return 1;
+	}
+#endif
+
+	/* Let the task load settle before doing another down migration */
+	/* hack - always use clock from first online CPU */
+	now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	if (((now - se->avg.hmp_last_down_migration) >> 10)
+					< hmp_next_down_threshold)
+		return 0;
+
+	if (cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+					tsk_cpus_allowed(p))
+		&& se->avg.load_avg_ratio < hmp_down_threshold) {
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * hmp_can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ * Ideally this function should be merged with can_migrate_task() to avoid
+ * redundant code.
+ */
+static int hmp_can_migrate_task(struct task_struct *p, struct lb_env *env)
+{
+	int tsk_cache_hot = 0;
+
+	/*
+	 * We do not migrate tasks that are:
+	 * 1) running (obviously), or
+	 * 2) cannot be migrated to this CPU due to cpus_allowed
+	 */
+	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+		return 0;
+	}
+	env->flags &= ~LBF_ALL_PINNED;
+
+	if (task_running(env->src_rq, p)) {
+		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
+		return 0;
+	}
+
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
+
+	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+	if (!tsk_cache_hot ||
+		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+		if (tsk_cache_hot) {
+			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
+	return 1;
+}
+
+/*
+ * move_specific_task tries to move a specific task.
+ * Returns 1 if successful and 0 otherwise.
+ * Called with both runqueues locked.
+ */
+static int move_specific_task(struct lb_env *env, struct task_struct *pm)
+{
+	struct task_struct *p, *n;
+
+	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+	if (throttled_lb_pair(task_group(p), env->src_rq->cpu,
+				env->dst_cpu))
+		continue;
+
+		if (!hmp_can_migrate_task(p, env))
+			continue;
+		/* Check if we found the right task */
+		if (p != pm)
+			continue;
+
+		move_task(p, env);
+		/*
+		 * Right now, this is only the third place move_task()
+		 * is called, so we can safely collect move_task()
+		 * stats here rather than inside move_task().
+		 */
+		schedstat_inc(env->sd, lb_gained[env->idle]);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * hmp_active_task_migration_cpu_stop is run by cpu stopper and used to
+ * migrate a specific task from one runqueue to another.
+ * hmp_force_up_migration uses this to push a currently running task
+ * off a runqueue. hmp_idle_pull uses this to pull a currently
+ * running task to an idle runqueue.
+ * Reuses __do_active_load_balance_cpu_stop to actually do the work.
+ */
+static int hmp_active_task_migration_cpu_stop(void *data)
+{
+	return __do_active_load_balance_cpu_stop(data, false);
+}
+
+/*
+ * Move task in a runnable state to another CPU.
+ *
+ * Tailored on 'active_load_balance_cpu_stop' with slight
+ * modification to locking and pre-transfer checks.  Note
+ * rq->lock must be held before calling.
+ */
+static void hmp_migrate_runnable_task(struct rq *rq)
+{
+	struct sched_domain *sd;
+	int src_cpu = cpu_of(rq);
+	struct rq *src_rq = rq;
+	int dst_cpu = rq->push_cpu;
+	struct rq *dst_rq = cpu_rq(dst_cpu);
+	struct task_struct *p = rq->migrate_task;
+	/*
+	 * One last check to make sure nobody else is playing
+	 * with the source rq.
+	 */
+	if (src_rq->active_balance)
+		goto out;
+
+	if (src_rq->nr_running <= 1)
+		goto out;
+
+	if (task_rq(p) != src_rq)
+		goto out;
+	/*
+	 * Not sure if this applies here but one can never
+	 * be too cautious
+	 */
+	BUG_ON(src_rq == dst_rq);
+
+	double_lock_balance(src_rq, dst_rq);
+
+	rcu_read_lock();
+	for_each_domain(dst_cpu, sd) {
+		if (cpumask_test_cpu(src_cpu, sched_domain_span(sd)))
+			break;
+	}
+
+	if (likely(sd)) {
+		struct lb_env env = {
+			.sd             = sd,
+			.dst_cpu        = dst_cpu,
+			.dst_rq         = dst_rq,
+			.src_cpu        = src_cpu,
+			.src_rq         = src_rq,
+			.idle           = CPU_IDLE,
+		};
+
+		schedstat_inc(sd, alb_count);
+
+		if (move_specific_task(&env, p))
+			schedstat_inc(sd, alb_pushed);
+		else
+			schedstat_inc(sd, alb_failed);
+	}
+
+	rcu_read_unlock();
+	double_unlock_balance(src_rq, dst_rq);
+out:
+	put_task_struct(p);
+}
+
+static DEFINE_SPINLOCK(hmp_force_migration);
+
+/*
+ * hmp_force_up_migration checks runqueues for tasks that need to
+ * be actively migrated to a faster cpu.
+ */
+static void hmp_force_up_migration(int this_cpu)
+{
+	int cpu, target_cpu;
+	struct sched_entity *curr, *orig;
+	struct rq *target;
+	unsigned long flags;
+	unsigned int force, got_target;
+	struct task_struct *p;
+
+	if (!spin_trylock(&hmp_force_migration))
+		return;
+	for_each_online_cpu(cpu) {
+		force = 0;
+		got_target = 0;
+		target = cpu_rq(cpu);
+		raw_spin_lock_irqsave(&target->lock, flags);
+		curr = target->cfs.curr;
+		if (!curr || target->active_balance) {
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			continue;
+		}
+		if (!entity_is_task(curr)) {
+			struct cfs_rq *cfs_rq;
+
+			cfs_rq = group_cfs_rq(curr);
+			while (cfs_rq) {
+				curr = cfs_rq->curr;
+				cfs_rq = group_cfs_rq(curr);
+			}
+		}
+		orig = curr;
+		curr = hmp_get_heaviest_task(curr, -1);
+		if (!curr) {
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			continue;
+		}
+		p = task_of(curr);
+		if (hmp_up_migration(cpu, &target_cpu, curr)) {
+			cpu_rq(target_cpu)->wake_for_idle_pull = 1;
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			spin_unlock(&hmp_force_migration);
+			smp_send_reschedule(target_cpu);
+			return;
+		}
+		if (!got_target) {
+			/*
+			 * For now we just check the currently running task.
+			 * Selecting the lightest task for offloading will
+			 * require extensive book keeping.
+			 */
+			curr = hmp_get_lightest_task(orig, 1);
+			p = task_of(curr);
+			target->push_cpu = hmp_offload_down(cpu, curr);
+			if (target->push_cpu < NR_CPUS) {
+				get_task_struct(p);
+				target->migrate_task = p;
+				got_target = 1;
+				trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_OFFLOAD);
+				hmp_next_down_delay(&p->se, target->push_cpu);
+			}
+		}
+		/*
+		 * We have a target with no active_balance.  If the task
+		 * is not currently running move it, otherwise let the
+		 * CPU stopper take care of it.
+		 */
+		if (got_target) {
+			if (!task_running(target, p)) {
+				trace_sched_hmp_migrate_force_running(p, 0);
+				hmp_migrate_runnable_task(target);
+			} else {
+				target->active_balance = 1;
+				force = 1;
+			}
+		}
+
+		raw_spin_unlock_irqrestore(&target->lock, flags);
+
+		if (force)
+			stop_one_cpu_nowait(cpu_of(target),
+				hmp_active_task_migration_cpu_stop,
+				target, &target->active_balance_work);
+	}
+	spin_unlock(&hmp_force_migration);
+}
+/*
+ * hmp_idle_pull looks at little domain runqueues to see
+ * if a task should be pulled.
+ *
+ * Reuses hmp_force_migration spinlock.
+ *
+ */
+static unsigned int hmp_idle_pull(int this_cpu)
+{
+	int cpu;
+	struct sched_entity *curr, *orig;
+	struct hmp_domain *hmp_domain = NULL;
+	struct rq *target = NULL, *rq;
+	unsigned long flags, ratio = 0;
+	unsigned int force = 0;
+	struct task_struct *p = NULL;
+
+	if (!hmp_cpu_is_slowest(this_cpu))
+		hmp_domain = hmp_slower_domain(this_cpu);
+	if (!hmp_domain)
+		return 0;
+
+	if (!spin_trylock(&hmp_force_migration))
+		return 0;
+
+	/* first select a task */
+	for_each_cpu(cpu, &hmp_domain->cpus) {
+		rq = cpu_rq(cpu);
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		curr = rq->cfs.curr;
+		if (!curr) {
+			raw_spin_unlock_irqrestore(&rq->lock, flags);
+			continue;
+		}
+		if (!entity_is_task(curr)) {
+			struct cfs_rq *cfs_rq;
+
+			cfs_rq = group_cfs_rq(curr);
+			while (cfs_rq) {
+				curr = cfs_rq->curr;
+				if (!entity_is_task(curr))
+					cfs_rq = group_cfs_rq(curr);
+				else
+					cfs_rq = NULL;
+			}
+		}
+		orig = curr;
+		curr = hmp_get_heaviest_task(curr, this_cpu);
+		/* check if heaviest eligible task on this
+		 * CPU is heavier than previous task
+		 */
+		if (curr && hmp_task_eligible_for_up_migration(curr) &&
+			curr->avg.load_avg_ratio > ratio &&
+			cpumask_test_cpu(this_cpu,
+					tsk_cpus_allowed(task_of(curr)))) {
+			p = task_of(curr);
+			target = rq;
+			ratio = curr->avg.load_avg_ratio;
+		}
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
+
+	if (!p)
+		goto done;
+
+	/* now we have a candidate */
+	raw_spin_lock_irqsave(&target->lock, flags);
+	if (!target->active_balance && task_rq(p) == target) {
+		get_task_struct(p);
+		target->push_cpu = this_cpu;
+		target->migrate_task = p;
+		trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_IDLE_PULL);
+		hmp_next_up_delay(&p->se, target->push_cpu);
+		/*
+		 * if the task isn't running move it right away.
+		 * Otherwise setup the active_balance mechanic and let
+		 * the CPU stopper do its job.
+		 */
+		if (!task_running(target, p)) {
+			trace_sched_hmp_migrate_idle_running(p, 0);
+			hmp_migrate_runnable_task(target);
+		} else {
+			target->active_balance = 1;
+			force = 1;
+		}
+	}
+	raw_spin_unlock_irqrestore(&target->lock, flags);
+
+	if (force) {
+		/* start timer to keep us awake */
+		hmp_cpu_keepalive_trigger();
+		stop_one_cpu_nowait(cpu_of(target),
+			hmp_active_task_migration_cpu_stop,
+			target, &target->active_balance_work);
+	}
+done:
+	spin_unlock(&hmp_force_migration);
+	return force;
+}
+#else
+static void hmp_force_up_migration(int this_cpu) { }
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * run_rebalance_domains is triggered when needed from the scheduler tick.
  * Also triggered for nohz idle balancing (with nohz_balancing_kick set).
@@ -5694,6 +7361,20 @@ static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
+#ifdef CONFIG_SCHED_HMP
+	/* shortcut for hmp idle pull wakeups */
+	if (unlikely(this_rq->wake_for_idle_pull)) {
+		this_rq->wake_for_idle_pull = 0;
+		if (hmp_idle_pull(this_cpu)) {
+			/* break out unless running nohz idle as well */
+			if (idle != CPU_IDLE)
+				return;
+		}
+	}
+#endif
+
+	hmp_force_up_migration(this_cpu);
+
 	rebalance_domains(this_cpu, idle);
 
 	/*
@@ -5726,11 +7407,17 @@ void trigger_load_balance(struct rq *rq, int cpu)
 
 static void rq_online_fair(struct rq *rq)
 {
+#ifdef CONFIG_SCHED_HMP
+	hmp_online_cpu(rq->cpu);
+#endif
 	update_sysctl();
 }
 
 static void rq_offline_fair(struct rq *rq)
 {
+#ifdef CONFIG_SCHED_HMP
+	hmp_offline_cpu(rq->cpu);
+#endif
 	update_sysctl();
 
 	/* Ensure any throttled groups are reachable by pick_next_task */
@@ -5778,11 +7465,15 @@ static void task_fork_fair(struct task_struct *p)
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
 
-	if (unlikely(task_cpu(p) != this_cpu)) {
-		rcu_read_lock();
-		__set_task_cpu(p, this_cpu);
-		rcu_read_unlock();
-	}
+	/*
+	 * Not only the cpu but also the task_group of the parent might have
+	 * been changed after parent->se.parent,cfs_rq were copied to
+	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
+	 * of child point to valid ones.
+	 */
+	rcu_read_lock();
+	__set_task_cpu(p, this_cpu);
+	rcu_read_unlock();
 
 	update_curr(cfs_rq);
 
@@ -5832,15 +7523,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when its
+	 * Ensure the task's vruntime is normalized, so that when it's
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !on_rq, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!se->on_rq && p->state != TASK_RUNNING) {
+	if (!p->on_rq && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
@@ -6061,7 +7752,8 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	update_load_set(&se->load, 0);
+	/* guarantee group entities always have weight */
+	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
 }
 
@@ -6193,6 +7885,139 @@ __init void init_sched_fair_class(void)
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	cpu_notifier(sched_ilb_notifier, 0);
 #endif
+
+#ifdef CONFIG_SCHED_HMP
+	hmp_cpu_mask_setup();
+#endif
 #endif /* SMP */
 
 }
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+static u32 cpufreq_calc_scale(u32 min, u32 max, u32 curr)
+{
+	u32 result = curr / max;
+	return result;
+}
+
+/* Called when the CPU Frequency is changed.
+ * Once for each CPU.
+ */
+static int cpufreq_callback(struct notifier_block *nb,
+					unsigned long val, void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu = freq->cpu;
+	struct cpufreq_extents *extents;
+
+	if (freq->flags & CPUFREQ_CONST_LOOPS)
+		return NOTIFY_OK;
+
+	if (val != CPUFREQ_POSTCHANGE)
+		return NOTIFY_OK;
+
+	/* if dynamic load scale is disabled, set the load scale to 1.0 */
+	if (!hmp_data.freqinvar_load_scale_enabled) {
+		freq_scale[cpu].curr_scale = 1024;
+		return NOTIFY_OK;
+	}
+
+	extents = &freq_scale[cpu];
+	if (extents->flags & SCHED_LOAD_FREQINVAR_SINGLEFREQ) {
+		/* If our governor was recognised as a single-freq governor,
+		 * use 1.0
+		 */
+		extents->curr_scale = 1024;
+	} else {
+		extents->curr_scale = cpufreq_calc_scale(extents->min,
+				extents->max, freq->new);
+	}
+
+	return NOTIFY_OK;
+}
+
+/* Called when the CPUFreq governor is changed.
+ * Only called for the CPUs which are actually changed by the
+ * userspace.
+ */
+static int cpufreq_policy_callback(struct notifier_block *nb,
+				       unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	struct cpufreq_extents *extents;
+	int cpu, singleFreq = 0;
+	static const char performance_governor[] = "performance";
+	static const char powersave_governor[] = "powersave";
+
+	if (event == CPUFREQ_START)
+		return 0;
+
+	if (event != CPUFREQ_INCOMPATIBLE)
+		return 0;
+
+	/* CPUFreq governors do not accurately report the range of
+	 * CPU Frequencies they will choose from.
+	 * We recognise performance and powersave governors as
+	 * single-frequency only.
+	 */
+	if (!strncmp(policy->governor->name, performance_governor,
+			strlen(performance_governor)) ||
+		!strncmp(policy->governor->name, powersave_governor,
+				strlen(powersave_governor)))
+		singleFreq = 1;
+
+	/* Make sure that all CPUs impacted by this policy are
+	 * updated since we will only get a notification when the
+	 * user explicitly changes the policy on a CPU.
+	 */
+	for_each_cpu(cpu, policy->cpus) {
+		extents = &freq_scale[cpu];
+		extents->max = policy->max >> SCHED_FREQSCALE_SHIFT;
+		extents->min = policy->min >> SCHED_FREQSCALE_SHIFT;
+		if (!hmp_data.freqinvar_load_scale_enabled) {
+			extents->curr_scale = 1024;
+		} else if (singleFreq) {
+			extents->flags |= SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+			extents->curr_scale = 1024;
+		} else {
+			extents->flags &= ~SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+			extents->curr_scale = cpufreq_calc_scale(extents->min,
+					extents->max, policy->cur);
+		}
+	}
+
+	return 0;
+}
+
+static struct notifier_block cpufreq_notifier = {
+	.notifier_call  = cpufreq_callback,
+};
+static struct notifier_block cpufreq_policy_notifier = {
+	.notifier_call  = cpufreq_policy_callback,
+};
+
+static int __init register_sched_cpufreq_notifier(void)
+{
+	int ret = 0;
+
+	/* init safe defaults since there are no policies at registration */
+	for (ret = 0; ret < CONFIG_NR_CPUS; ret++) {
+		/* safe defaults */
+		freq_scale[ret].max = 1024;
+		freq_scale[ret].min = 1024;
+		freq_scale[ret].curr_scale = 1024;
+	}
+
+	pr_info("sched: registering cpufreq notifiers for scale-invariant loads\n");
+	ret = cpufreq_register_notifier(&cpufreq_policy_notifier,
+			CPUFREQ_POLICY_NOTIFIER);
+
+	if (ret != -EINVAL)
+		ret = cpufreq_register_notifier(&cpufreq_notifier,
+			CPUFREQ_TRANSITION_NOTIFIER);
+
+	return ret;
+}
+
+core_initcall(register_sched_cpufreq_notifier);
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 127a2c4cf4ab..2dffc7b5d469 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -892,7 +892,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 
 			if (!once) {
 				once = true;
-				printk_sched("sched: RT throttling activated\n");
+				printk_deferred("sched: RT throttling activated\n");
 			}
 		} else {
 			/*
@@ -964,6 +964,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Change rq's cpupri only if rt_rq is the top queue.
+	 */
+	if (&rq->rt != rt_rq)
+		return;
+#endif
 	if (rq->online && prio < prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
@@ -973,6 +980,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Change rq's cpupri only if rt_rq is the top queue.
+	 */
+	if (&rq->rt != rt_rq)
+		return;
+#endif
 	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ce39224d6155..0d19ede6849e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -142,7 +142,7 @@ struct task_group {
 
 	atomic_t load_weight;
 	atomic64_t load_avg;
-	atomic_t runnable_avg;
+	atomic_t runnable_avg, usage_avg;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -279,7 +279,7 @@ struct cfs_rq {
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 /* These always depend on CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	u32 tg_runnable_contrib;
+	u32 tg_runnable_contrib, tg_usage_contrib;
 	u64 tg_load_contrib;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -464,6 +464,10 @@ struct rq {
 	int active_balance;
 	int push_cpu;
 	struct cpu_stop_work active_balance_work;
+#ifdef CONFIG_SCHED_HMP
+	struct task_struct *migrate_task;
+	int wake_for_idle_pull;
+#endif
 	/* cpu of this runqueue: */
 	int cpu;
 	int online;
@@ -642,6 +646,12 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#ifdef CONFIG_SCHED_HMP
+static LIST_HEAD(hmp_domains);
+DECLARE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+#define hmp_cpu_domain(cpu)	(per_cpu(hmp_cpu_domain, (cpu)))
+#endif /* CONFIG_SCHED_HMP */
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -1318,7 +1328,8 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
 
-extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
+extern void cfs_bandwidth_usage_inc(void);
+extern void cfs_bandwidth_usage_dec(void);
 
 #ifdef CONFIG_NO_HZ_COMMON
 enum rq_nohz_flag_bits {
diff --git a/kernel/smp.c b/kernel/smp.c
index 4dba0f7b72ad..74ba5e2c037c 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -12,6 +12,8 @@
 #include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/smp.h>
 
 #include "smpboot.h"
 
@@ -159,8 +161,10 @@ void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 	 * locking and barrier primitives. Generic code isn't really
 	 * equipped to do the right thing...
 	 */
-	if (ipi)
+	if (ipi) {
+		trace_smp_call_func_send(csd->func, cpu);
 		arch_send_call_function_single_ipi(cpu);
+	}
 
 	if (wait)
 		csd_lock_wait(csd);
@@ -197,8 +201,9 @@ void generic_smp_call_function_single_interrupt(void)
 		 * so save them away before making the call:
 		 */
 		csd_flags = csd->flags;
-
+		trace_smp_call_func_entry(csd->func);
 		csd->func(csd->info);
+		trace_smp_call_func_exit(csd->func);
 
 		/*
 		 * Unlocked CSDs are valid through generic_exec_single():
@@ -228,6 +233,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	int this_cpu;
 	int err = 0;
 
+	trace_smp_call_func_send(func, cpu);
 	/*
 	 * prevent preemption and reschedule on another processor,
 	 * as well as CPU removal
@@ -245,7 +251,9 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 
 	if (cpu == this_cpu) {
 		local_irq_save(flags);
+		trace_smp_call_func_entry(func);
 		func(info);
+		trace_smp_call_func_exit(func);
 		local_irq_restore(flags);
 	} else {
 		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
@@ -658,7 +666,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 			if (cond_func(cpu, info)) {
 				ret = smp_call_function_single(cpu, func,
 								info, wait);
-				WARN_ON_ONCE(!ret);
+				WARN_ON_ONCE(ret);
 			}
 		preempt_enable();
 	}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3d6833f125d3..787b3a032429 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -330,10 +330,19 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads)
-		__do_softirq();
-	else
+	if (!force_irqthreads) {
+		/*
+		 * We can safely execute softirq on the current stack if
+		 * it is the irq stack, because it should be near empty
+		 * at this stage. But we have no way to know if the arch
+		 * calls irq_exit() on the irq stack. So call softirq
+		 * in its own stack to prevent from any overrun on top
+		 * of a potentially deep task stack.
+		 */
+		do_softirq();
+	} else {
 		wakeup_softirqd();
+	}
 }
 
 static inline void tick_irq_exit(void)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9edcf456e0fc..9469f4c61a30 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -144,6 +144,11 @@ static int min_percpu_pagelist_fract = 8;
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
 
+/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+#ifdef CONFIG_DETECT_HUNG_TASK
+static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
+#endif
+
 #ifdef CONFIG_INOTIFY_USER
 #include <linux/inotify.h>
 #endif
@@ -966,6 +971,7 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= proc_dohung_task_timeout_secs,
+		.extra2		= &hung_task_timeout_max,
 	},
 	{
 		.procname	= "hung_task_warnings",
@@ -1043,6 +1049,16 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
 		.mode		= 0644,
 		.proc_handler	= perf_proc_update_handler,
+		.extra1		= &one,
+	},
+	{
+		.procname	= "perf_cpu_time_max_percent",
+		.data		= &sysctl_perf_cpu_time_max_percent,
+		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),
+		.mode		= 0644,
+		.proc_handler	= perf_cpu_time_max_percent_handler,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
 	},
 #endif
 #ifdef CONFIG_KMEMCHECK
diff --git a/kernel/time.c b/kernel/time.c
index d3617dbd3dca..d21398e6da87 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -496,17 +496,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -517,6 +520,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -533,31 +543,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
  *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ff7d9d2ab504..a64e0de74c0d 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y						+= tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT)			+= tick-broadcast-hrtimer.o
+endif
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index f11d83b12949..7d19fca0617e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -419,18 +419,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 							ktime_t now)
 {
+	unsigned long flags;
 	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
 						it.alarm.alarmtimer);
-	if (posix_timer_event(ptr, 0) != 0)
-		ptr->it_overrun++;
+	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&ptr->it_lock, flags);
+	if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+		if (posix_timer_event(ptr, 0) != 0)
+			ptr->it_overrun++;
+	}
 
 	/* Re-add periodic timers */
 	if (ptr->it.alarm.interval.tv64) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
-		return ALARMTIMER_RESTART;
+		result = ALARMTIMER_RESTART;
 	}
-	return ALARMTIMER_NORESTART;
+	spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+	return result;
 }
 
 /**
@@ -445,7 +453,7 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
 
 	if (!alarmtimer_get_rtcdev())
-		return -ENOTSUPP;
+		return -EINVAL;
 
 	return hrtimer_get_res(baseid, tp);
 }
@@ -462,7 +470,7 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
 	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
 
 	if (!alarmtimer_get_rtcdev())
-		return -ENOTSUPP;
+		return -EINVAL;
 
 	*tp = ktime_to_timespec(base->gettime());
 	return 0;
@@ -540,9 +548,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 				struct itimerspec *new_setting,
 				struct itimerspec *old_setting)
 {
+	ktime_t exp;
+
 	if (!rtcdev)
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (old_setting)
 		alarm_timer_get(timr, old_setting);
 
@@ -552,8 +565,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 
 	/* start the timer */
 	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
-	alarm_start(&timr->it.alarm.alarmtimer,
-			timespec_to_ktime(new_setting->it_value));
+	exp = timespec_to_ktime(new_setting->it_value);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now;
+
+		now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	alarm_start(&timr->it.alarm.alarmtimer, exp);
 	return 0;
 }
 
@@ -685,6 +706,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c6d6400ee137..378613bebb13 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,7 +15,6 @@
 #include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/notifier.h>
 #include <linux/smp.h>
 
 #include "tick-internal.h"
@@ -23,36 +22,67 @@
 /* The registered clock event devices */
 static LIST_HEAD(clockevent_devices);
 static LIST_HEAD(clockevents_released);
-
-/* Notification for clock events */
-static RAW_NOTIFIER_HEAD(clockevents_chain);
-
 /* Protection for the above */
 static DEFINE_RAW_SPINLOCK(clockevents_lock);
 
-/**
- * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
- * @latch:	value to convert
- * @evt:	pointer to clock event device descriptor
- *
- * Math helper, returns latch value converted to nanoseconds (bound checked)
- */
-u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+			bool ismax)
 {
 	u64 clc = (u64) latch << evt->shift;
+	u64 rnd;
 
 	if (unlikely(!evt->mult)) {
 		evt->mult = 1;
 		WARN_ON(1);
 	}
+	rnd = (u64) evt->mult - 1;
+
+	/*
+	 * Upper bound sanity check. If the backwards conversion is
+	 * not equal latch, we know that the above shift overflowed.
+	 */
+	if ((clc >> evt->shift) != (u64)latch)
+		clc = ~0ULL;
+
+	/*
+	 * Scaled math oddities:
+	 *
+	 * For mult <= (1 << shift) we can safely add mult - 1 to
+	 * prevent integer rounding loss. So the backwards conversion
+	 * from nsec to device ticks will be correct.
+	 *
+	 * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+	 * need to be careful. Adding mult - 1 will result in a value
+	 * which when converted back to device ticks can be larger
+	 * than latch by up to (mult - 1) >> shift. For the min_delta
+	 * calculation we still want to apply this in order to stay
+	 * above the minimum device ticks limit. For the upper limit
+	 * we would end up with a latch value larger than the upper
+	 * limit of the device, so we omit the add to stay below the
+	 * device upper boundary.
+	 *
+	 * Also omit the add if it would overflow the u64 boundary.
+	 */
+	if ((~0ULL - clc > rnd) &&
+	    (!ismax || evt->mult <= (1U << evt->shift)))
+		clc += rnd;
 
 	do_div(clc, evt->mult);
-	if (clc < 1000)
-		clc = 1000;
-	if (clc > KTIME_MAX)
-		clc = KTIME_MAX;
 
-	return clc;
+	/* Deltas less than 1usec are pointless noise */
+	return clc > 1000 ? clc : 1000;
+}
+
+/**
+ * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:	value to convert
+ * @evt:	pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+{
+	return cev_delta2ns(latch, evt, false);
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
@@ -108,7 +138,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 {
 	/* Nothing to do if we already reached the limit */
 	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
-		printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+		printk_deferred(KERN_WARNING
+				"CE: Reprogramming failure. Giving up\n");
 		dev->next_event.tv64 = KTIME_MAX;
 		return -ETIME;
 	}
@@ -121,9 +152,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
 		dev->min_delta_ns = MIN_DELTA_LIMIT;
 
-	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
-	       dev->name ? dev->name : "?",
-	       (unsigned long long) dev->min_delta_ns);
+	printk_deferred(KERN_WARNING
+			"CE: %s increased min_delta_ns to %llu nsec\n",
+			dev->name ? dev->name : "?",
+			(unsigned long long) dev->min_delta_ns);
 	return 0;
 }
 
@@ -232,30 +264,6 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
 }
 
-/**
- * clockevents_register_notifier - register a clock events change listener
- */
-int clockevents_register_notifier(struct notifier_block *nb)
-{
-	unsigned long flags;
-	int ret;
-
-	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-
-	return ret;
-}
-
-/*
- * Notify about a clock event change. Called with clockevents_lock
- * held.
- */
-static void clockevents_do_notify(unsigned long reason, void *dev)
-{
-	raw_notifier_call_chain(&clockevents_chain, reason, dev);
-}
-
 /*
  * Called after a notify add to make devices available which were
  * released from the notifier call.
@@ -269,7 +277,7 @@ static void clockevents_notify_released(void)
 				 struct clock_event_device, list);
 		list_del(&dev->list);
 		list_add(&dev->list, &clockevent_devices);
-		clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+		tick_check_new_device(dev);
 	}
 }
 
@@ -290,7 +298,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
-	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	tick_check_new_device(dev);
 	clockevents_notify_released();
 
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
@@ -317,8 +325,8 @@ void clockevents_config(struct clock_event_device *dev, u32 freq)
 		sec = 600;
 
 	clockevents_calc_mult_shift(dev, freq, sec);
-	dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
-	dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+	dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
+	dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
 }
 
 /**
@@ -386,6 +394,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		module_put(old->owner);
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
@@ -425,18 +434,45 @@ void clockevents_resume(void)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 /**
  * clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
  */
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
 {
 	struct clock_event_device *dev, *tmp;
 	unsigned long flags;
-	int cpu;
+	int cpu, ret = 0;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	clockevents_do_notify(reason, arg);
 
 	switch (reason) {
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		tick_broadcast_on_off(reason, arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+		ret = tick_broadcast_oneshot_control(reason);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_SUSPEND:
+		tick_suspend();
+		tick_suspend_broadcast();
+		break;
+
+	case CLOCK_EVT_NOTIFY_RESUME:
+		tick_resume();
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown_broadcast_oneshot(arg);
+		tick_shutdown_broadcast(arg);
+		tick_shutdown(arg);
 		/*
 		 * Unregister the clock event devices which were
 		 * released from the users in the notify chain.
@@ -460,6 +496,7 @@ void clockevents_notify(unsigned long reason, void *arg)
 		break;
 	}
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
 #endif
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba456fb..a6a5bf53e86d 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
  * HZ shrinks, so values greater than 8 overflow 32bits when
  * HZ=100.
  */
+#if HZ < 34
+#define JIFFIES_SHIFT	6
+#elif HZ < 67
+#define JIFFIES_SHIFT	7
+#else
 #define JIFFIES_SHIFT	8
+#endif
 
 static cycle_t jiffies_read(struct clocksource *cs)
 {
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8f5b3b98577b..af8d1d4f3d55 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -475,6 +475,7 @@ static void sync_cmos_clock(struct work_struct *work)
 	 * called as close as possible to 500 ms before the new second starts.
 	 * This code is run on a timer.  If the clock is set, that timer
 	 * may not expire at the correct time.  Thus, we adjust...
+	 * We want the clock to be within a couple of ticks from the target.
 	 */
 	if (!ntp_synced()) {
 		/*
@@ -485,7 +486,7 @@ static void sync_cmos_clock(struct work_struct *work)
 	}
 
 	getnstimeofday(&now);
-	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
 		struct timespec adjust = now;
 
 		fail = -ENODEV;
@@ -516,13 +517,13 @@ static void sync_cmos_clock(struct work_struct *work)
 	schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
 {
 	schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
 #endif
 
 
@@ -687,8 +688,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
 	if (!(time_status & STA_NANO))
 		txc->time.tv_usec /= NSEC_PER_USEC;
 
-	notify_cmos_timer();
-
 	return result;
 }
 
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 000000000000..eb682d5c697c
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+			struct clock_event_device *bc)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		/*
+		 * Note, we cannot cancel the timer here as we might
+		 * run into the following live lock scenario:
+		 *
+		 * cpu 0		cpu1
+		 * lock(broadcast_lock);
+		 *			hrtimer_interrupt()
+		 *			bc_handler()
+		 *			   tick_handle_oneshot_broadcast();
+		 *			    lock(broadcast_lock);
+		 * hrtimer_cancel()
+		 *  wait_for_callback()
+		 */
+		hrtimer_try_to_cancel(&bctimer);
+		break;
+	default:
+		break;
+	}
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+	/*
+	 * We try to cancel the timer first. If the callback is on
+	 * flight on some other cpu then we let it handle it. If we
+	 * were able to cancel the timer nothing can rearm it as we
+	 * own broadcast_lock.
+	 *
+	 * However we can also be called from the event handler of
+	 * ce_broadcast_hrtimer itself when it expires. We cannot
+	 * restart the timer because we are in the callback, but we
+	 * can set the expiry time and let the callback return
+	 * HRTIMER_RESTART.
+	 */
+	if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+		/* Bind the "device" to the cpu */
+		bc->bound_on = smp_processor_id();
+	} else if (bc->bound_on == smp_processor_id()) {
+		hrtimer_set_expires(&bctimer, expires);
+	}
+	return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+	.set_mode		= bc_set_mode,
+	.set_next_ktime		= bc_set_next,
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_KTIME |
+				  CLOCK_EVT_FEAT_HRTIMER,
+	.rating			= 0,
+	.bound_on		= -1,
+	.min_delta_ns		= 1,
+	.max_delta_ns		= KTIME_MAX,
+	.min_delta_ticks	= 1,
+	.max_delta_ticks	= ULONG_MAX,
+	.mult			= 1,
+	.shift			= 0,
+	.cpumask		= cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+	if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+		return HRTIMER_NORESTART;
+
+	return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+	hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	bctimer.function = bc_handler;
+	clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 297b90b5277e..16f4830a5498 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -19,6 +19,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/module.h>
 
 #include "tick-internal.h"
 
@@ -65,17 +66,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
 /*
  * Check, if the device can be utilized as broadcast device:
  */
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+					struct clock_event_device *newdev)
+{
+	if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return false;
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+	    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return false;
+
+	return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
 {
 	struct clock_event_device *cur = tick_broadcast_device.evtdev;
 
-	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
-	    (tick_broadcast_device.evtdev &&
-	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
-	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	if (!tick_check_broadcast_device(cur, dev))
+		return;
+
+	if (!try_module_get(dev->owner))
+		return;
 
-	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	clockevents_exchange_device(cur, dev);
 	if (cur)
 		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
@@ -91,7 +109,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	 */
 	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_clock_notify();
-	return 1;
 }
 
 /*
@@ -577,6 +594,13 @@ again:
 	cpumask_clear(tick_broadcast_force_mask);
 
 	/*
+	 * Sanity check. Catch the case where we try to broadcast to
+	 * offline cpus.
+	 */
+	if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+		cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+	/*
 	 * Wakeup the cpus which have an expired event.
 	 */
 	tick_do_broadcast(tmpmask);
@@ -602,24 +626,61 @@ again:
 	raw_spin_unlock(&tick_broadcast_lock);
 }
 
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+	if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+		return 0;
+	if (bc->next_event.tv64 == KTIME_MAX)
+		return 0;
+	return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+				     struct clock_event_device *dev)
+{
+	/*
+	 * For hrtimer based broadcasting we cannot shutdown the cpu
+	 * local device if our own event is the first one to expire or
+	 * if we own the broadcast timer.
+	 */
+	if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+		if (broadcast_needs_cpu(bc, smp_processor_id()))
+			return;
+		if (dev->next_event.tv64 < bc->next_event.tv64)
+			return;
+	}
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+		return;
+	/* This moves the broadcast assignment to this cpu */
+	clockevents_program_event(bc, bc->next_event, 1);
+}
+
 /*
  * Powerstate information: The system enters/leaves a state, where
  * affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
  */
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
 	unsigned long flags;
 	ktime_t now;
-	int cpu;
+	int cpu, ret = 0;
 
 	/*
 	 * Periodic mode does not care about the enter/exit of power
 	 * states
 	 */
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return;
+		return 0;
 
 	/*
 	 * We are called with preemtion disabled from the depth of the
@@ -630,7 +691,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	dev = td->evtdev;
 
 	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return;
+		return 0;
 
 	bc = tick_broadcast_device.evtdev;
 
@@ -638,7 +699,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
-			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+			broadcast_shutdown_local(bc, dev);
 			/*
 			 * We only reprogram the broadcast timer if we
 			 * did not mark ourself in the force mask and
@@ -651,6 +712,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 			    dev->next_event.tv64 < bc->next_event.tv64)
 				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
 		}
+		/*
+		 * If the current CPU owns the hrtimer broadcast
+		 * mechanism, it cannot go deep idle and we remove the
+		 * CPU from the broadcast mask. We don't have to go
+		 * through the EXIT path as the local timer is not
+		 * shutdown.
+		 */
+		ret = broadcast_needs_cpu(bc, cpu);
+		if (ret)
+			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -718,6 +789,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	}
 out:
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	return ret;
 }
 
 /*
@@ -728,6 +800,7 @@ out:
 static void tick_broadcast_clear_oneshot(int cpu)
 {
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 }
 
 static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -816,10 +889,14 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	/*
-	 * Clear the broadcast mask flag for the dead cpu, but do not
-	 * stop the broadcast device!
+	 * Clear the broadcast masks for the dead cpu, but do not stop
+	 * the broadcast device!
 	 */
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+
+	broadcast_move_bc(cpu);
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 7ce5e5a4a4c5..21711bc2bc25 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -206,14 +207,50 @@ static void tick_setup_device(struct tick_device *td,
 		tick_setup_oneshot(newdev, handler, next_event);
 }
 
+static bool tick_check_percpu(struct clock_event_device *curdev,
+			      struct clock_event_device *newdev, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		return false;
+	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+		return true;
+	/* Check if irq affinity can be set */
+	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+		return false;
+	/* Prefer an existing cpu local device */
+	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+		return false;
+	return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+				 struct clock_event_device *newdev)
+{
+	/* Prefer oneshot capable device */
+	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return false;
+		if (tick_oneshot_mode_active())
+			return false;
+	}
+
+	/*
+	 * Use the higher rated one, but prefer a CPU local device with a lower
+	 * rating than a non-CPU local device
+	 */
+	return !curdev ||
+		newdev->rating > curdev->rating ||
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
 /*
  * Check, if the new registered device should be used.
  */
-static int tick_check_new_device(struct clock_event_device *newdev)
+void tick_check_new_device(struct clock_event_device *newdev)
 {
 	struct clock_event_device *curdev;
 	struct tick_device *td;
-	int cpu, ret = NOTIFY_OK;
+	int cpu;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&tick_device_lock, flags);
@@ -226,40 +263,15 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	curdev = td->evtdev;
 
 	/* cpu local device ? */
-	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
-
-		/*
-		 * If the cpu affinity of the device interrupt can not
-		 * be set, ignore it.
-		 */
-		if (!irq_can_set_affinity(newdev->irq))
-			goto out_bc;
+	if (!tick_check_percpu(curdev, newdev, cpu))
+		goto out_bc;
 
-		/*
-		 * If we have a cpu local device already, do not replace it
-		 * by a non cpu local device
-		 */
-		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
-			goto out_bc;
-	}
+	/* Preference decision */
+	if (!tick_check_preferred(curdev, newdev))
+		goto out_bc;
 
-	/*
-	 * If we have an active device, then check the rating and the oneshot
-	 * feature.
-	 */
-	if (curdev) {
-		/*
-		 * Prefer one shot capable devices !
-		 */
-		if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-		    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
-			goto out_bc;
-		/*
-		 * Check the rating
-		 */
-		if (curdev->rating >= newdev->rating)
-			goto out_bc;
-	}
+	if (!try_module_get(newdev->owner))
+		return;
 
 	/*
 	 * Replace the eventually existing device by the new
@@ -276,18 +288,14 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 		tick_oneshot_notify();
 
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-	return NOTIFY_STOP;
+	return;
 
 out_bc:
 	/*
 	 * Can the new device be used as a broadcast device ?
 	 */
-	if (tick_check_broadcast_device(newdev))
-		ret = NOTIFY_STOP;
-
+	tick_install_broadcast_device(newdev);
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
-	return ret;
 }
 
 /*
@@ -295,7 +303,7 @@ out_bc:
  *
  * Called with interrupts disabled.
  */
-static void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(int *cpup)
 {
 	if (*cpup == tick_do_timer_cpu) {
 		int cpu = cpumask_first(cpu_online_mask);
@@ -312,7 +320,7 @@ static void tick_handover_do_timer(int *cpup)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-static void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int *cpup)
 {
 	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
 	struct clock_event_device *dev = td->evtdev;
@@ -333,7 +341,7 @@ static void tick_shutdown(unsigned int *cpup)
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_suspend(void)
+void tick_suspend(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 	unsigned long flags;
@@ -343,7 +351,7 @@ static void tick_suspend(void)
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_resume(void)
+void tick_resume(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 	unsigned long flags;
@@ -361,65 +369,10 @@ static void tick_resume(void)
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-/*
- * Notification about clock event devices
- */
-static int tick_notify(struct notifier_block *nb, unsigned long reason,
-			       void *dev)
-{
-	switch (reason) {
-
-	case CLOCK_EVT_NOTIFY_ADD:
-		return tick_check_new_device(dev);
-
-	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
-	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		tick_broadcast_on_off(reason, dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
-	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
-		tick_broadcast_oneshot_control(reason);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DYING:
-		tick_handover_do_timer(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DEAD:
-		tick_shutdown_broadcast_oneshot(dev);
-		tick_shutdown_broadcast(dev);
-		tick_shutdown(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_SUSPEND:
-		tick_suspend();
-		tick_suspend_broadcast();
-		break;
-
-	case CLOCK_EVT_NOTIFY_RESUME:
-		tick_resume();
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block tick_notifier = {
-	.notifier_call = tick_notify,
-};
-
 /**
  * tick_init - initialize the tick control
- *
- * Register the notifier with the clockevents framework
  */
 void __init tick_init(void)
 {
-	clockevents_register_notifier(&tick_notifier);
 	tick_broadcast_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f0299eae4602..c85edb18d68e 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -18,6 +18,11 @@ extern int tick_do_timer_cpu __read_mostly;
 
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
+extern void tick_handover_do_timer(int *cpup);
+extern void tick_shutdown(unsigned int *cpup);
+extern void tick_suspend(void);
+extern void tick_resume(void);
 
 extern void clockevents_shutdown(struct clock_event_device *dev);
 
@@ -34,7 +39,7 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
 extern void tick_resume_oneshot(void);
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -46,7 +51,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
 	BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
@@ -75,7 +80,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
 	BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
@@ -90,7 +95,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; }
  */
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
 extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
 extern void tick_shutdown_broadcast(unsigned int *cpup);
@@ -102,9 +107,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
 
 #else /* !BROADCAST */
 
-static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 {
-	return 0;
 }
 
 static inline int tick_is_broadcast_device(struct clock_event_device *dev)
@@ -141,6 +145,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
 
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
 #endif
 
 extern void do_timer(unsigned long ticks);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4251374578bc..67f7a2d2efbc 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -720,8 +720,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 	}
 
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+		ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
 		return false;
+	}
 
 	if (need_resched())
 		return false;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index baeeb5c87cf1..76fefb1613b2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -72,7 +72,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec_to_ktime(tmp);
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
 }
 
 static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -590,7 +590,7 @@ s32 timekeeping_get_tai_offset(void)
 static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
 {
 	tk->tai_offset = tai_offset;
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
 }
 
 /**
@@ -605,6 +605,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&timekeeper_seq);
 	__timekeeping_set_tai_offset(tk, tai_offset);
+	timekeeping_update(tk, false, true);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	clock_was_set();
@@ -1007,6 +1008,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
+
+	timekeeping_update(tk, false, true);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
@@ -1236,9 +1239,10 @@ out_adjust:
  * It also calls into the NTP code to handle leapsecond processing.
  *
  */
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1260,9 +1264,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
+			clock_set = 1;
 		}
 	}
+	return clock_set;
 }
 
 /**
@@ -1275,7 +1280,8 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1289,7 +1295,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1328,7 +1334,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	tk->xtime_nsec -= remainder;
 	tk->xtime_nsec += 1ULL << tk->shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-
+	tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
@@ -1347,6 +1353,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1381,7 +1388,8 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1399,7 +1407,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1419,6 +1427,10 @@ static void update_wall_time(void)
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_set)
+		/* have to call outside the timekeeper_seq */
+		clock_was_set_delayed();
+
 }
 
 /**
@@ -1677,11 +1689,16 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
-		clock_was_set_delayed();
+		timekeeping_update(tk, false, true);
 	}
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	if (tai != orig_tai)
+		clock_was_set();
+
+	ntp_notify_cmos_timer();
+
 	return ret;
 }
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 15bc1b41021d..20f45ea6f5a4 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -822,7 +822,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 
 	bit = find_last_bit(&mask, BITS_PER_LONG);
 
-	mask = (1 << bit) - 1;
+	mask = (1UL << bit) - 1;
 
 	expires_limit = expires_limit & ~(mask);
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b8b8560bfb95..686417ba5cd1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -685,6 +685,7 @@ void blk_trace_shutdown(struct request_queue *q)
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:		queue the io is for
  * @rq:		the source request
+ * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
  * Description:
@@ -692,7 +693,7 @@ void blk_trace_shutdown(struct request_queue *q)
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-			     u32 what)
+			     unsigned int nr_bytes, u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;
 
@@ -701,11 +702,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }
@@ -713,33 +714,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 static void blk_add_trace_rq_abort(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
-				      struct request *rq)
+				      struct request *rq,
+				      unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f23449d0650e..401d9bd1fe42 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@ int function_trace_stop __read_mostly;
 
 /* Current function tracing op */
 struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
 
 /* List for set_ftrace_pid's pids. */
 LIST_HEAD(ftrace_pids);
@@ -278,6 +280,29 @@ static void update_global_ops(void)
 	global_ops.func = func;
 }
 
+static void ftrace_sync(struct work_struct *work)
+{
+	/*
+	 * This function is just a stub to implement a hard force
+	 * of synchronize_sched(). This requires synchronizing
+	 * tasks even in userspace and idle.
+	 *
+	 * Yes, function tracing is rude.
+	 */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+	/* Probably not needed, but do it anyway */
+	smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
 static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
@@ -296,16 +321,61 @@ static void update_ftrace_function(void)
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
 		if (ftrace_ops_list == &global_ops)
-			function_trace_op = ftrace_global_list;
+			set_function_trace_op = ftrace_global_list;
 		else
-			function_trace_op = ftrace_ops_list;
+			set_function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
 	} else {
 		/* Just use the default ftrace_ops */
-		function_trace_op = &ftrace_list_end;
+		set_function_trace_op = &ftrace_list_end;
 		func = ftrace_ops_list_func;
 	}
 
+	update_function_graph_func();
+
+	/* If there's no change, then do nothing more here */
+	if (ftrace_trace_function == func)
+		return;
+
+	/*
+	 * If we are using the list function, it doesn't care
+	 * about the function_trace_ops.
+	 */
+	if (func == ftrace_ops_list_func) {
+		ftrace_trace_function = func;
+		/*
+		 * Don't even bother setting function_trace_ops,
+		 * it would be racy to do so anyway.
+		 */
+		return;
+	}
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+	/*
+	 * For static tracing, we need to be a bit more careful.
+	 * The function change takes affect immediately. Thus,
+	 * we need to coorditate the setting of the function_trace_ops
+	 * with the setting of the ftrace_trace_function.
+	 *
+	 * Set the function to the list ops, which will call the
+	 * function we want, albeit indirectly, but it handles the
+	 * ftrace_ops and doesn't depend on function_trace_op.
+	 */
+	ftrace_trace_function = ftrace_ops_list_func;
+	/*
+	 * Make sure all CPUs see this. Yes this is slow, but static
+	 * tracing is slow and nasty to have enabled.
+	 */
+	schedule_on_each_cpu(ftrace_sync);
+	/* Now all cpus are using the list ops. */
+	function_trace_op = set_function_trace_op;
+	/* Make sure the function_trace_op is visible on all CPUs */
+	smp_wmb();
+	/* Nasty way to force a rmb on all cpus */
+	smp_call_function(ftrace_sync_ipi, NULL, 1);
+	/* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
 	ftrace_trace_function = func;
 }
 
@@ -367,9 +437,6 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
-
 	if (FTRACE_WARN_ON(ops == &global_ops))
 		return -EINVAL;
 
@@ -417,9 +484,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
 
-	if (ftrace_disabled)
-		return -ENODEV;
-
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
@@ -434,16 +498,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
-		if (!ret) {
-			/*
-			 * The ftrace_ops is now removed from the list,
-			 * so there'll be no new users. We must ensure
-			 * all current users are done before we free
-			 * the control data.
-			 */
-			synchronize_sched();
-			control_ops_free(ops);
-		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -453,13 +507,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (ftrace_enabled)
 		update_ftrace_function();
 
-	/*
-	 * Dynamic ops may be freed, we must make sure that all
-	 * callers are done before leaving this function.
-	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		synchronize_sched();
-
 	return 0;
 }
 
@@ -756,7 +803,7 @@ static int ftrace_profile_init(void)
 	int cpu;
 	int ret = 0;
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		ret = ftrace_profile_init_cpu(cpu);
 		if (ret)
 			break;
@@ -1958,8 +2005,14 @@ void ftrace_modify_all_code(int command)
 	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
+	if (command & FTRACE_UPDATE_TRACE_FUNC) {
+		function_trace_op = set_function_trace_op;
+		smp_wmb();
+		/* If irqs are disabled, we are in stop machine */
+		if (!irqs_disabled())
+			smp_call_function(ftrace_sync_ipi, NULL, 1);
 		ftrace_update_ftrace_func(ftrace_trace_function);
+	}
 
 	if (command & FTRACE_START_FUNC_RET)
 		ftrace_enable_ftrace_graph_caller();
@@ -2048,10 +2101,15 @@ static void ftrace_startup_enable(int command)
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	bool hash_enable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
+	ret = __register_ftrace_function(ops);
+	if (ret)
+		return ret;
+
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
@@ -2073,12 +2131,17 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	return 0;
 }
 
-static void ftrace_shutdown(struct ftrace_ops *ops, int command)
+static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
 	bool hash_disable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
+
+	ret = __unregister_ftrace_function(ops);
+	if (ret)
+		return ret;
 
 	ftrace_start_up--;
 	/*
@@ -2112,10 +2175,42 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command)
 		command |= FTRACE_UPDATE_TRACE_FUNC;
 	}
 
-	if (!command || !ftrace_enabled)
-		return;
+	if (!command || !ftrace_enabled) {
+		/*
+		 * If these are control ops, they still need their
+		 * per_cpu field freed. Since, function tracing is
+		 * not currently active, we can just free them
+		 * without synchronizing all CPUs.
+		 */
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
+		return 0;
+	}
 
 	ftrace_run_update_code(command);
+
+	/*
+	 * Dynamic ops may be freed, we must make sure that all
+	 * callers are done before leaving this function.
+	 * The same goes for freeing the per_cpu data of the control
+	 * ops.
+	 *
+	 * Again, normal synchronize_sched() is not good enough.
+	 * We need to do a hard force of sched synchronization.
+	 * This is because we use preempt_disable() to do RCU, but
+	 * the function tracers can be called where RCU is not watching
+	 * (like before user_exit()). We can not rely on the RCU
+	 * infrastructure to do the synchronization, thus we must do it
+	 * ourselves.
+	 */
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+		schedule_on_each_cpu(ftrace_sync);
+
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
+	}
+
+	return 0;
 }
 
 static void ftrace_startup_sysctl(void)
@@ -3020,16 +3115,13 @@ static void __enable_ftrace_function_probe(void)
 	if (i == FTRACE_FUNC_HASHSIZE)
 		return;
 
-	ret = __register_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ret = ftrace_startup(&trace_probe_ops, 0);
+	ret = ftrace_startup(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 1;
 }
 
 static void __disable_ftrace_function_probe(void)
 {
-	int ret;
 	int i;
 
 	if (!ftrace_probe_registered)
@@ -3042,9 +3134,7 @@ static void __disable_ftrace_function_probe(void)
 	}
 
 	/* no more funcs left */
-	ret = __unregister_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ftrace_shutdown(&trace_probe_ops, 0);
+	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
 }
@@ -4132,16 +4222,11 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
 {
-	struct module *mod = data;
-
-	if (val == MODULE_STATE_COMING)
-		ftrace_init_module(mod, mod->ftrace_callsites,
-				   mod->ftrace_callsites +
-				   mod->num_ftrace_callsites);
-	return 0;
+	ftrace_init_module(mod, mod->ftrace_callsites,
+			   mod->ftrace_callsites +
+			   mod->num_ftrace_callsites);
 }
 
 static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4155,11 +4240,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 	return 0;
 }
 #else
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
-{
-	return 0;
-}
 static int ftrace_module_notify_exit(struct notifier_block *self,
 				     unsigned long val, void *data)
 {
@@ -4167,11 +4247,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_enter_nb = {
-	.notifier_call = ftrace_module_notify_enter,
-	.priority = INT_MAX,	/* Run before anything that can use kprobes */
-};
-
 struct notifier_block ftrace_module_exit_nb = {
 	.notifier_call = ftrace_module_notify_exit,
 	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
@@ -4208,10 +4283,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_enter_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module enter notifier\n");
-
 	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
 		pr_warning("Failed to register trace ftrace module exit notifier\n");
@@ -4241,12 +4312,15 @@ core_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)			\
-	({						\
-		(ops)->flags |= FTRACE_OPS_FL_ENABLED;	\
-		0;					\
+# define ftrace_startup(ops, command)					\
+	({								\
+		int ___ret = __register_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags |= FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
 	})
-# define ftrace_shutdown(ops, command)	do { } while (0)
+# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
 
@@ -4646,9 +4720,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_lock);
 
-	ret = __register_ftrace_function(ops);
-	if (!ret)
-		ret = ftrace_startup(ops, 0);
+	ret = ftrace_startup(ops, 0);
 
 	mutex_unlock(&ftrace_lock);
 
@@ -4667,9 +4739,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 	int ret;
 
 	mutex_lock(&ftrace_lock);
-	ret = __unregister_ftrace_function(ops);
-	if (!ret)
-		ftrace_shutdown(ops, 0);
+	ret = ftrace_shutdown(ops, 0);
 	mutex_unlock(&ftrace_lock);
 
 	return ret;
@@ -4729,6 +4799,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 trace_func_graph_ret_t ftrace_graph_return =
 			(trace_func_graph_ret_t)ftrace_stub;
 trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -4863,6 +4934,37 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
 	return NOTIFY_DONE;
 }
 
+/* Just a place holder for function graph */
+static struct ftrace_ops fgraph_ops __read_mostly = {
+	.func		= ftrace_stub,
+	.flags		= FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
+				FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+	if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+		return 0;
+	return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+	if (ftrace_ops_list == &ftrace_list_end ||
+	    (ftrace_ops_list == &global_ops &&
+	     global_ops.next == &ftrace_list_end))
+		ftrace_graph_entry = __ftrace_graph_entry;
+	else
+		ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -4887,9 +4989,18 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	}
 
 	ftrace_graph_return = retfunc;
-	ftrace_graph_entry = entryfunc;
 
-	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	/*
+	 * Update the indirect function to the entryfunc, and the
+	 * function that gets called to the entry_test first. Then
+	 * call the update fgraph entry function to determine if
+	 * the entryfunc should be called directly or not.
+	 */
+	__ftrace_graph_entry = entryfunc;
+	ftrace_graph_entry = ftrace_graph_entry_test;
+	update_function_graph_func();
+
+	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -4906,7 +5017,8 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+	__ftrace_graph_entry = ftrace_graph_entry_stub;
+	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e444ff88f0a4..3d9fee3a80b3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
@@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
 	}
@@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 		schedule();
 
 	finish_wait(&work->waiters, &wait);
+	return 0;
 }
 
 /**
@@ -613,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
-	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
-		return POLLIN | POLLRDNORM;
-
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
@@ -627,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	work->waiters_pending = true;
 	poll_wait(filp, &work->waiters, poll_table);
+	work->waiters_pending = true;
+	/*
+	 * There's a tight race between setting the waiters_pending and
+	 * checking if the ring buffer is empty.  Once the waiters_pending bit
+	 * is set, the next event will wake the task up, but we can get stuck
+	 * if there's only a single event in.
+	 *
+	 * FIXME: Ideally, we need a memory barrier on the writer side as well,
+	 * but adding a memory barrier to all events will cause too much of a
+	 * performance hit in the fast path.  We only need a memory barrier when
+	 * the buffer goes from empty to having content.  But as this race is
+	 * extremely small, and it's not a problem if another event comes in, we
+	 * will fix it later.
+	 */
+	smp_mb();
 
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
@@ -1981,7 +1994,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
 
 /**
  * rb_update_event - update event type and data
- * @event: the even to update
+ * @event: the event to update
  * @type: the type of event
  * @length: the size of the event field in the ring buffer
  *
@@ -2396,6 +2409,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	write &= RB_WRITE_MASK;
 	tail = write - length;
 
+	/*
+	 * If this is the first commit on the page, then it has the same
+	 * timestamp as the page itself.
+	 */
+	if (!tail)
+		delta = 0;
+
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE))
 		return rb_move_tail(cpu_buffer, length, tail,
@@ -3347,21 +3367,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
 	/* Iterator usage is expected to have record disabled */
-	if (list_empty(&cpu_buffer->reader_page->list)) {
-		iter->head_page = rb_set_head_page(cpu_buffer);
-		if (unlikely(!iter->head_page))
-			return;
-		iter->head = iter->head_page->read;
-	} else {
-		iter->head_page = cpu_buffer->reader_page;
-		iter->head = cpu_buffer->reader_page->read;
-	}
+	iter->head_page = cpu_buffer->reader_page;
+	iter->head = cpu_buffer->reader_page->read;
+
+	iter->cache_reader_page = iter->head_page;
+	iter->cache_read = cpu_buffer->read;
+
 	if (iter->head)
 		iter->read_stamp = cpu_buffer->read_stamp;
 	else
 		iter->read_stamp = iter->head_page->page->time_stamp;
-	iter->cache_reader_page = cpu_buffer->reader_page;
-	iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -3754,12 +3769,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return NULL;
 
 	/*
-	 * We repeat when a time extend is encountered.
-	 * Since the time extend is always attached to a data event,
-	 * we should never loop more than once.
-	 * (We never hit the following condition more than twice).
+	 * We repeat when a time extend is encountered or we hit
+	 * the end of the page. Since the time extend is always attached
+	 * to a data event, we should never loop more than three times.
+	 * Once for going to next page, once on time extend, and
+	 * finally once to get the event.
+	 * (We never hit the following condition more than thrice).
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0582a01a81e3..18cdf91b2f85 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -423,13 +423,19 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	int alloc;
+	int pc;
+
+	pc = preempt_count();
+
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
 
 	alloc = sizeof(*entry) + size + 2; /* possible \n added */
 
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -446,6 +452,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return size;
 }
@@ -463,11 +470,17 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
+	int pc;
+
+	pc = preempt_count();
+
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
 
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -476,6 +489,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return 1;
 }
@@ -727,7 +741,7 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
-	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock_jiffies,	"uptime",	0 },
 	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
@@ -826,9 +840,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	if (isspace(ch)) {
 		parser->buffer[parser->idx] = 0;
 		parser->cont = false;
-	} else {
+	} else if (parser->idx < parser->size - 1) {
 		parser->cont = true;
 		parser->buffer[parser->idx++] = ch;
+	} else {
+		ret = -EINVAL;
+		goto out;
 	}
 
 	*ppos += read;
@@ -1018,13 +1035,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static int default_wait_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
-		return;
+		return 0;
 
-	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1297,7 +1314,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&ftrace_max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1344,7 +1360,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
@@ -1391,12 +1406,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1405,7 +1420,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
 	idx = map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
@@ -1430,6 +1445,8 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
 void trace_find_cmdline(int pid, char comm[])
@@ -1471,9 +1488,8 @@ void tracing_record_cmdline(struct task_struct *tsk)
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
-	__this_cpu_write(trace_cmdline_save, false);
-
-	trace_save_cmdline(tsk);
+	if (trace_save_cmdline(tsk))
+		__this_cpu_write(trace_cmdline_save, false);
 }
 
 void
@@ -4046,17 +4062,19 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
  *
  *     Anyway, this is really very primitive wakeup.
  */
-void poll_wait_pipe(struct trace_iterator *iter)
+int poll_wait_pipe(struct trace_iterator *iter)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 	/* sleep for 100 msecs, and try again. */
 	schedule_timeout(HZ / 10);
+	return 0;
 }
 
 /* Must be called with trace_types_lock mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
 	struct trace_iterator *iter = filp->private_data;
+	int ret;
 
 	while (trace_empty(iter)) {
 
@@ -4066,10 +4084,13 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		iter->trace->wait_pipe(iter);
+		ret = iter->trace->wait_pipe(iter);
 
 		mutex_lock(&iter->mutex);
 
+		if (ret)
+			return ret;
+
 		if (signal_pending(current))
 			return -EINTR;
 
@@ -5003,8 +5024,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			iter->trace->wait_pipe(iter);
+			ret = iter->trace->wait_pipe(iter);
 			mutex_lock(&trace_types_lock);
+			if (ret) {
+				size = ret;
+				goto out_unlock;
+			}
 			if (signal_pending(current)) {
 				size = -EINTR;
 				goto out_unlock;
@@ -5216,8 +5241,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		iter->trace->wait_pipe(iter);
+		ret = iter->trace->wait_pipe(iter);
 		mutex_lock(&trace_types_lock);
+		if (ret)
+			goto out;
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
@@ -5875,6 +5902,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 
 	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
 
+	buf->tr = tr;
+
 	buf->buffer = ring_buffer_alloc(size, rb_flags);
 	if (!buf->buffer)
 		return -ENOMEM;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 51b44483eb78..aa0e736b72ac 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -342,7 +342,7 @@ struct tracer {
 	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
-	void			(*wait_pipe)(struct trace_iterator *iter);
+	int			(*wait_pipe)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	void			(*pipe_close)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
@@ -557,7 +557,7 @@ void trace_init_global_iter(struct trace_iterator *iter);
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void poll_wait_pipe(struct trace_iterator *iter);
+int poll_wait_pipe(struct trace_iterator *iter);
 
 void ftrace(struct trace_array *tr,
 			    struct trace_array_cpu *data,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 26dc348332b7..57b67b1f24d1 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -59,13 +59,14 @@ u64 notrace trace_clock(void)
 
 /*
  * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
  */
 u64 notrace trace_clock_jiffies(void)
 {
-	u64 jiffy = jiffies - INITIAL_JIFFIES;
-
-	/* Return nsecs */
-	return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+	return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
 }
 
 /*
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 84b1e045faba..8354dc81ae64 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -26,7 +26,7 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 {
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event) &&
-	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/* No tracing, just counting, so no obvious leak */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3d18aadef493..001b349af939 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
@@ -1860,6 +1854,16 @@ static void trace_module_add_events(struct module *mod)
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call **call, **start, **end;
 
+	if (!mod->num_trace_events)
+		return;
+
+	/* Don't add infrastructure for mods without tracepoints */
+	if (trace_module_has_bad_taint(mod)) {
+		pr_err("%s: module has bad taint, not creating trace events\n",
+		       mod->name);
+		return;
+	}
+
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d21a74670088..d7d0b50b1b70 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		mutex_lock(&event_storage_mutex);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), filter_type);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 322e16461072..bdb9ee0af991 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -312,7 +312,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
 		return;
@@ -354,7 +354,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
 		return;
@@ -557,7 +557,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
@@ -633,7 +633,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f26540e9c9..63630aef3bd3 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,17 +631,25 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
 static int tracepoint_module_coming(struct module *mod)
 {
 	struct tp_module *tp_mod, *iter;
 	int ret = 0;
 
+	if (!mod->num_tracepoints)
+		return 0;
+
 	/*
 	 * We skip modules that taint the kernel, especially those with different
 	 * module headers (for forced load), to make sure we don't cause a crash.
 	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+	if (trace_module_has_bad_taint(mod))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
@@ -679,6 +687,9 @@ static int tracepoint_module_going(struct module *mod)
 {
 	struct tp_module *pos;
 
+	if (!mod->num_tracepoints)
+		return 0;
+
 	mutex_lock(&tracepoints_mutex);
 	tracepoint_update_probe_range(mod->tracepoints_ptrs,
 		mod->tracepoints_ptrs + mod->num_tracepoints);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index f6c83d7ef000..d58cc4d8f0d1 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!nsown_capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/user.c b/kernel/user.c
index 69b4c3d48cde..6bbef5604101 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,7 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.flags = USERNS_INIT_FLAGS,
 	.may_mount_sysfs = true,
 	.may_mount_proc = true,
 };
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 9064b919a406..3f2fb33d291a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -24,6 +24,7 @@
 #include <linux/fs_struct.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
+static DEFINE_MUTEX(userns_state_mutex);
 
 static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
@@ -99,6 +100,11 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 
+	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+	mutex_lock(&userns_state_mutex);
+	ns->flags = parent_ns->flags;
+	mutex_unlock(&userns_state_mutex);
+
 	set_cred_user_ns(new, ns);
 
 	update_mnt_policy(ns);
@@ -148,7 +154,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].first;
 		last = first + map->extent[idx].count - 1;
@@ -172,7 +178,7 @@ static u32 map_id_down(struct uid_gid_map *map, u32 id)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].first;
 		last = first + map->extent[idx].count - 1;
@@ -195,7 +201,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].lower_first;
 		last = first + map->extent[idx].count - 1;
@@ -577,9 +583,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent
 	return false;
 }
 
-
-static DEFINE_MUTEX(id_map_mutex);
-
 static ssize_t map_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos,
 			 int cap_setid,
@@ -596,7 +599,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	ssize_t ret = -EINVAL;
 
 	/*
-	 * The id_map_mutex serializes all writes to any given map.
+	 * The userns_state_mutex serializes all writes to any given map.
 	 *
 	 * Any map is only ever written once.
 	 *
@@ -611,11 +614,10 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	 * were written before the count of the extents.
 	 *
 	 * To achieve this smp_wmb() is used on guarantee the write
-	 * order and smp_read_barrier_depends() is guaranteed that we
-	 * don't have crazy architectures returning stale data.
-	 *
+	 * order and smp_rmb() is guaranteed that we don't have crazy
+	 * architectures returning stale data.
 	 */
-	mutex_lock(&id_map_mutex);
+	mutex_lock(&userns_state_mutex);
 
 	ret = -EPERM;
 	/* Only allow one successful write to the map */
@@ -742,7 +744,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	*ppos = count;
 	ret = count;
 out:
-	mutex_unlock(&id_map_mutex);
+	mutex_unlock(&userns_state_mutex);
 	if (page)
 		free_page(page);
 	return ret;
@@ -801,17 +803,21 @@ static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
-	/* Allow mapping to your own filesystem ids */
-	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
+	const struct cred *cred = file->f_cred;
+	/* Don't allow mappings that would allow anything that wouldn't
+	 * be allowed without the establishment of unprivileged mappings.
+	 */
+	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
+	    uid_eq(ns->owner, cred->euid)) {
 		u32 id = new_map->extent[0].lower_first;
 		if (cap_setid == CAP_SETUID) {
 			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, file->f_cred->fsuid))
+			if (uid_eq(uid, cred->euid))
 				return true;
-		}
-		else if (cap_setid == CAP_SETGID) {
+		} else if (cap_setid == CAP_SETGID) {
 			kgid_t gid = make_kgid(ns->parent, id);
-			if (gid_eq(gid, file->f_cred->fsgid))
+			if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
+			    gid_eq(gid, cred->egid))
 				return true;
 		}
 	}
@@ -831,6 +837,100 @@ static bool new_idmap_permitted(const struct file *file,
 	return false;
 }
 
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+	seq_printf(seq, "%s\n",
+		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+		   "allow" : "deny");
+	return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	char kbuf[8], *pos;
+	bool setgroups_allowed;
+	ssize_t ret;
+
+	/* Only allow a very narrow range of strings to be written */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= sizeof(kbuf)))
+		goto out;
+
+	/* What was written? */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+	pos = kbuf;
+
+	/* What is being requested? */
+	ret = -EINVAL;
+	if (strncmp(pos, "allow", 5) == 0) {
+		pos += 5;
+		setgroups_allowed = true;
+	}
+	else if (strncmp(pos, "deny", 4) == 0) {
+		pos += 4;
+		setgroups_allowed = false;
+	}
+	else
+		goto out;
+
+	/* Verify there is not trailing junk on the line */
+	pos = skip_spaces(pos);
+	if (*pos != '\0')
+		goto out;
+
+	ret = -EPERM;
+	mutex_lock(&userns_state_mutex);
+	if (setgroups_allowed) {
+		/* Enabling setgroups after setgroups has been disabled
+		 * is not allowed.
+		 */
+		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+			goto out_unlock;
+	} else {
+		/* Permanently disabling setgroups after setgroups has
+		 * been enabled by writing the gid_map is not allowed.
+		 */
+		if (ns->gid_map.nr_extents != 0)
+			goto out_unlock;
+		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+	}
+	mutex_unlock(&userns_state_mutex);
+
+	/* Report a successful write */
+	*ppos = count;
+	ret = count;
+out:
+	return ret;
+out_unlock:
+	mutex_unlock(&userns_state_mutex);
+	goto out;
+}
+
+bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	bool allowed;
+
+	mutex_lock(&userns_state_mutex);
+	/* It is not safe to use setgroups until a gid mapping in
+	 * the user namespace has been established.
+	 */
+	allowed = ns->gid_map.nr_extents != 0;
+	/* Is setgroups allowed? */
+	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
+	mutex_unlock(&userns_state_mutex);
+
+	return allowed;
+}
+
 static void *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e52d002d3893..a2c7e4377960 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -272,6 +272,15 @@ static cpumask_var_t *wq_numa_possible_cpumask;
 static bool wq_disable_numa;
 module_param_named(disable_numa, wq_disable_numa, bool, 0444);
 
+/* see the comment above the definition of WQ_POWER_EFFICIENT */
+#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT
+static bool wq_power_efficient = true;
+#else
+static bool wq_power_efficient;
+#endif
+
+module_param_named(power_efficient, wq_power_efficient, bool, 0444);
+
 static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
 
 /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
@@ -295,6 +304,9 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
 /* I: attributes used when instantiating standard unbound pools on demand */
 static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
 struct workqueue_struct *system_wq __read_mostly;
 EXPORT_SYMBOL(system_wq);
 struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -305,6 +317,10 @@ struct workqueue_struct *system_unbound_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 struct workqueue_struct *system_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
+struct workqueue_struct *system_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_power_efficient_wq);
+struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
 
 static int worker_thread(void *__worker);
 static void copy_workqueue_attrs(struct workqueue_attrs *to,
@@ -1820,6 +1836,12 @@ static void destroy_worker(struct worker *worker)
 	if (worker->flags & WORKER_IDLE)
 		pool->nr_idle--;
 
+	/*
+	 * Once WORKER_DIE is set, the kworker may destroy itself at any
+	 * point.  Pin to ensure the task stays until we're done with it.
+	 */
+	get_task_struct(worker->task);
+
 	list_del_init(&worker->entry);
 	worker->flags |= WORKER_DIE;
 
@@ -1828,6 +1850,7 @@ static void destroy_worker(struct worker *worker)
 	spin_unlock_irq(&pool->lock);
 
 	kthread_stop(worker->task);
+	put_task_struct(worker->task);
 	kfree(worker);
 
 	spin_lock_irq(&pool->lock);
@@ -1871,6 +1894,12 @@ static void send_mayday(struct work_struct *work)
 
 	/* mayday mayday mayday */
 	if (list_empty(&pwq->mayday_node)) {
+		/*
+		 * If @pwq is for an unbound wq, its base ref may be put at
+		 * any time due to an attribute change.  Pin @pwq until the
+		 * rescuer is done with it.
+		 */
+		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
 	}
@@ -2346,6 +2375,7 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
+	bool should_stop;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2357,11 +2387,15 @@ static int rescuer_thread(void *__rescuer)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop()) {
-		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
-		return 0;
-	}
+	/*
+	 * By the time the rescuer is requested to stop, the workqueue
+	 * shouldn't have any work pending, but @wq->maydays may still have
+	 * pwq(s) queued.  This can happen by non-rescuer workers consuming
+	 * all the work items before the rescuer got to them.  Go through
+	 * @wq->maydays processing before acting on should_stop so that the
+	 * list is always empty on exit.
+	 */
+	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
 	spin_lock_irq(&wq_mayday_lock);
@@ -2393,6 +2427,12 @@ repeat:
 		process_scheduled_works(rescuer);
 
 		/*
+		 * Put the reference grabbed by send_mayday().  @pool won't
+		 * go away while we're holding its lock.
+		 */
+		put_pwq(pwq);
+
+		/*
 		 * Leave this pool.  If keep_working() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
@@ -2407,6 +2447,12 @@ repeat:
 
 	spin_unlock_irq(&wq_mayday_lock);
 
+	if (should_stop) {
+		__set_current_state(TASK_RUNNING);
+		rescuer->task->flags &= ~PF_WQ_WORKER;
+		return 0;
+	}
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -3340,6 +3386,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 		}
 	}
 
+	dev_set_uevent_suppress(&wq_dev->dev, false);
 	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
 	return 0;
 }
@@ -4033,7 +4080,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	if (!pwq) {
 		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
 			   wq->name);
-		goto out_unlock;
+		mutex_lock(&wq->mutex);
+		goto use_dfl_pwq;
 	}
 
 	/*
@@ -4059,7 +4107,7 @@ out_unlock:
 static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 {
 	bool highpri = wq->flags & WQ_HIGHPRI;
-	int cpu;
+	int cpu, ret;
 
 	if (!(wq->flags & WQ_UNBOUND)) {
 		wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4079,6 +4127,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 			mutex_unlock(&wq->mutex);
 		}
 		return 0;
+	} else if (wq->flags & __WQ_ORDERED) {
+		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+		/* there should only be single pwq for ordering guarantee */
+		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+		     "ordering guarantee broken for workqueue %s\n", wq->name);
+		return ret;
 	} else {
 		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
@@ -4107,6 +4162,10 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
 
+	/* see the comment above the definition of WQ_POWER_EFFICIENT */
+	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
+		flags |= WQ_UNBOUND;
+
 	/* allocate wq and format name */
 	if (flags & WQ_UNBOUND)
 		tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]);
@@ -4926,7 +4985,7 @@ static void __init wq_numa_init(void)
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+		BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
 				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {
@@ -4990,13 +5049,23 @@ static int __init init_workqueues(void)
 		}
 	}
 
-	/* create default unbound wq attrs */
+	/* create default unbound and ordered wq attrs */
 	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
 		struct workqueue_attrs *attrs;
 
 		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
 		attrs->nice = std_nice[i];
 		unbound_std_wq_attrs[i] = attrs;
+
+		/*
+		 * An ordered wq should have only one pwq as ordering is
+		 * guaranteed by max_active which is enforced by pwqs.
+		 * Turn off NUMA so that dfl_pwq is used for all nodes.
+		 */
+		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		attrs->nice = std_nice[i];
+		attrs->no_numa = true;
+		ordered_wq_attrs[i] = attrs;
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);
@@ -5006,8 +5075,15 @@ static int __init init_workqueues(void)
 					    WQ_UNBOUND_MAX_ACTIVE);
 	system_freezable_wq = alloc_workqueue("events_freezable",
 					      WQ_FREEZABLE, 0);
+	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
+					      WQ_POWER_EFFICIENT, 0);
+	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
+					      WQ_FREEZABLE | WQ_POWER_EFFICIENT,
+					      0);
 	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-	       !system_unbound_wq || !system_freezable_wq);
+	       !system_unbound_wq || !system_freezable_wq ||
+	       !system_power_efficient_wq ||
+	       !system_freezable_power_efficient_wq);
 	return 0;
 }
 early_initcall(init_workqueues);
diff --git a/lib/Makefile b/lib/Makefile
index 1dcad1b93284..3def8e1ce905 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,7 @@ lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
 
+GCOV_PROFILE_hweight.o := n
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06f7e4fe8d2d..e5c4ebe586ba 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -131,7 +131,9 @@ void __bitmap_shift_right(unsigned long *dst,
 		lower = src[off + k];
 		if (left && off + k == lim - 1)
 			lower &= mask;
-		dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
+		dst[k] = lower >> rem;
+		if (rem)
+			dst[k] |= upper << (BITS_PER_LONG - rem);
 		if (left && k == lim - 1)
 			dst[k] &= mask;
 	}
@@ -172,7 +174,9 @@ void __bitmap_shift_left(unsigned long *dst,
 		upper = src[k];
 		if (left && k == lim - 1)
 			upper &= (1UL << left) - 1;
-		dst[k + off] = lower  >> (BITS_PER_LONG - rem) | upper << rem;
+		dst[k + off] = upper << rem;
+		if (rem)
+			dst[k + off] |= lower >> (BITS_PER_LONG - rem);
 		if (left && k + off == lim - 1)
 			dst[k + off] &= (1UL << left) - 1;
 	}
diff --git a/lib/btree.c b/lib/btree.c
index f9a484676cb6..4264871ea1a0 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init);
 
 void btree_destroy(struct btree_head *head)
 {
+	mempool_free(head->node, head->mempool);
 	mempool_destroy(head->mempool);
 	head->mempool = NULL;
 }
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 19ff89e34eec..d619b28c456f 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -48,7 +48,7 @@ STATIC int INIT gunzip(unsigned char *buf, int len,
 		out_len = 0x8000; /* 32 K */
 		out_buf = malloc(out_len);
 	} else {
-		out_len = 0x7fffffff; /* no limit */
+		out_len = ((size_t)~0) - (size_t)out_buf; /* no limit */
 	}
 	if (!out_buf) {
 		error("Out of memory while allocating output buffer");
diff --git a/lib/genalloc.c b/lib/genalloc.c
index f8b131bd920e..9e9c46c267db 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -37,6 +37,11 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 
+static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
+{
+	return chunk->end_addr - chunk->start_addr + 1;
+}
+
 static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
 {
 	unsigned long val, nval;
@@ -188,7 +193,7 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
 
 	chunk->phys_addr = phys;
 	chunk->start_addr = virt;
-	chunk->end_addr = virt + size;
+	chunk->end_addr = virt + size - 1;
 	atomic_set(&chunk->avail, size);
 
 	spin_lock(&pool->lock);
@@ -213,7 +218,7 @@ phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
-		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+		if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
 			paddr = chunk->phys_addr + (addr - chunk->start_addr);
 			break;
 		}
@@ -242,7 +247,7 @@ void gen_pool_destroy(struct gen_pool *pool)
 		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
 		list_del(&chunk->next_chunk);
 
-		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		end_bit = chunk_size(chunk) >> order;
 		bit = find_next_bit(chunk->bits, end_bit, 0);
 		BUG_ON(bit < end_bit);
 
@@ -283,7 +288,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		if (size > atomic_read(&chunk->avail))
 			continue;
 
-		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
 				pool->data);
@@ -330,8 +335,8 @@ void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
 	nbits = (size + (1UL << order) - 1) >> order;
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
-		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
-			BUG_ON(addr + size > chunk->end_addr);
+		if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
+			BUG_ON(addr + size - 1 > chunk->end_addr);
 			start_bit = (addr - chunk->start_addr) >> order;
 			remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
 			BUG_ON(remain);
@@ -429,7 +434,7 @@ size_t gen_pool_size(struct gen_pool *pool)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
-		size += chunk->end_addr - chunk->start_addr;
+		size += chunk_size(chunk);
 	rcu_read_unlock();
 	return size;
 }
diff --git a/lib/idr.c b/lib/idr.c
index cca4b9302a71..a3bfde8ad60e 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -250,7 +250,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
 			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
 
 			/* if already at the top layer, we need to grow */
-			if (id >= 1 << (idp->layers * IDR_BITS)) {
+			if (id > idr_max(idp->layers)) {
 				*starting_id = id;
 				return -EAGAIN;
 			}
@@ -829,12 +829,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 	if (!p)
 		return ERR_PTR(-EINVAL);
 
-	n = (p->layer+1) * IDR_BITS;
-
-	if (id >= (1 << n))
+	if (id > idr_max(p->layer + 1))
 		return ERR_PTR(-EINVAL);
 
-	n -= IDR_BITS;
+	n = p->layer * IDR_BITS;
 	while ((n > 0) && p) {
 		p = p->ary[(id >> n) & IDR_MASK];
 		n -= IDR_BITS;
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d522d5..a1c387f6afba 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -25,6 +25,16 @@
 #define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
 #define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
 
+/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
+ * count without overflowing an integer. The multiply will overflow when
+ * multiplying 255 by more than MAXINT/255. The sum will overflow earlier
+ * depending on the base count. Since the base count is taken from a u8
+ * and a few bits, it is safe to assume that it will always be lower than
+ * or equal to 2*255, thus we can always prevent any overflow by accepting
+ * two less 255 steps. See Documentation/lzo.txt for more information.
+ */
+#define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
+
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
 {
@@ -55,12 +65,19 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 		if (t < 16) {
 			if (likely(state == 0)) {
 				if (unlikely(t == 0)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
 					while (unlikely(*ip == 0)) {
-						t += 255;
 						ip++;
 						NEED_IP(1);
 					}
-					t += 15 + *ip++;
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
@@ -116,12 +133,19 @@ copy_literal_run:
 		} else if (t >= 32) {
 			t = (t & 31) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
 					NEED_IP(1);
 				}
-				t += 31 + *ip++;
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 31 + *ip++;
 				NEED_IP(2);
 			}
 			m_pos = op - 1;
@@ -134,12 +158,19 @@ copy_literal_run:
 			m_pos -= (t & 8) << 11;
 			t = (t & 7) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
 					NEED_IP(1);
 				}
-				t += 7 + *ip++;
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 7 + *ip++;
 				NEED_IP(2);
 			}
 			next = get_unaligned_le16(ip);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 18eca7809b08..10ad042d01be 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -201,8 +201,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
 	}
 
 	if (unlikely(rem > 0))
-		printk(KERN_WARNING "netlink: %d bytes leftover after parsing "
-		       "attributes.\n", rem);
+		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+				    rem, current->comm);
 
 	err = 0;
 errout:
@@ -303,9 +303,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);
 
diff --git a/lib/random32.c b/lib/random32.c
index 52280d5526be..01e8890d1089 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -141,7 +141,7 @@ void prandom_seed(u32 entropy)
 	 */
 	for_each_possible_cpu (i) {
 		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		state->s1 = __seed(state->s1 ^ entropy, 1);
+		state->s1 = __seed(state->s1 ^ entropy, 2);
 	}
 }
 EXPORT_SYMBOL(prandom_seed);
@@ -158,9 +158,9 @@ static int __init prandom_init(void)
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
 
 #define LCG(x)	((x) * 69069)	/* super-duper LCG */
-		state->s1 = __seed(LCG(i + jiffies), 1);
-		state->s2 = __seed(LCG(state->s1), 7);
-		state->s3 = __seed(LCG(state->s2), 15);
+		state->s1 = __seed(LCG(i + jiffies), 2);
+		state->s2 = __seed(LCG(state->s1), 8);
+		state->s3 = __seed(LCG(state->s2), 16);
 
 		/* "warm it up" */
 		prandom_u32_state(state);
@@ -187,9 +187,9 @@ static int __init prandom_reseed(void)
 		u32 seeds[3];
 
 		get_random_bytes(&seeds, sizeof(seeds));
-		state->s1 = __seed(seeds[0], 1);
-		state->s2 = __seed(seeds[1], 7);
-		state->s3 = __seed(seeds[2], 15);
+		state->s1 = __seed(seeds[0], 2);
+		state->s2 = __seed(seeds[1], 8);
+		state->s3 = __seed(seeds[2], 16);
 
 		/* mix it in */
 		prandom_u32_state(state);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index a1cf8cae60e7..3e7df38067ae 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -529,7 +529,8 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
 		miter->__offset += miter->consumed;
 		miter->__remaining -= miter->consumed;
 
-		if (miter->__flags & SG_MITER_TO_SG)
+		if ((miter->__flags & SG_MITER_TO_SG) &&
+		    !PageSlab(miter->page))
 			flush_kernel_dcache_page(miter->page);
 
 		if (miter->__flags & SG_MITER_ATOMIC) {
diff --git a/lib/string.c b/lib/string.c
index e5878de4f101..43d0781daf47 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -586,6 +586,22 @@ void *memset(void *s, int c, size_t count)
 EXPORT_SYMBOL(memset);
 #endif
 
+/**
+ * memzero_explicit - Fill a region of memory (e.g. sensitive
+ *		      keying data) with 0s.
+ * @s: Pointer to the start of the area.
+ * @count: The size of the area.
+ *
+ * memzero_explicit() doesn't need an arch-specific version as
+ * it just invokes the one of memset() implicitly.
+ */
+void memzero_explicit(void *s, size_t count)
+{
+	memset(s, 0, count);
+	OPTIMIZER_HIDE_VAR(s);
+}
+EXPORT_SYMBOL(memzero_explicit);
+
 #ifndef __HAVE_ARCH_MEMCPY
 /**
  * memcpy - Copy one area of memory to another
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index e149c6416384..620fae4c11f6 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -26,6 +26,7 @@
 #include <linux/math64.h>
 #include <linux/uaccess.h>
 #include <linux/ioport.h>
+#include <linux/cred.h>
 #include <net/addrconf.h>
 
 #include <asm/page.h>		/* for PAGE_SIZE */
@@ -1118,11 +1119,37 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 				spec.field_width = default_width;
 			return string(buf, end, "pK-error", spec);
 		}
-		if (!((kptr_restrict == 0) ||
-		      (kptr_restrict == 1 &&
-		       has_capability_noaudit(current, CAP_SYSLOG))))
+
+		switch (kptr_restrict) {
+		case 0:
+			/* Always print %pK values */
+			break;
+		case 1: {
+			/*
+			 * Only print the real pointer value if the current
+			 * process has CAP_SYSLOG and is running with the
+			 * same credentials it started with. This is because
+			 * access to files is checked at open() time, but %pK
+			 * checks permission at read() time. We don't want to
+			 * leak pointer values if a binary opens a file using
+			 * %pK and then elevates privileges before reading it.
+			 */
+			const struct cred *cred = current_cred();
+
+			if (!has_capability_noaudit(current, CAP_SYSLOG) ||
+			    !uid_eq(cred->euid, cred->uid) ||
+			    !gid_eq(cred->egid, cred->gid))
+				ptr = NULL;
+			break;
+		}
+		case 2:
+		default:
+			/* Always print 0's for %pK */
 			ptr = NULL;
+			break;
+		}
 		break;
+
 	case 'N':
 		switch (fmt[1]) {
 		case 'F':
diff --git a/linaro/configs/android.conf b/linaro/configs/android.conf
new file mode 100644
index 000000000000..e4fd1ad19028
--- /dev/null
+++ b/linaro/configs/android.conf
@@ -0,0 +1,42 @@
+CONFIG_IPV6=y
+# CONFIG_IPV6_SIT is not set
+CONFIG_PANIC_TIMEOUT=0
+CONFIG_HAS_WAKELOCK=y
+CONFIG_WAKELOCK=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DM_CRYPT=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_ANDROID_PARANOID_NETWORK=y
+CONFIG_NET_ACTIVITY_STATS=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+CONFIG_USB_G_ANDROID=y
+CONFIG_SWITCH=y
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOGGER=y
+CONFIG_ANDROID_TIMED_OUTPUT=y
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ANDROID_INTF_ALARM_DEV=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_FUSE_FS=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y
+CONFIG_ION=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION_TEST=y
+CONFIG_ION_DUMMY=y
+CONFIG_ADF=y
+CONFIG_ADF_FBDEV=y
+CONFIG_ADF_MEMBLOCK=y
+CONFIG_DMA_SHARED_BUFFER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/arndale.conf b/linaro/configs/arndale.conf
new file mode 100644
index 000000000000..109052f2f6ec
--- /dev/null
+++ b/linaro/configs/arndale.conf
@@ -0,0 +1,66 @@
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_S3C_LOWLEVEL_UART_PORT=2
+CONFIG_ARCH_EXYNOS5=y
+# CONFIG_EXYNOS_ATAGS is not set
+CONFIG_MACH_EXYNOS4_DT=y
+CONFIG_VMSPLIT_2G=y
+CONFIG_NR_CPUS=2
+CONFIG_HIGHMEM=y
+# CONFIG_COMPACTION is not set
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init= mem=256M"
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_EXYNOS=y
+CONFIG_AX88796=y
+CONFIG_AX88796_93CX6=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_SAMSUNG=y
+CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C=y
+CONFIG_I2C_S3C2410=y
+CONFIG_THERMAL=y
+CONFIG_CPU_THERMAL=y
+CONFIG_EXYNOS_THERMAL=y
+CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_S5M8767=y
+CONFIG_DRM=y
+CONFIG_DRM_LOAD_EDID_FIRMWARE=y
+CONFIG_DRM_EXYNOS=y
+CONFIG_DRM_EXYNOS_DMABUF=y
+CONFIG_DRM_EXYNOS_HDMI=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+CONFIG_MMC_DW_EXYNOS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_S3C=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_INFO=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_DEBUG_USER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/big-LITTLE-IKS.conf b/linaro/configs/big-LITTLE-IKS.conf
new file mode 100644
index 000000000000..b067fde86eaa
--- /dev/null
+++ b/linaro/configs/big-LITTLE-IKS.conf
@@ -0,0 +1,5 @@
+CONFIG_BIG_LITTLE=y
+CONFIG_BL_SWITCHER=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
diff --git a/linaro/configs/big-LITTLE-MP.conf b/linaro/configs/big-LITTLE-MP.conf
new file mode 100644
index 000000000000..ced3cf974f13
--- /dev/null
+++ b/linaro/configs/big-LITTLE-MP.conf
@@ -0,0 +1,12 @@
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_NO_HZ=y
+CONFIG_SCHED_MC=y
+CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE=y
+CONFIG_SCHED_HMP=y
+CONFIG_HMP_FAST_CPU_MASK=""
+CONFIG_HMP_SLOW_CPU_MASK=""
+CONFIG_HMP_VARIABLE_SCALE=y
+CONFIG_HMP_FREQUENCY_INVARIANT_SCALE=y
+CONFIG_SCHED_HMP_LITTLE_PACKING=y
diff --git a/linaro/configs/bigendian.conf b/linaro/configs/bigendian.conf
new file mode 100644
index 000000000000..6a1020299e85
--- /dev/null
+++ b/linaro/configs/bigendian.conf
@@ -0,0 +1,4 @@
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_CPU_ENDIAN_BE8=y
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_MMC_DW_IDMAC is not set
diff --git a/linaro/configs/booting-test.conf b/linaro/configs/booting-test.conf
new file mode 100644
index 000000000000..7592b2185963
--- /dev/null
+++ b/linaro/configs/booting-test.conf
@@ -0,0 +1,66 @@
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_CHECK=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_SELFTEST=y
+CONFIG_DEBUG_OBJECTS_TIMERS=y
+CONFIG_DEBUG_OBJECTS_WORK=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
+CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
+CONFIG_DEBUG_KMEMLEAK=y
+CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=400
+CONFIG_DEBUG_KMEMLEAK_TEST=m
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_PI_LIST=y
+CONFIG_RT_MUTEX_TESTER=y
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_KOBJECT=y
+CONFIG_DEBUG_HIGHMEM=y
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_RB=y
+CONFIG_DEBUG_WRITECOUNT=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_LIST=y
+CONFIG_TEST_LIST_SORT=y
+CONFIG_DEBUG_SG=y
+CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_DEBUG_CREDENTIALS=y
+CONFIG_DEBUG_BLOCK_EXT_DEVT=y
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_TRACER_MAX_TRACE=y
+CONFIG_GENERIC_TRACER=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FUNCTION_GRAPH_TRACER=y
+CONFIG_IRQSOFF_TRACER=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_FTRACE_MCOUNT_RECORD=y
+CONFIG_FTRACE_SELFTEST=y
+CONFIG_FTRACE_STARTUP_TEST=y
+CONFIG_EVENT_TRACE_TEST_SYSCALLS=y
+CONFIG_RING_BUFFER_BENCHMARK=y
+CONFIG_RING_BUFFER_STARTUP_TEST=y
+CONFIG_DYNAMIC_DEBUG=y
+CONFIG_DMA_API_DEBUG=y
+CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_STRING_HELPERS=y
+CONFIG_TEST_KSTRTOX=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_OLD_MCOUNT=y
+CONFIG_DEBUG_USER=y
+
diff --git a/linaro/configs/debug.conf b/linaro/configs/debug.conf
new file mode 100644
index 000000000000..36980566b2d8
--- /dev/null
+++ b/linaro/configs/debug.conf
@@ -0,0 +1 @@
+CONFIG_PROVE_LOCKING=y
diff --git a/linaro/configs/distribution.conf b/linaro/configs/distribution.conf
new file mode 100644
index 000000000000..729b9b8979e4
--- /dev/null
+++ b/linaro/configs/distribution.conf
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_CGROUPS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
+CONFIG_SECCOMP=y
+CONFIG_CC_STACKPROTECTOR=y
+CONFIG_SYN_COOKIES=y
+CONFIG_IPV6=y
+CONFIG_NETLABEL=y
+CONFIG_BRIDGE_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NETFILTER_XT_CONNMARK=m
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE=m
+CONFIG_TUN=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+# CONFIG_DEVKMEM is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SECURITY=y
+CONFIG_LSM_MMAP_MIN_ADDR=0
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SMACK=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_DEFAULT_SECURITY_APPARMOR=y
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
diff --git a/linaro/configs/highbank.conf b/linaro/configs/highbank.conf
new file mode 100644
index 000000000000..bf0f3c14b0d0
--- /dev/null
+++ b/linaro/configs/highbank.conf
@@ -0,0 +1,40 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_ARCH_HIGHBANK=y
+CONFIG_ARM_ERRATA_754322=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_AEABI=y
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_CPU_IDLE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_NET=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_HIGHBANK=y
+CONFIG_NETDEVICES=y
+CONFIG_NET_CALXEDA_XGMAC=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_IPMI_HANDLER=y
+CONFIG_IPMI_SI=y
+CONFIG_I2C=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_SPI=y
+CONFIG_SPI_PL022=y
+CONFIG_GPIO_PL061=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_HIGHBANK_MC=y
+CONFIG_EDAC_HIGHBANK_L2=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_DMADEVICES=y
+CONFIG_PL330_DMA=y
diff --git a/linaro/configs/kvm-guest.conf b/linaro/configs/kvm-guest.conf
new file mode 100644
index 000000000000..00e84a3ba1ec
--- /dev/null
+++ b/linaro/configs/kvm-guest.conf
@@ -0,0 +1,11 @@
+CONFIG_BALLOON_COMPACTION=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_NET=y
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_VIRTUALIZATION=y
+# CONFIG_THUMB2_KERNEL is not set
diff --git a/linaro/configs/kvm-host.conf b/linaro/configs/kvm-host.conf
new file mode 100644
index 000000000000..21a40e031372
--- /dev/null
+++ b/linaro/configs/kvm-host.conf
@@ -0,0 +1,11 @@
+CONFIG_VIRTUALIZATION=y
+CONFIG_ARM_LPAE=y
+CONFIG_ARM_VIRT_EXT=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_KVM_ARM_HOST=y
+CONFIG_KVM_ARM_MAX_VCPUS=4
+CONFIG_KVM_ARM_TIMER=y
+CONFIG_KVM_ARM_VGIC=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM=y
+CONFIG_BLK_DEV_NBD=m
diff --git a/linaro/configs/linaro-base.conf b/linaro/configs/linaro-base.conf
new file mode 100644
index 000000000000..15f6ea784f63
--- /dev/null
+++ b/linaro/configs/linaro-base.conf
@@ -0,0 +1,120 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_HOTPLUG=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_SCHED_SMT=y
+CONFIG_THUMB2_KERNEL=y
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_IDLE=y
+CONFIG_BINFMT_MISC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_LRO is not set
+CONFIG_NETFILTER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_OOPS=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_NAND=y
+CONFIG_NETDEVICES=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_BTRFS_FS=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_ECRYPT_FS=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+CONFIG_JFFS2_LZO=y
+CONFIG_JFFS2_RUBIN=y
+CONFIG_CRAMFS=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V2 is not set
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_KEYS=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC7=y
+CONFIG_HW_PERF_EVENTS=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_JUMP_LABEL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_KGDB=y
+CONFIG_KGDB_TESTS=y
+CONFIG_OF_IDLE_STATES=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_MAILBOX=y
+CONFIG_AUDIT=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=4096
+CONFIG_SECURITY_SELINUX=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DEBUG_INFO=y
+CONFIG_FANOTIFY=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_TORTURE_TEST_RUNNABLE=n
diff --git a/linaro/configs/omap4.conf b/linaro/configs/omap4.conf
new file mode 100644
index 000000000000..50fb9d9cb5b5
--- /dev/null
+++ b/linaro/configs/omap4.conf
@@ -0,0 +1,194 @@
+CONFIG_EXPERT=y
+CONFIG_KPROBES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_GPIO_PCA953X=y
+CONFIG_OMAP_RESET_CLOCKS=y
+CONFIG_OMAP_MUX_DEBUG=y
+CONFIG_ARCH_OMAP2PLUS=y
+CONFIG_SOC_OMAP5=y
+# CONFIG_ARCH_OMAP2 is not set
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_ARM_THUMBEE=y
+CONFIG_ARM_ERRATA_411920=y
+CONFIG_NR_CPUS=2
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE="root=/dev/mmcblk0p2 rootwait console=ttyO2,115200"
+CONFIG_KEXEC=y
+CONFIG_PM_DEBUG=y
+CONFIG_CAN=m
+CONFIG_CAN_C_CAN=m
+CONFIG_CAN_C_CAN_PLATFORM=m
+CONFIG_BT=m
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_H4=y
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_LL=y
+CONFIG_BT_HCIBCM203X=m
+CONFIG_BT_HCIBPA10X=m
+CONFIG_CFG80211=m
+CONFIG_MAC80211=m
+CONFIG_MAC80211_RC_PID=y
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+CONFIG_CMA=y
+CONFIG_MTD_NAND_OMAP2=y
+CONFIG_MTD_ONENAND=y
+CONFIG_MTD_ONENAND_VERIFY_WRITE=y
+CONFIG_MTD_ONENAND_OMAP2=y
+CONFIG_MTD_UBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_SENSORS_TSL2550=m
+CONFIG_SENSORS_LIS3_I2C=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_SCAN_ASYNC=y
+CONFIG_KS8851=y
+CONFIG_KS8851_MLL=y
+CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
+CONFIG_TI_CPSW=y
+CONFIG_SMSC_PHY=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_ALI_M5632=y
+CONFIG_USB_AN2720=y
+CONFIG_USB_EPSON2888=y
+CONFIG_USB_KC2190=y
+CONFIG_LIBERTAS=m
+CONFIG_LIBERTAS_USB=m
+CONFIG_LIBERTAS_SDIO=m
+CONFIG_LIBERTAS_DEBUG=y
+CONFIG_INPUT_JOYDEV=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_MATRIX=m
+CONFIG_KEYBOARD_TWL4030=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
+CONFIG_INPUT_TWL4030_PWRBUTTON=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_OMAP=y
+CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_SPI=y
+CONFIG_SPI_OMAP24XX=y
+CONFIG_PINCTRL_SINGLE=y
+CONFIG_DEBUG_GPIO=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_W1=y
+CONFIG_SENSORS_LM75=m
+CONFIG_WATCHDOG=y
+CONFIG_OMAP_WATCHDOG=y
+CONFIG_TWL4030_WATCHDOG=y
+CONFIG_MFD_TPS65217=y
+CONFIG_MFD_TPS65910=y
+CONFIG_TWL6040_CORE=y
+CONFIG_REGULATOR_TPS65023=y
+CONFIG_REGULATOR_TPS6507X=y
+CONFIG_REGULATOR_TPS65217=y
+CONFIG_REGULATOR_TPS65910=y
+CONFIG_REGULATOR_TWL4030=y
+CONFIG_FB=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_OMAP2_DSS=m
+CONFIG_OMAP2_DSS_RFBI=y
+CONFIG_OMAP2_DSS_SDI=y
+CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP2=m
+CONFIG_PANEL_GENERIC_DPI=m
+CONFIG_PANEL_TFP410=m
+CONFIG_PANEL_SHARP_LS037V7DW01=m
+CONFIG_PANEL_NEC_NL8048HL11_01B=m
+CONFIG_PANEL_TAAL=m
+CONFIG_PANEL_TPO_TD043MTEA1=m
+CONFIG_PANEL_ACX565AKM=m
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+CONFIG_LCD_PLATFORM=y
+CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+CONFIG_SOUND=m
+CONFIG_SND=m
+CONFIG_SND_VERBOSE_PRINTK=y
+CONFIG_SND_DEBUG=y
+CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_OMAP_SOC=m
+CONFIG_SND_OMAP_SOC_OMAP_TWL4030=m
+CONFIG_SND_OMAP_SOC_OMAP_ABE_TWL6040=m
+CONFIG_SND_OMAP_SOC_OMAP3_PANDORA=m
+CONFIG_USB=y
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_WDM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_TEST=y
+CONFIG_USB_PHY=y
+CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_GADGET_DEBUG=y
+CONFIG_USB_GADGET_DEBUG_FILES=y
+CONFIG_USB_GADGET_DEBUG_FS=y
+CONFIG_USB_ZERO=m
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_SDIO_UART=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_MMC_OMAP=y
+CONFIG_MMC_OMAP_HS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_ONESHOT=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_TWL92330=y
+CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_OMAP=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_OMAP=y
+# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_UBIFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/preempt-rt.conf b/linaro/configs/preempt-rt.conf
new file mode 100644
index 000000000000..98e036d75442
--- /dev/null
+++ b/linaro/configs/preempt-rt.conf
@@ -0,0 +1,4 @@
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_RT_FULL=y
+CONFIG_SLUB=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/ubuntu-minimal.conf b/linaro/configs/ubuntu-minimal.conf
new file mode 120000
index 000000000000..794e82f3bc17
--- /dev/null
+++ b/linaro/configs/ubuntu-minimal.conf
@@ -0,0 +1 @@
+distribution.conf
\ No newline at end of file
diff --git a/linaro/configs/vexpress-tuning.conf b/linaro/configs/vexpress-tuning.conf
new file mode 100644
index 000000000000..adea6cc66ded
--- /dev/null
+++ b/linaro/configs/vexpress-tuning.conf
@@ -0,0 +1 @@
+# CONFIG_PROVE_LOCKING is not set
diff --git a/linaro/configs/vexpress.conf b/linaro/configs/vexpress.conf
new file mode 100644
index 000000000000..73cae2b8f8f7
--- /dev/null
+++ b/linaro/configs/vexpress.conf
@@ -0,0 +1,63 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_BIG_LITTLE=y
+CONFIG_ARCH_VEXPRESS_TC2=y
+CONFIG_ARCH_VEXPRESS_DCSCB=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_PM_OPP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_ARM_PSCI=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
+CONFIG_NR_CPUS=8
+CONFIG_HIGHMEM=y
+CONFIG_HIGHPTE=y
+CONFIG_CMDLINE="console=ttyAMA0,38400n8 root=/dev/mmcblk0p2 rootwait mmci.fmax=4000000"
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SMSC911X=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FB_ARMHDLCD=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_ARMAACI=y
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VEXPRESS_CONFIG=y
+CONFIG_SENSORS_VEXPRESS=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
diff --git a/linaro/configs/vexpress64.conf b/linaro/configs/vexpress64.conf
new file mode 100644
index 000000000000..c9b66a198586
--- /dev/null
+++ b/linaro/configs/vexpress64.conf
@@ -0,0 +1,55 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_COMPAT=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+# CONFIG_SERIO_I8042 is not set
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_CMA=y
+CONFIG_DMA_CMA=y
+CONFIG_COMMON_CLK_SCPI=y
+CONFIG_SMSC911X=y
+CONFIG_I2C=y
+CONFIG_ARM_MHU_MBOX=y
+CONFIG_ARM_SCPI_PROTOCOL=y
+CONFIG_USB_HIDDEV=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB=y
+CONFIG_USB_ULPI=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_SYNOPSYS=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_PHY=y
+CONFIG_PM_OPP=y
+CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM64_CPUIDLE=y
+CONFIG_ARM64_CRYPTO=y
diff --git a/linaro/configs/xen.conf b/linaro/configs/xen.conf
new file mode 100644
index 000000000000..d24fabbea076
--- /dev/null
+++ b/linaro/configs/xen.conf
@@ -0,0 +1,7 @@
+CONFIG_XEN=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+CONFIG_XEN_NETDEV_BACKEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_BACKEND=y
+CONFIG_XENFS=y
+CONFIG_XEN_COMPAT_XENFS=y
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 502517492258..2e53312b8907 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -232,8 +232,6 @@ static ssize_t stable_pages_required_show(struct device *dev,
 			bdi_cap_stable_pages_required(bdi) ? 1 : 0);
 }
 
-#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
-
 static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RW(read_ahead_kb),
 	__ATTR_RW(min_ratio),
@@ -287,13 +285,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
  * Note, we wouldn't bother setting up the timer, but this function is on the
  * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
  * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
  */
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 {
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -306,9 +310,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
-
-	/* bdi_list is now unused, clear it to mark @bdi dying */
-	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -359,6 +360,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	bdi_remove_from_list(bdi);
 
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
diff --git a/mm/bounce.c b/mm/bounce.c
index c9f0a4339a7d..5a7d58fb883b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -204,6 +204,8 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	struct bio_vec *to, *from;
 	unsigned i;
 
+	if (force)
+		goto bounce;
 	bio_for_each_segment(from, *bio_orig, i)
 		if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
 			goto bounce;
diff --git a/mm/compaction.c b/mm/compaction.c
index 05ccb4cc0bdb..fb797a32362f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
 			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+
+	if (cc->ignore_skip_hint)
+		return;
+
 	if (!page)
 		return;
 
@@ -248,7 +252,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
 
@@ -261,11 +264,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -286,12 +290,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -302,7 +304,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -312,7 +322,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
@@ -647,17 +657,21 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+	unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
-	 * scanned from (or the end of the zone if starting). The low point
-	 * is the end of the pageblock the migration scanner is using.
+	 * successfully isolated from, zone-cached value, or the end of the
+	 * zone when isolating for the first time. We need this aligned to
+	 * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+	 * in the for loop.
+	 * The low boundary is the end of the pageblock the migration scanner
+	 * is using.
 	 */
-	pfn = cc->free_pfn;
-	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+	pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
 	 * Take care that if the migration scanner is at the end of the zone
@@ -673,9 +687,10 @@ static void isolate_freepages(struct zone *zone,
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
+	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
+		unsigned long end_pfn;
 
 		if (!pfn_valid(pfn))
 			continue;
@@ -703,13 +718,10 @@ static void isolate_freepages(struct zone *zone,
 		isolated = 0;
 
 		/*
-		 * As pfn may not start aligned, pfn+pageblock_nr_page
-		 * may cross a MAX_ORDER_NR_PAGES boundary and miss
-		 * a pfn_valid check. Ensure isolate_freepages_block()
-		 * only scans within a pageblock
+		 * Take care when isolating in last pageblock of a zone which
+		 * ends in the middle of a pageblock.
 		 */
-		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, z_end_pfn);
+		end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
 		isolated = isolate_freepages_block(cc, pfn, end_pfn,
 						   freelist, false);
 		nr_freepages += isolated;
@@ -728,7 +740,14 @@ static void isolate_freepages(struct zone *zone,
 	/* split_free_page does not map the pages */
 	map_pages(freelist);
 
-	cc->free_pfn = high_pfn;
+	/*
+	 * If we crossed the migrate scanner, we want to keep it that way
+	 * so that compact_finished() may detect this
+	 */
+	if (pfn < low_pfn)
+		cc->free_pfn = max(pfn, zone->zone_start_pfn);
+	else
+		cc->free_pfn = high_pfn;
 	cc->nr_freepages = nr_freepages;
 }
 
@@ -937,6 +956,14 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	}
 
 	/*
+	 * Clear pageblock skip if there were failures recently and compaction
+	 * is about to be retried after being deferred. kswapd does not do
+	 * this reset as it'll reset the cached information when going to sleep.
+	 */
+	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
+		__reset_isolation_suitable(zone);
+
+	/*
 	 * Setup to move all movable pages to the end of the zone. Used cached
 	 * information on where the scanners should start but check that it
 	 * is initialised by ensuring the values are within zone boundaries.
@@ -952,14 +979,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
 	}
 
-	/*
-	 * Clear pageblock skip if there were failures recently and compaction
-	 * is about to be retried after being deferred. kswapd does not do
-	 * this reset as it'll reset the cached information when going to sleep.
-	 */
-	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
-		__reset_isolation_suitable(zone);
-
 	migrate_prep_local();
 
 	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
@@ -993,7 +1012,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
-			if (err == -ENOMEM) {
+			/*
+			 * migrate_pages() may return -ENOMEM when scanners meet
+			 * and we want compact_finished() to detect it
+			 */
+			if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) {
 				ret = COMPACT_PARTIAL;
 				goto out;
 			}
diff --git a/mm/fremap.c b/mm/fremap.c
index 87da3590c61e..1fb6bfe39d8c 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -203,9 +203,10 @@ get_write_lock:
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
 
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -213,7 +214,7 @@ get_write_lock:
 				BUG_ON(addr != start);
 				err = 0;
 			}
-			goto out;
+			goto out_freed;
 		}
 		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
@@ -248,6 +249,7 @@ get_write_lock:
 out:
 	if (vma)
 		vm_flags = vma->vm_flags;
+out_freed:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 1b24bdcb3197..a55036a68487 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -244,8 +244,10 @@ int __frontswap_store(struct page *page)
 		  the (older) page from frontswap
 		 */
 		inc_frontswap_failed_stores();
-		if (dup)
+		if (dup) {
 			__frontswap_clear(sis, offset);
+			frontswap_ops->invalidate_page(type, offset);
+		}
 	}
 	if (frontswap_writethrough_enabled)
 		/* report failure so swap also writes to swap device */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b92d0ce428b1..d21c9ef0943c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,7 +1166,7 @@ alloc:
 
 	if (unlikely(!new_page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
 					address, pmd, orig_pmd, haddr);
 		} else {
@@ -1190,7 +1190,7 @@ alloc:
 		goto out;
 	}
 
-	if (is_huge_zero_pmd(orig_pmd))
+	if (!page)
 		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
 	else
 		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1215,7 +1215,7 @@ alloc:
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 			put_huge_zero_page();
 		} else {
@@ -1288,64 +1288,104 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	bool page_locked;
+	bool migrated = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
+
+		/*
+		 * Otherwise wait for potential migrations and retry. We do
+		 * relock and check_same as the page may no longer be mapped.
+		 * As the fault is being retried, do not account for it.
+		 */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked)
+		lock_page(page);
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
+	/*
+	 * The page_table_lock above provides a memory barrier
+	 * with change_protection_range.
+	 */
+	if (mm_tlb_flush_pending(mm))
+		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
+	if (migrated)
+		page_nid = target_nid;
 
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
-
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
 	return 0;
 }
 
@@ -1693,21 +1733,24 @@ static int __split_huge_page_map(struct page *page,
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm);
 		pmd_populate(mm, &_pmd, pgtable);
+		if (pmd_write(*pmd))
+			BUG_ON(page_mapcount(page) != 1);
 
 		haddr = address;
 		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
+			/*
+			 * Note that pmd_numa is not transferred deliberately
+			 * to avoid any possibility that pte_numa leaks to
+			 * a PROT_NONE VMA by accident.
+			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 			if (!pmd_write(*pmd))
 				entry = pte_wrprotect(entry);
-			else
-				BUG_ON(page_mapcount(page) != 1);
 			if (!pmd_young(*pmd))
 				entry = pte_mkold(entry);
-			if (pmd_numa(*pmd))
-				entry = pte_mknuma(entry);
 			pte = pte_offset_map(&_pmd, haddr);
 			BUG_ON(!pte_none(*pte));
 			set_pte_at(mm, haddr, pte, entry);
@@ -2699,6 +2742,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 
 	mmun_start = haddr;
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
+again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2721,7 +2765,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 	split_huge_page(page);
 
 	put_page(page);
-	BUG_ON(pmd_trans_huge(*pmd));
+
+	/*
+	 * We don't always have down_write of mmap_sem here: a racing
+	 * do_huge_pmd_wp_page() might have copied-on-write to another
+	 * huge page before our split_huge_page() got the anon_vma lock.
+	 */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		goto again;
 }
 
 void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index de608bbc8389..ea32a04296f0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -21,6 +21,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/page-isolation.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -434,25 +435,6 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
-/* Decrement the reserved pages in the hugepage pool by one */
-static void decrement_hugepage_resv_vma(struct hstate *h,
-			struct vm_area_struct *vma)
-{
-	if (vma->vm_flags & VM_NORESERVE)
-		return;
-
-	if (vma->vm_flags & VM_MAYSHARE) {
-		/* Shared mappings always use reserves */
-		h->resv_huge_pages--;
-	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
-		/*
-		 * Only the process that called mmap() has reserves for
-		 * private mappings.
-		 */
-		h->resv_huge_pages--;
-	}
-}
-
 /* Reset counters to 0 and clear all HPAGE_RESV_* flags */
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
@@ -462,12 +444,35 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 }
 
 /* Returns true if the VMA has associated reserve pages */
-static int vma_has_reserves(struct vm_area_struct *vma)
+static int vma_has_reserves(struct vm_area_struct *vma, long chg)
 {
+	if (vma->vm_flags & VM_NORESERVE) {
+		/*
+		 * This address is already reserved by other process(chg == 0),
+		 * so, we should decrement reserved count. Without decrementing,
+		 * reserve count remains after releasing inode, because this
+		 * allocated page will go into page cache and is regarded as
+		 * coming from reserved pool in releasing step.  Currently, we
+		 * don't have any other solution to deal with this situation
+		 * properly, so add work-around here.
+		 */
+		if (vma->vm_flags & VM_MAYSHARE && chg == 0)
+			return 1;
+		else
+			return 0;
+	}
+
+	/* Shared mappings always use reserves */
 	if (vma->vm_flags & VM_MAYSHARE)
 		return 1;
+
+	/*
+	 * Only the process that called mmap() has reserves for
+	 * private mappings.
+	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		return 1;
+
 	return 0;
 }
 
@@ -517,9 +522,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
 
-	if (list_empty(&h->hugepage_freelists[nid]))
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+		if (!is_migrate_isolate_page(page))
+			break;
+	/*
+	 * if 'non-isolated free hugepage' not found on the list,
+	 * the allocation fails.
+	 */
+	if (&h->hugepage_freelists[nid] == &page->lru)
 		return NULL;
-	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
 	h->free_huge_pages--;
@@ -529,7 +540,8 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
-				unsigned long address, int avoid_reserve)
+				unsigned long address, int avoid_reserve,
+				long chg)
 {
 	struct page *page = NULL;
 	struct mempolicy *mpol;
@@ -548,7 +560,7 @@ retry_cpuset:
 	 * have no page reserves. This check ensures that reservations are
 	 * not "stolen". The child may still get SIGKILLed
 	 */
-	if (!vma_has_reserves(vma) &&
+	if (!vma_has_reserves(vma, chg) &&
 			h->free_huge_pages - h->resv_huge_pages == 0)
 		goto err;
 
@@ -561,8 +573,13 @@ retry_cpuset:
 		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
 			page = dequeue_huge_page_node(h, zone_to_nid(zone));
 			if (page) {
-				if (!avoid_reserve)
-					decrement_hugepage_resv_vma(h, vma);
+				if (avoid_reserve)
+					break;
+				if (!vma_has_reserves(vma, chg))
+					break;
+
+				SetPagePrivate(page);
+				h->resv_huge_pages--;
 				break;
 			}
 		}
@@ -620,15 +637,20 @@ static void free_huge_page(struct page *page)
 	int nid = page_to_nid(page);
 	struct hugepage_subpool *spool =
 		(struct hugepage_subpool *)page_private(page);
+	bool restore_reserve;
 
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
+	restore_reserve = PagePrivate(page);
 
 	spin_lock(&hugetlb_lock);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
 				     pages_per_huge_page(h), page);
+	if (restore_reserve)
+		h->resv_huge_pages++;
+
 	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
 		/* remove the page from active list */
 		list_del(&page->lru);
@@ -690,6 +712,23 @@ int PageHuge(struct page *page)
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageHead(page_head))
+		return 0;
+
+	dtor = get_compound_page_dtor(page_head);
+
+	return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
 pgoff_t __basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
@@ -772,33 +811,6 @@ static int hstate_next_node_to_alloc(struct hstate *h,
 	return nid;
 }
 
-static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
-{
-	struct page *page;
-	int start_nid;
-	int next_nid;
-	int ret = 0;
-
-	start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
-	next_nid = start_nid;
-
-	do {
-		page = alloc_fresh_huge_page_node(h, next_nid);
-		if (page) {
-			ret = 1;
-			break;
-		}
-		next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
-	} while (next_nid != start_nid);
-
-	if (ret)
-		count_vm_event(HTLB_BUDDY_PGALLOC);
-	else
-		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
-
-	return ret;
-}
-
 /*
  * helper for free_pool_huge_page() - return the previously saved
  * node ["this node"] from which to free a huge page.  Advance the
@@ -817,6 +829,40 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 	return nid;
 }
 
+#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask)		\
+	for (nr_nodes = nodes_weight(*mask);				\
+		nr_nodes > 0 &&						\
+		((node = hstate_next_node_to_alloc(hs, mask)) || 1);	\
+		nr_nodes--)
+
+#define for_each_node_mask_to_free(hs, nr_nodes, node, mask)		\
+	for (nr_nodes = nodes_weight(*mask);				\
+		nr_nodes > 0 &&						\
+		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
+		nr_nodes--)
+
+static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
+{
+	struct page *page;
+	int nr_nodes, node;
+	int ret = 0;
+
+	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+		page = alloc_fresh_huge_page_node(h, node);
+		if (page) {
+			ret = 1;
+			break;
+		}
+	}
+
+	if (ret)
+		count_vm_event(HTLB_BUDDY_PGALLOC);
+	else
+		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
+	return ret;
+}
+
 /*
  * Free huge page from pool from next node to free.
  * Attempt to keep persistent huge pages more or less
@@ -826,36 +872,31 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 							 bool acct_surplus)
 {
-	int start_nid;
-	int next_nid;
+	int nr_nodes, node;
 	int ret = 0;
 
-	start_nid = hstate_next_node_to_free(h, nodes_allowed);
-	next_nid = start_nid;
-
-	do {
+	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
 		/*
 		 * If we're returning unused surplus pages, only examine
 		 * nodes with surplus pages.
 		 */
-		if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) &&
-		    !list_empty(&h->hugepage_freelists[next_nid])) {
+		if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
+		    !list_empty(&h->hugepage_freelists[node])) {
 			struct page *page =
-				list_entry(h->hugepage_freelists[next_nid].next,
+				list_entry(h->hugepage_freelists[node].next,
 					  struct page, lru);
 			list_del(&page->lru);
 			h->free_huge_pages--;
-			h->free_huge_pages_node[next_nid]--;
+			h->free_huge_pages_node[node]--;
 			if (acct_surplus) {
 				h->surplus_huge_pages--;
-				h->surplus_huge_pages_node[next_nid]--;
+				h->surplus_huge_pages_node[node]--;
 			}
 			update_and_free_page(h, page);
 			ret = 1;
 			break;
 		}
-		next_nid = hstate_next_node_to_free(h, nodes_allowed);
-	} while (next_nid != start_nid);
+	}
 
 	return ret;
 }
@@ -944,10 +985,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
  */
 struct page *alloc_huge_page_node(struct hstate *h, int nid)
 {
-	struct page *page;
+	struct page *page = NULL;
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page_node(h, nid);
+	if (h->free_huge_pages - h->resv_huge_pages > 0)
+		page = dequeue_huge_page_node(h, nid);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
@@ -1035,11 +1077,8 @@ free:
 	spin_unlock(&hugetlb_lock);
 
 	/* Free unnecessary surplus pages to the buddy allocator */
-	if (!list_empty(&surplus_list)) {
-		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
-			put_page(page);
-		}
-	}
+	list_for_each_entry_safe(page, tmp, &surplus_list, lru)
+		put_page(page);
 	spin_lock(&hugetlb_lock);
 
 	return ret;
@@ -1076,6 +1115,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	while (nr_pages--) {
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 }
 
@@ -1106,9 +1146,9 @@ static long vma_needs_reservation(struct hstate *h,
 	} else  {
 		long err;
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		struct resv_map *reservations = vma_resv_map(vma);
+		struct resv_map *resv = vma_resv_map(vma);
 
-		err = region_chg(&reservations->regions, idx, idx + 1);
+		err = region_chg(&resv->regions, idx, idx + 1);
 		if (err < 0)
 			return err;
 		return 0;
@@ -1126,10 +1166,10 @@ static void vma_commit_reservation(struct hstate *h,
 
 	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		struct resv_map *reservations = vma_resv_map(vma);
+		struct resv_map *resv = vma_resv_map(vma);
 
 		/* Mark this page used in the map. */
-		region_add(&reservations->regions, idx, idx + 1);
+		region_add(&resv->regions, idx, idx + 1);
 	}
 }
 
@@ -1155,38 +1195,35 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
 		return ERR_PTR(-ENOMEM);
-	if (chg)
-		if (hugepage_subpool_get_pages(spool, chg))
+	if (chg || avoid_reserve)
+		if (hugepage_subpool_get_pages(spool, 1))
 			return ERR_PTR(-ENOSPC);
 
 	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
 	if (ret) {
-		hugepage_subpool_put_pages(spool, chg);
+		if (chg || avoid_reserve)
+			hugepage_subpool_put_pages(spool, 1);
 		return ERR_PTR(-ENOSPC);
 	}
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
-	if (page) {
-		/* update page cgroup details */
-		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
-					     h_cg, page);
-		spin_unlock(&hugetlb_lock);
-	} else {
+	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
+	if (!page) {
 		spin_unlock(&hugetlb_lock);
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
 			hugetlb_cgroup_uncharge_cgroup(idx,
 						       pages_per_huge_page(h),
 						       h_cg);
-			hugepage_subpool_put_pages(spool, chg);
+			if (chg || avoid_reserve)
+				hugepage_subpool_put_pages(spool, 1);
 			return ERR_PTR(-ENOSPC);
 		}
 		spin_lock(&hugetlb_lock);
-		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
-					     h_cg, page);
 		list_move(&page->lru, &h->hugepage_activelist);
-		spin_unlock(&hugetlb_lock);
+		/* Fall through */
 	}
+	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
+	spin_unlock(&hugetlb_lock);
 
 	set_page_private(page, (unsigned long)spool);
 
@@ -1197,14 +1234,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 int __weak alloc_bootmem_huge_page(struct hstate *h)
 {
 	struct huge_bootmem_page *m;
-	int nr_nodes = nodes_weight(node_states[N_MEMORY]);
+	int nr_nodes, node;
 
-	while (nr_nodes) {
+	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
 		void *addr;
 
-		addr = __alloc_bootmem_node_nopanic(
-				NODE_DATA(hstate_next_node_to_alloc(h,
-						&node_states[N_MEMORY])),
+		addr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
 				huge_page_size(h), huge_page_size(h), 0);
 
 		if (addr) {
@@ -1216,7 +1251,6 @@ int __weak alloc_bootmem_huge_page(struct hstate *h)
 			m = addr;
 			goto found;
 		}
-		nr_nodes--;
 	}
 	return 0;
 
@@ -1355,48 +1389,28 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count,
 static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
 				int delta)
 {
-	int start_nid, next_nid;
-	int ret = 0;
+	int nr_nodes, node;
 
 	VM_BUG_ON(delta != -1 && delta != 1);
 
-	if (delta < 0)
-		start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
-	else
-		start_nid = hstate_next_node_to_free(h, nodes_allowed);
-	next_nid = start_nid;
-
-	do {
-		int nid = next_nid;
-		if (delta < 0)  {
-			/*
-			 * To shrink on this node, there must be a surplus page
-			 */
-			if (!h->surplus_huge_pages_node[nid]) {
-				next_nid = hstate_next_node_to_alloc(h,
-								nodes_allowed);
-				continue;
-			}
+	if (delta < 0) {
+		for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+			if (h->surplus_huge_pages_node[node])
+				goto found;
 		}
-		if (delta > 0) {
-			/*
-			 * Surplus cannot exceed the total number of pages
-			 */
-			if (h->surplus_huge_pages_node[nid] >=
-						h->nr_huge_pages_node[nid]) {
-				next_nid = hstate_next_node_to_free(h,
-								nodes_allowed);
-				continue;
-			}
+	} else {
+		for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+			if (h->surplus_huge_pages_node[node] <
+					h->nr_huge_pages_node[node])
+				goto found;
 		}
+	}
+	return 0;
 
-		h->surplus_huge_pages += delta;
-		h->surplus_huge_pages_node[nid] += delta;
-		ret = 1;
-		break;
-	} while (next_nid != start_nid);
-
-	return ret;
+found:
+	h->surplus_huge_pages += delta;
+	h->surplus_huge_pages_node[node] += delta;
+	return 1;
 }
 
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
@@ -1463,6 +1477,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	while (min_count < persistent_huge_pages(h)) {
 		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))
@@ -2207,7 +2222,7 @@ out:
 
 static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 {
-	struct resv_map *reservations = vma_resv_map(vma);
+	struct resv_map *resv = vma_resv_map(vma);
 
 	/*
 	 * This new VMA should share its siblings reservation map if present.
@@ -2217,34 +2232,34 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 	 * after this open call completes.  It is therefore safe to take a
 	 * new reference here without additional locking.
 	 */
-	if (reservations)
-		kref_get(&reservations->refs);
+	if (resv)
+		kref_get(&resv->refs);
 }
 
 static void resv_map_put(struct vm_area_struct *vma)
 {
-	struct resv_map *reservations = vma_resv_map(vma);
+	struct resv_map *resv = vma_resv_map(vma);
 
-	if (!reservations)
+	if (!resv)
 		return;
-	kref_put(&reservations->refs, resv_map_release);
+	kref_put(&resv->refs, resv_map_release);
 }
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
-	struct resv_map *reservations = vma_resv_map(vma);
+	struct resv_map *resv = vma_resv_map(vma);
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	unsigned long reserve;
 	unsigned long start;
 	unsigned long end;
 
-	if (reservations) {
+	if (resv) {
 		start = vma_hugecache_offset(h, vma, vma->vm_start);
 		end = vma_hugecache_offset(h, vma, vma->vm_end);
 
 		reserve = (end - start) -
-			region_count(&reservations->regions, start, end);
+			region_count(&resv->regions, start, end);
 
 		resv_map_put(vma);
 
@@ -2302,6 +2317,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 		update_mmu_cache(vma, address, ptep);
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_migration_entry(swp))
+		return 1;
+	else
+		return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
+		return 1;
+	else
+		return 0;
+}
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
@@ -2339,7 +2379,24 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 
 		spin_lock(&dst->page_table_lock);
 		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
-		if (!huge_pte_none(huge_ptep_get(src_pte))) {
+		entry = huge_ptep_get(src_pte);
+		if (huge_pte_none(entry)) { /* skip none entry */
+			;
+		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
+				    is_hugetlb_entry_hwpoisoned(entry))) {
+			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+			if (is_write_migration_entry(swp_entry) && cow) {
+				/*
+				 * COW mappings require pages in both
+				 * parent and child to be set to read.
+				 */
+				make_migration_entry_read(&swp_entry);
+				entry = swp_entry_to_pte(swp_entry);
+				set_huge_pte_at(src, addr, src_pte, entry);
+			}
+			set_huge_pte_at(dst, addr, dst_pte, entry);
+		} else {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			entry = huge_ptep_get(src_pte);
@@ -2358,32 +2415,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	return ret;
 }
 
-static int is_hugetlb_entry_migration(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
 void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			    unsigned long start, unsigned long end,
 			    struct page *ref_page)
@@ -2568,7 +2599,6 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
-	int avoidcopy;
 	int outside_reserve = 0;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
@@ -2578,10 +2608,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 retry_avoidcopy:
 	/* If no-one else is actually using this page, avoid the copy
 	 * and just make the page writable */
-	avoidcopy = (page_mapcount(old_page) == 1);
-	if (avoidcopy) {
-		if (PageAnon(old_page))
-			page_move_anon_rmap(old_page, vma, address);
+	if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
+		page_move_anon_rmap(old_page, vma, address);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
@@ -2595,8 +2623,7 @@ retry_avoidcopy:
 	 * at the time of fork() could consume its reserves on COW instead
 	 * of the full address range.
 	 */
-	if (!(vma->vm_flags & VM_MAYSHARE) &&
-			is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
+	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
 			old_page != pagecache_page)
 		outside_reserve = 1;
 
@@ -2668,6 +2695,8 @@ retry_avoidcopy:
 	spin_lock(&mm->page_table_lock);
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
+		ClearPagePrivate(new_page);
+
 		/* Break COW */
 		huge_ptep_clear_flush(vma, address, ptep);
 		set_huge_pte_at(mm, address, ptep,
@@ -2679,10 +2708,11 @@ retry_avoidcopy:
 	}
 	spin_unlock(&mm->page_table_lock);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-	/* Caller expects lock to be held */
-	spin_lock(&mm->page_table_lock);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
+
+	/* Caller expects lock to be held */
+	spin_lock(&mm->page_table_lock);
 	return 0;
 }
 
@@ -2778,6 +2808,7 @@ retry:
 					goto retry;
 				goto out;
 			}
+			ClearPagePrivate(page);
 
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += blocks_per_huge_page(h);
@@ -2824,8 +2855,10 @@ retry:
 	if (!huge_pte_none(huge_ptep_get(ptep)))
 		goto backout;
 
-	if (anon_rmap)
+	if (anon_rmap) {
+		ClearPagePrivate(page);
 		hugepage_add_new_anon_rmap(page, vma, address);
+	}
 	else
 		page_dup_rmap(page);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
diff --git a/mm/ksm.c b/mm/ksm.c
index b6afe0c440d8..784d1e4bc385 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item)
 static struct page *page_trans_compound_anon(struct page *page)
 {
 	if (PageTransCompound(page)) {
-		struct page *head = compound_trans_head(page);
+		struct page *head = compound_head(page);
 		/*
 		 * head may actually be splitted and freed from under
 		 * us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 905ce72c8c4e..eaa3accb01e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -302,6 +302,7 @@ struct mem_cgroup {
 
 	bool		oom_lock;
 	atomic_t	under_oom;
+	atomic_t	oom_wakeups;
 
 	atomic_t	refcnt;
 
@@ -379,7 +380,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
@@ -1220,7 +1221,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 			if (dead_count == iter->last_dead_count) {
 				smp_rmb();
 				last_visited = iter->last_visited;
-				if (last_visited &&
+				if (last_visited && last_visited != root &&
 				    !css_tryget(&last_visited->css))
 					last_visited = NULL;
 			}
@@ -1229,7 +1230,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
-			if (last_visited)
+			if (last_visited && last_visited != root)
 				css_put(&last_visited->css);
 
 			iter->last_visited = memcg;
@@ -2075,15 +2076,18 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 	return total;
 }
 
+static DEFINE_SPINLOCK(memcg_oom_lock);
+
 /*
  * Check OOM-Killer is already running under our hierarchy.
  * If someone is running, return false.
- * Has to be called with memcg_oom_lock
  */
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *iter, *failed = NULL;
 
+	spin_lock(&memcg_oom_lock);
+
 	for_each_mem_cgroup_tree(iter, memcg) {
 		if (iter->oom_lock) {
 			/*
@@ -2097,33 +2101,33 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
 			iter->oom_lock = true;
 	}
 
-	if (!failed)
-		return true;
-
-	/*
-	 * OK, we failed to lock the whole subtree so we have to clean up
-	 * what we set up to the failing subtree
-	 */
-	for_each_mem_cgroup_tree(iter, memcg) {
-		if (iter == failed) {
-			mem_cgroup_iter_break(memcg, iter);
-			break;
+	if (failed) {
+		/*
+		 * OK, we failed to lock the whole subtree so we have
+		 * to clean up what we set up to the failing subtree
+		 */
+		for_each_mem_cgroup_tree(iter, memcg) {
+			if (iter == failed) {
+				mem_cgroup_iter_break(memcg, iter);
+				break;
+			}
+			iter->oom_lock = false;
 		}
-		iter->oom_lock = false;
 	}
-	return false;
+
+	spin_unlock(&memcg_oom_lock);
+
+	return !failed;
 }
 
-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *iter;
 
+	spin_lock(&memcg_oom_lock);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
-	return 0;
+	spin_unlock(&memcg_oom_lock);
 }
 
 static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
@@ -2147,7 +2151,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
 		atomic_add_unless(&iter->under_oom, -1, 0);
 }
 
-static DEFINE_SPINLOCK(memcg_oom_lock);
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
 
 struct oom_wait_info {
@@ -2177,6 +2180,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait,
 
 static void memcg_wakeup_oom(struct mem_cgroup *memcg)
 {
+	atomic_inc(&memcg->oom_wakeups);
 	/* for filtering, pass "memcg" as argument. */
 	__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
 }
@@ -2187,57 +2191,97 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		memcg_wakeup_oom(memcg);
 }
 
-/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+{
+	if (!current->memcg_oom.may_oom)
+		return;
+	/*
+	 * We are in the middle of the charge context here, so we
+	 * don't want to block when potentially sitting on a callstack
+	 * that holds all kinds of filesystem and mm locks.
+	 *
+	 * Also, the caller may handle a failed allocation gracefully
+	 * (like optional page cache readahead) and so an OOM killer
+	 * invocation might not even be necessary.
+	 *
+	 * That's why we don't do anything here except remember the
+	 * OOM context and then deal with it at the end of the page
+	 * fault when the stack is unwound, the locks are released,
+	 * and when we know whether the fault was overall successful.
+	 */
+	css_get(&memcg->css);
+	current->memcg_oom.memcg = memcg;
+	current->memcg_oom.gfp_mask = mask;
+	current->memcg_oom.order = order;
+}
+
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ * @handle: actually kill/wait or just clean up the OOM state
+ *
+ * This has to be called at the end of a page fault if the memcg OOM
+ * handler was enabled.
+ *
+ * Memcg supports userspace OOM handling where failed allocations must
+ * sleep on a waitqueue until the userspace task resolves the
+ * situation.  Sleeping directly in the charge context with all kinds
+ * of locks held is not a good idea, instead we remember an OOM state
+ * in the task and mem_cgroup_oom_synchronize() has to be called at
+ * the end of the page fault to complete the OOM handling.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * completed, %false otherwise.
  */
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
-				  int order)
+bool mem_cgroup_oom_synchronize(bool handle)
 {
+	struct mem_cgroup *memcg = current->memcg_oom.memcg;
 	struct oom_wait_info owait;
-	bool locked, need_to_kill;
+	bool locked;
+
+	/* OOM is global, do not handle */
+	if (!memcg)
+		return false;
+
+	if (!handle)
+		goto cleanup;
 
 	owait.memcg = memcg;
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
 	INIT_LIST_HEAD(&owait.wait.task_list);
-	need_to_kill = true;
-	mem_cgroup_mark_under_oom(memcg);
 
-	/* At first, try to OOM lock hierarchy under memcg.*/
-	spin_lock(&memcg_oom_lock);
-	locked = mem_cgroup_oom_lock(memcg);
-	/*
-	 * Even if signal_pending(), we can't quit charge() loop without
-	 * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
-	 * under OOM is always welcomed, use TASK_KILLABLE here.
-	 */
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
-	if (!locked || memcg->oom_kill_disable)
-		need_to_kill = false;
+	mem_cgroup_mark_under_oom(memcg);
+
+	locked = mem_cgroup_oom_trylock(memcg);
+
 	if (locked)
 		mem_cgroup_oom_notify(memcg);
-	spin_unlock(&memcg_oom_lock);
 
-	if (need_to_kill) {
+	if (locked && !memcg->oom_kill_disable) {
+		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
-		mem_cgroup_out_of_memory(memcg, mask, order);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+					 current->memcg_oom.order);
 	} else {
 		schedule();
+		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
 	}
-	spin_lock(&memcg_oom_lock);
-	if (locked)
-		mem_cgroup_oom_unlock(memcg);
-	memcg_wakeup_oom(memcg);
-	spin_unlock(&memcg_oom_lock);
-
-	mem_cgroup_unmark_under_oom(memcg);
 
-	if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
-		return false;
-	/* Give chance to dying process */
-	schedule_timeout_uninterruptible(1);
+	if (locked) {
+		mem_cgroup_oom_unlock(memcg);
+		/*
+		 * There is no guarantee that an OOM-lock contender
+		 * sees the wakeups triggered by the OOM kill
+		 * uncharges.  Wake any sleepers explicitely.
+		 */
+		memcg_oom_recover(memcg);
+	}
+cleanup:
+	current->memcg_oom.memcg = NULL;
+	css_put(&memcg->css);
 	return true;
 }
 
@@ -2550,12 +2594,11 @@ enum {
 	CHARGE_RETRY,		/* need to retry but retry is not bad */
 	CHARGE_NOMEM,		/* we can't do more. return -ENOMEM */
 	CHARGE_WOULDBLOCK,	/* GFP_WAIT wasn't set and no enough res. */
-	CHARGE_OOM_DIE,		/* the current is killed because of OOM */
 };
 
 static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				unsigned int nr_pages, unsigned int min_pages,
-				bool oom_check)
+				bool invoke_oom)
 {
 	unsigned long csize = nr_pages * PAGE_SIZE;
 	struct mem_cgroup *mem_over_limit;
@@ -2612,14 +2655,10 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	if (mem_cgroup_wait_acct_move(mem_over_limit))
 		return CHARGE_RETRY;
 
-	/* If we don't need to call oom-killer at el, return immediately */
-	if (!oom_check)
-		return CHARGE_NOMEM;
-	/* check OOM */
-	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
-		return CHARGE_OOM_DIE;
+	if (invoke_oom)
+		mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
 
-	return CHARGE_RETRY;
+	return CHARGE_NOMEM;
 }
 
 /*
@@ -2663,6 +2702,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		     || fatal_signal_pending(current)))
 		goto bypass;
 
+	if (unlikely(task_in_memcg_oom(current)))
+		goto bypass;
+
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
@@ -2722,7 +2764,7 @@ again:
 	}
 
 	do {
-		bool oom_check;
+		bool invoke_oom = oom && !nr_oom_retries;
 
 		/* If killed, bypass charge */
 		if (fatal_signal_pending(current)) {
@@ -2730,14 +2772,8 @@ again:
 			goto bypass;
 		}
 
-		oom_check = false;
-		if (oom && !nr_oom_retries) {
-			oom_check = true;
-			nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
-		}
-
-		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
-		    oom_check);
+		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+					   nr_pages, invoke_oom);
 		switch (ret) {
 		case CHARGE_OK:
 			break;
@@ -2750,16 +2786,12 @@ again:
 			css_put(&memcg->css);
 			goto nomem;
 		case CHARGE_NOMEM: /* OOM routine works */
-			if (!oom) {
+			if (!oom || invoke_oom) {
 				css_put(&memcg->css);
 				goto nomem;
 			}
-			/* If oom, we never return -ENOMEM */
 			nr_oom_retries--;
 			break;
-		case CHARGE_OOM_DIE: /* Killed by OOM Killer */
-			css_put(&memcg->css);
-			goto bypass;
 		}
 	} while (ret != CHARGE_OK);
 
@@ -6326,9 +6358,23 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
 static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct cgroup *iter;
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	rcu_read_lock();
+	cgroup_for_each_descendant_post(iter, cont) {
+		rcu_read_unlock();
+		mem_cgroup_reparent_charges(mem_cgroup_from_cont(iter));
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
 	mem_cgroup_reparent_charges(memcg);
+
 	mem_cgroup_destroy_all_caches(memcg);
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ceb0c7f1932f..603f1fa1b7a3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #endif
 	si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
 
-	if ((flags & MF_ACTION_REQUIRED) && t == current) {
+	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
 		si.si_code = BUS_MCEERR_AR;
-		ret = force_sig_info(SIGBUS, &si, t);
+		ret = force_sig_info(SIGBUS, &si, current);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
@@ -382,10 +382,12 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk)
+static int task_early_kill(struct task_struct *tsk, int force_early)
 {
 	if (!tsk->mm)
 		return 0;
+	if (force_early)
+		return 1;
 	if (tsk->flags & PF_MCE_PROCESS)
 		return !!(tsk->flags & PF_MCE_EARLY);
 	return sysctl_memory_failure_early_kill;
@@ -395,7 +397,7 @@ static int task_early_kill(struct task_struct *tsk)
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -411,7 +413,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
@@ -430,7 +432,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -441,7 +443,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
@@ -467,7 +469,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;
 
@@ -478,9 +481,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }
 
@@ -854,14 +857,14 @@ static int page_action(struct page_state *ps, struct page *p,
  * the pages and send SIGBUS to the processes if the data was dirty.
  */
 static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
-				  int trapno, int flags)
+				  int trapno, int flags, struct page **hpagep)
 {
 	enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
 	int kill = 1, forcekill;
-	struct page *hpage = compound_head(p);
+	struct page *hpage = *hpagep;
 	struct page *ppage;
 
 	if (PageReserved(p) || PageSlab(p))
@@ -936,6 +939,21 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/*
+			 * We pinned the head page for hwpoison handling,
+			 * now we split the thp and we are interested in
+			 * the hwpoisoned raw page, so move the refcount
+			 * to it. Similarly, page lock is shifted.
+			 */
+			if (hpage != p) {
+				if (!(flags & MF_COUNT_INCREASED)) {
+					put_page(hpage);
+					get_page(p);
+				}
+				lock_page(p);
+				unlock_page(hpage);
+				*hpagep = p;
+			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
 		}
@@ -950,19 +968,13 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
-
-	if (hpage != ppage)
-		lock_page(ppage);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
 				pfn, page_mapcount(ppage));
 
-	if (hpage != ppage)
-		unlock_page(ppage);
-
 	/*
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
@@ -1074,15 +1086,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
-			 * Check "just unpoisoned", "filter hit", and
-			 * "race with other subpage."
+			 * Check "filter hit" and "race with other subpage."
 			 */
 			lock_page(hpage);
-			if (!PageHWPoison(hpage)
-			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-				return 0;
+			if (PageHWPoison(hpage)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != hpage && TestSetPageHWPoison(hpage))) {
+					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					unlock_page(hpage);
+					return 0;
+				}
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1143,6 +1156,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		put_page(hpage);
 		res = 0;
 		goto out;
 	}
@@ -1179,8 +1194,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * Now take care of user space mappings.
 	 * Abort on fail: __delete_from_page_cache() assumes unmapped page.
+	 *
+	 * When the raw error page is thp tail page, hpage points to the raw
+	 * page after thp split.
 	 */
-	if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
+	if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
+	    != SWAP_SUCCESS) {
 		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
 		res = -EBUSY;
 		goto out;
@@ -1410,7 +1429,8 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 
 	/*
 	 * Isolate the page, so that it doesn't get reallocated if it
-	 * was free.
+	 * was free. This flag should be kept set until the source page
+	 * is freed and PG_hwpoison on it is set.
 	 */
 	set_migratetype_isolate(p, true);
 	/*
@@ -1433,7 +1453,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		/* Not a free page */
 		ret = 1;
 	}
-	unset_migratetype_isolate(p, MIGRATE_MOVABLE);
 	unlock_memory_hotplug();
 	return ret;
 }
@@ -1489,12 +1508,17 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
 	} else {
-		set_page_hwpoison_huge_page(hpage);
-		dequeue_hwpoisoned_huge_page(hpage);
-		atomic_long_add(1 << compound_trans_order(hpage),
-				&num_poisoned_pages);
+		/* overcommit hugetlb page will be freed to buddy */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
-	/* keep elevated page count for bad page */
 	return ret;
 }
 
@@ -1526,7 +1550,7 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_trans_head(page);
+	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
@@ -1559,7 +1583,7 @@ int soft_offline_page(struct page *page, int flags)
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	}
-	/* keep elevated page count for bad page */
+	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
 	return ret;
 }
 
@@ -1625,7 +1649,22 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (ret > 0)
 				ret = -EIO;
 		} else {
+			/*
+			 * After page migration succeeds, the source page can
+			 * be trapped in pagevec and actual freeing is delayed.
+			 * Freeing code works differently based on PG_hwpoison,
+			 * so there's a race. We need to make sure that the
+			 * source page should be freed back to buddy before
+			 * setting PG_hwpoison.
+			 */
+			if (!is_free_buddy_page(page))
+				lru_add_drain_all();
+			if (!is_free_buddy_page(page))
+				drain_all_pages();
 			SetPageHWPoison(page);
+			if (!is_free_buddy_page(page))
+				pr_info("soft offline: %#lx: page leaked\n",
+					pfn);
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index 20bb9e901781..1df7bd48cdae 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -836,20 +836,20 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		if (!pte_file(pte)) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (swap_duplicate(entry) < 0)
-				return entry.val;
-
-			/* make sure dst_mm is on swapoff's mmlist. */
-			if (unlikely(list_empty(&dst_mm->mmlist))) {
-				spin_lock(&mmlist_lock);
-				if (list_empty(&dst_mm->mmlist))
-					list_add(&dst_mm->mmlist,
-						 &src_mm->mmlist);
-				spin_unlock(&mmlist_lock);
-			}
-			if (likely(!non_swap_entry(entry)))
+			if (likely(!non_swap_entry(entry))) {
+				if (swap_duplicate(entry) < 0)
+					return entry.val;
+
+				/* make sure dst_mm is on swapoff's mmlist. */
+				if (unlikely(list_empty(&dst_mm->mmlist))) {
+					spin_lock(&mmlist_lock);
+					if (list_empty(&dst_mm->mmlist))
+						list_add(&dst_mm->mmlist,
+							 &src_mm->mmlist);
+					spin_unlock(&mmlist_lock);
+				}
 				rss[MM_SWAPENTS]++;
-			else if (is_migration_entry(entry)) {
+			} else if (is_migration_entry(entry)) {
 				page = migration_entry_to_page(entry);
 
 				if (PageAnon(page))
@@ -1939,12 +1939,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags)
 {
 	struct vm_area_struct *vma;
+	vm_flags_t vm_flags;
 	int ret;
 
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		return -EFAULT;
 
+	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+	if (!(vm_flags & vma->vm_flags))
+		return -EFAULT;
+
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)
@@ -3197,7 +3202,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (prev && prev->vm_end == address)
 			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-		expand_downwards(vma, address - PAGE_SIZE);
+		return expand_downwards(vma, address - PAGE_SIZE);
 	}
 	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
 		struct vm_area_struct *next = vma->vm_next;
@@ -3206,7 +3211,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (next && next->vm_start == address + PAGE_SIZE)
 			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
 
-		expand_upwards(vma, address + PAGE_SIZE);
+		return expand_upwards(vma, address + PAGE_SIZE);
 	}
 	return 0;
 }
@@ -3527,12 +3532,12 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	return mpol_misplaced(page, vma, addr);
@@ -3543,7 +3548,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
 	int target_nid;
 	bool migrated = false;
 
@@ -3573,15 +3578,10 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
@@ -3589,11 +3589,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, target_nid);
 	if (migrated)
-		current_nid = target_nid;
+		page_nid = target_nid;
 
 out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
+	if (page_nid != -1)
+		task_numa_fault(page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3608,7 +3608,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int local_nid = numa_node_id();
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3631,9 +3630,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
-		int curr_nid = local_nid;
+		int page_nid = -1;
 		int target_nid;
-		bool migrated;
+		bool migrated = false;
+
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3655,25 +3655,19 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
+		page_nid = page_to_nid(page);
+		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+		pte_unmap_unlock(pte, ptl);
+		if (target_nid != -1) {
+			migrated = migrate_misplaced_page(page, target_nid);
+			if (migrated)
+				page_nid = target_nid;
+		} else {
 			put_page(page);
-			continue;
 		}
 
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
+		if (page_nid != -1)
+			task_numa_fault(page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
@@ -3762,22 +3756,14 @@ unlock:
 /*
  * By the time we get here, we already hold the mm semaphore
  */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+			     unsigned long address, unsigned int flags)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
-	__set_current_state(TASK_RUNNING);
-
-	count_vm_event(PGFAULT);
-	mem_cgroup_count_vm_event(mm, PGFAULT);
-
-	/* do counter updates before entering really critical section. */
-	check_sync_rss_stat(current);
-
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
@@ -3858,6 +3844,43 @@ retry:
 	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
 
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		    unsigned long address, unsigned int flags)
+{
+	int ret;
+
+	__set_current_state(TASK_RUNNING);
+
+	count_vm_event(PGFAULT);
+	mem_cgroup_count_vm_event(mm, PGFAULT);
+
+	/* do counter updates before entering really critical section. */
+	check_sync_rss_stat(current);
+
+	/*
+	 * Enable the memcg OOM handling for faults triggered in user
+	 * space.  Kernel faults are handled more gracefully.
+	 */
+	if (flags & FAULT_FLAG_USER)
+		mem_cgroup_oom_enable();
+
+	ret = __handle_mm_fault(mm, vma, address, flags);
+
+	if (flags & FAULT_FLAG_USER) {
+		mem_cgroup_oom_disable();
+                /*
+                 * The task may have entered a memcg OOM situation but
+                 * if the allocation error was handled gracefully (no
+                 * VM_FAULT_OOM), there is no need to kill anything.
+                 * Just clean up the OOM state peacefully.
+                 */
+                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+                        mem_cgroup_oom_synchronize(false);
+	}
+
+	return ret;
+}
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.
@@ -4076,6 +4099,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(generic_access_phys);
 #endif
 
 /*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4baf12e534d1..b2061bb5af73 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -608,19 +608,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  * If pagelist != NULL then isolate pages from the LRU and
  * put them on the pagelist.
  */
-static struct vm_area_struct *
+static int
 check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		const nodemask_t *nodes, unsigned long flags, void *private)
 {
-	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
+	int err = 0;
+	struct vm_area_struct *vma, *prev;
 
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
+	vma = find_vma(mm, start);
+	if (!vma)
+		return -EFAULT;
 	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
 		unsigned long endvma = vma->vm_end;
 
 		if (endvma > end)
@@ -630,9 +629,9 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 		}
 
 		if (is_vm_hugetlb_page(vma))
@@ -649,15 +648,13 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 			err = check_pgd_range(vma, start, endvma, nodes,
 						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
+			if (err)
 				break;
-			}
 		}
 next:
 		prev = vma;
 	}
-	return first;
+	return err;
 }
 
 /*
@@ -1138,16 +1135,17 @@ out:
 
 /*
  * Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
  * Search forward from there, if not.  N.B., this assumes that the
  * list of pages handed to migrate_pages()--which is how we get here--
  * is in virtual address order.
  */
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
-	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
 
+	vma = find_vma(current->mm, start);
 	while (vma) {
 		address = page_address_in_vma(page, vma);
 		if (address != -EFAULT)
@@ -1173,7 +1171,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
 	return NULL;
 }
@@ -1183,7 +1181,6 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     unsigned short mode, unsigned short mode_flags,
 		     nodemask_t *nmask, unsigned long flags)
 {
-	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	struct mempolicy *new;
 	unsigned long end;
@@ -1249,11 +1246,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (err)
 		goto mpol_out;
 
-	vma = check_range(mm, start, end, nmask,
+	err = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
-
-	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma))
+	if (!err)
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -1261,9 +1256,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_vma_page,
-					(unsigned long)vma,
-					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+			nr_failed = migrate_pages(&pagelist, new_page,
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
@@ -2092,7 +2086,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	} else
 		*new = *old;
 
-	rcu_read_lock();
 	if (current_cpuset_is_being_rebound()) {
 		nodemask_t mems = cpuset_mems_allowed(current);
 		if (new->flags & MPOL_F_REBINDING)
@@ -2100,7 +2093,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		else
 			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
 	}
-	rcu_read_unlock();
 	atomic_set(&new->refcnt, 1);
 	return new;
 }
@@ -2801,7 +2793,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	 */
 	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
 
-	if (!pol || pol == &default_policy)
+	if (!pol || pol == &default_policy || (pol->flags & MPOL_F_MORON))
 		mode = MPOL_DEFAULT;
 	else
 		mode = pol->mode;
diff --git a/mm/migrate.c b/mm/migrate.c
index 6f0c24438bba..a88c12f2235d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -103,7 +103,7 @@ void putback_movable_pages(struct list_head *l)
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (unlikely(balloon_page_movable(page)))
+		if (unlikely(isolated_balloon_page(page)))
 			balloon_page_putback(page);
 		else
 			putback_lru_page(page);
@@ -1710,12 +1710,13 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
 
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		goto out_unlock;
 	}
 
 	/*
@@ -1732,9 +1733,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1753,7 +1754,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1762,6 +1762,11 @@ out:
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
+out_unlock:
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mlock.c b/mm/mlock.c
index 79b7cf7d1bca..713e462c0776 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -76,6 +76,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -106,6 +107,7 @@ unsigned int munlock_vma_page(struct page *page)
 {
 	unsigned int page_mask = 0;
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 8d25fdc653be..43a7089c6a7c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1853,7 +1853,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
 
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1862,7 +1862,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
@@ -1901,7 +1901,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1911,14 +1911,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 				(!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
 	addr = vm_unmapped_area(&info);
@@ -2056,14 +2056,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start;
+	unsigned long new_start, actual_size;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	actual_size = size;
+	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+		actual_size -= PAGE_SIZE;
+	if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 94722a4d6b43..e9f65aaa3182 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -135,6 +135,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
+	unsigned long nr_huge_updates = 0;
 	bool all_same_node;
 
 	pmd = pmd_offset(pud, addr);
@@ -146,6 +147,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			else if (change_huge_pmd(vma, pmd, addr, newprot,
 						 prot_numa)) {
 				pages += HPAGE_PMD_NR;
+				nr_huge_updates++;
 				continue;
 			}
 			/* fall through */
@@ -165,6 +167,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
+
 	return pages;
 }
 
@@ -201,6 +206,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -212,6 +218,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
 
 	return pages;
 }
diff --git a/mm/mremap.c b/mm/mremap.c
index 463a25705ac6..2201d060c31b 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -175,10 +175,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 79e451a78c9e..4d87d7c4ed2e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -47,19 +47,21 @@ static DEFINE_SPINLOCK(zone_scan_lock);
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
  * @mask: nodemask passed to page allocator for mempolicy ooms
  *
  * Task eligibility is determined by whether or not a candidate task, @tsk,
  * shares the same mempolicy nodes as current if it is bound by such a policy
  * and whether or not it has the same set of allowed cpuset nodes.
  */
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
 					const nodemask_t *mask)
 {
-	struct task_struct *start = tsk;
+	struct task_struct *tsk;
+	bool ret = false;
 
-	do {
+	rcu_read_lock();
+	for_each_thread(start, tsk) {
 		if (mask) {
 			/*
 			 * If this is a mempolicy constrained oom, tsk's
@@ -67,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			 * mempolicy intersects current, otherwise it may be
 			 * needlessly killed.
 			 */
-			if (mempolicy_nodemask_intersects(tsk, mask))
-				return true;
+			ret = mempolicy_nodemask_intersects(tsk, mask);
 		} else {
 			/*
 			 * This is not a mempolicy constrained oom, so only
 			 * check the mems of tsk's cpuset.
 			 */
-			if (cpuset_mems_allowed_intersects(current, tsk))
-				return true;
+			ret = cpuset_mems_allowed_intersects(current, tsk);
 		}
-	} while_each_thread(start, tsk);
+		if (ret)
+			break;
+	}
+	rcu_read_unlock();
 
-	return false;
+	return ret;
 }
 #else
 static bool has_intersects_mems_allowed(struct task_struct *tsk,
@@ -97,16 +100,21 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
  */
 struct task_struct *find_lock_task_mm(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 
-	do {
+	rcu_read_lock();
+
+	for_each_thread(p, t) {
 		task_lock(t);
 		if (likely(t->mm))
-			return t;
+			goto found;
 		task_unlock(t);
-	} while_each_thread(p, t);
+	}
+	t = NULL;
+found:
+	rcu_read_unlock();
 
-	return NULL;
+	return t;
 }
 
 /* return true if the task is not adequate as candidate victim task. */
@@ -170,7 +178,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		adj -= 30;
+		points -= (points * 3) / 100;
 
 	/* Normalize to oom_score_adj units */
 	adj *= totalpages / 1000;
@@ -301,7 +309,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	unsigned long chosen_points = 0;
 
 	rcu_read_lock();
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		unsigned int points;
 
 		switch (oom_scan_process_thread(p, totalpages, nodemask,
@@ -323,7 +331,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			chosen = p;
 			chosen_points = points;
 		}
-	} while_each_thread(g, p);
+	}
 	if (chosen)
 		get_task_struct(chosen);
 	rcu_read_unlock();
@@ -394,6 +402,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
@@ -406,7 +431,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
-	struct task_struct *t = p;
+	struct task_struct *t;
 	struct mm_struct *mm;
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
@@ -437,7 +462,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * still freeing memory.
 	 */
 	read_lock(&tasklist_lock);
-	do {
+	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 
@@ -455,13 +480,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 				get_task_struct(victim);
 			}
 		}
-	} while_each_thread(p, t);
+	}
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
 	p = find_lock_task_mm(victim);
 	if (!p) {
-		rcu_read_unlock();
 		put_task_struct(victim);
 		return;
 	} else if (victim != p) {
@@ -487,6 +510,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * That thread will now get access to memory reserves since it has a
 	 * pending fatal signal.
 	 */
+	rcu_read_lock();
 	for_each_process(p)
 		if (p->mm == mm && !same_thread_group(p, victim) &&
 		    !(p->flags & PF_KTHREAD)) {
@@ -678,9 +702,12 @@ out:
  */
 void pagefault_out_of_memory(void)
 {
-	struct zonelist *zonelist = node_zonelist(first_online_node,
-						  GFP_KERNEL);
+	struct zonelist *zonelist;
+
+	if (mem_cgroup_oom_synchronize(true))
+		return;
 
+	zonelist = node_zonelist(first_online_node, GFP_KERNEL);
 	if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
 		out_of_memory(NULL, 0, 0, NULL, false);
 		clear_zonelist_oom(zonelist, GFP_KERNEL);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4514ad7415c3..73cbc5dc150b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -188,6 +188,26 @@ static unsigned long writeout_period_time = 0;
  * global dirtyable memory first.
  */
 
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+	unsigned long nr_pages;
+
+	nr_pages = zone_page_state(zone, NR_FREE_PAGES);
+	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+
+	nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+	nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+
+	return nr_pages;
+}
+
 static unsigned long highmem_dirtyable_memory(unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
@@ -195,11 +215,9 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 	unsigned long x = 0;
 
 	for_each_node_state(node, N_HIGH_MEMORY) {
-		struct zone *z =
-			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+		struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 
-		x += zone_page_state(z, NR_FREE_PAGES) +
-		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+		x += zone_dirtyable_memory(z);
 	}
 	/*
 	 * Unreclaimable memory (kernel memory or anonymous memory
@@ -235,9 +253,12 @@ static unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x = global_page_state(NR_FREE_PAGES);
 	x -= min(x, dirty_balance_reserve);
 
+	x += global_page_state(NR_INACTIVE_FILE);
+	x += global_page_state(NR_ACTIVE_FILE);
+
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
 
@@ -289,32 +310,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 }
 
 /**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
- *
- * Returns the zone's number of pages potentially available for dirty
- * page cache.  This is the base value for the per-zone dirty limits.
- */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
-{
-	/*
-	 * The effective global number of dirtyable pages may exclude
-	 * highmem as a big-picture measure to keep the ratio between
-	 * dirty memory and lowmem reasonable.
-	 *
-	 * But this function is purely about the individual zone and a
-	 * highmem zone can hold its share of dirty pages, so we don't
-	 * care about vm_highmem_is_dirtyable here.
-	 */
-	unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
-		zone_reclaimable_pages(zone);
-
-	/* don't allow this to underflow */
-	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
-	return nr_pages;
-}
-
-/**
  * zone_dirty_limit - maximum number of dirty pages allowed in a zone
  * @zone: the zone
  *
@@ -1104,11 +1099,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 	return 1;
 }
 
-static long bdi_max_pause(struct backing_dev_info *bdi,
-			  unsigned long bdi_dirty)
+static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
+				   unsigned long bdi_dirty)
 {
-	long bw = bdi->avg_write_bandwidth;
-	long t;
+	unsigned long bw = bdi->avg_write_bandwidth;
+	unsigned long t;
 
 	/*
 	 * Limit pause time for small memory systems. If sleeping for too long
@@ -1120,7 +1115,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi,
 	t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
 	t++;
 
-	return min_t(long, t, MAX_PAUSE);
+	return min_t(unsigned long, t, MAX_PAUSE);
 }
 
 static long bdi_min_pause(struct backing_dev_info *bdi,
@@ -2031,11 +2026,12 @@ int __set_page_dirty_nobuffers(struct page *page)
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
+		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
-		spin_lock_irq(&mapping->tree_lock);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
@@ -2044,7 +2040,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2ee0fd313f03..494a081ec5e4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -360,9 +360,11 @@ void prep_compound_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-		__SetPageTail(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -2118,6 +2120,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.
@@ -2337,7 +2347,7 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2346,20 +2356,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 6d757e3a872a..e007236f345a 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -170,6 +170,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5da2cbcfdbb5..2beeabf502c5 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -242,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 		if (err)
 			break;
 		pgd++;
-	} while (addr = next, addr != end);
+	} while (addr = next, addr < end);
 
 	return err;
 }
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 3707c71ae4cd..51108165f829 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			    int page_start, int page_end)
 {
 	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-	unsigned int cpu;
+	unsigned int cpu, tcpu;
 	int i;
 
 	for_each_possible_cpu(cpu) {
@@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
 
 			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-			if (!*pagep) {
-				pcpu_free_pages(chunk, pages, populated,
-						page_start, page_end);
-				return -ENOMEM;
-			}
+			if (!*pagep)
+				goto err;
 		}
 	}
 	return 0;
+
+err:
+	while (--i >= page_start)
+		__free_page(pages[pcpu_page_idx(cpu, i)]);
+
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		for (i = page_start; i < page_end; i++)
+			__free_page(pages[pcpu_page_idx(tcpu, i)]);
+	}
+	return -ENOMEM;
 }
 
 /**
@@ -263,6 +272,7 @@ err:
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
 				   page_end - page_start);
 	}
+	pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
 	return err;
 }
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 8c8e08f3a692..25e2ea52db82 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
 						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0c8323fe6c8f..4b62a16fc3c1 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -86,9 +86,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
 		       pte_t *ptep)
 {
+	struct mm_struct *mm = (vma)->vm_mm;
 	pte_t pte;
-	pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
-	if (pte_accessible(pte))
+	pte = ptep_get_and_clear(mm, address, ptep);
+	if (pte_accessible(mm, pte))
 		flush_tlb_page(vma, address);
 	return pte;
 }
@@ -166,6 +167,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
+	pmd_t entry = *pmdp;
+	if (pmd_numa(entry))
+		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 6280da86b5d6..705bfc8e6fcd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
+	might_sleep();
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock_write(anon_vma);
@@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	 * above cannot corrupt).
 	 */
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
+		return NULL;
 	}
 out:
 	rcu_read_unlock();
@@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	}
 
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
-		goto out;
+		return NULL;
 	}
 
 	/* we pinned the anon_vma, its safe to sleep */
@@ -600,7 +602,11 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 	spinlock_t *ptl;
 
 	if (unlikely(PageHuge(page))) {
+		/* when pud is not present, pte will be NULL */
 		pte = huge_pte_offset(mm, address);
+		if (!pte)
+			return NULL;
+
 		ptl = &mm->page_table_lock;
 		goto check;
 	}
@@ -1386,9 +1392,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}
 
@@ -1661,10 +1677,9 @@ void __put_anon_vma(struct anon_vma *anon_vma)
 {
 	struct anon_vma *root = anon_vma->root;
 
+	anon_vma_free(anon_vma);
 	if (root != anon_vma && atomic_dec_and_test(&root->refcount))
 		anon_vma_free(root);
-
-	anon_vma_free(anon_vma);
 }
 
 #ifdef CONFIG_MIGRATION
diff --git a/mm/shmem.c b/mm/shmem.c
index 5e6a8422658b..4e4a7349c5cd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt;
 #define SHORT_SYMLINK_LEN 128
 
 /*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
  */
 struct shmem_falloc {
+	wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
 	pgoff_t start;		/* start of range currently being fallocated */
 	pgoff_t next;		/* the next page offset to be fallocated */
 	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
@@ -533,22 +534,19 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		return;
 
 	index = start;
-	for ( ; ; ) {
+	while (index < end) {
 		cond_resched();
 		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 							pvec.pages, indices);
 		if (!pvec.nr) {
-			if (index == start || unfalloc)
+			/* If all gone or hole-punch or unfalloc, we're done */
+			if (index == start || end != -1)
 				break;
+			/* But if truncating, restart to make sure all gone */
 			index = start;
 			continue;
 		}
-		if ((index == start || unfalloc) && indices[0] >= end) {
-			shmem_deswap_pagevec(&pvec);
-			pagevec_release(&pvec);
-			break;
-		}
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
@@ -560,8 +558,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (radix_tree_exceptional_entry(page)) {
 				if (unfalloc)
 					continue;
-				nr_swaps_freed += !shmem_free_swap(mapping,
-								index, page);
+				if (shmem_free_swap(mapping, index, page)) {
+					/* Swap was replaced by page: retry */
+					index--;
+					break;
+				}
+				nr_swaps_freed++;
 				continue;
 			}
 
@@ -570,6 +572,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				if (page->mapping == mapping) {
 					VM_BUG_ON(PageWriteback(page));
 					truncate_inode_page(mapping, page);
+				} else {
+					/* Page was replaced by swap: retry */
+					unlock_page(page);
+					index--;
+					break;
 				}
 			}
 			unlock_page(page);
@@ -826,6 +833,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 			spin_lock(&inode->i_lock);
 			shmem_falloc = inode->i_private;
 			if (shmem_falloc &&
+			    !shmem_falloc->waitq &&
 			    index >= shmem_falloc->start &&
 			    index < shmem_falloc->next)
 				shmem_falloc->nr_unswapped++;
@@ -1300,6 +1308,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	int error;
 	int ret = VM_FAULT_LOCKED;
 
+	/*
+	 * Trinity finds that probing a hole which tmpfs is punching can
+	 * prevent the hole-punch from ever completing: which in turn
+	 * locks writers out with its hold on i_mutex.  So refrain from
+	 * faulting pages into the hole while it's being punched.  Although
+	 * shmem_undo_range() does remove the additions, it may be unable to
+	 * keep up, as each new page needs its own unmap_mapping_range() call,
+	 * and the i_mmap tree grows ever slower to scan if new vmas are added.
+	 *
+	 * It does not matter if we sometimes reach this check just before the
+	 * hole-punch begins, so that one fault then races with the punch:
+	 * we just need to make racing faults a rare case.
+	 *
+	 * The implementation below would be much simpler if we just used a
+	 * standard mutex or completion: but we cannot take i_mutex in fault,
+	 * and bloating every shmem inode for this unlikely case would be sad.
+	 */
+	if (unlikely(inode->i_private)) {
+		struct shmem_falloc *shmem_falloc;
+
+		spin_lock(&inode->i_lock);
+		shmem_falloc = inode->i_private;
+		if (shmem_falloc &&
+		    shmem_falloc->waitq &&
+		    vmf->pgoff >= shmem_falloc->start &&
+		    vmf->pgoff < shmem_falloc->next) {
+			wait_queue_head_t *shmem_falloc_waitq;
+			DEFINE_WAIT(shmem_fault_wait);
+
+			ret = VM_FAULT_NOPAGE;
+			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				/* It's polite to up mmap_sem if we can */
+				up_read(&vma->vm_mm->mmap_sem);
+				ret = VM_FAULT_RETRY;
+			}
+
+			shmem_falloc_waitq = shmem_falloc->waitq;
+			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+					TASK_UNINTERRUPTIBLE);
+			spin_unlock(&inode->i_lock);
+			schedule();
+
+			/*
+			 * shmem_falloc_waitq points into the shmem_fallocate()
+			 * stack of the hole-punching task: shmem_falloc_waitq
+			 * is usually invalid by the time we reach here, but
+			 * finish_wait() does not dereference it in that case;
+			 * though i_lock needed lest racing with wake_up_all().
+			 */
+			spin_lock(&inode->i_lock);
+			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+			spin_unlock(&inode->i_lock);
+			return ret;
+		}
+		spin_unlock(&inode->i_lock);
+	}
+
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
@@ -1821,12 +1887,25 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		struct address_space *mapping = file->f_mapping;
 		loff_t unmap_start = round_up(offset, PAGE_SIZE);
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+		shmem_falloc.waitq = &shmem_falloc_waitq;
+		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+		spin_lock(&inode->i_lock);
+		inode->i_private = &shmem_falloc;
+		spin_unlock(&inode->i_lock);
 
 		if ((u64)unmap_end > (u64)unmap_start)
 			unmap_mapping_range(mapping, unmap_start,
 					    1 + unmap_end - unmap_start, 0);
 		shmem_truncate_range(inode, offset, offset + len - 1);
 		/* No need to unmap again: hole-punching leaves COWed pages */
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = NULL;
+		wake_up_all(&shmem_falloc_waitq);
+		spin_unlock(&inode->i_lock);
 		error = 0;
 		goto out;
 	}
@@ -1844,6 +1923,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		goto out;
 	}
 
+	shmem_falloc.waitq = NULL;
 	shmem_falloc.start = start;
 	shmem_falloc.next  = start;
 	shmem_falloc.nr_falloced = 0;
@@ -2048,8 +2128,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct
 
 	if (new_dentry->d_inode) {
 		(void) shmem_unlink(new_dir, new_dentry);
-		if (they_are_dirs)
+		if (they_are_dirs) {
+			drop_nlink(new_dentry->d_inode);
 			drop_nlink(old_dir);
+		}
 	} else if (they_are_dirs) {
 		drop_nlink(old_dir);
 		inc_nlink(new_dir);
@@ -2879,14 +2961,8 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 /* common code */
 
-static char *shmem_dname(struct dentry *dentry, char *buffer, int buflen)
-{
-	return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
-				dentry->d_name.name);
-}
-
 static struct dentry_operations anon_ops = {
-	.d_dname = shmem_dname
+	.d_dname = simple_dname
 };
 
 /**
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2d414508e9ec..7d21d3fddbf0 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -55,6 +55,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			continue;
 		}
 
+#if !defined(CONFIG_SLUB)
 		/*
 		 * For simplicity, we won't check this in the list of memcg
 		 * caches. We have control over memcg naming, and if there
@@ -68,6 +69,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			s = NULL;
 			return -EINVAL;
 		}
+#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
diff --git a/mm/slub.c b/mm/slub.c
index 57707f01bcfb..deaed7b47213 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1201,8 +1201,8 @@ static unsigned long kmem_cache_flags(unsigned long object_size,
 	/*
 	 * Enable debugging if selected on the kernel commandline.
 	 */
-	if (slub_debug && (!slub_debug_slabs ||
-		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+	if (slub_debug && (!slub_debug_slabs || (name &&
+		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
 		flags |= slub_debug;
 
 	return flags;
@@ -4285,7 +4285,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 			page = ACCESS_ONCE(c->partial);
 			if (page) {
-				x = page->pobjects;
+				node = page_to_nid(page);
+				if (flags & SO_TOTAL)
+					WARN_ON_ONCE(1);
+				else if (flags & SO_OBJECTS)
+					WARN_ON_ONCE(1);
+				else
+					x = page->pages;
 				total += x;
 				nodes[node] += x;
 			}
diff --git a/mm/swap.c b/mm/swap.c
index dfd7d71d6841..4e35f3ff0427 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -31,6 +31,7 @@
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
 #include <linux/uio.h>
+#include <linux/hugetlb.h>
 
 #include "internal.h"
 
@@ -80,7 +81,7 @@ static void put_compound_page(struct page *page)
 {
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
-		struct page *page_head = compound_trans_head(page);
+		struct page *page_head = compound_head(page);
 
 		if (likely(page != page_head &&
 			   get_page_unless_zero(page_head))) {
@@ -94,14 +95,31 @@ static void put_compound_page(struct page *page)
 			 * still hot on arches that do not support
 			 * this_cpu_cmpxchg_double().
 			 */
-			if (PageSlab(page_head)) {
-				if (PageTail(page)) {
+			if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+				if (likely(PageTail(page))) {
+					/*
+					 * __split_huge_page_refcount
+					 * cannot race here.
+					 */
+					VM_BUG_ON(!PageHead(page_head));
+					atomic_dec(&page->_mapcount);
 					if (put_page_testzero(page_head))
 						VM_BUG_ON(1);
-
-					atomic_dec(&page->_mapcount);
-					goto skip_lock_tail;
+					if (put_page_testzero(page_head))
+						__put_compound_page(page_head);
+					return;
 				} else
+					/*
+					 * __split_huge_page_refcount
+					 * run before us, "page" was a
+					 * THP tail. The split
+					 * page_head has been freed
+					 * and reallocated as slab or
+					 * hugetlbfs page of smaller
+					 * order (only possible if
+					 * reallocated as slab on
+					 * x86).
+					 */
 					goto skip_lock;
 			}
 			/*
@@ -115,8 +133,27 @@ static void put_compound_page(struct page *page)
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 skip_lock:
-				if (put_page_testzero(page_head))
-					__put_single_page(page_head);
+				if (put_page_testzero(page_head)) {
+					/*
+					 * The head page may have been
+					 * freed and reallocated as a
+					 * compound page of smaller
+					 * order and then freed again.
+					 * All we know is that it
+					 * cannot have become: a THP
+					 * page, a compound page of
+					 * higher order, a tail page.
+					 * That is because we still
+					 * hold the refcount of the
+					 * split THP tail and
+					 * page_head was the THP head
+					 * before the split.
+					 */
+					if (PageHead(page_head))
+						__put_compound_page(page_head);
+					else
+						__put_single_page(page_head);
+				}
 out_put_single:
 				if (put_page_testzero(page))
 					__put_single_page(page);
@@ -138,7 +175,6 @@ out_put_single:
 			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 
-skip_lock_tail:
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
@@ -183,16 +219,30 @@ bool __get_page_tail(struct page *page)
 	 */
 	unsigned long flags;
 	bool got = false;
-	struct page *page_head = compound_trans_head(page);
+	struct page *page_head = compound_head(page);
 
 	if (likely(page != page_head && get_page_unless_zero(page_head))) {
-
 		/* Ref to put_compound_page() comment. */
-		if (PageSlab(page_head)) {
+		if (PageSlab(page_head) || PageHeadHuge(page_head)) {
 			if (likely(PageTail(page))) {
+				/*
+				 * This is a hugetlbfs page or a slab
+				 * page. __split_huge_page_refcount
+				 * cannot race here.
+				 */
+				VM_BUG_ON(!PageHead(page_head));
 				__get_page_tail_foll(page, false);
 				return true;
 			} else {
+				/*
+				 * __split_huge_page_refcount run
+				 * before us, "page" was a THP
+				 * tail. The split page_head has been
+				 * freed and reallocated as slab or
+				 * hugetlbfs page of smaller order
+				 * (only possible if reallocated as
+				 * slab on x86).
+				 */
 				put_page(page_head);
 				return false;
 			}
diff --git a/mm/truncate.c b/mm/truncate.c
index c75b736e54b7..2d6151fc8f08 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 
@@ -567,16 +568,67 @@ EXPORT_SYMBOL(truncate_pagecache);
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
-	loff_t oldsize;
+	loff_t oldsize = inode->i_size;
 
-	oldsize = inode->i_size;
 	i_size_write(inode, newsize);
-
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, oldsize, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
  * @lstart: offset of beginning of hole
diff --git a/mm/util.c b/mm/util.c
index ab1424dbe2e6..0b1725254ff1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -272,17 +272,14 @@ pid_t vm_is_stack(struct task_struct *task,
 
 	if (in_group) {
 		struct task_struct *t;
-		rcu_read_lock();
-		if (!pid_alive(task))
-			goto done;
 
-		t = task;
-		do {
+		rcu_read_lock();
+		for_each_thread(task, t) {
 			if (vm_is_stack_for_task(t, vma)) {
 				ret = t->pid;
 				goto done;
 			}
-		} while_each_thread(task, t);
+		}
 done:
 		rcu_read_unlock();
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d365724feb05..d4565606cc96 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -388,12 +388,12 @@ nocache:
 		addr = ALIGN(first->va_end, align);
 		if (addr < vstart)
 			goto nocache;
-		if (addr + size - 1 < addr)
+		if (addr + size < addr)
 			goto overflow;
 
 	} else {
 		addr = ALIGN(vstart, align);
-		if (addr + size - 1 < addr)
+		if (addr + size < addr)
 			goto overflow;
 
 		n = vmap_area_root.rb_node;
@@ -420,7 +420,7 @@ nocache:
 		if (addr + cached_hole_size < first->va_start)
 			cached_hole_size = first->va_start - addr;
 		addr = ALIGN(first->va_end, align);
-		if (addr + size - 1 < addr)
+		if (addr + size < addr)
 			goto overflow;
 
 		if (list_is_last(&first->list, &vmap_area_list))
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fa6a85378ee4..a2fd7e759cb7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,7 @@
 #include <asm/div64.h>
 
 #include <linux/swapops.h>
+#include <linux/balloon_compaction.h>
 
 #include "internal.h"
 
@@ -978,7 +979,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_cache(page) && !PageDirty(page)) {
+		if (page_is_file_cache(page) && !PageDirty(page) &&
+		    !isolated_balloon_page(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -2115,6 +2117,20 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	return aborted_reclaim;
 }
 
+static unsigned long zone_reclaimable_pages(struct zone *zone)
+{
+	int nr;
+
+	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+	     zone_page_state(zone, NR_INACTIVE_FILE);
+
+	if (get_nr_swap_pages() > 0)
+		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+		      zone_page_state(zone, NR_INACTIVE_ANON);
+
+	return nr;
+}
+
 static bool zone_reclaimable(struct zone *zone)
 {
 	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
@@ -2270,10 +2286,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2298,9 +2321,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2319,10 +2342,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
@@ -2584,18 +2631,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		return false;
 
 	/*
-	 * There is a potential race between when kswapd checks its watermarks
-	 * and a process gets throttled. There is also a potential race if
-	 * processes get throttled, kswapd wakes, a large process exits therby
-	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
-	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
-	 * so wake them now if necessary. If necessary, processes will wake
-	 * kswapd and get throttled again
+	 * The throttled processes are normally woken up in balance_pgdat() as
+	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * race between when kswapd checks the watermarks and a process gets
+	 * throttled. There is also a potential race if processes get
+	 * throttled, kswapd wakes, a large process exits thereby balancing the
+	 * zones, which causes kswapd to exit balance_pgdat() before reaching
+	 * the wake up checks. If kswapd is going to sleep, no process should
+	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+	 * the wake up is premature, processes will wake kswapd and get
+	 * throttled again. The difference from wake ups in balance_pgdat() is
+	 * that here we are under prepare_to_wait().
 	 */
-	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
-		wake_up(&pgdat->pfmemalloc_wait);
-		return false;
-	}
+	if (waitqueue_active(&pgdat->pfmemalloc_wait))
+		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	return pgdat_balanced(pgdat, order, classzone_idx);
 }
@@ -3043,7 +3092,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }
 
@@ -3073,41 +3125,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
-	int nr;
-
-	nr = global_page_state(NR_ACTIVE_FILE) +
-	     global_page_state(NR_INACTIVE_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += global_page_state(NR_ACTIVE_ANON) +
-		      global_page_state(NR_INACTIVE_ANON);
-
-	return nr;
-}
-
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
-	int nr;
-
-	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
-	     zone_page_state(zone, NR_INACTIVE_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
-		      zone_page_state(zone, NR_INACTIVE_ANON);
-
-	return nr;
-}
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f42745e65780..6d9bace4e589 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <linux/vmstat.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
@@ -432,11 +433,12 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
  */
-void refresh_cpu_vm_stats(int cpu)
+bool refresh_cpu_vm_stats(int cpu)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	bool vm_activity = false;
 
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset *p;
@@ -483,14 +485,21 @@ void refresh_cpu_vm_stats(int cpu)
 		if (p->expire)
 			continue;
 
-		if (p->pcp.count)
+		if (p->pcp.count) {
+			vm_activity = true;
 			drain_zone_pages(zone, &p->pcp);
+		}
 #endif
 	}
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (global_diff[i])
+		if (global_diff[i]) {
 			atomic_long_add(global_diff[i], &vm_stat[i]);
+			vm_activity = true;
+		}
+
+	return vm_activity;
+
 }
 
 /*
@@ -779,6 +788,7 @@ const char * const vmstat_text[] = {
 
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
+	"numa_huge_pte_updates",
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
@@ -1174,22 +1184,72 @@ static const struct file_operations proc_vmstat_file_operations = {
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
+static struct cpumask vmstat_off_cpus;
+struct delayed_work vmstat_monitor_work;
 
-static void vmstat_update(struct work_struct *w)
+static inline bool need_vmstat(int cpu)
 {
-	refresh_cpu_vm_stats(smp_processor_id());
-	schedule_delayed_work(&__get_cpu_var(vmstat_work),
-		round_jiffies_relative(sysctl_stat_interval));
+	struct zone *zone;
+	int i;
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p;
+
+		p = per_cpu_ptr(zone->pageset, cpu);
+
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+			if (p->vm_stat_diff[i])
+				return true;
+
+		if (zone_to_nid(zone) != numa_node_id() && p->pcp.count)
+			return true;
+	}
+
+	return false;
 }
 
-static void __cpuinit start_cpu_timer(int cpu)
+static void vmstat_update(struct work_struct *w);
+
+static void start_cpu_timer(int cpu)
 {
 	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
-	INIT_DEFERRABLE_WORK(work, vmstat_update);
+	cpumask_clear_cpu(cpu, &vmstat_off_cpus);
 	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
+static void __cpuinit setup_cpu_timer(int cpu)
+{
+	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
+
+	INIT_DEFERRABLE_WORK(work, vmstat_update);
+	start_cpu_timer(cpu);
+}
+
+static void vmstat_update_monitor(struct work_struct *w)
+{
+	int cpu;
+
+	for_each_cpu_and(cpu, &vmstat_off_cpus, cpu_online_mask)
+		if (need_vmstat(cpu))
+			start_cpu_timer(cpu);
+
+	queue_delayed_work(system_unbound_wq, &vmstat_monitor_work,
+		round_jiffies_relative(sysctl_stat_interval));
+}
+
+
+static void vmstat_update(struct work_struct *w)
+{
+	int cpu = smp_processor_id();
+
+	if (likely(refresh_cpu_vm_stats(cpu)))
+		schedule_delayed_work(&__get_cpu_var(vmstat_work),
+				round_jiffies_relative(sysctl_stat_interval));
+	else
+		cpumask_set_cpu(cpu, &vmstat_off_cpus);
+}
+
 /*
  * Use the cpu notifier to insure that the thresholds are recalculated
  * when necessary.
@@ -1204,17 +1264,19 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		refresh_zone_stat_thresholds();
-		start_cpu_timer(cpu);
+		setup_cpu_timer(cpu);
 		node_set_state(cpu_to_node(cpu), N_CPU);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		per_cpu(vmstat_work, cpu).work.func = NULL;
+		if (!cpumask_test_cpu(cpu, &vmstat_off_cpus)) {
+			cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+			per_cpu(vmstat_work, cpu).work.func = NULL;
+		}
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
+		setup_cpu_timer(cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -1237,8 +1299,14 @@ static int __init setup_vmstat(void)
 
 	register_cpu_notifier(&vmstat_notifier);
 
+	INIT_DEFERRABLE_WORK(&vmstat_monitor_work,
+				vmstat_update_monitor);
+	queue_delayed_work(system_unbound_wq,
+				&vmstat_monitor_work,
+				round_jiffies_relative(HZ));
+
 	for_each_online_cpu(cpu)
-		start_cpu_timer(cpu);
+		setup_cpu_timer(cpu);
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9424f3718ea7..86abb2e59aea 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -305,9 +305,11 @@ static void vlan_sync_address(struct net_device *dev,
 static void vlan_transfer_features(struct net_device *dev,
 				   struct net_device *vlandev)
 {
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
 	vlandev->gso_max_size = dev->gso_max_size;
 
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
 		vlandev->hard_header_len = dev->hard_header_len;
 	else
 		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 4a78c4de9f20..42ef36a85e69 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -103,8 +103,11 @@ EXPORT_SYMBOL(vlan_dev_vlan_id);
 
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
-	if (skb_cow(skb, skb_headroom(skb)) < 0)
+	if (skb_cow(skb, skb_headroom(skb)) < 0) {
+		kfree_skb(skb);
 		return NULL;
+	}
+
 	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 1cd3d2a406f5..698e922f41ea 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -512,10 +512,48 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 	}
 }
 
+static int vlan_calculate_locking_subclass(struct net_device *real_dev)
+{
+	int subclass = 0;
+
+	while (is_vlan_dev(real_dev)) {
+		subclass++;
+		real_dev = vlan_dev_priv(real_dev)->real_dev;
+	}
+
+	return subclass;
+}
+
+static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
+{
+	int err = 0, subclass;
+
+	subclass = vlan_calculate_locking_subclass(to);
+
+	spin_lock_nested(&to->addr_list_lock, subclass);
+	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	spin_unlock(&to->addr_list_lock);
+}
+
+static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
+{
+	int err = 0, subclass;
+
+	subclass = vlan_calculate_locking_subclass(to);
+
+	spin_lock_nested(&to->addr_list_lock, subclass);
+	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	spin_unlock(&to->addr_list_lock);
+}
+
 static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 {
-	dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
-	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
 /*
@@ -549,6 +587,26 @@ static const struct header_ops vlan_header_ops = {
 	.parse	 = eth_header_parse,
 };
 
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+				     unsigned short type,
+				     const void *daddr, const void *saddr,
+				     unsigned int len)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
+	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
+
+static const struct header_ops vlan_passthru_header_ops = {
+	.create	 = vlan_passthru_hard_header,
+	.rebuild = dev_rebuild_header,
+	.parse	 = eth_header_parse,
+};
+
 static struct device_type vlan_type = {
 	.name	= "vlan",
 };
@@ -591,8 +649,9 @@ static int vlan_dev_init(struct net_device *dev)
 #endif
 
 	dev->needed_headroom = real_dev->needed_headroom;
-	if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
-		dev->header_ops      = real_dev->header_ops;
+	if (vlan_hw_offload_capable(real_dev->features,
+				    vlan_dev_priv(dev)->vlan_proto)) {
+		dev->header_ops      = &vlan_passthru_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
 	} else {
 		dev->header_ops      = &vlan_header_ops;
@@ -603,9 +662,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	if (is_vlan_dev(real_dev))
-		subclass = 1;
-
+	subclass = vlan_calculate_locking_subclass(dev);
 	vlan_dev_set_lockdep_class(dev, subclass);
 
 	vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 309129732285..c7e634af8516 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev)
 
 	return nla_total_size(2) +	/* IFLA_VLAN_PROTOCOL */
 	       nla_total_size(2) +	/* IFLA_VLAN_ID */
-	       sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
+	       nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */
 	       vlan_qos_map_size(vlan->nr_ingress_mappings) +
 	       vlan_qos_map_size(vlan->nr_egress_mappings);
 }
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index e1c26b101830..c76a4388a5d7 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -340,7 +340,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 		int count = nr_pages;
 		while (nr_pages) {
 			s = rest_of_page(data);
-			pages[index++] = kmap_to_page(data);
+			if (is_vmalloc_addr(data))
+				pages[index++] = vmalloc_to_page(data);
+			else
+				pages[index++] = kmap_to_page(data);
 			data += s;
 			nr_pages--;
 		}
@@ -577,6 +580,10 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 	mutex_lock(&virtio_9p_lock);
 	list_add_tail(&chan->chan_list, &virtio_chan_list);
 	mutex_unlock(&virtio_9p_lock);
+
+	/* Let udev rules use the new mount_tag attribute. */
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
 	return 0;
 
 out_free_tag:
@@ -654,6 +661,7 @@ static void p9_virtio_remove(struct virtio_device *vdev)
 	list_del(&chan->chan_list);
 	mutex_unlock(&virtio_9p_lock);
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
 	kfree(chan->tag);
 	kfree(chan->vc_wq);
 	kfree(chan);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index ef12839a7cfe..8799e171addf 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	/* Queue packet (standard) */
-	skb->sk = sock;
-
 	if (sock_queue_rcv_skb(sock, skb) < 0)
 		goto drop;
 
@@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	if (!skb)
 		goto out;
 
-	skb->sk = sk;
 	skb_reserve(skb, ddp_dl->header_length);
 	skb_reserve(skb, dev->hard_header_len);
 	skb->dev = dev;
@@ -1735,7 +1732,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 			 size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
 	struct ddpehdr *ddp;
 	int copied = 0;
 	int offset = 0;
@@ -1764,14 +1760,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	}
 	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
 
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
+	if (!err && msg->msg_name) {
+		struct sockaddr_at *sat = msg->msg_name;
+		sat->sat_family      = AF_APPLETALK;
+		sat->sat_port        = ddp->deh_sport;
+		sat->sat_addr.s_node = ddp->deh_snode;
+		sat->sat_addr.s_net  = ddp->deh_snet;
+		msg->msg_namelen     = sizeof(*sat);
 	}
 
 	skb_free_datagram(sk, skb);	/* Free the datagram. */
diff --git a/net/atm/common.c b/net/atm/common.c
index 737bef59ce89..7b491006eaf4 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	struct sk_buff *skb;
 	int copied, error = -EINVAL;
 
-	msg->msg_namelen = 0;
-
 	if (sock->state != SS_CONNECTED)
 		return -ENOTCONN;
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e277e38f736b..ba6db78a02b1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (msg->msg_namelen != 0) {
-		struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+	if (msg->msg_name) {
 		ax25_digi digi;
 		ax25_address src;
 		const unsigned char *mac = skb_mac_header(skb);
+		struct sockaddr_ax25 *sax = msg->msg_name;
 
 		memset(sax, 0, sizeof(struct full_sockaddr_ax25));
 		ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 51aafd669cbb..f1cb1f56cda9 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -61,6 +61,7 @@ static int __init batadv_init(void)
 	batadv_recv_handler_init();
 
 	batadv_iv_init();
+	batadv_nc_init();
 
 	batadv_event_workqueue = create_singlethread_workqueue("bat_events");
 
@@ -138,7 +139,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	if (ret < 0)
 		goto err;
 
-	ret = batadv_nc_init(bat_priv);
+	ret = batadv_nc_mesh_init(bat_priv);
 	if (ret < 0)
 		goto err;
 
@@ -163,7 +164,7 @@ void batadv_mesh_free(struct net_device *soft_iface)
 	batadv_vis_quit(bat_priv);
 
 	batadv_gw_node_purge(bat_priv);
-	batadv_nc_free(bat_priv);
+	batadv_nc_mesh_free(bat_priv);
 	batadv_dat_free(bat_priv);
 	batadv_bla_free(bat_priv);
 
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index e84629ece9b7..f97aeee2201c 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
 				       struct batadv_hard_iface *recv_if);
 
 /**
+ * batadv_nc_init - one-time initialization for network coding
+ */
+int __init batadv_nc_init(void)
+{
+	int ret;
+
+	/* Register our packet type */
+	ret = batadv_recv_handler_register(BATADV_CODED,
+					   batadv_nc_recv_coded_packet);
+
+	return ret;
+}
+
+/**
  * batadv_nc_start_timer - initialise the nc periodic worker
  * @bat_priv: the bat priv with all the soft interface information
  */
@@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv)
 }
 
 /**
- * batadv_nc_init - initialise coding hash table and start house keeping
+ * batadv_nc_mesh_init - initialise coding hash table and start house keeping
  * @bat_priv: the bat priv with all the soft interface information
  */
-int batadv_nc_init(struct batadv_priv *bat_priv)
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
 {
 	bat_priv->nc.timestamp_fwd_flush = jiffies;
 	bat_priv->nc.timestamp_sniffed_purge = jiffies;
@@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv)
 	batadv_hash_set_lock_class(bat_priv->nc.coding_hash,
 				   &batadv_nc_decoding_hash_lock_class_key);
 
-	/* Register our packet type */
-	if (batadv_recv_handler_register(BATADV_CODED,
-					 batadv_nc_recv_coded_packet) < 0)
-		goto err;
-
 	INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker);
 	batadv_nc_start_timer(bat_priv);
 
@@ -1722,12 +1731,11 @@ free_nc_packet:
 }
 
 /**
- * batadv_nc_free - clean up network coding memory
+ * batadv_nc_mesh_free - clean up network coding memory
  * @bat_priv: the bat priv with all the soft interface information
  */
-void batadv_nc_free(struct batadv_priv *bat_priv)
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
 {
-	batadv_recv_handler_unregister(BATADV_CODED);
 	cancel_delayed_work_sync(&bat_priv->nc.work);
 
 	batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL);
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 4fa6d0caddbd..bd4295fb960f 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -22,8 +22,9 @@
 
 #ifdef CONFIG_BATMAN_ADV_NC
 
-int batadv_nc_init(struct batadv_priv *bat_priv);
-void batadv_nc_free(struct batadv_priv *bat_priv);
+int batadv_nc_init(void);
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv);
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv);
 void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
 			      struct batadv_orig_node *orig_node,
 			      struct batadv_orig_node *orig_neigh_node,
@@ -47,12 +48,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv);
 
 #else /* ifdef CONFIG_BATMAN_ADV_NC */
 
-static inline int batadv_nc_init(struct batadv_priv *bat_priv)
+static inline int batadv_nc_init(void)
 {
 	return 0;
 }
 
-static inline void batadv_nc_free(struct batadv_priv *bat_priv)
+static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
 {
 	return;
 }
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9096137c889c..6629cdc134dc 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -221,8 +221,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags & (MSG_OOB))
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -287,8 +285,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	BT_DBG("sk %p size %zu", sk, size);
 
 	lock_sock(sk);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 6c7f36379722..8e7290aea8f8 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -652,14 +652,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
 		struct hci_cp_auth_requested cp;
 
-		/* encrypt must be pending if auth is also pending */
-		set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
 		cp.handle = cpu_to_le16(conn->handle);
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
-		if (conn->key_type != 0xff)
+
+		/* If we're already encrypted set the REAUTH_PEND flag,
+		 * otherwise set the ENCRYPT_PEND.
+		 */
+		if (conn->link_mode & HCI_LM_ENCRYPT)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+		else
+			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
 	return 0;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ace5e55fe5a3..7c88f5f83598 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1123,7 +1123,11 @@ int hci_dev_open(__u16 dev)
 		goto done;
 	}
 
-	if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) {
+	/* Check for rfkill but allow the HCI setup stage to proceed
+	 * (which in itself doesn't cause any RF activity).
+	 */
+	if (test_bit(HCI_RFKILLED, &hdev->dev_flags) &&
+	    !test_bit(HCI_SETUP, &hdev->dev_flags)) {
 		ret = -ERFKILL;
 		goto done;
 	}
@@ -1545,10 +1549,13 @@ static int hci_rfkill_set_block(void *data, bool blocked)
 
 	BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked);
 
-	if (!blocked)
-		return 0;
-
-	hci_dev_do_close(hdev);
+	if (blocked) {
+		set_bit(HCI_RFKILLED, &hdev->dev_flags);
+		if (!test_bit(HCI_SETUP, &hdev->dev_flags))
+			hci_dev_do_close(hdev);
+	} else {
+		clear_bit(HCI_RFKILLED, &hdev->dev_flags);
+}
 
 	return 0;
 }
@@ -1570,9 +1577,13 @@ static void hci_power_on(struct work_struct *work)
 		return;
 	}
 
-	if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+	if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) {
+		clear_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+		hci_dev_do_close(hdev);
+	} else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
 		queue_delayed_work(hdev->req_workqueue, &hdev->power_off,
 				   HCI_AUTO_OFF_TIMEOUT);
+	}
 
 	if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags))
 		mgmt_index_added(hdev);
@@ -2241,6 +2252,9 @@ int hci_register_dev(struct hci_dev *hdev)
 		}
 	}
 
+	if (hdev->rfkill && rfkill_blocked(hdev->rfkill))
+		set_bit(HCI_RFKILLED, &hdev->dev_flags);
+
 	set_bit(HCI_SETUP, &hdev->dev_flags);
 
 	if (hdev->dev_type != HCI_AMP)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index b93cd2eb5d58..5daf7ab26710 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3051,6 +3051,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev,
 	if (!conn)
 		goto unlock;
 
+	/* For BR/EDR the necessary steps are taken through the
+	 * auth_complete event.
+	 */
+	if (conn->type != LE_LINK)
+		goto unlock;
+
 	if (!ev->status)
 		conn->sec_level = conn->pending_sec_level;
 
@@ -3212,8 +3218,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		/* If we're not the initiators request authorization to
 		 * proceed from user space (mgmt_user_confirm with
-		 * confirm_hint set to 1). */
-		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+		 * confirm_hint set to 1). The exception is if neither
+		 * side had MITM in which case we do auto-accept.
+		 */
+		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+		    (loc_mitm || rem_mitm)) {
 			BT_DBG("Confirming auto-accept as acceptor");
 			confirm_hint = 1;
 			goto confirm;
@@ -3611,11 +3620,21 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	cp.handle = cpu_to_le16(conn->handle);
 
 	if (ltk->authenticated)
-		conn->sec_level = BT_SECURITY_HIGH;
+		conn->pending_sec_level = BT_SECURITY_HIGH;
+	else
+		conn->pending_sec_level = BT_SECURITY_MEDIUM;
+
+	conn->enc_key_size = ltk->enc_size;
 
 	hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
 
-	if (ltk->type & HCI_SMP_STK) {
+	/* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
+	 * temporary key used to encrypt a connection following
+	 * pairing. It is used during the Encrypted Session Setup to
+	 * distribute the keys. Later, security can be re-established
+	 * using a distributed LTK.
+	 */
+	if (ltk->type == HCI_SMP_STK_SLAVE) {
 		list_del(&ltk->list);
 		kfree(ltk);
 	}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 9bd7d959e384..fa4bf6631425 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return err;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 940f5acb6694..de030f50f72b 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -231,17 +231,22 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb)
 
 static int hidp_send_report(struct hidp_session *session, struct hid_report *report)
 {
-	unsigned char buf[32], hdr;
-	int rsize;
+	unsigned char hdr;
+	u8 *buf;
+	int rsize, ret;
 
-	rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0);
-	if (rsize > sizeof(buf))
+	buf = hid_alloc_report_buf(report, GFP_ATOMIC);
+	if (!buf)
 		return -EIO;
 
 	hid_output_report(report, buf);
 	hdr = HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT;
 
-	return hidp_send_intr_message(session, hdr, buf, rsize);
+	rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+	ret = hidp_send_intr_message(session, hdr, buf, rsize);
+
+	kfree(buf);
+	return ret;
 }
 
 static int hidp_get_raw_report(struct hid_device *hid,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 36fed40c162c..5f36f70ce44d 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -887,7 +887,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how)
 		l2cap_chan_close(chan, 0);
 		lock_sock(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED,
 						 sk->sk_lingertime);
 	}
@@ -949,13 +950,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		release_sock(parent);
 		return NULL;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
 			      GFP_ATOMIC);
-	if (!sk)
+	if (!sk) {
+		release_sock(parent);
 		return NULL;
+        }
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f8ecbc70293d..8208a13a9837 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2333,8 +2333,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
-		/* Continue with pairing via SMP */
+		/* Continue with pairing via SMP. The hdev lock must be
+		 * released as SMP may try to recquire it for crypto
+		 * purposes.
+		 */
+		hci_dev_unlock(hdev);
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+		hci_dev_lock(hdev);
 
 		if (!err)
 			err = cmd_complete(sk, hdev->id, mgmt_op,
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index ca957d34b0c8..19ba192e9dbf 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1857,10 +1857,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
 	/* Get data directly from socket receive queue without copying it. */
 	while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
 		skb_orphan(skb);
-		if (!skb_linearize(skb))
+		if (!skb_linearize(skb)) {
 			s = rfcomm_recv_frame(s, skb);
-		else
+			if (!s)
+				break;
+		} else {
 			kfree_skb(skb);
+		}
 	}
 
 	if (s && (sk->sk_state == BT_CLOSED))
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 30b3721dc6d7..7ca014daa5ab 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -608,7 +608,6 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
 		rfcomm_dlc_accept(d);
-		msg->msg_namelen = 0;
 		return 0;
 	}
 
@@ -888,7 +887,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how)
 		sk->sk_shutdown = SHUTDOWN_MASK;
 		__rfcomm_sock_close(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
 	}
 	release_sock(sk);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e7bd4eea575c..c9ae6b703c13 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -700,7 +700,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	    test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
 		sco_conn_defer_accept(pi->conn->hcon, 0);
 		sk->sk_state = BT_CONFIG;
-		msg->msg_namelen = 0;
 
 		release_sock(sk);
 		return 0;
@@ -859,7 +858,8 @@ static int sco_sock_shutdown(struct socket *sock, int how)
 		sco_sock_clear_timer(sk);
 		__sco_sock_close(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED,
 						 sk->sk_lingertime);
 	}
@@ -879,7 +879,8 @@ static int sco_sock_release(struct socket *sock)
 
 	sco_sock_close(sk);
 
-	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) {
+	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+	    !(current->flags & PF_EXITING)) {
 		lock_sock(sk);
 		err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
 		release_sock(sk);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 4cdba60926ff..32bd1e87f149 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
 		del_nbp(p);
 	}
 
+	br_fdb_delete_by_port(br, NULL, 1);
+
 	del_timer_sync(&br->gc_timer);
 
 	br_sysfs_delbr(br->dev);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 828e2bcc1f52..0a3bc82782cf 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -71,7 +71,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
 		goto drop;
 
 	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
-		goto drop;
+		goto out;
 
 	/* insert into forwarding database after filtering to avoid spoofing */
 	br = p->br;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d82058f6fc79..81de0106528b 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1176,6 +1176,12 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;
@@ -1839,7 +1845,7 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
 	u32 old;
 	struct net_bridge_mdb_htable *mdb;
 
-	spin_lock(&br->multicast_lock);
+	spin_lock_bh(&br->multicast_lock);
 	if (!netif_running(br->dev))
 		goto unlock;
 
@@ -1871,7 +1877,7 @@ rollback:
 	}
 
 unlock:
-	spin_unlock(&br->multicast_lock);
+	spin_unlock_bh(&br->multicast_lock);
 
 	return err;
 }
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index f66a03453a8e..f16e9e487750 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -203,7 +203,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	       struct net_device *dev, u32 filter_mask)
 {
 	int err = 0;
-	struct net_bridge_port *port = br_port_get_rcu(dev);
+	struct net_bridge_port *port = br_port_get_rtnl(dev);
 
 	/* not a bridge port and  */
 	if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN))
@@ -438,12 +438,26 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_link_af_size(const struct net_device *dev)
 {
 	struct net_port_vlans *pv;
 
 	if (br_port_exists(dev))
-		pv = nbp_get_vlan_info(br_port_get_rcu(dev));
+		pv = nbp_get_vlan_info(br_port_get_rtnl(dev));
 	else if (dev->priv_flags & IFF_EBRIDGE)
 		pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
 	else
@@ -466,6 +480,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct net_bridge),
 	.setup		= br_dev_setup,
 	.validate	= br_validate,
+	.newlink	= br_dev_newlink,
 	.dellink	= br_dev_delete,
 };
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d2c043a857b6..11ab6628027a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -183,13 +183,10 @@ struct net_bridge_port
 
 static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
 {
-	struct net_bridge_port *port =
-			rcu_dereference_rtnl(dev->rx_handler_data);
-
-	return br_port_exists(dev) ? port : NULL;
+	return rcu_dereference(dev->rx_handler_data);
 }
 
-static inline struct net_bridge_port *br_port_get_rtnl(struct net_device *dev)
+static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev)
 {
 	return br_port_exists(dev) ?
 		rtnl_dereference(dev->rx_handler_data) : NULL;
@@ -432,6 +429,16 @@ extern netdev_features_t br_features_recompute(struct net_bridge *br,
 extern int br_handle_frame_finish(struct sk_buff *skb);
 extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
 
+static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
+{
+	return rcu_dereference(dev->rx_handler) == br_handle_frame;
+}
+
+static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev)
+{
+	return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL;
+}
+
 /* br_ioctl.c */
 extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg);
@@ -714,6 +721,7 @@ extern struct net_bridge_port *br_get_port(struct net_bridge *br,
 extern void br_init_port(struct net_bridge_port *p);
 extern void br_become_designated_port(struct net_bridge_port *p);
 
+extern void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
 extern int br_set_forward_delay(struct net_bridge *br, unsigned long x);
 extern int br_set_hello_time(struct net_bridge *br, unsigned long x);
 extern int br_set_max_age(struct net_bridge *br, unsigned long x);
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 1c0a50f13229..3c86f0538cbb 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -209,7 +209,7 @@ static void br_record_config_information(struct net_bridge_port *p,
 	p->designated_age = jiffies - bpdu->message_age;
 
 	mod_timer(&p->message_age_timer, jiffies
-		  + (p->br->max_age - bpdu->message_age));
+		  + (bpdu->max_age - bpdu->message_age));
 }
 
 /* called under bridge lock */
@@ -544,18 +544,27 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
 
 }
 
+void __br_set_forward_delay(struct net_bridge *br, unsigned long t)
+{
+	br->bridge_forward_delay = t;
+	if (br_is_root_bridge(br))
+		br->forward_delay = br->bridge_forward_delay;
+}
+
 int br_set_forward_delay(struct net_bridge *br, unsigned long val)
 {
 	unsigned long t = clock_t_to_jiffies(val);
+	int err = -ERANGE;
 
+	spin_lock_bh(&br->lock);
 	if (br->stp_enabled != BR_NO_STP &&
 	    (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY))
-		return -ERANGE;
+		goto unlock;
 
-	spin_lock_bh(&br->lock);
-	br->bridge_forward_delay = t;
-	if (br_is_root_bridge(br))
-		br->forward_delay = br->bridge_forward_delay;
+	__br_set_forward_delay(br, t);
+	err = 0;
+
+unlock:
 	spin_unlock_bh(&br->lock);
-	return 0;
+	return err;
 }
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 8660ea3be705..bdb459d21ad8 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 	if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0)
 		goto err;
 
-	p = br_port_get_rcu(dev);
+	p = br_port_get_check_rcu(dev);
 	if (!p)
 		goto err;
 
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index d45e760141bb..656a6f3e40de 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -129,6 +129,14 @@ static void br_stp_start(struct net_bridge *br)
 	char *envp[] = { NULL };
 
 	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+
+	spin_lock_bh(&br->lock);
+
+	if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY)
+		__br_set_forward_delay(br, BR_MIN_FORWARD_DELAY);
+	else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
+		__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
+
 	if (r == 0) {
 		br->stp_enabled = BR_USER_STP;
 		br_debug(br, "userspace STP started\n");
@@ -137,10 +145,10 @@ static void br_stp_start(struct net_bridge *br)
 		br_debug(br, "using kernel STP\n");
 
 		/* To start timers on any ports left in blocking */
-		spin_lock_bh(&br->lock);
 		br_port_state_selection(br);
-		spin_unlock_bh(&br->lock);
 	}
+
+	spin_unlock_bh(&br->lock);
 }
 
 static void br_stp_stop(struct net_bridge *br)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 9a9ffe7e4019..d8deb8bda736 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -202,7 +202,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	 * rejected.
 	 */
 	if (!v)
-		return false;
+		goto drop;
 
 	if (br_vlan_get_tag(skb, vid)) {
 		u16 pvid = br_get_pvid(v);
@@ -212,7 +212,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		 * traffic belongs to.
 		 */
 		if (pvid == VLAN_N_VID)
-			return false;
+			goto drop;
 
 		/* PVID is set on this port.  Any untagged ingress
 		 * frame is considered to belong to this vlan.
@@ -224,7 +224,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	/* Frame had a valid vlan tag.  See if vlan is allowed */
 	if (test_bit(*vid, v->vlan_bitmap))
 		return true;
-
+drop:
+	kfree_skb(skb);
 	return false;
 }
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 3d110c4fc787..6651a7797d46 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1044,10 +1044,9 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 	if (repl->num_counters &&
 	   copy_to_user(repl->counters, counterstmp,
 	   repl->num_counters * sizeof(struct ebt_counter))) {
-		ret = -EFAULT;
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n");
 	}
-	else
-		ret = 0;
 
 	/* decrease module count and free resources */
 	EBT_ENTRY_ITERATE(table->entries, table->entries_size,
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 05a41c7ec304..d6be3edb7a43 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -286,8 +286,6 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (m->msg_flags&MSG_OOB)
 		goto read_error;
 
-	m->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
 	if (!skb)
 		goto read_error;
@@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	/*
 	 * Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c
index 2bd4b58f4372..0f455227da83 100644
--- a/net/caif/cfctrl.c
+++ b/net/caif/cfctrl.c
@@ -293,9 +293,10 @@ int cfctrl_linkup_request(struct cflayer *layer,
 
 		count = cfctrl_cancel_req(&cfctrl->serv.layer,
 						user_layer);
-		if (count != 1)
+		if (count != 1) {
 			pr_err("Could not remove request (%d)", count);
 			return -ENODEV;
+		}
 	}
 	return 0;
 }
diff --git a/net/can/af_can.c b/net/can/af_can.c
index c4e50852c9f4..f59859a3f562 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
 #include <linux/skbuff.h>
 #include <linux/can.h>
 #include <linux/can/core.h>
+#include <linux/can/skb.h>
 #include <linux/ratelimit.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -290,7 +291,7 @@ int can_send(struct sk_buff *skb, int loop)
 				return -ENOMEM;
 			}
 
-			newskb->sk = skb->sk;
+			can_skb_set_owner(newskb, skb->sk);
 			newskb->ip_summed = CHECKSUM_UNNECESSARY;
 			newskb->pkt_type = PACKET_BROADCAST;
 		}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8f113e6ff327..35cf02d92766 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op)
 
 	/* send with loopback */
 	skb->dev = dev;
-	skb->sk = op->sk;
+	can_skb_set_owner(skb, op->sk);
 	can_send(skb, 1);
 
 	/* update statistics */
@@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	skb->dev = dev;
-	skb->sk  = sk;
+	can_skb_set_owner(skb, sk);
 	err = can_send(skb, 1); /* send with loopback */
 	dev_put(dev);
 
diff --git a/net/can/gw.c b/net/can/gw.c
index 3ee690e8c7d3..de25455b4e3e 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -784,7 +784,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	struct cgw_job *gwj;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
@@ -876,7 +876,7 @@ static int cgw_remove_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	struct can_can_gw ccgw;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 96238ba95f2b..de6662b14e1f 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -13,8 +13,6 @@
 #include "auth_x.h"
 #include "auth_x_protocol.h"
 
-#define TEMP_TICKET_BUF_LEN	256
-
 static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
 
 static int ceph_x_is_authenticated(struct ceph_auth_client *ac)
@@ -64,7 +62,7 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret,
 }
 
 static int ceph_x_decrypt(struct ceph_crypto_key *secret,
-			  void **p, void *end, void *obuf, size_t olen)
+			  void **p, void *end, void **obuf, size_t olen)
 {
 	struct ceph_x_encrypt_header head;
 	size_t head_len = sizeof(head);
@@ -75,8 +73,14 @@ static int ceph_x_decrypt(struct ceph_crypto_key *secret,
 		return -EINVAL;
 
 	dout("ceph_x_decrypt len %d\n", len);
-	ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen,
-			    *p, len);
+	if (*obuf == NULL) {
+		*obuf = kmalloc(len, GFP_NOFS);
+		if (!*obuf)
+			return -ENOMEM;
+		olen = len;
+	}
+
+	ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len);
 	if (ret)
 		return ret;
 	if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC)
@@ -129,139 +133,120 @@ static void remove_ticket_handler(struct ceph_auth_client *ac,
 	kfree(th);
 }
 
-static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
-				    struct ceph_crypto_key *secret,
-				    void *buf, void *end)
+static int process_one_ticket(struct ceph_auth_client *ac,
+			      struct ceph_crypto_key *secret,
+			      void **p, void *end)
 {
 	struct ceph_x_info *xi = ac->private;
-	int num;
-	void *p = buf;
+	int type;
+	u8 tkt_struct_v, blob_struct_v;
+	struct ceph_x_ticket_handler *th;
+	void *dbuf = NULL;
+	void *dp, *dend;
+	int dlen;
+	char is_enc;
+	struct timespec validity;
+	struct ceph_crypto_key old_key;
+	void *ticket_buf = NULL;
+	void *tp, *tpend;
+	struct ceph_timespec new_validity;
+	struct ceph_crypto_key new_session_key;
+	struct ceph_buffer *new_ticket_blob;
+	unsigned long new_expires, new_renew_after;
+	u64 new_secret_id;
 	int ret;
-	char *dbuf;
-	char *ticket_buf;
-	u8 reply_struct_v;
 
-	dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
-	if (!dbuf)
-		return -ENOMEM;
+	ceph_decode_need(p, end, sizeof(u32) + 1, bad);
 
-	ret = -ENOMEM;
-	ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
-	if (!ticket_buf)
-		goto out_dbuf;
+	type = ceph_decode_32(p);
+	dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
 
-	ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
-	reply_struct_v = ceph_decode_8(&p);
-	if (reply_struct_v != 1)
+	tkt_struct_v = ceph_decode_8(p);
+	if (tkt_struct_v != 1)
 		goto bad;
-	num = ceph_decode_32(&p);
-	dout("%d tickets\n", num);
-	while (num--) {
-		int type;
-		u8 tkt_struct_v, blob_struct_v;
-		struct ceph_x_ticket_handler *th;
-		void *dp, *dend;
-		int dlen;
-		char is_enc;
-		struct timespec validity;
-		struct ceph_crypto_key old_key;
-		void *tp, *tpend;
-		struct ceph_timespec new_validity;
-		struct ceph_crypto_key new_session_key;
-		struct ceph_buffer *new_ticket_blob;
-		unsigned long new_expires, new_renew_after;
-		u64 new_secret_id;
-
-		ceph_decode_need(&p, end, sizeof(u32) + 1, bad);
-
-		type = ceph_decode_32(&p);
-		dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
-
-		tkt_struct_v = ceph_decode_8(&p);
-		if (tkt_struct_v != 1)
-			goto bad;
-
-		th = get_ticket_handler(ac, type);
-		if (IS_ERR(th)) {
-			ret = PTR_ERR(th);
-			goto out;
-		}
 
-		/* blob for me */
-		dlen = ceph_x_decrypt(secret, &p, end, dbuf,
-				      TEMP_TICKET_BUF_LEN);
-		if (dlen <= 0) {
-			ret = dlen;
-			goto out;
-		}
-		dout(" decrypted %d bytes\n", dlen);
-		dend = dbuf + dlen;
-		dp = dbuf;
+	th = get_ticket_handler(ac, type);
+	if (IS_ERR(th)) {
+		ret = PTR_ERR(th);
+		goto out;
+	}
 
-		tkt_struct_v = ceph_decode_8(&dp);
-		if (tkt_struct_v != 1)
-			goto bad;
+	/* blob for me */
+	dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0);
+	if (dlen <= 0) {
+		ret = dlen;
+		goto out;
+	}
+	dout(" decrypted %d bytes\n", dlen);
+	dp = dbuf;
+	dend = dp + dlen;
 
-		memcpy(&old_key, &th->session_key, sizeof(old_key));
-		ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
-		if (ret)
-			goto out;
+	tkt_struct_v = ceph_decode_8(&dp);
+	if (tkt_struct_v != 1)
+		goto bad;
 
-		ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
-		ceph_decode_timespec(&validity, &new_validity);
-		new_expires = get_seconds() + validity.tv_sec;
-		new_renew_after = new_expires - (validity.tv_sec / 4);
-		dout(" expires=%lu renew_after=%lu\n", new_expires,
-		     new_renew_after);
+	memcpy(&old_key, &th->session_key, sizeof(old_key));
+	ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
+	if (ret)
+		goto out;
 
-		/* ticket blob for service */
-		ceph_decode_8_safe(&p, end, is_enc, bad);
-		tp = ticket_buf;
-		if (is_enc) {
-			/* encrypted */
-			dout(" encrypted ticket\n");
-			dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf,
-					      TEMP_TICKET_BUF_LEN);
-			if (dlen < 0) {
-				ret = dlen;
-				goto out;
-			}
-			dlen = ceph_decode_32(&tp);
-		} else {
-			/* unencrypted */
-			ceph_decode_32_safe(&p, end, dlen, bad);
-			ceph_decode_need(&p, end, dlen, bad);
-			ceph_decode_copy(&p, ticket_buf, dlen);
+	ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
+	ceph_decode_timespec(&validity, &new_validity);
+	new_expires = get_seconds() + validity.tv_sec;
+	new_renew_after = new_expires - (validity.tv_sec / 4);
+	dout(" expires=%lu renew_after=%lu\n", new_expires,
+	     new_renew_after);
+
+	/* ticket blob for service */
+	ceph_decode_8_safe(p, end, is_enc, bad);
+	if (is_enc) {
+		/* encrypted */
+		dout(" encrypted ticket\n");
+		dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0);
+		if (dlen < 0) {
+			ret = dlen;
+			goto out;
 		}
-		tpend = tp + dlen;
-		dout(" ticket blob is %d bytes\n", dlen);
-		ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
-		blob_struct_v = ceph_decode_8(&tp);
-		new_secret_id = ceph_decode_64(&tp);
-		ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
-		if (ret)
+		tp = ticket_buf;
+		dlen = ceph_decode_32(&tp);
+	} else {
+		/* unencrypted */
+		ceph_decode_32_safe(p, end, dlen, bad);
+		ticket_buf = kmalloc(dlen, GFP_NOFS);
+		if (!ticket_buf) {
+			ret = -ENOMEM;
 			goto out;
-
-		/* all is well, update our ticket */
-		ceph_crypto_key_destroy(&th->session_key);
-		if (th->ticket_blob)
-			ceph_buffer_put(th->ticket_blob);
-		th->session_key = new_session_key;
-		th->ticket_blob = new_ticket_blob;
-		th->validity = new_validity;
-		th->secret_id = new_secret_id;
-		th->expires = new_expires;
-		th->renew_after = new_renew_after;
-		dout(" got ticket service %d (%s) secret_id %lld len %d\n",
-		     type, ceph_entity_type_name(type), th->secret_id,
-		     (int)th->ticket_blob->vec.iov_len);
-		xi->have_keys |= th->service;
+		}
+		tp = ticket_buf;
+		ceph_decode_need(p, end, dlen, bad);
+		ceph_decode_copy(p, ticket_buf, dlen);
 	}
+	tpend = tp + dlen;
+	dout(" ticket blob is %d bytes\n", dlen);
+	ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
+	blob_struct_v = ceph_decode_8(&tp);
+	new_secret_id = ceph_decode_64(&tp);
+	ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
+	if (ret)
+		goto out;
+
+	/* all is well, update our ticket */
+	ceph_crypto_key_destroy(&th->session_key);
+	if (th->ticket_blob)
+		ceph_buffer_put(th->ticket_blob);
+	th->session_key = new_session_key;
+	th->ticket_blob = new_ticket_blob;
+	th->validity = new_validity;
+	th->secret_id = new_secret_id;
+	th->expires = new_expires;
+	th->renew_after = new_renew_after;
+	dout(" got ticket service %d (%s) secret_id %lld len %d\n",
+	     type, ceph_entity_type_name(type), th->secret_id,
+	     (int)th->ticket_blob->vec.iov_len);
+	xi->have_keys |= th->service;
 
-	ret = 0;
 out:
 	kfree(ticket_buf);
-out_dbuf:
 	kfree(dbuf);
 	return ret;
 
@@ -270,6 +255,34 @@ bad:
 	goto out;
 }
 
+static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
+				    struct ceph_crypto_key *secret,
+				    void *buf, void *end)
+{
+	void *p = buf;
+	u8 reply_struct_v;
+	u32 num;
+	int ret;
+
+	ceph_decode_8_safe(&p, end, reply_struct_v, bad);
+	if (reply_struct_v != 1)
+		return -EINVAL;
+
+	ceph_decode_32_safe(&p, end, num, bad);
+	dout("%d tickets\n", num);
+
+	while (num--) {
+		ret = process_one_ticket(ac, secret, &p, end);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
 static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 				   struct ceph_x_ticket_handler *th,
 				   struct ceph_x_authorizer *au)
@@ -583,13 +596,14 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
 	struct ceph_x_ticket_handler *th;
 	int ret = 0;
 	struct ceph_x_authorize_reply reply;
+	void *preply = &reply;
 	void *p = au->reply_buf;
 	void *end = p + sizeof(au->reply_buf);
 
 	th = get_ticket_handler(ac, au->service);
 	if (IS_ERR(th))
 		return PTR_ERR(th);
-	ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply));
+	ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply));
 	if (ret < 0)
 		return ret;
 	if (ret != sizeof(reply))
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 6e7a236525b6..06f19b9e159a 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
 
 static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
 
+/*
+ * Should be used for buffers allocated with ceph_kvmalloc().
+ * Currently these are encrypt out-buffer (ceph_buffer) and decrypt
+ * in-buffer (msg front).
+ *
+ * Dispose of @sgt with teardown_sgtable().
+ *
+ * @prealloc_sg is to avoid memory allocation inside sg_alloc_table()
+ * in cases where a single sg is sufficient.  No attempt to reduce the
+ * number of sgs by squeezing physically contiguous pages together is
+ * made though, for simplicity.
+ */
+static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg,
+			 const void *buf, unsigned int buf_len)
+{
+	struct scatterlist *sg;
+	const bool is_vmalloc = is_vmalloc_addr(buf);
+	unsigned int off = offset_in_page(buf);
+	unsigned int chunk_cnt = 1;
+	unsigned int chunk_len = PAGE_ALIGN(off + buf_len);
+	int i;
+	int ret;
+
+	if (buf_len == 0) {
+		memset(sgt, 0, sizeof(*sgt));
+		return -EINVAL;
+	}
+
+	if (is_vmalloc) {
+		chunk_cnt = chunk_len >> PAGE_SHIFT;
+		chunk_len = PAGE_SIZE;
+	}
+
+	if (chunk_cnt > 1) {
+		ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS);
+		if (ret)
+			return ret;
+	} else {
+		WARN_ON(chunk_cnt != 1);
+		sg_init_table(prealloc_sg, 1);
+		sgt->sgl = prealloc_sg;
+		sgt->nents = sgt->orig_nents = 1;
+	}
+
+	for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) {
+		struct page *page;
+		unsigned int len = min(chunk_len - off, buf_len);
+
+		if (is_vmalloc)
+			page = vmalloc_to_page(buf);
+		else
+			page = virt_to_page(buf);
+
+		sg_set_page(sg, page, len, off);
+
+		off = 0;
+		buf += len;
+		buf_len -= len;
+	}
+	WARN_ON(buf_len != 0);
+
+	return 0;
+}
+
+static void teardown_sgtable(struct sg_table *sgt)
+{
+	if (sgt->orig_nents > 1)
+		sg_free_table(sgt);
+}
+
 static int ceph_aes_encrypt(const void *key, int key_len,
 			    void *dst, size_t *dst_len,
 			    const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[2], sg_out[1];
+	struct scatterlist sg_in[2], prealloc_sg;
+	struct sg_table sg_out;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
 	int ret;
@@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 
 	*dst_len = src_len + zero_padding;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	sg_init_table(sg_in, 2);
 	sg_set_buf(&sg_in[0], src, src_len);
 	sg_set_buf(&sg_in[1], pad, zero_padding);
-	sg_init_table(sg_out, 1);
-	sg_set_buf(sg_out, dst, *dst_len);
+	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+	if (ret)
+		goto out_tfm;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
+
 	/*
 	print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
 		       key, key_len, 1);
@@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
 				     src_len + zero_padding);
-	crypto_free_blkcipher(tfm);
-	if (ret < 0)
+	if (ret < 0) {
 		pr_err("ceph_aes_crypt failed %d\n", ret);
+		goto out_sg;
+	}
 	/*
 	print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_out);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
@@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 			     const void *src1, size_t src1_len,
 			     const void *src2, size_t src2_len)
 {
-	struct scatterlist sg_in[3], sg_out[1];
+	struct scatterlist sg_in[3], prealloc_sg;
+	struct sg_table sg_out;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
 	int ret;
@@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 
 	*dst_len = src1_len + src2_len + zero_padding;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	sg_init_table(sg_in, 3);
 	sg_set_buf(&sg_in[0], src1, src1_len);
 	sg_set_buf(&sg_in[1], src2, src2_len);
 	sg_set_buf(&sg_in[2], pad, zero_padding);
-	sg_init_table(sg_out, 1);
-	sg_set_buf(sg_out, dst, *dst_len);
+	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+	if (ret)
+		goto out_tfm;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
+
 	/*
 	print_hex_dump(KERN_ERR, "enc  key: ", DUMP_PREFIX_NONE, 16, 1,
 		       key, key_len, 1);
@@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 	print_hex_dump(KERN_ERR, "enc  pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
 				     src1_len + src2_len + zero_padding);
-	crypto_free_blkcipher(tfm);
-	if (ret < 0)
+	if (ret < 0) {
 		pr_err("ceph_aes_crypt2 failed %d\n", ret);
+		goto out_sg;
+	}
 	/*
 	print_hex_dump(KERN_ERR, "enc  out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_out);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_decrypt(const void *key, int key_len,
 			    void *dst, size_t *dst_len,
 			    const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[1], sg_out[2];
+	struct sg_table sg_in;
+	struct scatterlist sg_out[2], prealloc_sg;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm };
 	char pad[16];
@@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	sg_init_table(sg_in, 1);
 	sg_init_table(sg_out, 2);
-	sg_set_buf(sg_in, src, src_len);
 	sg_set_buf(&sg_out[0], dst, *dst_len);
 	sg_set_buf(&sg_out[1], pad, sizeof(pad));
+	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+	if (ret)
+		goto out_tfm;
 
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
 
 	/*
@@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec  in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
-	crypto_free_blkcipher(tfm);
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		return ret;
+		goto out_sg;
 	}
 
 	if (src_len <= *dst_len)
@@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_in);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_decrypt2(const void *key, int key_len,
@@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 			     void *dst2, size_t *dst2_len,
 			     const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[1], sg_out[3];
+	struct sg_table sg_in;
+	struct scatterlist sg_out[3], prealloc_sg;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm };
 	char pad[16];
@@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	sg_init_table(sg_in, 1);
-	sg_set_buf(sg_in, src, src_len);
 	sg_init_table(sg_out, 3);
 	sg_set_buf(&sg_out[0], dst1, *dst1_len);
 	sg_set_buf(&sg_out[1], dst2, *dst2_len);
 	sg_set_buf(&sg_out[2], pad, sizeof(pad));
+	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+	if (ret)
+		goto out_tfm;
 
 	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
 
 	/*
@@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec   in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
-	crypto_free_blkcipher(tfm);
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		return ret;
+		goto out_sg;
 	}
 
 	if (src_len <= *dst1_len)
@@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 		       dst2, *dst2_len, 1);
 	*/
 
-	return 0;
+out_sg:
+	teardown_sgtable(&sg_in);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index eb0a46a49bd4..e3bea2e0821a 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -290,7 +290,8 @@ int ceph_msgr_init(void)
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
 
-	ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0);
+	ceph_msgr_wq = alloc_workqueue("ceph-msgr",
+				       WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
 	if (ceph_msgr_wq)
 		return 0;
 
@@ -556,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
 	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -569,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	return ret;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, bool more)
+{
+	int ret;
+	struct kvec iov;
+
+	/* sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fallback to sendmsg if that's the case */
+	if (page_count(page) >= 1)
+		return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+	iov.iov_base = kmap(page) + offset;
+	iov.iov_len = size;
+	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+	kunmap(page);
+
+	return ret;
+}
 
 /*
  * Shutdown/close the socket for the given connection.
@@ -886,7 +905,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor,
 	BUG_ON(page_count > (int)USHRT_MAX);
 	cursor->page_count = (unsigned short)page_count;
 	BUG_ON(length > SIZE_MAX - cursor->page_offset);
-	cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE;
+	cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE;
 }
 
 static struct page *
@@ -3126,7 +3145,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	INIT_LIST_HEAD(&m->data);
 
 	/* front */
-	m->front_max = front_len;
+	m->front_alloc_len = front_len;
 	if (front_len) {
 		if (front_len > PAGE_CACHE_SIZE) {
 			m->front.iov_base = __vmalloc(front_len, flags,
@@ -3301,8 +3320,8 @@ EXPORT_SYMBOL(ceph_msg_last_put);
 
 void ceph_msg_dump(struct ceph_msg *msg)
 {
-	pr_debug("msg_dump %p (front_max %d length %zd)\n", msg,
-		 msg->front_max, msg->data_length);
+	pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg,
+		 msg->front_alloc_len, msg->data_length);
 	print_hex_dump(KERN_DEBUG, "header: ",
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       &msg->hdr, sizeof(msg->hdr), true);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 1fe25cd29d0e..dbcbf5a4707f 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -152,7 +152,7 @@ static int __open_session(struct ceph_mon_client *monc)
 		/* initiatiate authentication handshake */
 		ret = ceph_auth_build_hello(monc->auth,
 					    monc->m_auth->front.iov_base,
-					    monc->m_auth->front_max);
+					    monc->m_auth->front_alloc_len);
 		__send_prepared_auth_request(monc, ret);
 	} else {
 		dout("open_session mon%d already open\n", monc->cur_mon);
@@ -196,7 +196,7 @@ static void __send_subscribe(struct ceph_mon_client *monc)
 		int num;
 
 		p = msg->front.iov_base;
-		end = p + msg->front_max;
+		end = p + msg->front_alloc_len;
 
 		num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
 		ceph_encode_32(&p, num);
@@ -897,7 +897,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
 				     msg->front.iov_len,
 				     monc->m_auth->front.iov_base,
-				     monc->m_auth->front_max);
+				     monc->m_auth->front_alloc_len);
 	if (ret < 0) {
 		monc->client->auth_err = ret;
 		wake_up_all(&monc->client->auth_wq);
@@ -939,7 +939,7 @@ static int __validate_auth(struct ceph_mon_client *monc)
 		return 0;
 
 	ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base,
-			      monc->m_auth->front_max);
+			      monc->m_auth->front_alloc_len);
 	if (ret <= 0)
 		return ret; /* either an error, or no need to authenticate */
 	__send_prepared_auth_request(monc, ret);
@@ -1041,7 +1041,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	if (!m) {
 		pr_info("alloc_msg unknown type %d\n", type);
 		*skip = 1;
+	} else if (front_len > m->front_alloc_len) {
+		pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n",
+			   front_len, m->front_alloc_len,
+			   (unsigned int)con->peer_name.type,
+			   le64_to_cpu(con->peer_name.num));
+		ceph_msg_put(m);
+		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
 	}
+
 	return m;
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 46ec7672cccc..3663a305daf7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -733,12 +733,14 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 
 	object_size = le32_to_cpu(layout->fl_object_size);
 	object_base = off - objoff;
-	if (truncate_size <= object_base) {
-		truncate_size = 0;
-	} else {
-		truncate_size -= object_base;
-		if (truncate_size > object_size)
-			truncate_size = object_size;
+	if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
+		if (truncate_size <= object_base) {
+			truncate_size = 0;
+		} else {
+			truncate_size -= object_base;
+			if (truncate_size > object_size)
+				truncate_size = object_size;
+		}
 	}
 
 	osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
@@ -1174,6 +1176,7 @@ static void __register_linger_request(struct ceph_osd_client *osdc,
 				    struct ceph_osd_request *req)
 {
 	dout("__register_linger_request %p\n", req);
+	ceph_osdc_get_request(req);
 	list_add_tail(&req->r_linger_item, &osdc->req_linger);
 	if (req->r_osd)
 		list_add_tail(&req->r_linger_osd,
@@ -1196,6 +1199,7 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc,
 		if (list_empty(&req->r_osd_item))
 			req->r_osd = NULL;
 	}
+	ceph_osdc_put_request(req);
 }
 
 void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,
@@ -1203,9 +1207,8 @@ void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,
 {
 	mutex_lock(&osdc->request_mutex);
 	if (req->r_linger) {
-		__unregister_linger_request(osdc, req);
 		req->r_linger = 0;
-		ceph_osdc_put_request(req);
+		__unregister_linger_request(osdc, req);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1217,16 +1220,27 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
 	if (!req->r_linger) {
 		dout("set_request_linger %p\n", req);
 		req->r_linger = 1;
-		/*
-		 * caller is now responsible for calling
-		 * unregister_linger_request
-		 */
-		ceph_osdc_get_request(req);
 	}
 }
 EXPORT_SYMBOL(ceph_osdc_set_request_linger);
 
 /*
+ * Returns whether a request should be blocked from being sent
+ * based on the current osdmap and osd_client settings.
+ *
+ * Caller should hold map_sem for read.
+ */
+static bool __req_should_be_paused(struct ceph_osd_client *osdc,
+				   struct ceph_osd_request *req)
+{
+	bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
+	bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) ||
+		(req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr);
+}
+
+/*
  * Pick an osd (the first 'up' osd in the pg), allocate the osd struct
  * (as needed), and set the request r_osd appropriately.  If there is
  * no up osd, set r_osd to NULL.  Move the request to the appropriate list
@@ -1243,6 +1257,7 @@ static int __map_request(struct ceph_osd_client *osdc,
 	int acting[CEPH_PG_MAX_SIZE];
 	int o = -1, num = 0;
 	int err;
+	bool was_paused;
 
 	dout("map_request %p tid %lld\n", req, req->r_tid);
 	err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap,
@@ -1259,12 +1274,18 @@ static int __map_request(struct ceph_osd_client *osdc,
 		num = err;
 	}
 
+	was_paused = req->r_paused;
+	req->r_paused = __req_should_be_paused(osdc, req);
+	if (was_paused && !req->r_paused)
+		force_resend = 1;
+
 	if ((!force_resend &&
 	     req->r_osd && req->r_osd->o_osd == o &&
 	     req->r_sent >= req->r_osd->o_incarnation &&
 	     req->r_num_pg_osds == num &&
 	     memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
-	    (req->r_osd == NULL && o == -1))
+	    (req->r_osd == NULL && o == -1) ||
+	    req->r_paused)
 		return 0;  /* no change */
 
 	dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n",
@@ -1339,10 +1360,6 @@ static void __send_request(struct ceph_osd_client *osdc,
 
 	ceph_msg_get(req->r_request); /* send consumes a ref */
 
-	/* Mark the request unsafe if this is the first timet's being sent. */
-
-	if (!req->r_sent && req->r_unsafe_callback)
-		req->r_unsafe_callback(req, true);
 	req->r_sent = req->r_osd->o_incarnation;
 
 	ceph_con_send(&req->r_osd->o_con, req->r_request);
@@ -1433,8 +1450,6 @@ static void handle_osds_timeout(struct work_struct *work)
 
 static void complete_request(struct ceph_osd_request *req)
 {
-	if (req->r_unsafe_callback)
-		req->r_unsafe_callback(req, false);
 	complete_all(&req->r_safe_completion);  /* fsync waiter */
 }
 
@@ -1496,14 +1511,14 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	dout("handle_reply %p tid %llu req %p result %d\n", msg, tid,
 	     req, result);
 
-	ceph_decode_need(&p, end, 4, bad);
+	ceph_decode_need(&p, end, 4, bad_put);
 	numops = ceph_decode_32(&p);
 	if (numops > CEPH_OSD_MAX_OP)
 		goto bad_put;
 	if (numops != req->r_num_ops)
 		goto bad_put;
 	payload_len = 0;
-	ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad);
+	ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad_put);
 	for (i = 0; i < numops; i++) {
 		struct ceph_osd_op *op = p;
 		int len;
@@ -1521,11 +1536,13 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 		goto bad_put;
 	}
 
-	ceph_decode_need(&p, end, 4 + numops * 4, bad);
+	ceph_decode_need(&p, end, 4 + numops * 4, bad_put);
 	retry_attempt = ceph_decode_32(&p);
 	for (i = 0; i < numops; i++)
 		req->r_reply_op_result[i] = ceph_decode_32(&p);
 
+	already_completed = req->r_got_reply;
+
 	if (!req->r_got_reply) {
 
 		req->r_result = result;
@@ -1556,19 +1573,23 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	    ((flags & CEPH_OSD_FLAG_WRITE) == 0))
 		__unregister_request(osdc, req);
 
-	already_completed = req->r_completed;
-	req->r_completed = 1;
 	mutex_unlock(&osdc->request_mutex);
-	if (already_completed)
-		goto done;
 
-	if (req->r_callback)
-		req->r_callback(req, msg);
-	else
-		complete_all(&req->r_completion);
+	if (!already_completed) {
+		if (req->r_unsafe_callback &&
+		    result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK))
+			req->r_unsafe_callback(req, true);
+		if (req->r_callback)
+			req->r_callback(req, msg);
+		else
+			complete_all(&req->r_completion);
+	}
 
-	if (flags & CEPH_OSD_FLAG_ONDISK)
+	if (flags & CEPH_OSD_FLAG_ONDISK) {
+		if (req->r_unsafe_callback && already_completed)
+			req->r_unsafe_callback(req, false);
 		complete_request(req);
+	}
 
 done:
 	dout("req=%p req->r_linger=%d\n", req, req->r_linger);
@@ -1608,14 +1629,17 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
  *
  * Caller should hold map_sem for read.
  */
-static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
+static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
+			  bool force_resend_writes)
 {
 	struct ceph_osd_request *req, *nreq;
 	struct rb_node *p;
 	int needmap = 0;
 	int err;
+	bool force_resend_req;
 
-	dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
+	dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "",
+		force_resend_writes ? " (force resend writes)" : "");
 	mutex_lock(&osdc->request_mutex);
 	for (p = rb_first(&osdc->requests); p; ) {
 		req = rb_entry(p, struct ceph_osd_request, r_node);
@@ -1633,12 +1657,17 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 			dout("%p tid %llu restart on osd%d\n",
 			     req, req->r_tid,
 			     req->r_osd ? req->r_osd->o_osd : -1);
+			ceph_osdc_get_request(req);
 			__unregister_request(osdc, req);
 			__register_linger_request(osdc, req);
+			ceph_osdc_put_request(req);
 			continue;
 		}
 
-		err = __map_request(osdc, req, force_resend);
+		force_resend_req = force_resend ||
+			(force_resend_writes &&
+				req->r_flags & CEPH_OSD_FLAG_WRITE);
+		err = __map_request(osdc, req, force_resend_req);
 		if (err < 0)
 			continue;  /* error */
 		if (req->r_osd == NULL) {
@@ -1658,7 +1687,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 				 r_linger_item) {
 		dout("linger req=%p req->r_osd=%p\n", req, req->r_osd);
 
-		err = __map_request(osdc, req, force_resend);
+		err = __map_request(osdc, req,
+				    force_resend || force_resend_writes);
 		dout("__map_request returned %d\n", err);
 		if (err == 0)
 			continue;  /* no change and no osd was specified */
@@ -1700,6 +1730,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	struct ceph_osdmap *newmap = NULL, *oldmap;
 	int err;
 	struct ceph_fsid fsid;
+	bool was_full;
 
 	dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0);
 	p = msg->front.iov_base;
@@ -1713,6 +1744,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 
 	down_write(&osdc->map_sem);
 
+	was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+
 	/* incremental maps */
 	ceph_decode_32_safe(&p, end, nr_maps, bad);
 	dout(" %d inc maps\n", nr_maps);
@@ -1737,7 +1770,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 				ceph_osdmap_destroy(osdc->osdmap);
 				osdc->osdmap = newmap;
 			}
-			kick_requests(osdc, 0);
+			was_full = was_full ||
+				ceph_osdmap_flag(osdc->osdmap,
+						 CEPH_OSDMAP_FULL);
+			kick_requests(osdc, 0, was_full);
 		} else {
 			dout("ignoring incremental map %u len %d\n",
 			     epoch, maplen);
@@ -1780,12 +1816,17 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 					skipped_map = 1;
 				ceph_osdmap_destroy(oldmap);
 			}
-			kick_requests(osdc, skipped_map);
+			was_full = was_full ||
+				ceph_osdmap_flag(osdc->osdmap,
+						 CEPH_OSDMAP_FULL);
+			kick_requests(osdc, skipped_map, was_full);
 		}
 		p += maplen;
 		nr_maps--;
 	}
 
+	if (!osdc->osdmap)
+		goto bad;
 done:
 	downgrade_write(&osdc->map_sem);
 	ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch);
@@ -1795,7 +1836,9 @@ done:
 	 * we find out when we are no longer full and stop returning
 	 * ENOSPC.
 	 */
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
+	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR))
 		ceph_monc_request_next_osdmap(&osdc->client->monc);
 
 	mutex_lock(&osdc->request_mutex);
@@ -2123,7 +2166,6 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 	__register_request(osdc, req);
 	req->r_sent = 0;
 	req->r_got_reply = 0;
-	req->r_completed = 0;
 	rc = __map_request(osdc, req, 0);
 	if (rc < 0) {
 		if (nofail) {
@@ -2208,6 +2250,17 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc)
 EXPORT_SYMBOL(ceph_osdc_sync);
 
 /*
+ * Call all pending notify callbacks - for use after a watch is
+ * unregistered, to make sure no more callbacks for it will be invoked
+ */
+extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
+{
+	flush_workqueue(osdc->notify_wq);
+}
+EXPORT_SYMBOL(ceph_osdc_flush_notifies);
+
+
+/*
  * init, shutdown
  */
 int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
@@ -2256,12 +2309,10 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 	if (err < 0)
 		goto out_msgpool;
 
+	err = -ENOMEM;
 	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
-	if (IS_ERR(osdc->notify_wq)) {
-		err = PTR_ERR(osdc->notify_wq);
-		osdc->notify_wq = NULL;
+	if (!osdc->notify_wq)
 		goto out_msgpool;
-	}
 	return 0;
 
 out_msgpool:
diff --git a/net/compat.c b/net/compat.c
index f0a1ba6c8086..cbc1a2a26587 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
+	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	kmsg->msg_name = compat_ptr(tmp1);
 	kmsg->msg_iov = compat_ptr(tmp2);
 	kmsg->msg_control = compat_ptr(tmp3);
@@ -83,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 {
 	int tot_len;
 
-	if (kern_msg->msg_namelen) {
+	if (kern_msg->msg_name && kern_msg->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
@@ -92,8 +94,10 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 				return err;
 		}
 		kern_msg->msg_name = kern_address;
-	} else
+	} else {
 		kern_msg->msg_name = NULL;
+		kern_msg->msg_namelen = 0;
+	}
 
 	tot_len = iov_from_user_compat_to_kern(kern_iov,
 					  (struct compat_iovec __user *)kern_msg->msg_iov,
@@ -777,21 +781,16 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 
-	if (COMPAT_USE_64BIT_TIME)
-		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
-				      flags | MSG_CMSG_COMPAT,
-				      (struct timespec *) timeout);
-
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
 
-	if (get_compat_timespec(&ktspec, timeout))
+	if (compat_get_timespec(&ktspec, timeout))
 		return -EFAULT;
 
 	datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				   flags | MSG_CMSG_COMPAT, &ktspec);
-	if (datagrams > 0 && put_compat_timespec(&ktspec, timeout))
+	if (datagrams > 0 && compat_put_timespec(&ktspec, timeout))
 		datagrams = -EFAULT;
 
 	return datagrams;
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ddbb31b10d3..cca7ae0ba915 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2374,7 +2374,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
 	int i;
@@ -2454,46 +2454,51 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-	__be16 protocol, netdev_features_t features)
+					    __be16 protocol,
+					    const struct net_device *dev,
+					    netdev_features_t features)
 {
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(skb->dev, skb)) {
+	} else if (illegal_highdma(dev, skb)) {
 		features &= ~NETIF_F_SG;
 	}
 
 	return features;
 }
 
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev)
 {
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = skb->dev->features;
+	netdev_features_t features = dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	}
 
-	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
 					       NETIF_F_HW_VLAN_STAG_TX);
 
 	if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) {
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	} else {
 		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
 				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_STAG_TX;
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	}
+
+	return harmonize_features(skb, protocol, dev, features);
 }
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
 
 /*
  * Returns true if either:
@@ -3893,6 +3898,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
 }
@@ -4478,7 +4484,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
-	if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+	if (ops->ndo_change_rx_flags)
 		ops->ndo_change_rx_flags(dev, flags);
 }
 
@@ -4629,6 +4635,7 @@ void __dev_set_rx_mode(struct net_device *dev)
 	if (ops->ndo_set_rx_mode)
 		ops->ndo_set_rx_mode(dev);
 }
+EXPORT_SYMBOL(__dev_set_rx_mode);
 
 void dev_set_rx_mode(struct net_device *dev)
 {
@@ -5820,6 +5827,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -5829,6 +5839,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -6245,7 +6256,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }
 
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index d23b6682f4e9..a974dfec4bf1 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = {
 	.hdrsize        = 0,
 	.name           = "NET_DM",
 	.version        = 2,
-	.maxattr        = NET_DM_CMD_MAX,
 };
 
 static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
diff --git a/net/core/dst.c b/net/core/dst.c
index df9cc810ec8e..c0e021871df8 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -267,6 +267,15 @@ again:
 }
 EXPORT_SYMBOL(dst_destroy);
 
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+	dst = dst_destroy(dst);
+	if (dst)
+		__dst_free(dst);
+}
+
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
@@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
-			dst = dst_destroy(dst);
-			if (dst)
-				__dst_free(dst);
-		}
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
 EXPORT_SYMBOL(dst_release);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d5a9f8ead0d8..55e08e2de3a1 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -445,7 +445,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		if (frh->action && (frh->action != rule->action))
 			continue;
 
-		if (frh->table && (frh_get_table(frh, tb) != rule->table))
+		if (frh_get_table(frh, tb) &&
+		    (frh_get_table(frh, tb) != rule->table))
 			continue;
 
 		if (tb[FRA_PRIORITY] &&
@@ -719,6 +720,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event,
 			attach_rules(&ops->rules_list, dev);
 		break;
 
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
+		break;
+
 	case NETDEV_UNREGISTER:
 		list_for_each_entry(ops, &net->rules_ops, list)
 			detach_rules(&ops->rules_list, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index 6438f29ff266..c6c18d8a2d88 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -36,7 +36,6 @@
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
-#include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
@@ -166,7 +165,7 @@ unsigned int sk_run_filter(const struct sk_buff *skb,
 			A /= X;
 			continue;
 		case BPF_S_ALU_DIV_K:
-			A = reciprocal_divide(A, K);
+			A /= K;
 			continue;
 		case BPF_S_ALU_MOD_X:
 			if (X == 0)
@@ -356,6 +355,8 @@ load_b:
 
 			if (skb_is_nonlinear(skb))
 				return 0;
+			if (skb->len < sizeof(struct nlattr))
+				return 0;
 			if (A > skb->len - sizeof(struct nlattr))
 				return 0;
 
@@ -372,11 +373,13 @@ load_b:
 
 			if (skb_is_nonlinear(skb))
 				return 0;
+			if (skb->len < sizeof(struct nlattr))
+				return 0;
 			if (A > skb->len - sizeof(struct nlattr))
 				return 0;
 
 			nla = (struct nlattr *)&skb->data[A];
-			if (nla->nla_len > A - skb->len)
+			if (nla->nla_len > skb->len - A)
 				return 0;
 
 			nla = nla_find_nested(nla, X);
@@ -553,11 +556,6 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 		/* Some instructions need special checks */
 		switch (code) {
 		case BPF_S_ALU_DIV_K:
-			/* check for division by zero */
-			if (ftest->k == 0)
-				return -EINVAL;
-			ftest->k = reciprocal_value(ftest->k);
-			break;
 		case BPF_S_ALU_MOD_K:
 			/* check for division by zero */
 			if (ftest->k == 0)
@@ -853,27 +851,7 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
 	to->code = decodes[code];
 	to->jt = filt->jt;
 	to->jf = filt->jf;
-
-	if (code == BPF_S_ALU_DIV_K) {
-		/*
-		 * When loaded this rule user gave us X, which was
-		 * translated into R = r(X). Now we calculate the
-		 * RR = r(R) and report it back. If next time this
-		 * value is loaded and RRR = r(RR) is calculated
-		 * then the R == RRR will be true.
-		 *
-		 * One exception. X == 1 translates into R == 0 and
-		 * we can't calculate RR out of it with r().
-		 */
-
-		if (filt->k == 0)
-			to->k = 1;
-		else
-			to->k = reciprocal_value(filt->k);
-
-		BUG_ON(reciprocal_value(to->k) != filt->k);
-	} else
-		to->k = filt->k;
+	to->k = filt->k;
 }
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c99cc371bbd7..f97101b4d373 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -40,7 +40,7 @@ again:
 		struct iphdr _iph;
 ip:
 		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-		if (!iph)
+		if (!iph || iph->ihl < 5)
 			return false;
 
 		if (ip_is_fragment(iph))
@@ -149,8 +149,8 @@ ipv6:
 	if (poff >= 0) {
 		__be32 *ports, _ports;
 
-		nhoff += poff;
-		ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
+		ports = skb_header_pointer(skb, nhoff + poff,
+					   sizeof(_ports), &_ports);
 		if (ports)
 			flow->ports = *ports;
 	}
@@ -347,7 +347,7 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 
 		if (queue_index != new_index && sk &&
 		    rcu_access_pointer(sk->sk_dst_cache))
-			sk_tx_queue_set(sk, queue_index);
+			sk_tx_queue_set(sk, new_index);
 
 		queue_index = new_index;
 	}
diff --git a/net/core/iovec.c b/net/core/iovec.c
index de178e462682..1117a26a8548 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 {
 	int size, ct, err;
 
-	if (m->msg_namelen) {
+	if (m->msg_name && m->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			void __user *namep;
 			namep = (void __user __force *) m->msg_name;
@@ -51,6 +51,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 		m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
+		m->msg_namelen = 0;
 	}
 
 	size = m->msg_iovlen * sizeof(struct iovec);
@@ -106,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend);
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len)
 {
+	/* No data? Done! */
+	if (len == 0)
+		return 0;
+
 	/* Skip over the finished iovecs */
 	while (offset >= iov->iov_len) {
 		offset -= iov->iov_len;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 0034b611fa5e..b49e8bafab17 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -764,9 +764,6 @@ static void neigh_periodic_work(struct work_struct *work)
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
-		goto out;
-
 	/*
 	 *	periodically recompute ReachableTime from random function
 	 */
@@ -779,6 +776,9 @@ static void neigh_periodic_work(struct work_struct *work)
 				neigh_rand_reach_time(p->base_reachable_time);
 	}
 
+	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+		goto out;
+
 	for (i = 0 ; i < (1 << nht->hash_shift); i++) {
 		np = &nht->hash_buckets[i];
 
@@ -1274,7 +1274,7 @@ int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
 			    skb->len) < 0 &&
-	    dev->header_ops->rebuild(skb))
+	    dev_rebuild_header(skb))
 		return 0;
 
 	return dev_queue_xmit(skb);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index cec074be8c43..e861438d5454 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -386,8 +386,14 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 					    !vlan_hw_offload_capable(netif_skb_features(skb),
 								     skb->vlan_proto)) {
 						skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
-						if (unlikely(!skb))
-							break;
+						if (unlikely(!skb)) {
+							/* This is actually a packet drop, but we
+							 * don't want the code at the end of this
+							 * function to try and re-queue a NULL skb.
+							 */
+							status = NETDEV_TX_OK;
+							goto unlock_txq;
+						}
 						skb->vlan_tci = 0;
 					}
 
@@ -395,6 +401,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 					if (status == NETDEV_TX_OK)
 						txq_trans_update(txq);
 				}
+			unlock_txq:
 				__netif_tx_unlock(txq);
 
 				if (status == NETDEV_TX_OK)
@@ -550,7 +557,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 		return;
 
 	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto == ETH_P_IP) {
+	if (proto == ETH_P_ARP) {
 		struct arphdr *arp;
 		unsigned char *arp_ptr;
 		/* No arp on this interface */
@@ -738,7 +745,7 @@ static bool pkt_is_ns(struct sk_buff *skb)
 	struct nd_msg *msg;
 	struct ipv6hdr *hdr;
 
-	if (skb->protocol != htons(ETH_P_ARP))
+	if (skb->protocol != htons(ETH_P_IPV6))
 		return false;
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
 		return false;
@@ -941,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 {
 	char *cur=opt, *delim;
 	int ipv6;
+	bool ipversion_set = false;
 
 	if (*cur != '@') {
 		if ((delim = strchr(cur, '@')) == NULL)
@@ -953,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	cur++;
 
 	if (*cur != '/') {
+		ipversion_set = true;
 		if ((delim = strchr(cur, '/')) == NULL)
 			goto parse_failed;
 		*delim = 0;
@@ -995,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
 	if (ipv6 < 0)
 		goto parse_failed;
-	else if (np->ipv6 != (bool)ipv6)
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
 		goto parse_failed;
 	else
 		np->ipv6 = (bool)ipv6;
@@ -1289,15 +1298,14 @@ EXPORT_SYMBOL_GPL(__netpoll_free_async);
 
 void netpoll_cleanup(struct netpoll *np)
 {
-	if (!np->dev)
-		return;
-
 	rtnl_lock();
+	if (!np->dev)
+		goto out;
 	__netpoll_cleanup(np);
-	rtnl_unlock();
-
 	dev_put(np->dev);
 	np->dev = NULL;
+out:
+	rtnl_unlock();
 }
 EXPORT_SYMBOL(netpoll_cleanup);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 11f2704c3810..ebbea5371967 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2515,6 +2515,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
 		if (x) {
 			int ret;
 			__u8 *eth;
+			struct iphdr *iph;
+
 			nhead = x->props.header_len - skb_headroom(skb);
 			if (nhead > 0) {
 				ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
@@ -2536,6 +2538,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
 			eth = (__u8 *) skb_push(skb, ETH_HLEN);
 			memcpy(eth, pkt_dev->hh, 12);
 			*(u16 *) &eth[12] = protocol;
+
+			/* Update IPv4 header len as well as checksum value */
+			iph = ip_hdr(skb);
+			iph->tot_len = htons(skb->len - ETH_HLEN);
+			ip_send_check(iph);
 		}
 	}
 	return 1;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fd01eca52a13..25c4dd563a79 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -714,7 +714,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 		return 0;
 }
 
-static size_t rtnl_port_size(const struct net_device *dev)
+static size_t rtnl_port_size(const struct net_device *dev,
+			     u32 ext_filter_mask)
 {
 	size_t port_size = nla_total_size(4)		/* PORT_VF */
 		+ nla_total_size(PORT_PROFILE_MAX)	/* PORT_PROFILE */
@@ -730,7 +731,8 @@ static size_t rtnl_port_size(const struct net_device *dev)
 	size_t port_self_size = nla_total_size(sizeof(struct nlattr))
 		+ port_size;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 	if (dev_num_vf(dev->dev.parent))
 		return port_self_size + vf_ports_size +
@@ -765,7 +767,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
-	       + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */
 }
@@ -826,11 +828,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
+			  u32 ext_filter_mask)
 {
 	int err;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 
 	err = rtnl_port_self_fill(skb, dev);
@@ -985,7 +989,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		nla_nest_end(skb, vfinfo);
 	}
 
-	if (rtnl_port_fill(skb, dev))
+	if (rtnl_port_fill(skb, dev, ext_filter_mask))
 		goto nla_put_failure;
 
 	if (dev->rtnl_link_ops) {
@@ -1039,6 +1043,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct hlist_head *head;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
+	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
@@ -1046,8 +1052,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1059,11 +1074,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
-			if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq, 0,
-					     NLM_F_MULTI,
-					     ext_filter_mask) <= 0)
+			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+					       NETLINK_CB(cb->skb).portid,
+					       cb->nlh->nlmsg_seq, 0,
+					       NLM_F_MULTI,
+					       ext_filter_mask);
+			/* If we ran out of room on the first message,
+			 * we're in trouble
+			 */
+			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
+
+			if (err <= 0)
 				goto out;
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1283,7 +1304,8 @@ static int do_set_master(struct net_device *dev, int ifindex)
 	return 0;
 }
 
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+		      struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -1295,7 +1317,8 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			err = PTR_ERR(net);
 			goto errout;
 		}
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+			put_net(net);
 			err = -EPERM;
 			goto errout;
 		}
@@ -1549,7 +1572,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
 errout:
 	return err;
 }
@@ -1589,7 +1612,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -1667,7 +1689,8 @@ err:
 }
 EXPORT_SYMBOL(rtnl_create_link);
 
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+		struct net *net, int group,
 		struct ifinfomsg *ifm,
 		struct nlattr **tb)
 {
@@ -1676,7 +1699,7 @@ static int rtnl_group_changelink(struct net *net, int group,
 
 	for_each_netdev(net, dev) {
 		if (dev->group == group) {
-			err = do_setlink(dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}
@@ -1778,12 +1801,12 @@ replay:
 				modified = 1;
 			}
 
-			return do_setlink(dev, ifm, tb, ifname, modified);
+			return do_setlink(skb, dev, ifm, tb, ifname, modified);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
-				return rtnl_group_changelink(net,
+				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
 						ifm, tb);
 			return -ENODEV;
@@ -1895,9 +1918,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -1973,12 +2000,13 @@ EXPORT_SYMBOL(rtmsg_ifinfo);
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   u8 *addr, u32 pid, u32 seq,
-				   int type, unsigned int flags)
+				   int type, unsigned int flags,
+				   int nlflags)
 {
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -2016,7 +2044,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
 	if (!skb)
 		goto errout;
 
-	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
@@ -2167,7 +2195,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err = -EINVAL;
 	__u8 *addr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2249,7 +2277,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
 
 		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
 					      portid, seq,
-					      RTM_NEWNEIGH, NTF_SELF);
+					      RTM_NEWNEIGH, NTF_SELF,
+					      NLM_F_MULTI);
 		if (err < 0)
 			return err;
 skip:
@@ -2622,7 +2651,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	sz_idx = type>>2;
 	kind = type&3;
 
-	if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 6a2f13cee86a..d0afc322b961 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -10,12 +10,27 @@
 
 #include <net/secure_seq.h>
 
-static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
-void net_secret_init(void)
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static void net_secret_init(void)
 {
-	get_random_bytes(net_secret, sizeof(net_secret));
+	u32 tmp;
+	int i;
+
+	if (likely(net_secret[0]))
+		return;
+
+	for (i = NET_SECRET_SIZE; i > 0;) {
+		do {
+			get_random_bytes(&tmp, sizeof(tmp));
+		} while (!tmp);
+		cmpxchg(&net_secret[--i], 0, tmp);
+	}
 }
+#endif
 
 #ifdef CONFIG_INET
 static u32 seq_scale(u32 seq)
@@ -42,6 +57,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32)daddr[i];
@@ -63,6 +79,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32) daddr[i];
@@ -78,35 +95,13 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	hash[0] = (__force __u32) daddr;
-	hash[1] = net_secret[13];
-	hash[2] = net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
-	__u32 hash[4];
-
-	memcpy(hash, daddr, 16);
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
 
 __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 				 __be16 sport, __be16 dport)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -121,6 +116,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = (__force u32)dport ^ net_secret[14];
@@ -140,6 +136,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u64 seq;
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -164,6 +161,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 	u64 seq;
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + daddr[i];
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1c1738cc4538..6148716884ae 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -47,6 +47,8 @@
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/netdevice.h>
 #ifdef CONFIG_NET_CLS_ACT
 #include <net/pkt_sched.h>
@@ -74,36 +76,6 @@
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
 
-static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
-				  struct pipe_buffer *buf)
-{
-	put_page(buf->page);
-}
-
-static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
-				struct pipe_buffer *buf)
-{
-	get_page(buf->page);
-}
-
-static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
-			       struct pipe_buffer *buf)
-{
-	return 1;
-}
-
-
-/* Pipe buffer operations for a socket. */
-static const struct pipe_buf_operations sock_pipe_buf_ops = {
-	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
-	.confirm = generic_pipe_buf_confirm,
-	.release = sock_pipe_buf_release,
-	.steal = sock_pipe_buf_steal,
-	.get = sock_pipe_buf_get,
-};
-
 /**
  *	skb_panic - private function for out-of-line support
  *	@skb:	buffer
@@ -585,9 +557,6 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 #endif
@@ -1814,7 +1783,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 		.partial = partial,
 		.nr_pages_max = MAX_SKB_FRAGS,
 		.flags = flags,
-		.ops = &sock_pipe_buf_ops,
+		.ops = &nosteal_pipe_buf_ops,
 		.spd_release = sock_spd_release,
 	};
 	struct sk_buff *frag_iter;
@@ -2841,7 +2810,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		tail = nskb;
 
 		__copy_skb_header(nskb, skb);
-		nskb->mac_len = skb->mac_len;
 
 		/* nskb and skb might have different headroom */
 		if (nskb->ip_summed == CHECKSUM_PARTIAL)
@@ -2851,13 +2819,14 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		skb_set_network_header(nskb, skb->mac_len);
 		nskb->transport_header = (nskb->network_header +
 					  skb_network_header_len(skb));
+		skb_reset_mac_len(nskb);
 
 		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
 						 doffset + tnl_hlen);
 
 		if (fskb != skb_shinfo(skb)->frag_list)
-			continue;
+			goto perform_csum_check;
 
 		if (!sg) {
 			nskb->ip_summed = CHECKSUM_NONE;
@@ -2875,6 +2844,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
 
 		while (pos < offset + len && i < nfrags) {
+			if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+				goto err;
 			*frag = skb_shinfo(skb)->frags[i];
 			__skb_frag_ref(frag);
 			size = skb_frag_size(frag);
@@ -2921,6 +2892,7 @@ skip_fraglist:
 		nskb->len += nskb->data_len;
 		nskb->truesize += nskb->data_len;
 
+perform_csum_check:
 		if (!csum) {
 			nskb->csum = skb_checksum(nskb, doffset,
 						  nskb->len - doffset, 0);
@@ -3503,3 +3475,28 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	return true;
 }
 EXPORT_SYMBOL(skb_try_coalesce);
+
+/**
+ * skb_gso_transport_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_transport_seglen is used to determine the real size of the
+ * individual segments, including Layer4 headers (TCP/UDP).
+ *
+ * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
+ */
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		return tcp_hdrlen(skb) + shinfo->gso_size;
+
+	/* UFO sets gso_size to the size of the fragmentation
+	 * payload, i.e. the size of the L4 (UDP) header is already
+	 * accounted for.
+	 */
+	return shinfo->gso_size;
+}
+EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
diff --git a/net/core/sock.c b/net/core/sock.c
index d6d024cfaaaf..af65d17517b8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,6 +142,55 @@
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
+/**
+ * sk_ns_capable - General socket capability test
+ * @sk: Socket to use a capability on or through
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in the user
+ * namespace @user_ns.
+ */
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap)
+{
+	return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(sk_ns_capable);
+
+/**
+ * sk_capable - Socket global capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The global capbility to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in all user
+ * namespaces.
+ */
+bool sk_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(sk_capable);
+
+/**
+ * sk_net_capable - Network namespace socket capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socke was created
+ * and the current process has the capability @cap over the network namespace
+ * the socket is a member of.
+ */
+bool sk_net_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(sk_net_capable);
+
+
 #ifdef CONFIG_MEMCG_KMEM
 int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
@@ -885,7 +934,7 @@ set_rcvbuf:
 
 	case SO_PEEK_OFF:
 		if (sock->ops->set_peek_off)
-			sock->ops->set_peek_off(sk, val);
+			ret = sock->ops->set_peek_off(sk, val);
 		else
 			ret = -EOPNOTSUPP;
 		break;
@@ -1814,7 +1863,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 		gfp_t gfp = sk->sk_allocation;
 
 		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN;
+			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
 		pfrag->page = alloc_pages(gfp, order);
 		if (likely(pfrag->page)) {
 			pfrag->offset = 0;
@@ -2271,6 +2320,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_stamp = ktime_set(-1L, 0);
 
+	sk->sk_pacing_rate = ~0U;
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)
@@ -2308,10 +2358,13 @@ void release_sock(struct sock *sk)
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
 
+	/* Warning : release_cb() might need to release sk ownership,
+	 * ie call sock_release_ownership(sk) before us.
+	 */
 	if (sk->sk_prot->release_cb)
 		sk->sk_prot->release_cb(sk);
 
-	sk->sk_lock.owned = 0;
+	sock_release_ownership(sk);
 	if (waitqueue_active(&sk->sk_lock.wq))
 		wake_up(&sk->sk_lock.wq);
 	spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6379de..c38e7a2b5a8e 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 }
 EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
 
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype)
 {
 	struct nlattr *attr;
@@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
 	unsigned int len;
 	int err = 0;
 
-	if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+	if (!may_report_filterinfo) {
 		nla_reserve(skb, attrtype, 0);
 		return 0;
 	}
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 40d5829ed36a..1074ffb6d533 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1670,7 +1670,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlmsghdr *reply_nlh = NULL;
 	const struct reply_func *fn;
 
-	if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+	if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c61f9c02fdb..6cf9f7782ad4 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -135,6 +135,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		if (dst)
 			dst->ops->redirect(dst, sk, skb);
+		goto out;
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 7d9197063ebb..b5e52100a89a 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -573,7 +573,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr __rcu **ifap;
 	int err = -EINVAL;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -617,7 +617,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr *ifa;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 57dc159245ec..d332aefb0846 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 2a7efe388344..f3dc69a41d63 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		RCV_SKB_FAIL(-EPERM);
 
 	/* Eventually we might send routing messages too */
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index c32be292c7e3..2022b46ab38f 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -150,7 +150,9 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	if (!*_result)
 		goto put;
 
-	memcpy(*_result, upayload->data, len + 1);
+	memcpy(*_result, upayload->data, len);
+	(*_result)[len] = '\0';
+
 	if (_expiry)
 		*_expiry = rkey->expiry;
 
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 55e1fd5b3e56..ca118e8cb141 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -862,7 +862,7 @@ lowpan_process_data(struct sk_buff *skb)
 	 * Traffic class carried in-line
 	 * ECN + DSCP (1 byte), Flow Label is elided
 	 */
-	case 1: /* 10b */
+	case 2: /* 10b */
 		if (lowpan_fetch_skb_u8(skb, &tmp))
 			goto drop;
 
@@ -875,7 +875,7 @@ lowpan_process_data(struct sk_buff *skb)
 	 * Flow Label carried in-line
 	 * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
 	 */
-	case 2: /* 01b */
+	case 1: /* 01b */
 		if (lowpan_fetch_skb_u8(skb, &tmp))
 			goto drop;
 
@@ -1173,7 +1173,27 @@ static struct header_ops lowpan_header_ops = {
 	.create	= lowpan_header_create,
 };
 
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+	dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	return 0;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
+	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_set_mac_address	= lowpan_set_address,
 };
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 581a59504bd5..1865fdf5a5a5 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (saddr) {
 		saddr->family = AF_IEEE802154;
 		saddr->addr = mac_cb(skb)->sa;
-	}
-	if (addr_len)
 		*addr_len = sizeof(*saddr);
+	}
 
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 22b1a7058fd3..4efd2375d7e1 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -224,8 +224,10 @@ static int ieee802154_add_iface(struct sk_buff *skb,
 
 	if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) {
 		type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]);
-		if (type >= __IEEE802154_DEV_MAX)
-			return -EINVAL;
+		if (type >= __IEEE802154_DEV_MAX) {
+			rc = -EINVAL;
+			goto nla_put_failure;
+		}
 	}
 
 	dev = phy->add_iface(phy, devname, type);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d01be2a3ae53..c4adc319cc2e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,10 +263,8 @@ void build_ehash_secret(void)
 		get_random_bytes(&rnd, sizeof(rnd));
 	} while (rnd == 0);
 
-	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) {
+	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
 		get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
-		net_secret_init();
-	}
 }
 EXPORT_SYMBOL(build_ehash_secret);
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index b28e863fe0a7..5f3dc1df04bf 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		goto out;
 	}
 
@@ -86,18 +86,26 @@ out:
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
 
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
 void ip4_datagram_release_cb(struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
 	__be32 daddr = inet->inet_daddr;
+	struct dst_entry *dst;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
-		return;
-
 	rcu_read_lock();
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+		rcu_read_unlock();
+		return;
+	}
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
@@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk)
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
 				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
-	if (!IS_ERR(rt))
-		__sk_dst_set(sk, &rt->dst);
+
+	dst = !IS_ERR(rt) ? &rt->dst : NULL;
+	sk_dst_set(sk, dst);
+
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 9e38217c3931..e40eef4ac697 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1433,7 +1433,8 @@ static size_t inet_nlmsg_size(void)
 	       + nla_total_size(4) /* IFA_ADDRESS */
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
-	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
+	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+	       + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
 }
 
 static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a209f9d..4556cd25acde 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1049,6 +1049,8 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	}
 
 	in_dev = __in_dev_get_rtnl(dev);
+	if (!in_dev)
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 26aa65d1fce4..c5c8b248d8f6 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
 	else
 		res->tclassid = 0;
 #endif
+
+	if (err == -ESRCH)
+		err = -ENETUNREACH;
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(__fib_lookup);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8f6cb7a87cd6..bc773a10dca6 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -533,7 +533,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			return 1;
 
 		attrlen = rtnh_attrlen(rtnh);
-		if (attrlen < 0) {
+		if (attrlen > 0) {
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
@@ -818,13 +818,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 76e10b47e053..ea78ef5ac352 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -697,8 +697,6 @@ static void icmp_unreach(struct sk_buff *skb)
 					       &iph->daddr);
 			} else {
 				info = ntohs(icmph->un.frag.mtu);
-				if (!info)
-					goto out;
 			}
 			break;
 		case ICMP_SR_FAILED:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index d8c232794bcb..155adf8729c2 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -343,7 +343,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	pip->saddr    = fl4.saddr;
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
-	ip_select_ident(pip, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&pip[1])[0] = IPOPT_RA;
 	((u8 *)&pip[1])[1] = 4;
 	((u8 *)&pip[1])[2] = 0;
@@ -687,7 +687,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	iph->daddr    = dst;
 	iph->saddr    = fl4.saddr;
 	iph->protocol = IPPROTO_IGMP;
-	ip_select_ident(iph, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -709,7 +709,7 @@ static void igmp_gq_timer_expire(unsigned long data)
 
 	in_dev->mr_gq_running = 0;
 	igmpv3_send_report(in_dev, NULL);
-	__in_dev_put(in_dev);
+	in_dev_put(in_dev);
 }
 
 static void igmp_ifc_timer_expire(unsigned long data)
@@ -721,7 +721,7 @@ static void igmp_ifc_timer_expire(unsigned long data)
 		in_dev->mr_ifc_count--;
 		igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval);
 	}
-	__in_dev_put(in_dev);
+	in_dev_put(in_dev);
 }
 
 static void igmp_ifc_event(struct in_device *in_dev)
@@ -1874,6 +1874,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 	rtnl_lock();
 	in_dev = ip_mc_find_dev(net, imr);
+	if (!in_dev) {
+		ret = -ENODEV;
+		goto out;
+	}
 	ifindex = imr->imr_ifindex;
 	for (imlp = &inet->mc_list;
 	     (iml = rtnl_dereference(*imlp)) != NULL;
@@ -1891,16 +1895,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 		*imlp = iml->next_rcu;
 
-		if (in_dev)
-			ip_mc_dec_group(in_dev, group);
+		ip_mc_dec_group(in_dev, group);
 		rtnl_unlock();
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
 		kfree_rcu(iml, rcu);
 		return 0;
 	}
-	if (!in_dev)
-		ret = -ENODEV;
+out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5f648751fce2..45dbdab915e2 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = inet->inet_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
@@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 
 	r->idiag_family	      = tw->tw_family;
 	r->idiag_retrans      = 0;
+
 	r->id.idiag_if	      = tw->tw_bound_dev_if;
 	sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
 	r->id.idiag_sport     = tw->tw_sport;
 	r->id.idiag_dport     = tw->tw_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
 	r->id.idiag_dst[0]    = tw->tw_daddr;
+
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
 	r->idiag_expires      = DIV_ROUND_UP(tmo * 1000, HZ);
@@ -732,8 +743,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = ireq->rmt_port;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = ireq->loc_addr;
 	r->id.idiag_dst[0] = ireq->rmt_addr;
+
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
@@ -945,7 +961,7 @@ next_normal:
 			++num;
 		}
 
-		if (r->idiag_states & TCPF_TIME_WAIT) {
+		if (r->idiag_states & (TCPF_TIME_WAIT | TCPF_FIN_WAIT2)) {
 			struct inet_timewait_sock *tw;
 
 			inet_twsk_for_each(tw, node,
@@ -955,6 +971,8 @@ next_normal:
 
 				if (num < s_num)
 					goto next_dying;
+				if (!(r->idiag_states & (1 << tw->tw_substate)))
+					goto next_dying;
 				if (r->sdiag_family != AF_UNSPEC &&
 						tw->tw_family != r->sdiag_family)
 					goto next_dying;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7e06641e36ae..af02a39175e3 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -211,7 +211,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
 	}
 
 	work = frag_mem_limit(nf) - nf->low_thresh;
-	while (work > 0) {
+	while (work > 0 || force) {
 		spin_lock(&nf->lru_lock);
 
 		if (list_empty(&nf->lru_list)) {
@@ -283,9 +283,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &hb->chain);
+	inet_frag_lru_add(nf, qp);
 	spin_unlock(&hb->chain_lock);
 	read_unlock(&f->lock);
-	inet_frag_lru_add(nf, qp);
+
 	return qp;
 }
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6af375afeeef..c95848d00039 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -287,7 +287,7 @@ begintw:
 			if (unlikely(!INET_TW_MATCH(sk, net, acookie,
 						    saddr, daddr, ports,
 						    dif))) {
-				sock_put(sk);
+				inet_twsk_put(inet_twsk(sk));
 				goto begintw;
 			}
 			goto out;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 000e3d239d64..67140efc15fd 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
  *  Theory of operations.
  *  We keep one entry for each peer IP address.  The nodes contains long-living
  *  information about the peer which doesn't depend on routes.
- *  At this moment this information consists only of ID field for the next
- *  outgoing IP packet.  This field is incremented with each packet as encoded
- *  in inet_getid() function (include/net/inetpeer.h).
- *  At the moment of writing this notes identifier of IP packets is generated
- *  to be unpredictable using this code only for packets subjected
- *  (actually or potentially) to defragmentation.  I.e. DF packets less than
- *  PMTU in size uses a constant ID and do not use this code (see
- *  ip_select_ident() in include/net/ip.h).
  *
- *  Route cache entries hold references to our nodes.
- *  New cache entries get references via lookup by destination IP address in
- *  the avl tree.  The reference is grabbed only when it's needed i.e. only
- *  when we try to output IP packet which needs an unpredictable ID (see
- *  __ip_select_ident() in net/ipv4/route.c).
  *  Nodes are removed only when reference counter goes to 0.
  *  When it's happened the node may be removed when a sufficient amount of
  *  time has been passed since its last use.  The less-recently-used entry can
@@ -62,7 +49,6 @@
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
- *		ip_id_count: atomic value (no lock needed)
  */
 
 static struct kmem_cache *peer_cachep __read_mostly;
@@ -504,10 +490,6 @@ relookup:
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count,
-				(daddr->family == AF_INET) ?
-					secure_ip_id(daddr->addr.a4) :
-					secure_ipv6_id(daddr->addr.a6));
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b7aebf..bd1c5baf69be 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+		skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+	unsigned int mtu;
+
+	if (skb->local_df || !skb_is_gso(skb))
+		return false;
+
+	mtu = dst_mtu(skb_dst(skb));
+
+	/* if seglen > mtu, do software segmentation for IP fragmentation on
+	 * output.  DF bit cannot be set since ip_forward would have sent
+	 * icmp error.
+	 */
+	return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	features = netif_skb_dev_features(skb, dst->dev);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = dst_output(segs);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	if (ip_gso_exceeds_dst_mtu(skb))
+		return ip_forward_finish_gso(skb);
+
 	return dst_output(skb);
 }
 
@@ -88,8 +156,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(dst_mtu(&rt->dst)));
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c52fee0976da..fae5a8459538 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -335,7 +335,8 @@ static int ipgre_rcv(struct sk_buff *skb)
 				  iph->saddr, iph->daddr, tpi.key);
 
 	if (tunnel) {
-		ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+		skb_pop_mac_header(skb);
+		ip_tunnel_rcv(tunnel, skb, &tpi, hdr_len, log_ecn_error);
 		return 0;
 	}
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
@@ -651,6 +652,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
 static void ipgre_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipgre_netdev_ops;
+	dev->type		= ARPHRD_IPGRE;
 	ip_tunnel_setup(dev, ipgre_net_id);
 }
 
@@ -689,7 +691,6 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_IPGRE;
 	dev->flags		= IFF_NOARP;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 	dev->addr_len		= 4;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 15e3e683adec..0a22bb0ce1a8 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -313,7 +313,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 
-	if (sysctl_ip_early_demux && !skb_dst(skb)) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct net_protocol *ipprot;
 		int protocol = iph->protocol;
 
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec7264514a82..089ed81d1878 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -288,6 +288,10 @@ int ip_options_compile(struct net *net,
 			optptr++;
 			continue;
 		}
+		if (unlikely(l < 2)) {
+			pp_ptr = optptr;
+			goto error;
+		}
 		optlen = optptr[1];
 		if (optlen<2 || optlen>l) {
 			pp_ptr = optptr;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4bcabf3ab4ca..22fa05e041ea 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(iph, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -394,8 +394,7 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(iph, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
@@ -844,7 +843,7 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+	if (((length > mtu) || (skb && skb_has_frags(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
@@ -1324,7 +1323,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
 
-	iph = (struct iphdr *)skb->data;
+	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
 	iph->tos = inet->tos;
@@ -1332,7 +1331,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(iph, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
@@ -1482,6 +1481,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	struct sk_buff *nskb;
 	struct sock *sk;
 	struct inet_sock *inet;
+	int err;
 
 	if (ip_options_echo(&replyopts.opt.opt, skb))
 		return;
@@ -1518,8 +1518,13 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	sock_net_set(sk, net);
 	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
-	ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
-		       &ipc, &rt, MSG_DONTWAIT);
+	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
+			     len, 0, &ipc, &rt, MSG_DONTWAIT);
+	if (unlikely(err)) {
+		ip_flush_pending_frames(sk);
+		goto out;
+	}
+
 	nskb = skb_peek(&sk->sk_write_queue);
 	if (nskb) {
 		if (arg->csumoffset >= 0)
@@ -1531,7 +1536,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
-
+out:
 	put_cpu_var(unicast_sock);
 
 	ip_rt_put(rt);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f113d709..23e6ab0a2dc0 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct sock_exterr_skb *serr;
 	struct sk_buff *skb, *skb2;
@@ -405,6 +405,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
 						   serr->addr_offset);
 		sin->sin_port = serr->port;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index b7a4c21c06ec..84aa69caee59 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -166,6 +166,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (remote != t->parms.iph.daddr ||
+		    t->parms.iph.saddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -182,10 +183,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
+		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+			continue;
+
+		if (!(t->dev->flags & IFF_UP))
 			continue;
 
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -202,6 +204,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (t->parms.i_key != key ||
+		    t->parms.iph.saddr != 0 ||
+		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -402,7 +406,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 }
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
-		  const struct tnl_ptk_info *tpi, bool log_ecn_error)
+		  const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error)
 {
 	struct pcpu_tstats *tstats;
 	const struct iphdr *iph = ip_hdr(skb);
@@ -413,7 +417,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 	skb->protocol = tpi->proto;
 
 	skb->mac_header = skb->network_header;
-	__pskb_pull(skb, tunnel->hlen);
+	__pskb_pull(skb, hdr_len);
 	skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
@@ -636,6 +640,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
+			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
@@ -659,13 +664,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
 					       + rt->dst.header_len;
-	if (max_headroom > dev->needed_headroom) {
+	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
-		if (skb_cow_head(skb, dev->needed_headroom)) {
-			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
-			return;
-		}
+
+	if (skb_cow_head(skb, dev->needed_headroom)) {
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		return;
 	}
 
 	skb_dst_drop(skb);
@@ -686,7 +691,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	iph->daddr	=	fl4.daddr;
 	iph->saddr	=	fl4.saddr;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
 	iptunnel_xmit(skb, dev);
 	return;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 17cc0ffa8c0d..4ec34275160b 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -285,8 +285,17 @@ static int vti_rcv(struct sk_buff *skb)
 	tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
 		struct pcpu_tstats *tstats;
+		u32 oldmark = skb->mark;
+		int ret;
 
-		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+		/* temporarily mark the skb with the tunnel o_key, to
+		 * only match policies with this mark.
+		 */
+		skb->mark = be32_to_cpu(tunnel->parms.o_key);
+		ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+		skb->mark = oldmark;
+		if (!ret)
 			return -1;
 
 		tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -295,7 +304,6 @@ static int vti_rcv(struct sk_buff *skb)
 		tstats->rx_bytes += skb->len;
 		u64_stats_update_end(&tstats->syncp);
 
-		skb->mark = 0;
 		secpath_reset(skb);
 		skb->dev = tunnel->dev;
 		return 1;
@@ -327,7 +335,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	memset(&fl4, 0, sizeof(fl4));
 	flowi4_init_output(&fl4, tunnel->parms.link,
-			   be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+			   be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
 			   RT_SCOPE_UNIVERSE,
 			   IPPROTO_IPIP, 0,
 			   dst, tiph->saddr, 0, 0);
@@ -342,6 +350,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!rt->dst.xfrm ||
 	    rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
 		dev->stats.tx_carrier_errors++;
+		ip_rt_put(rt);
 		goto tx_error_icmp;
 	}
 	tdev = rt->dst.dev;
@@ -570,9 +579,9 @@ static void vti_dev_free(struct net_device *dev)
 static void vti_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &vti_netdev_ops;
+	dev->type		= ARPHRD_TUNNEL;
 	dev->destructor		= vti_dev_free;
 
-	dev->type		= ARPHRD_TUNNEL;
 	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 7cfc45624b6d..897b784e9c05 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
@@ -195,7 +195,7 @@ static int ipip_rcv(struct sk_buff *skb)
 	if (tunnel) {
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
-		return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+		return ip_tunnel_rcv(tunnel, skb, &tpi, 0, log_ecn_error);
 	}
 
 	return -1;
@@ -483,4 +483,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d9610ae7855..56d079b63ad3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
-	struct ipmr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv4.mr_rules_ops,
 			       flowi4_to_flowi(flp4), 0, &arg);
@@ -1658,7 +1661,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 	iph->protocol	=	IPPROTO_IPIP;
 	iph->ihl	=	5;
 	iph->tot_len	=	htons(skb->len);
-	ip_select_ident(iph, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -2252,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 }
 
 static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
-			    u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+			    u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+			    int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2326,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 	if (skb == NULL)
 		goto errout;
 
-	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2365,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 				if (ipmr_fill_mroute(mrt, skb,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
-						     mfc, RTM_NEWROUTE) < 0)
+						     mfc, RTM_NEWROUTE,
+						     NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2379,7 +2384,8 @@ next_entry:
 			if (ipmr_fill_mroute(mrt, skb,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     mfc, RTM_NEWROUTE) < 0) {
+					     mfc, RTM_NEWROUTE,
+					     NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 85a4f21aac1a..c8abe31961ed 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1039,8 +1039,10 @@ static int __do_replace(struct net *net, const char *name,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d23118d95ff9..651c10774d58 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1226,8 +1226,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 32b0e978c8e0..f8629c04f35b 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net,
 	ub->qlen++;
 
 	pm = nlmsg_data(nlh);
+	memset(pm, 0, sizeof(*pm));
 
 	/* We might not have a timestamp, get one */
 	if (skb->tstamp.tv64 == 0)
@@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net,
 	}
 	else if (loginfo->prefix[0] != '\0')
 		strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix));
-	else
-		*(pm->prefix) = '\0';
 
 	if (in && in->hard_header_len > 0 &&
 	    skb->mac_header != skb->network_header &&
@@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net,
 
 	if (in)
 		strncpy(pm->indev_name, in->name, sizeof(pm->indev_name));
-	else
-		pm->indev_name[0] = '\0';
 
 	if (out)
 		strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
-	else
-		pm->outdev_name[0] = '\0';
 
 	/* copy_len <= skb->len, so can't fail. */
 	if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 742815518b0f..4cfb3bd1677c 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->local_df = 1;
+	}
 
 	return err;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7d93d62cd5fd..aa857a4a06a8 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -204,26 +204,33 @@ static int ping_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	kgid_t group = current_egid();
-	struct group_info *group_info = get_current_groups();
-	int i, j, count = group_info->ngroups;
+	struct group_info *group_info;
+	int i, j, count;
 	kgid_t low, high;
+	int ret = 0;
 
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
 
+	group_info = get_current_groups();
+	count = group_info->ngroups;
 	for (i = 0; i < group_info->nblocks; i++) {
 		int cp_count = min_t(int, NGROUPS_PER_BLOCK, count);
 		for (j = 0; j < cp_count; j++) {
 			kgid_t gid = group_info->blocks[i][j];
 			if (gid_lte(low, gid) && gid_lte(gid, high))
-				return 0;
+				goto out_release_group;
 		}
 
 		count -= cp_count;
 	}
 
-	return -EACCES;
+	ret = -EACCES;
+
+out_release_group:
+	put_group_info(group_info);
+	return ret;
 }
 
 static void ping_close(struct sock *sk, long timeout)
@@ -570,7 +577,7 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		err = PTR_ERR(rt);
 		rt = NULL;
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 		goto out;
 	}
 
@@ -626,7 +633,6 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *isk = inet_sk(sk);
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
 	struct sk_buff *skb;
 	int copied, err;
 
@@ -636,11 +642,8 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+		return ip_recv_error(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -660,11 +663,14 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	sock_recv_timestamp(msg, sk, skb);
 
 	/* Copy the address. */
-	if (sin) {
+	if (msg->msg_name) {
+		struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+
 		sin->sin_family = AF_INET;
 		sin->sin_port = 0 /* skb->h.uh->source */;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (isk->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 61e60d67adca..b4a1c42a627f 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -387,7 +387,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		iph->check   = 0;
 		iph->tot_len = htons(length);
 		if (!iph->id)
-			ip_select_ident(iph, &rt->dst, NULL);
+			ip_select_ident(skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
@@ -692,11 +692,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE) {
-		err = ip_recv_error(sk, msg, len);
+		err = ip_recv_error(sk, msg, len, addr_len);
 		goto out;
 	}
 
@@ -722,6 +719,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		sin->sin_port = 0;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0cf404..d4d162eac4df 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -464,39 +465,53 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	return neigh_create(&arp_tbl, pkey, dev);
 }
 
-/*
- * Peer allocation may fail only in serious out-of-memory conditions.  However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+	atomic_t	id;
+	u32		stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
  */
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
 {
-	static DEFINE_SPINLOCK(ip_fb_id_lock);
-	static u32 ip_fallback_id;
-	u32 salt;
+	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 now = (u32)jiffies;
+	u32 delta = 0;
+
+	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) {
+		u64 x = prandom_u32();
 
-	spin_lock_bh(&ip_fb_id_lock);
-	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
-	iph->id = htons(salt & 0xFFFF);
-	ip_fallback_id = salt;
-	spin_unlock_bh(&ip_fb_id_lock);
+		x *= (now - old);
+		delta = (u32)(x >> 32);
+	}
+
+	return atomic_add_return(segs + delta, &bucket->id) - segs;
 }
+EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
 {
-	struct net *net = dev_net(dst->dev);
-	struct inet_peer *peer;
+	static u32 ip_idents_hashrnd __read_mostly;
+	static bool hashrnd_initialized = false;
+	u32 hash, id;
 
-	peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
-	if (peer) {
-		iph->id = htons(inet_getid(peer, more));
-		inet_putpeer(peer);
-		return;
+	if (unlikely(!hashrnd_initialized)) {
+		hashrnd_initialized = true;
+		get_random_bytes(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
 	}
 
-	ip_select_fb_ident(iph);
+	hash = jhash_3words((__force u32)iph->daddr,
+			    (__force u32)iph->saddr,
+			    iph->protocol,
+			    ip_idents_hashrnd);
+	id = ip_idents_reserve(hash, segs);
+	iph->id = htons(id);
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
@@ -985,20 +1000,21 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
-	struct dst_entry *dst;
+	struct dst_entry *odst = NULL;
 	bool new = false;
 
 	bh_lock_sock(sk);
-	rt = (struct rtable *) __sk_dst_get(sk);
+	odst = sk_dst_get(sk);
 
-	if (sock_owned_by_user(sk) || !rt) {
+	if (sock_owned_by_user(sk) || !odst) {
 		__ipv4_sk_update_pmtu(skb, sk, mtu);
 		goto out;
 	}
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
-	if (!__sk_dst_check(sk, 0)) {
+	rt = (struct rtable *)odst;
+	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1008,8 +1024,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 	__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
 
-	dst = dst_check(&rt->dst, 0);
-	if (!dst) {
+	if (!dst_check(&rt->dst, 0)) {
 		if (new)
 			dst_release(&rt->dst);
 
@@ -1021,10 +1036,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	}
 
 	if (new)
-		__sk_dst_set(sk, &rt->dst);
+		sk_dst_set(sk, &rt->dst);
 
 out:
 	bh_unlock_sock(sk);
+	dst_release(odst);
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
@@ -1478,7 +1494,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
@@ -1544,6 +1560,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
@@ -1645,8 +1662,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (err != 0)
 		goto no_route;
 
-	RT_CACHE_STAT_INC(in_slow_tot);
-
 	if (res.type == RTN_BROADCAST)
 		goto brd_input;
 
@@ -1715,13 +1730,18 @@ local_input:
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
-	if (do_cache)
-		rt_cache_route(&FIB_RES_NH(res), rth);
+	if (do_cache) {
+		if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+			rth->dst.flags |= DST_NOCACHE;
+			rt_add_uncached_list(rth);
+		}
+	}
 	skb_dst_set(skb, &rth->dst);
 	err = 0;
 	goto out;
@@ -2020,7 +2040,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 							      RT_SCOPE_LINK);
 			goto make_route;
 		}
-		if (fl4->saddr) {
+		if (!fl4->saddr) {
 			if (ipv4_is_multicast(fl4->daddr))
 				fl4->saddr = inet_select_addr(dev_out, 0,
 							      fl4->flowi4_scope);
@@ -2302,7 +2322,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
 				goto nla_put_failure;
 	}
 
@@ -2651,6 +2671,12 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
+	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+	if (!ip_idents)
+		panic("IP: failed to allocate ip_idents\n");
+
+	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3f25e75ae692..90b26beb84d4 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
 static int zero;
 static int one = 1;
 static int four = 4;
+static int gso_max_segs = GSO_MAX_SEGS;
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -753,6 +754,15 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &four,
 	},
 	{
+		.procname	= "tcp_min_tso_segs",
+		.data		= &sysctl_tcp_min_tso_segs,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &gso_max_segs,
+	},
+	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
 		.maxlen		= sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2005561861ad..5d4bd6ca3ab1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,6 +282,8 @@
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
@@ -786,14 +788,24 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 	xmit_size_goal = mss_now;
 
 	if (large_allowed && sk_can_gso(sk)) {
-		xmit_size_goal = ((sk->sk_gso_max_size - 1) -
-				  inet_csk(sk)->icsk_af_ops->net_header_len -
-				  inet_csk(sk)->icsk_ext_hdr_len -
-				  tp->tcp_header_len);
+		u32 gso_size, hlen;
+
+		/* Maybe we should/could use sk->sk_prot->max_header here ? */
+		hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+		       inet_csk(sk)->icsk_ext_hdr_len +
+		       tp->tcp_header_len;
 
-		/* TSQ : try to have two TSO segments in flight */
-		xmit_size_goal = min_t(u32, xmit_size_goal,
-				       sysctl_tcp_limit_output_bytes >> 1);
+		/* Goal is to send at least one packet per ms,
+		 * not one big TSO packet every 100 ms.
+		 * This preserves ACK clocking and is consistent
+		 * with tcp_tso_should_defer() heuristic.
+		 */
+		gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+		gso_size = max_t(u32, gso_size,
+				 sysctl_tcp_min_tso_segs * mss_now);
+
+		xmit_size_goal = min_t(u32, gso_size,
+				       sk->sk_gso_max_size - 1 - hlen);
 
 		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
 
@@ -989,7 +1001,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int err, flags;
@@ -1004,11 +1017,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
 	if (unlikely(tp->fastopen_req == NULL))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
+	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
-	*size = tp->fastopen_req->copied;
+	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
 }
@@ -1028,7 +1042,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	flags = msg->msg_flags;
 	if (flags & MSG_FASTOPEN) {
-		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
 		else if (err)
@@ -1051,7 +1065,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);
-			goto out;
+			goto out_nopush;
 		}
 
 		err = -EINVAL;
@@ -1224,6 +1238,7 @@ wait_for_memory:
 out:
 	if (copied)
 		tcp_push(sk, flags, mss_now, tp->nonagle);
+out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
 
@@ -2447,10 +2462,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_THIN_DUPACK:
 		if (val < 0 || val > 1)
 			err = -EINVAL;
-		else
+		else {
 			tp->thin_dupack = val;
 			if (tp->thin_dupack)
 				tcp_disable_early_retrans(tp);
+		}
 		break;
 
 	case TCP_REPAIR:
@@ -2886,6 +2902,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int sum_truesize = 0;
 	struct tcphdr *th;
 	unsigned int thlen;
 	unsigned int seq;
@@ -2969,13 +2986,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 		if (copy_destructor) {
 			skb->destructor = gso_skb->destructor;
 			skb->sk = gso_skb->sk;
-			/* {tcp|sock}_wfree() use exact truesize accounting :
-			 * sum(skb->truesize) MUST be exactly be gso_skb->truesize
-			 * So we account mss bytes of 'true size' for each segment.
-			 * The last segment will contain the remaining.
-			 */
-			skb->truesize = mss;
-			gso_skb->truesize -= mss;
+			sum_truesize += skb->truesize;
 		}
 		skb = skb->next;
 		th = tcp_hdr(skb);
@@ -2992,7 +3003,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 	if (copy_destructor) {
 		swap(gso_skb->sk, skb->sk);
 		swap(gso_skb->destructor, skb->destructor);
-		swap(gso_skb->truesize, skb->truesize);
+		sum_truesize += skb->truesize;
+		atomic_add(sum_truesize - gso_skb->truesize,
+			   &skb->sk->sk_wmem_alloc);
 	}
 
 	delta = htonl(oldlen + (skb->tail - skb->transport_header) +
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index b6ae92a51f58..894b7cea5d7b 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -408,7 +408,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
 		ratio += cnt;
 
-		ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
+		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
 	}
 
 	/* Some calls are for duplicates without timetamps */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4b75aad14b04..ea7f52f3062d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -699,6 +699,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 	}
 }
 
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	u64 rate;
+
+	/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+	rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+	rate *= max(tp->snd_cwnd, tp->packets_out);
+
+	/* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+	 * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+	 * We probably need usec resolution in the future.
+	 * Note: This also takes care of possible srtt=0 case,
+	 * when tcp_rtt_estimator() was not yet called.
+	 */
+	if (tp->srtt > 8 + 2)
+		do_div(rate, tp->srtt);
+
+	sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
  * routine referred to above.
  */
@@ -1047,7 +1075,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 	}
 
 	/* D-SACK for already forgotten data... Do dumb counting. */
-	if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+	if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
 	    !after(end_seq_0, prior_snd_una) &&
 	    after(end_seq_0, tp->undo_marker))
 		tp->undo_retrans--;
@@ -1102,7 +1130,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 			unsigned int new_len = (pkt_len / mss) * mss;
 			if (!in_sack && new_len < pkt_len) {
 				new_len += mss;
-				if (new_len > skb->len)
+				if (new_len >= skb->len)
 					return 0;
 			}
 			pkt_len = new_len;
@@ -1126,7 +1154,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
-		if (tp->undo_marker && tp->undo_retrans &&
+		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
@@ -1264,7 +1292,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 		tp->lost_cnt_hint -= tcp_skb_pcount(prev);
 	}
 
-	TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+	TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+		TCP_SKB_CB(prev)->end_seq++;
+
 	if (skb == tcp_highest_sack(sk))
 		tcp_advance_highest_sack(sk, skb);
 
@@ -1819,7 +1850,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp)
 	tp->lost_out = 0;
 
 	tp->undo_marker = 0;
-	tp->undo_retrans = 0;
+	tp->undo_retrans = -1;
 }
 
 void tcp_clear_retrans(struct tcp_sock *tp)
@@ -2669,7 +2700,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 
 	tp->prior_ssthresh = 0;
 	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out;
+	tp->undo_retrans = tp->retrans_out ? : -1;
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
@@ -2689,13 +2720,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
-		if (flag & FLAG_ORIG_SACK_ACKED) {
-			/* Step 3.b. A timeout is spurious if not all data are
-			 * lost, i.e., never-retransmitted data are (s)acked.
-			 */
-			tcp_try_undo_loss(sk, true);
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
 			return;
-		}
+
 		if (after(tp->snd_nxt, tp->high_seq) &&
 		    (flag & FLAG_DATA_SACKED || is_dupack)) {
 			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
@@ -3314,7 +3344,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 			tcp_init_cwnd_reduction(sk, true);
 			tcp_set_ca_state(sk, TCP_CA_CWR);
 			tcp_end_cwnd_reduction(sk);
-			tcp_set_ca_state(sk, TCP_CA_Open);
+			tcp_try_keep_open(sk);
 			NET_INC_STATS_BH(sock_net(sk),
 					 LINUX_MIB_TCPLOSSPROBERECOVERY);
 		}
@@ -3330,7 +3360,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
-	u32 prior_in_flight;
+	u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
 	u32 prior_fackets;
 	int prior_packets = tp->packets_out;
 	int prior_sacked = tp->sacked_out;
@@ -3438,6 +3468,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
 		tcp_schedule_loss_probe(sk);
+	if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+		tcp_update_pacing_rate(sk);
 	return 1;
 
 no_queue:
@@ -5736,6 +5768,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 				} else
 					tcp_init_metrics(sk);
 
+				tcp_update_pacing_rate(sk);
+
 				/* Prevent spurious tcp_cwnd_restart() on
 				 * first data packet.
 				 */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7999fc55c83b..e025c1c788a1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -176,7 +176,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		return err;
 	}
 
@@ -268,7 +268,7 @@ EXPORT_SYMBOL(tcp_v4_connect);
  * It can be called through tcp_release_cb() if socket was owned by user
  * at the time tcp_v4_err() was called to handle ICMP message.
  */
-static void tcp_v4_mtu_reduced(struct sock *sk)
+void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
@@ -298,6 +298,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
 		tcp_simple_retransmit(sk);
 	} /* else let the usual retransmit timer handle it */
 }
+EXPORT_SYMBOL(tcp_v4_mtu_reduced);
 
 static void do_redirect(struct sk_buff *skb, struct sock *sk)
 {
@@ -2142,6 +2143,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 EXPORT_SYMBOL(ipv4_specific);
 
@@ -2867,7 +2869,6 @@ struct proto tcp_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v4_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.mtu_reduced		= tcp_v4_mtu_reduced,
 	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index f6a005c485a9..b500d2ddc476 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+						   struct net *net, unsigned int hash);
+
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 	}
 }
 
+#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+		tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH	5
+#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 					  struct inetpeer_addr *addr,
-					  unsigned int hash,
-					  bool reclaim)
+					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
 	struct net *net;
+	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
 	net = dev_net(dst->dev);
+
+	/* While waiting for the spin-lock the cache might have been populated
+	 * with this entry and so we have to check again.
+	 */
+	tm = __tcp_get_metrics(addr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR) {
+		reclaim = true;
+		tm = NULL;
+	}
+	if (tm) {
+		tcpm_check_stamp(tm, dst);
+		goto out_unlock;
+	}
+
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
@@ -169,17 +197,6 @@ out_unlock:
 	return tm;
 }
 
-#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
-		tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH	5
-#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
-
 static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
 {
 	if (tm)
@@ -280,7 +297,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	struct inetpeer_addr addr;
 	unsigned int hash;
 	struct net *net;
-	bool reclaim;
 
 	addr.family = sk->sk_family;
 	switch (addr.family) {
@@ -300,13 +316,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
 	tm = __tcp_get_metrics(&addr, net, hash);
-	reclaim = false;
-	if (tm == TCP_METRICS_RECLAIM_PTR) {
-		reclaim = true;
+	if (tm == TCP_METRICS_RECLAIM_PTR)
 		tm = NULL;
-	}
 	if (!tm && create)
-		tm = tcpm_new(dst, &addr, hash, reclaim);
+		tm = tcpm_new(dst, &addr, hash);
 	else
 		tcpm_check_stamp(tm, dst);
 
@@ -665,10 +678,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 			    struct tcp_fastopen_cookie *cookie, bool syn_lost)
 {
+	struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_metrics_block *tm;
 
+	if (!dst)
+		return;
 	rcu_read_lock();
-	tm = tcp_get_metrics(sk, __sk_dst_get(sk), true);
+	tm = tcp_get_metrics(sk, dst, true);
 	if (tm) {
 		struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0145ce7e6098..11ef25c9cf43 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -686,7 +686,8 @@ static void tcp_tsq_handler(struct sock *sk)
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
  * One tasklest per cpu tries to send more skbs.
@@ -754,6 +755,17 @@ void tcp_release_cb(struct sock *sk)
 	if (flags & (1UL << TCP_TSQ_DEFERRED))
 		tcp_tsq_handler(sk);
 
+	/* Here begins the tricky part :
+	 * We are called from release_sock() with :
+	 * 1) BH disabled
+	 * 2) sk_lock.slock spinlock held
+	 * 3) socket owned by us (sk->sk_lock.owned == 1)
+	 *
+	 * But following code is meant to be called from BH handlers,
+	 * so we should keep BH disabled, but early release socket ownership
+	 */
+	sock_release_ownership(sk);
+
 	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
 		tcp_write_timer_handler(sk);
 		__sock_put(sk);
@@ -763,7 +775,7 @@ void tcp_release_cb(struct sock *sk)
 		__sock_put(sk);
 	}
 	if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
-		sk->sk_prot->mtu_reduced(sk);
+		inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
 		__sock_put(sk);
 	}
 }
@@ -887,8 +899,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-			  tcp_wfree : sock_wfree;
+	skb->destructor = tcp_wfree;
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
 	/* Build TCP header and checksum it. */
@@ -977,6 +988,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
+	/* Make sure we own this skb before messing gso_size/gso_segs */
+	WARN_ON_ONCE(skb_cloned(skb));
+
 	if (skb->len <= mss_now || !sk_can_gso(sk) ||
 	    skb->ip_summed == CHECKSUM_NONE) {
 		/* Avoid the costly divide in the normal
@@ -1058,9 +1072,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (skb_cloned(skb) &&
-	    skb_is_nonlinear(skb) &&
-	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
@@ -1623,7 +1635,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 
 	/* If a full-sized TSO skb can be sent, do it. */
 	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-			   sk->sk_gso_max_segs * tp->mss_cache))
+			   tp->xmit_size_goal_segs * tp->mss_cache))
 		goto send_now;
 
 	/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1844,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
@@ -1861,13 +1872,32 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		/* TSQ : sk_wmem_alloc accounts skb truesize,
-		 * including skb overhead. But thats OK.
+		/* TCP Small Queues :
+		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+		 * This allows for :
+		 *  - better RTT estimation and ACK scheduling
+		 *  - faster recovery
+		 *  - high rates
+		 * Alas, some drivers / subsystems require a fair amount
+		 * of queued bytes to ensure line rate.
+		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+			      sk->sk_pacing_rate >> 10);
+
+		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 * We abuse smp_mb__after_clear_bit() because
+			 * there is no smp_mb__after_set_bit() yet
+			 */
+			smp_mb__after_clear_bit();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
+
 		limit = mss_now;
 		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2006,9 +2036,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	/* Probe with zero data doesn't trigger fast recovery. */
-	if (skb->len > 0)
-		err = __tcp_retransmit_skb(sk, skb);
+	err = __tcp_retransmit_skb(sk, skb);
 
 	/* Record snd_nxt for loss detection. */
 	if (likely(!err))
@@ -2329,6 +2357,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		int oldpcount = tcp_skb_pcount(skb);
 
 		if (unlikely(oldpcount > 1)) {
+			if (skb_unclone(skb, GFP_ATOMIC))
+				return -ENOMEM;
 			tcp_init_tso_segs(sk, skb, cur_mss);
 			tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
 		}
@@ -2396,13 +2426,15 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
 
-		tp->undo_retrans += tcp_skb_pcount(skb);
-
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
 		 */
 		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
 	}
+
+	if (tp->undo_retrans < 0)
+		tp->undo_retrans = 0;
+	tp->undo_retrans += tcp_skb_pcount(skb);
 	return err;
 }
 
@@ -2871,7 +2903,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
-	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+	space = min_t(size_t, space, fo->size);
+
+	/* limit to order-0 allocations */
+	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
 				   sk->sk_allocation);
 	if (syn_data == NULL)
 		goto fallback;
@@ -3090,7 +3127,6 @@ void tcp_send_window_probe(struct sock *sk)
 {
 	if (sk->sk_state == TCP_ESTABLISHED) {
 		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
-		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
 		tcp_xmit_probe_skb(sk, 0);
 	}
 }
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 80fa2bfd7ede..c042e529a11e 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -218,7 +218,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 			 * This is:
 			 *     (actual rate in segments) * baseRTT
 			 */
-			target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
+			target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
+			do_div(target_cwnd, rtt);
 
 			/* Calculate the difference between the window we had,
 			 * and the window we would like to have. This quantity
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index ac43cd747bce..b4d1858be550 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -144,7 +144,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 		rtt = veno->minrtt;
 
-		target_cwnd = (tp->snd_cwnd * veno->basertt);
+		target_cwnd = (u64)tp->snd_cwnd * veno->basertt;
 		target_cwnd <<= V_PARAM_SHIFT;
 		do_div(target_cwnd, rtt);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 93b731d53221..c3075b552248 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -971,7 +971,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			err = PTR_ERR(rt);
 			rt = NULL;
 			if (err == -ENETUNREACH)
-				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+				IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 			goto out;
 		}
 
@@ -1070,6 +1070,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	struct udp_sock *up = udp_sk(sk);
 	int ret;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (!up->pending) {
 		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };
 
@@ -1207,14 +1210,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int is_udplite = IS_UDPLITE(sk);
 	bool slow;
 
-	/*
-	 *	Check any passed addresses
-	 */
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1274,6 +1271,7 @@ try_again:
 		sin->sin_port = udp_hdr(skb)->source;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index eb1dd4d643f2..e3f64831bc36 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
 		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-	ip_select_ident(top_iph, dst->child, NULL);
 
 	top_iph->ttl = ip4_dst_hoplimit(dst->child);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(skb, NULL);
 
 	return 0;
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d3057f9b04a1..d0912acd9522 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1111,8 +1111,11 @@ retry:
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;
@@ -1533,6 +1536,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 	return false;
 }
 
+/* Compares an address/prefix_len with addresses on device @dev.
+ * If one is found it returns true.
+ */
+bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
+	const unsigned int prefix_len, struct net_device *dev)
+{
+	struct inet6_dev *idev;
+	struct inet6_ifaddr *ifa;
+	bool ret = false;
+
+	rcu_read_lock();
+	idev = __in6_dev_get(dev);
+	if (idev) {
+		read_lock_bh(&idev->lock);
+		list_for_each_entry(ifa, &idev->addr_list, if_list) {
+			ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len);
+			if (ret)
+				break;
+		}
+		read_unlock_bh(&idev->lock);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(ipv6_chk_custom_prefix);
+
 int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
 {
 	struct inet6_dev *idev;
@@ -2661,8 +2691,18 @@ static void init_loopback(struct net_device *dev)
 			if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
 				continue;
 
-			if (sp_ifa->rt)
-				continue;
+			if (sp_ifa->rt) {
+				/* This dst has been added to garbage list when
+				 * lo device down, release this obsolete dst and
+				 * reallocate a new router for ifa.
+				 */
+				if (sp_ifa->rt->dst.obsolete > 0) {
+					ip6_rt_put(sp_ifa->rt);
+					sp_ifa->rt = NULL;
+				} else {
+					continue;
+				}
+			}
 
 			sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0);
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4b56cbbc7890..8997340e3742 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
@@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 					       &sin->sin6_addr);
 			sin->sin6_scope_id = 0;
 		}
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
@@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
+		sin->sin6_port = 0;
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
@@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);
 /*
  *	Handle IPV6_RECVPATHMTU
  */
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+		     int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
@@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
 		sin->sin6_port = 0;
 		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
 		sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+		*addr_len = sizeof(*sin);
 	}
 
 	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 07a7d65a7cb6..8d67900aa003 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -162,12 +162,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
 		off += optlen;
 		len -= optlen;
 	}
-	/* This case will not be caught by above check since its padding
-	 * length is smaller than 7:
-	 * 1 byte NH + 1 byte Length + 6 bytes Padding
-	 */
-	if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8))
-		goto bad;
 
 	if (len == 0)
 		return true;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index c5e83fae4df4..51af9d0d019a 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		found = (nexthdr == target);
 
 		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-			if (target < 0)
+			if (target < 0 || found)
 				break;
 			return -ENOENT;
 		}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3abfd06..447a7fbd1bb6 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void)
 	int ret;
 
 	ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
-	if (!ret)
+	if (ret)
 		goto out;
 
 	ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
-	if (!ret)
+	if (ret)
 		goto out_rt;
 
 out:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 70e704d49007..2dee1d9d7305 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -508,7 +508,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 32b4a1675d82..066640e0ba8e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -116,7 +116,7 @@ begintw:
 			}
 			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
 						     ports, dif))) {
-				sock_put(sk);
+				inet_twsk_put(inet_twsk(sk));
 				goto begintw;
 			}
 			goto out;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 2221ff6a308b..009c9620f442 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -825,9 +825,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 	fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
 			rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst),
 			allow_create, replace_required);
-
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
+		fn = NULL;
 		goto out;
 	}
 
@@ -1418,7 +1418,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 
 				if (w->skip) {
 					w->skip--;
-					continue;
+					goto skip;
 				}
 
 				err = w->func(w);
@@ -1428,6 +1428,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 				w->count++;
 				continue;
 			}
+skip:
 			w->state = FWS_U;
 		case FWS_U:
 			if (fn == w->root)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 46e88433ec7d..f0ccdb787100 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -453,8 +453,10 @@ static int mem_check(struct sock *sk)
 	if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
 		return 0;
 
+	rcu_read_lock_bh();
 	for_each_sk_fl_rcu(np, sfl)
 		count++;
+	rcu_read_unlock_bh();
 
 	if (room <= 0 ||
 	    ((count >= FL_MAX_PER_SOCK ||
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ecd60733e5e2..65156a73b3f3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -512,11 +512,11 @@ static int ip6gre_rcv(struct sk_buff *skb)
 
 		skb->protocol = gre_proto;
 		/* WCCP version 1 and 2 protocol decoding.
-		 * - Change protocol to IP
+		 * - Change protocol to IPv6
 		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 		 */
 		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
-			skb->protocol = htons(ETH_P_IP);
+			skb->protocol = htons(ETH_P_IPV6);
 			if ((*(h + offset) & 0xF0) != 0x40)
 				offset += 4;
 		}
@@ -620,7 +620,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 	struct ip6_tnl *tunnel = netdev_priv(dev);
 	struct net_device *tdev;    /* Device to other host */
 	struct ipv6hdr  *ipv6h;     /* Our new IP header */
-	unsigned int max_headroom;  /* The extra header space needed */
+	unsigned int max_headroom = 0; /* The extra header space needed */
 	int    gre_hlen;
 	struct ipv6_tel_txoption opt;
 	int    mtu;
@@ -693,7 +693,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 			tunnel->err_count = 0;
 	}
 
-	max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
+	max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
 
 	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
 	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
@@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPIP;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv4_get_dsfield(iph);
 
@@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPV6;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
@@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
 
-	dev->iflink = p->link;
-
 	/* Precalculate GRE options length */
 	if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
 		if (t->parms.o_flags&GRE_CSUM)
@@ -1267,6 +1265,8 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	dev->iflink = tunnel->parms.link;
+
 	return 0;
 }
 
@@ -1282,7 +1282,6 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev)
 	dev_hold(dev);
 }
 
-
 static struct inet6_protocol ip6gre_protocol __read_mostly = {
 	.handler     = ip6gre_rcv,
 	.err_handler = ip6gre_err,
@@ -1458,6 +1457,8 @@ static int ip6gre_tap_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	dev->iflink = tunnel->parms.link;
+
 	return 0;
 }
 
@@ -1549,6 +1550,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	return 0;
 }
 
+static void ip6gre_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	if (dev != ign->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static size_t ip6gre_get_size(const struct net_device *dev)
 {
 	return
@@ -1626,6 +1636,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.validate	= ip6gre_tunnel_validate,
 	.newlink	= ip6gre_newlink,
 	.changelink	= ip6gre_changelink,
+	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
 };
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 2bab2aa59745..774b09cb2920 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,7 +49,7 @@
 
 int ip6_rcv_finish(struct sk_buff *skb)
 {
-	if (sysctl_ip_early_demux && !skb_dst(skb)) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct inet6_protocol *ipprot;
 
 		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6e3ddf806ec2..071edcba4158 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+	nexthop = rt6_nexthop((struct rt6_info *)dst);
 	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -141,8 +141,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	}
 	rcu_read_unlock_bh();
 
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
 	return -EINVAL;
 }
@@ -150,7 +150,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
 static int ip6_finish_output(struct sk_buff *skb)
 {
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
-	    dst_allfrag(skb_dst(skb)))
+	    dst_allfrag(skb_dst(skb)) ||
+	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(skb, ip6_finish_output2);
 	else
 		return ip6_finish_output2(skb);
@@ -344,6 +345,24 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 	return dst_output(skb);
 }
 
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	/* ipv6 conntrack defrag sets max_frag_size + local_df */
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb->local_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +485,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -522,6 +540,23 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	static bool hashrnd_initialized = false;
+	u32 hash, id;
+
+	if (unlikely(!hashrnd_initialized)) {
+		hashrnd_initialized = true;
+		get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+	}
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
+}
+
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
@@ -898,7 +933,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 */
 	rt = (struct rt6_info *) *dst;
 	rcu_read_lock_bh();
-	n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+	n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
 	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
 	rcu_read_unlock_bh();
 
@@ -1039,6 +1074,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	 * udp datagram
 	 */
 	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+		struct frag_hdr fhdr;
+
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
@@ -1059,12 +1096,6 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
-	}
-
-	err = skb_append_datato_frags(sk,skb, getfrag, from,
-				      (length - transhdrlen));
-	if (!err) {
-		struct frag_hdr fhdr;
 
 		/* Specify the length of each IPv6 datagram fragment.
 		 * It has to be a multiple of 8.
@@ -1075,15 +1106,10 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		ipv6_select_ident(&fhdr, rt);
 		skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
 		__skb_queue_tail(&sk->sk_write_queue, skb);
-
-		return 0;
 	}
-	/* There is not enough support do UPD LSO,
-	 * so follow normal path
-	 */
-	kfree_skb(skb);
 
-	return err;
+	return skb_append_datato_frags(sk, skb, getfrag, from,
+				       (length - transhdrlen));
 }
 
 static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
@@ -1103,21 +1129,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);
@@ -1134,7 +1158,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;
@@ -1216,6 +1240,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
@@ -1250,27 +1275,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 * --yoshfuji
 	 */
 
-	cork->length += length;
-	if (length > mtu) {
-		int proto = sk->sk_protocol;
-		if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
-			ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
-			return -EMSGSIZE;
-		}
-
-		if (proto == IPPROTO_UDP &&
-		    (rt->dst.dev->features & NETIF_F_UFO)) {
+	if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
+					   sk->sk_protocol == IPPROTO_RAW)) {
+		ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
+		return -EMSGSIZE;
+	}
 
-			err = ip6_ufo_append_data(sk, getfrag, from, length,
-						  hh_len, fragheaderlen,
-						  transhdrlen, mtu, flags, rt);
-			if (err)
-				goto error;
-			return 0;
-		}
+	skb = skb_peek_tail(&sk->sk_write_queue);
+	cork->length += length;
+	if (((length > mtu) ||
+	     (skb && skb_has_frags(skb))) &&
+	    (sk->sk_protocol == IPPROTO_UDP) &&
+	    (rt->dst.dev->features & NETIF_F_UFO)) {
+		err = ip6_ufo_append_data(sk, getfrag, from, length,
+					  hh_len, fragheaderlen,
+					  transhdrlen, mtu, flags, rt);
+		if (err)
+			goto error;
+		return 0;
 	}
 
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+	if (!skb)
 		goto alloc_new_skb;
 
 	while (length > 0) {
@@ -1295,8 +1320,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;
 
@@ -1551,8 +1575,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e55866cead7..14f46af17704 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -61,6 +61,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG
@@ -264,9 +265,6 @@ static int ip6_tnl_create2(struct net_device *dev)
 	int err;
 
 	t = netdev_priv(dev);
-	err = ip6_tnl_dev_init(dev);
-	if (err < 0)
-		goto out;
 
 	err = register_netdevice(dev);
 	if (err < 0)
@@ -1432,6 +1430,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 
 
 static const struct net_device_ops ip6_tnl_netdev_ops = {
+	.ndo_init	= ip6_tnl_dev_init,
 	.ndo_uninit	= ip6_tnl_dev_uninit,
 	.ndo_start_xmit = ip6_tnl_xmit,
 	.ndo_do_ioctl	= ip6_tnl_ioctl,
@@ -1513,16 +1512,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-	int err = ip6_tnl_dev_init_gen(dev);
-
-	if (err)
-		return err;
 
 	t->parms.proto = IPPROTO_IPV6;
 	dev_hold(dev);
 
-	ip6_tnl_link_config(t);
-
 	rcu_assign_pointer(ip6n->tnls_wc[0], t);
 	return 0;
 }
@@ -1531,7 +1524,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	u8 proto;
 
-	if (!data)
+	if (!data || !data[IFLA_IPTUN_PROTO])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
@@ -1617,6 +1610,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	return ip6_tnl_update(t, &p);
 }
 
+static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+
+	if (dev != ip6n->fb_tnl_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static size_t ip6_tnl_get_size(const struct net_device *dev)
 {
 	return
@@ -1646,9 +1648,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
 	    nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr),
-		    &parm->raddr) ||
-	    nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
 		    &parm->laddr) ||
+	    nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
+		    &parm->raddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
 	    nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
 	    nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
@@ -1681,6 +1683,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
 	.validate	= ip6_tnl_validate,
 	.newlink	= ip6_tnl_newlink,
 	.changelink	= ip6_tnl_changelink,
+	.dellink	= ip6_tnl_dellink,
 	.get_size	= ip6_tnl_get_size,
 	.fill_info	= ip6_tnl_fill_info,
 };
@@ -1732,6 +1735,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	if (!ip6n->fb_tnl_dev)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
+	ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops;
 
 	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 4b421249532f..2c84072b1da7 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
-	struct ip6mr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ip6mr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
 			       flowi6_to_flowi(flp6), 0, &arg);
@@ -2348,13 +2351,14 @@ int ip6mr_get_route(struct net *net,
 }
 
 static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
-			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+			     int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2422,7 +2426,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 	if (skb == NULL)
 		goto errout;
 
-	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2461,7 +2465,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 				if (ip6mr_fill_mroute(mrt, skb,
 						      NETLINK_CB(cb->skb).portid,
 						      cb->nlh->nlmsg_seq,
-						      mfc, RTM_NEWROUTE) < 0)
+						      mfc, RTM_NEWROUTE,
+						      NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2475,7 +2480,8 @@ next_entry:
 			if (ip6mr_fill_mroute(mrt, skb,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      mfc, RTM_NEWROUTE) < 0) {
+					      mfc, RTM_NEWROUTE,
+					      NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index c3998c2bbc5a..734aec059ffd 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1439,11 +1439,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;
@@ -2158,7 +2159,7 @@ static void mld_gq_timer_expire(unsigned long data)
 
 	idev->mc_gq_running = 0;
 	mld_send_report(idev, NULL);
-	__in6_dev_put(idev);
+	in6_dev_put(idev);
 }
 
 static void mld_ifc_timer_expire(unsigned long data)
@@ -2171,7 +2172,7 @@ static void mld_ifc_timer_expire(unsigned long data)
 		if (idev->mc_ifc_count)
 			mld_ifc_start_timer(idev, idev->mc_maxdelay);
 	}
-	__in6_dev_put(idev);
+	in6_dev_put(idev);
 }
 
 static void mld_ifc_event(struct inet6_dev *idev)
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7f..d38e6a8d8b9f 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 44400c216dc6..89a4e4ddd8bb 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1236,8 +1236,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index c9b6a6e6a1e8..97cd7507c1a4 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -172,63 +172,13 @@ out:
 	return nf_conntrack_confirm(skb);
 }
 
-static unsigned int __ipv6_conntrack_in(struct net *net,
-					unsigned int hooknum,
-					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
-					int (*okfn)(struct sk_buff *))
-{
-	struct sk_buff *reasm = skb->nfct_reasm;
-	const struct nf_conn_help *help;
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-
-	/* This packet is fragmented and has reassembled packet. */
-	if (reasm) {
-		/* Reassembled packet isn't parsed yet ? */
-		if (!reasm->nfct) {
-			unsigned int ret;
-
-			ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-
-		/* Conntrack helpers need the entire reassembled packet in the
-		 * POST_ROUTING hook. In case of unconfirmed connections NAT
-		 * might reassign a helper, so the entire packet is also
-		 * required.
-		 */
-		ct = nf_ct_get(reasm, &ctinfo);
-		if (ct != NULL && !nf_ct_is_untracked(ct)) {
-			help = nfct_help(ct);
-			if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
-				nf_conntrack_get_reasm(reasm);
-				NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
-					       (struct net_device *)in,
-					       (struct net_device *)out,
-					       okfn, NF_IP6_PRI_CONNTRACK + 1);
-				return NF_DROP_ERR(-ECANCELED);
-			}
-		}
-
-		nf_conntrack_get(reasm->nfct);
-		skb->nfct = reasm->nfct;
-		skb->nfctinfo = reasm->nfctinfo;
-		return NF_ACCEPT;
-	}
-
-	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
-}
-
 static unsigned int ipv6_conntrack_in(unsigned int hooknum,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+	return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb);
 }
 
 static unsigned int ipv6_conntrack_local(unsigned int hooknum,
@@ -242,7 +192,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+	return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index dffdc1a389c5..253566a8d55b 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -621,31 +621,16 @@ ret_orig:
 	return skb;
 }
 
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			struct net_device *in, struct net_device *out,
-			int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
 {
 	struct sk_buff *s, *s2;
-	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
-		nf_conntrack_put_reasm(s->nfct_reasm);
-		nf_conntrack_get_reasm(skb);
-		s->nfct_reasm = skb;
-
 		s2 = s->next;
 		s->next = NULL;
-
-		if (ret != -ECANCELED)
-			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
-					     in, out, okfn,
-					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
-		else
-			kfree_skb(s);
-
+		consume_skb(s);
 		s = s2;
 	}
-	nf_conntrack_put_reasm(skb);
 }
 
 static int nf_ct_net_init(struct net *net)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index aacd121fe8c5..581dd9ede0de 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
-			   (struct net_device *)out, okfn);
+	nf_ct_frag6_consume_orig(reasm);
+
+	NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+		       (struct net_device *) in, (struct net_device *) out,
+		       okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
 
 	return NF_STOLEN;
 }
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index c2e73e647e44..a5d465105b69 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -6,34 +6,6 @@
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static atomic_t ipv6_fragmentation_id;
-	int old, new;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-		struct net *net;
-
-		net = dev_net(rt->dst.dev);
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			inet_putpeer(peer);
-			return;
-		}
-	}
-#endif
-	do {
-		old = atomic_read(&ipv6_fragmentation_id);
-		new = old + 1;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
-	fhdr->identification = htonl(new);
-}
-EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index eedff8ccded5..464b1c9c08e4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -459,14 +459,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (addr_len)
-		*addr_len=sizeof(*sin6);
-
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -500,6 +497,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		sin6->sin6_flowinfo = 0;
 		sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
 							  IP6CB(skb)->iif);
+		*addr_len = sizeof(*sin6);
 	}
 
 	sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bacce6c08644..b2614b22622b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -84,6 +84,8 @@ static int		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
 static int		ip6_pkt_discard_out(struct sk_buff *skb);
+static int		ip6_pkt_prohibit(struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
@@ -233,9 +235,6 @@ static const struct rt6_info ip6_null_entry_template = {
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 
-static int ip6_pkt_prohibit(struct sk_buff *skb);
-static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-
 static const struct rt6_info ip6_prohibit_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
@@ -473,6 +472,24 @@ out:
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
+struct __rt6_probe_work {
+	struct work_struct work;
+	struct in6_addr target;
+	struct net_device *dev;
+};
+
+static void rt6_probe_deferred(struct work_struct *w)
+{
+	struct in6_addr mcaddr;
+	struct __rt6_probe_work *work =
+		container_of(w, struct __rt6_probe_work, work);
+
+	addrconf_addr_solict_mult(&work->target, &mcaddr);
+	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+	dev_put(work->dev);
+	kfree(w);
+}
+
 static void rt6_probe(struct rt6_info *rt)
 {
 	struct neighbour *neigh;
@@ -496,17 +513,23 @@ static void rt6_probe(struct rt6_info *rt)
 
 	if (!neigh ||
 	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
-		struct in6_addr mcaddr;
-		struct in6_addr *target;
+		struct __rt6_probe_work *work;
 
-		if (neigh) {
+		work = kmalloc(sizeof(*work), GFP_ATOMIC);
+
+		if (neigh && work)
 			neigh->updated = jiffies;
+
+		if (neigh)
 			write_unlock(&neigh->lock);
-		}
 
-		target = (struct in6_addr *)&rt->rt6i_gateway;
-		addrconf_addr_solict_mult(target, &mcaddr);
-		ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
+		if (work) {
+			INIT_WORK(&work->work, rt6_probe_deferred);
+			work->target = rt->rt6i_gateway;
+			dev_hold(rt->dst.dev);
+			work->dev = rt->dst.dev;
+			schedule_work(&work->work);
+		}
 	} else {
 out:
 		write_unlock(&neigh->lock);
@@ -704,8 +727,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		prefix = &prefix_buf;
 	}
 
-	rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
-				dev->ifindex);
+	if (rinfo->prefix_len == 0)
+		rt = rt6_get_dflt_router(gwaddr, dev);
+	else
+		rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
+					gwaddr, dev->ifindex);
 
 	if (rt && !lifetime) {
 		ip6_del_rt(rt);
@@ -848,7 +874,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
 			if (ort->rt6i_dst.plen != 128 &&
 			    ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
 				rt->rt6i_flags |= RTF_ANYCAST;
-			rt->rt6i_gateway = *daddr;
 		}
 
 		rt->rt6i_flags |= RTF_CACHE;
@@ -1061,10 +1086,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
 		return NULL;
 
-	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
-		return dst;
+	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+		return NULL;
 
-	return NULL;
+	if (rt6_check_expired(rt))
+		return NULL;
+
+	return dst;
 }
 
 static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1208,7 +1236,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
 	if (mtu)
-		return mtu;
+		goto out;
 
 	mtu = IPV6_MIN_MTU;
 
@@ -1218,7 +1246,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 		mtu = idev->cnf.mtu6;
 	rcu_read_unlock();
 
-	return mtu;
+out:
+	return min_t(unsigned int, mtu, IP6_MAX_MTU);
 }
 
 static struct dst_entry *icmp6_dst_gc_list;
@@ -1245,6 +1274,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	rt->dst.flags |= DST_HOST;
 	rt->dst.output  = ip6_output;
 	atomic_set(&rt->dst.__refcnt, 1);
+	rt->rt6i_gateway  = fl6->daddr;
 	rt->rt6i_dst.addr = fl6->daddr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_idev     = idev;
@@ -1399,7 +1429,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
@@ -1468,21 +1498,24 @@ int ip6_route_add(struct fib6_config *cfg)
 				goto out;
 			}
 		}
-		rt->dst.output = ip6_pkt_discard_out;
-		rt->dst.input = ip6_pkt_discard;
 		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
+			rt->dst.output = dst_discard;
+			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
 			rt->dst.error = -EACCES;
+			rt->dst.output = ip6_pkt_prohibit_out;
+			rt->dst.input = ip6_pkt_prohibit;
 			break;
 		case RTN_THROW:
-			rt->dst.error = -EAGAIN;
-			break;
 		default:
-			rt->dst.error = -ENETUNREACH;
+			rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
+					: -ENETUNREACH;
+			rt->dst.output = ip6_pkt_discard_out;
+			rt->dst.input = ip6_pkt_discard;
 			break;
 		}
 		goto install_route;
@@ -1801,11 +1834,12 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 			in6_dev_hold(rt->rt6i_idev);
 		rt->dst.lastuse = jiffies;
 
-		rt->rt6i_gateway = ort->rt6i_gateway;
+		if (ort->rt6i_flags & RTF_GATEWAY)
+			rt->rt6i_gateway = ort->rt6i_gateway;
+		else
+			rt->rt6i_gateway = *dest;
 		rt->rt6i_flags = ort->rt6i_flags;
-		if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
-		    (RTF_DEFAULT | RTF_ADDRCONF))
-			rt6_set_from(rt, ort);
+		rt6_set_from(rt, ort);
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -2044,8 +2078,6 @@ static int ip6_pkt_discard_out(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
 }
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-
 static int ip6_pkt_prohibit(struct sk_buff *skb)
 {
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
@@ -2057,8 +2089,6 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
 }
 
-#endif
-
 /*
  *	Allocate a dst for local (unicast / anycast) address.
  */
@@ -2068,12 +2098,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    bool anycast)
 {
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
-
-	if (!rt) {
-		net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
+	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
+					    DST_NOCOUNT, NULL);
+	if (!rt)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	in6_dev_hold(idev);
 
@@ -2088,6 +2116,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	else
 		rt->rt6i_flags |= RTF_LOCAL;
 
+	rt->rt6i_gateway  = *addr;
 	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 60df36d15390..4ddf67c6355b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -530,12 +530,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
@@ -566,6 +566,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr,
 	return false;
 }
 
+/* Checks if an address matches an address on the tunnel interface.
+ * Used to detect the NAT of proto 41 packets and let them pass spoofing test.
+ * Long story:
+ * This function is called after we considered the packet as spoofed
+ * in is_spoofed_6rd.
+ * We may have a router that is doing NAT for proto 41 packets
+ * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb
+ * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd
+ * function will return true, dropping the packet.
+ * But, we can still check if is spoofed against the IP
+ * addresses associated with the interface.
+ */
+static bool only_dnatted(const struct ip_tunnel *tunnel,
+	const struct in6_addr *v6dst)
+{
+	int prefix_len;
+
+#ifdef CONFIG_IPV6_SIT_6RD
+	prefix_len = tunnel->ip6rd.prefixlen + 32
+		- tunnel->ip6rd.relay_prefixlen;
+#else
+	prefix_len = 48;
+#endif
+	return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev);
+}
+
+/* Returns true if a packet is spoofed */
+static bool packet_is_spoofed(struct sk_buff *skb,
+			      const struct iphdr *iph,
+			      struct ip_tunnel *tunnel)
+{
+	const struct ipv6hdr *ipv6h;
+
+	if (tunnel->dev->priv_flags & IFF_ISATAP) {
+		if (!isatap_chksrc(skb, iph, tunnel))
+			return true;
+
+		return false;
+	}
+
+	if (tunnel->dev->flags & IFF_POINTOPOINT)
+		return false;
+
+	ipv6h = ipv6_hdr(skb);
+
+	if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) {
+		net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+				     &iph->saddr, &ipv6h->saddr,
+				     &iph->daddr, &ipv6h->daddr);
+		return true;
+	}
+
+	if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr)))
+		return false;
+
+	if (only_dnatted(tunnel, &ipv6h->daddr))
+		return false;
+
+	net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+			     &iph->saddr, &ipv6h->saddr,
+			     &iph->daddr, &ipv6h->daddr);
+	return true;
+}
+
 static int ipip6_rcv(struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
@@ -584,19 +648,9 @@ static int ipip6_rcv(struct sk_buff *skb)
 		skb->protocol = htons(ETH_P_IPV6);
 		skb->pkt_type = PACKET_HOST;
 
-		if (tunnel->dev->priv_flags & IFF_ISATAP) {
-			if (!isatap_chksrc(skb, iph, tunnel)) {
-				tunnel->dev->stats.rx_errors++;
-				goto out;
-			}
-		} else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) {
-			if (is_spoofed_6rd(tunnel, iph->saddr,
-					   &ipv6_hdr(skb)->saddr) ||
-			    is_spoofed_6rd(tunnel, iph->daddr,
-					   &ipv6_hdr(skb)->daddr)) {
-				tunnel->dev->stats.rx_errors++;
-				goto out;
-			}
+		if (packet_is_spoofed(skb, iph, tunnel)) {
+			tunnel->dev->stats.rx_errors++;
+			goto out;
 		}
 
 		__skb_tunnel_rx(skb, tunnel->dev);
@@ -713,7 +767,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
 		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
+			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
 
@@ -742,7 +796,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
 		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
+			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
 
@@ -865,7 +919,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		iph->ttl	=	iph6->hop_limit;
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(iph, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	iptunnel_xmit(skb, dev);
 	return NETDEV_TX_OK;
 
@@ -1453,6 +1507,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 #endif
 };
 
+static void ipip6_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct sit_net *sitn = net_generic(net, sit_net_id);
+
+	if (dev != sitn->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.kind		= "sit",
 	.maxtype	= IFLA_IPTUN_MAX,
@@ -1463,6 +1526,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.changelink	= ipip6_changelink,
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
+	.dellink	= ipip6_dellink,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1507,6 +1571,7 @@ static int __net_init sit_init_net(struct net *net)
 		goto err_alloc_dev;
 	}
 	dev_net_set(sitn->fb_tunnel_dev, net);
+	sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops;
 
 	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
 	if (err)
@@ -1589,4 +1654,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 66c718854e5a..1a87659a6139 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1651,6 +1651,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v6_mtu_reduced,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1682,6 +1683,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1919,7 +1921,6 @@ struct proto tcpv6_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.mtu_reduced		= tcp_v6_mtu_reduced,
 	.hash			= tcp_v6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e7b28f9bb02b..6b298dc614e3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -373,14 +373,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	int is_udp4;
 	bool slow;
 
-	if (addr_len)
-		*addr_len = sizeof(struct sockaddr_in6);
-
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -461,7 +458,7 @@ try_again:
 				ipv6_iface_scope_id(&sin6->sin6_addr,
 						    IP6CB(skb)->iif);
 		}
-
+		*addr_len = sizeof(*sin6);
 	}
 	if (is_udp4) {
 		if (inet->cmsg_flags)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index d3cfaf9c7a08..2f65b022627b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -85,7 +85,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 	/* Check if there is enough headroom to insert fragment header. */
 	tnl_hlen = skb_tnl_header_len(skb);
-	if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) {
+	if (skb_mac_header(skb) < skb->head + tnl_hlen + frag_hdr_sz) {
 		if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
 			goto out;
 	}
@@ -108,7 +108,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 	fptr->nexthdr = nexthdr;
 	fptr->reserved = 0;
-	ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+	fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 	/* Fragment the skb. ipv6 header and the remaining fields of the
 	 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index f547a47d381c..2665bf4b8d05 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1778,6 +1778,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct ipxhdr *ipx = NULL;
 	struct sk_buff *skb;
 	int copied, rc;
+	bool locked = true;
 
 	lock_sock(sk);
 	/* put the autobinding in */
@@ -1804,6 +1805,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sock_flag(sk, SOCK_ZAPPED))
 		goto out;
 
+	release_sock(sk);
+	locked = false;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &rc);
 	if (!skb)
@@ -1823,8 +1826,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb->tstamp.tv64)
 		sk->sk_stamp = skb->tstamp;
 
-	msg->msg_namelen = sizeof(*sipx);
-
 	if (sipx) {
 		sipx->sipx_family	= AF_IPX;
 		sipx->sipx_port		= ipx->ipx_source.sock;
@@ -1832,13 +1833,15 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sipx->sipx_network	= IPX_SKB_CB(skb)->ipx_source_net;
 		sipx->sipx_type 	= ipx->ipx_type;
 		sipx->sipx_zero		= 0;
+		msg->msg_namelen	= sizeof(*sipx);
 	}
 	rc = copied;
 
 out_free:
 	skb_free_datagram(sk, skb);
 out:
-	release_sock(sk);
+	if (locked)
+		release_sock(sk);
 	return rc;
 }
 
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0578d4fa00a9..a5e62ef57155 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 
 	IRDA_DEBUG(4, "%s()\n", __func__);
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)
@@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
 
-	msg->msg_namelen = 0;
-
 	do {
 		int chunk;
 		struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ae691651b721..215e9b008db6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int err = 0;
 	u32 offset;
 
-	msg->msg_namelen = 0;
-
 	if ((sk->sk_state == IUCV_DISCONN) &&
 	    skb_queue_empty(&iucv->backlog_skb_q) &&
 	    skb_queue_empty(&sk->sk_receive_queue) &&
@@ -1831,7 +1829,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ab8bd2cabfa0..66f51c5a8a3a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3623,7 +3623,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
 		goto out;
 
-	msg->msg_namelen = 0;
 	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6984c3a353cd..8c27de2b4d5a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -115,6 +115,11 @@ struct l2tp_net {
 static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
+static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
+{
+	return sk->sk_user_data;
+}
+
 static inline struct l2tp_net *l2tp_pernet(struct net *net)
 {
 	BUG_ON(!net);
@@ -507,7 +512,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk,
 		return 0;
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == PF_INET6) {
+	if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
 		if (!uh->check) {
 			LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
 			return 1;
@@ -1071,7 +1076,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 	/* Queue the packet to IP for output */
 	skb->local_df = 1;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (skb->sk->sk_family == PF_INET6)
+	if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
 		error = inet6_csk_xmit(skb, NULL);
 	else
 #endif
@@ -1198,7 +1203,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 		/* Calculate UDP checksum if configured to do so */
 #if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == PF_INET6)
+		if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
 			l2tp_xmit_ipv6_csum(sk, skb, udp_len);
 		else
 #endif
@@ -1247,10 +1252,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
  */
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel;
+	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
 	struct l2tp_net *pn;
 
-	tunnel = sk->sk_user_data;
 	if (tunnel == NULL)
 		goto end;
 
@@ -1618,7 +1622,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	}
 
 	/* Check if this socket has already been prepped */
-	tunnel = (struct l2tp_tunnel *)sk->sk_user_data;
+	tunnel = l2tp_tunnel(sk);
 	if (tunnel != NULL) {
 		/* This socket has already been prepped */
 		err = -EBUSY;
@@ -1647,6 +1651,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	if (cfg != NULL)
 		tunnel->debug = cfg->debug;
 
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == PF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+
+		if (ipv6_addr_v4mapped(&np->saddr) &&
+		    ipv6_addr_v4mapped(&np->daddr)) {
+			struct inet_sock *inet = inet_sk(sk);
+
+			tunnel->v4mapped = true;
+			inet->inet_saddr = np->saddr.s6_addr32[3];
+			inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
+			inet->inet_daddr = np->daddr.s6_addr32[3];
+		} else {
+			tunnel->v4mapped = false;
+		}
+	}
+#endif
+
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
@@ -1655,7 +1677,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
 		udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy;
 #if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == PF_INET6)
+		if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
 			udpv6_encap_enable();
 		else
 #endif
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 485a490fd990..2f89d43877d7 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -189,6 +189,9 @@ struct l2tp_tunnel {
 	struct sock		*sock;		/* Parent socket */
 	int			fd;		/* Parent fd, if tunnel socket
 						 * was created by userspace */
+#if IS_ENABLED(CONFIG_IPV6)
+	bool			v4mapped;
+#endif
 
 	struct work_struct	del_work;
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 571db8dd2292..da1a1cee1a08 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
 		goto out;
@@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		sin->sin_port = 0;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b8a6039314e8..e6e8408c9e36 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		*addr_len = sizeof(*lsa);
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5ebee2ded9e9..c3ae2411650c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sk->sk_state & PPPOX_BOUND)
 		goto end;
 
-	msg->msg_namelen = 0;
-
 	err = 0;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
@@ -353,7 +351,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
 		goto error_put_sess_tun;
 	}
 
+	local_bh_disable();
 	l2tp_xmit_skb(session, skb, session->hdr_len);
+	local_bh_enable();
 
 	sock_put(ps->tunnel_sock);
 	sock_put(sk);
@@ -422,7 +422,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	skb->data[0] = ppph[0];
 	skb->data[1] = ppph[1];
 
+	local_bh_disable();
 	l2tp_xmit_skb(session, skb, session->hdr_len);
+	local_bh_enable();
 
 	sock_put(sk_tun);
 	sock_put(sk);
@@ -752,9 +754,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	session->deref = pppol2tp_session_sock_put;
 
 	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	dst = sk_dst_get(sk);
+	dst = sk_dst_get(tunnel->sock);
 	if (dst != NULL) {
-		u32 pmtu = dst_mtu(__sk_dst_get(sk));
+		u32 pmtu = dst_mtu(dst);
+
 		if (pmtu != 0)
 			session->mtu = session->mru = pmtu -
 				PPPOL2TP_HEADER_OVERHEAD;
@@ -1363,7 +1366,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1489,7 +1492,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	struct pppol2tp_session *ps;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 48aaa89253e0..c3ee80547066 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -715,13 +715,11 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 	unsigned long cpu_flags;
 	size_t copied = 0;
 	u32 peek_seq = 0;
-	u32 *seq;
+	u32 *seq, skb_len;
 	unsigned long used;
 	int target;	/* Read at least this many bytes */
 	long timeo;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	copied = -ENOTCONN;
 	if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
@@ -814,6 +812,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 		continue;
 	found_ok_skb:
+		skb_len = skb->len;
 		/* Ok so how much can we use? */
 		used = skb->len - offset;
 		if (len < used)
@@ -846,7 +845,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 
 		/* Partial read */
-		if (used + offset < skb->len)
+		if (used + offset < skb_len)
 			continue;
 	} while (len > 0);
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ae36f8e11ae4..e922bf3f422c 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -975,8 +975,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 					IEEE80211_P2P_OPPPS_ENABLE_BIT;
 
 	err = ieee80211_assign_beacon(sdata, &params->beacon);
-	if (err < 0)
+	if (err < 0) {
+		ieee80211_vif_release_channel(sdata);
 		return err;
+	}
 	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata);
@@ -985,6 +987,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		if (old)
 			kfree_rcu(old, rcu_head);
 		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
+		ieee80211_vif_release_channel(sdata);
 		return err;
 	}
 
@@ -2356,8 +2359,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
 
-	if (sdata->vif.type != NL80211_IFTYPE_STATION &&
-	    sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
 		return -EOPNOTSUPP;
 
 	if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS))
@@ -2477,6 +2479,24 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
 	INIT_LIST_HEAD(&roc->dependents);
 
+	/*
+	 * cookie is either the roc cookie (for normal roc)
+	 * or the SKB (for mgmt TX)
+	 */
+	if (!txskb) {
+		/* local->mtx protects this */
+		local->roc_cookie_counter++;
+		roc->cookie = local->roc_cookie_counter;
+		/* wow, you wrapped 64 bits ... more likely a bug */
+		if (WARN_ON(roc->cookie == 0)) {
+			roc->cookie = 1;
+			local->roc_cookie_counter++;
+		}
+		*cookie = roc->cookie;
+	} else {
+		*cookie = (unsigned long)txskb;
+	}
+
 	/* if there's one pending or we're scanning, queue this one */
 	if (!list_empty(&local->roc_list) ||
 	    local->scanning || local->radar_detect_enabled)
@@ -2611,24 +2631,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	if (!queued)
 		list_add_tail(&roc->list, &local->roc_list);
 
-	/*
-	 * cookie is either the roc cookie (for normal roc)
-	 * or the SKB (for mgmt TX)
-	 */
-	if (!txskb) {
-		/* local->mtx protects this */
-		local->roc_cookie_counter++;
-		roc->cookie = local->roc_cookie_counter;
-		/* wow, you wrapped 64 bits ... more likely a bug */
-		if (WARN_ON(roc->cookie == 0)) {
-			roc->cookie = 1;
-			local->roc_cookie_counter++;
-		}
-		*cookie = roc->cookie;
-	} else {
-		*cookie = (unsigned long)txskb;
-	}
-
 	return 0;
 }
 
@@ -3315,7 +3317,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 		return -EINVAL;
 	}
 	band = chanctx_conf->def.chan->band;
-	sta = sta_info_get(sdata, peer);
+	sta = sta_info_get_bss(sdata, peer);
 	if (sta) {
 		qos = test_sta_flag(sta, WLAN_STA_WME);
 	} else {
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 14abcf44f974..2d5b4f65c519 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read(
 	ssize_t ret = -EINVAL;
 
 	read_lock(&dev_base_lock);
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*format)(sdata, buf, sizeof(buf));
+	ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
 	if (ret >= 0)
@@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write(
 
 	ret = -ENODEV;
 	rtnl_lock();
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*write)(sdata, buf, count);
+	ret = (*write)(sdata, buf, count);
 	rtnl_unlock();
 
 	return ret;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9ca8e3278cc0..845563b81a0f 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -311,6 +311,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 
@@ -842,6 +843,8 @@ struct tpt_led_trigger {
  *	that the scan completed.
  * @SCAN_ABORTED: Set for our scan work function when the driver reported
  *	a scan complete for an aborted scan.
+ * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being
+ *	cancelled.
  */
 enum {
 	SCAN_SW_SCANNING,
@@ -849,6 +852,7 @@ enum {
 	SCAN_ONCHANNEL_SCANNING,
 	SCAN_COMPLETED,
 	SCAN_ABORTED,
+	SCAN_HW_CANCELLED,
 };
 
 /**
@@ -1267,6 +1271,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
 				  __le16 fc, bool acked);
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 514e90f470bf..2c64ab27b515 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1746,7 +1746,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
 	}
 	mutex_unlock(&local->iflist_mtx);
 	unregister_netdevice_many(&unreg_list);
-	list_del(&unreg_list);
 
 	list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
 		list_del(&sdata->list);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 67059b88fea5..635d0972b688 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -607,7 +607,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 	int i;
 
 	mutex_lock(&local->key_mtx);
-	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
+	for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
 		key = key_mtx_dereference(local, sta->gtk[i]);
 		if (!key)
 			continue;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 8a7bfc47d577..6658c5809353 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -157,6 +157,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		if (!rcu_access_pointer(sdata->vif.chanctx_conf))
 			continue;
+		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+			continue;
 		power = min(power, sdata->vif.bss_conf.txpower);
 	}
 	rcu_read_unlock();
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 3b7bfc01ee36..ddda201832b3 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 				      sdata->vif.addr);
 	nullfunc->frame_control = fc;
 	nullfunc->duration_id = 0;
+	nullfunc->seq_ctrl = 0;
 	/* no address resolution for this frame -> set addr 1 immediately */
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5b4328dcbe4e..e606e4a113e1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -310,6 +310,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	switch (vht_oper->chan_width) {
 	case IEEE80211_VHT_CHANWIDTH_USE_HT:
 		vht_chandef.width = chandef->width;
+		vht_chandef.center_freq1 = chandef->center_freq1;
 		break;
 	case IEEE80211_VHT_CHANWIDTH_80MHZ:
 		vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -359,6 +360,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	ret = 0;
 
 out:
+	/*
+	 * When tracking the current AP, don't do any further checks if the
+	 * new chandef is identical to the one we're currently using for the
+	 * connection. This keeps us from playing ping-pong with regulatory,
+	 * without it the following can happen (for example):
+	 *  - connect to an AP with 80 MHz, world regdom allows 80 MHz
+	 *  - AP advertises regdom US
+	 *  - CRDA loads regdom US with 80 MHz prohibited (old database)
+	 *  - the code below detects an unsupported channel, downgrades, and
+	 *    we disconnect from the AP in the caller
+	 *  - disconnect causes CRDA to reload world regdomain and the game
+	 *    starts anew.
+	 * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+	 *
+	 * It seems possible that there are still scenarios with CSA or real
+	 * bandwidth changes where a this could happen, but those cases are
+	 * less common and wouldn't completely prevent using the AP.
+	 */
+	if (tracking &&
+	    cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+		return ret;
+
 	/* don't print the message below for VHT mismatch if VHT is disabled */
 	if (ret & IEEE80211_STA_DISABLE_VHT)
 		vht_chandef = *chandef;
@@ -3731,6 +3754,32 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata)
 }
 
 #ifdef CONFIG_PM
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+
+	mutex_lock(&ifmgd->mtx);
+
+	if (ifmgd->auth_data) {
+		/*
+		 * If we are trying to authenticate while suspending, cfg80211
+		 * won't know and won't actually abort those attempts, thus we
+		 * need to do that ourselves.
+		 */
+		ieee80211_send_deauth_disassoc(sdata,
+					       ifmgd->auth_data->bss->bssid,
+					       IEEE80211_STYPE_DEAUTH,
+					       WLAN_REASON_DEAUTH_LEAVING,
+					       false, frame_buf);
+		ieee80211_destroy_auth_data(sdata, false);
+		cfg80211_send_deauth(sdata->dev, frame_buf,
+				     IEEE80211_DEAUTH_FRAME_LEN);
+	}
+
+	mutex_unlock(&ifmgd->mtx);
+}
+
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -4346,8 +4395,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	if (bss->wmm_used && bss->uapsd_supported &&
-	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) &&
-	    sdata->wmm_acm != 0xff) {
+	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
 		assoc_data->uapsd = true;
 		ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED;
 	} else {
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index acd1f71adc03..0427a58b4397 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 
@@ -354,13 +354,24 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
+		WARN_ON(local->use_chanctx);
+
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan;
 
-		/* switch channel etc */
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);
@@ -379,9 +390,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 340126204343..efb510e6f206 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -101,10 +101,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata) ||
-		    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-		    sdata->vif.type == NL80211_IFTYPE_MONITOR)
+		if (!ieee80211_sdata_running(sdata))
 			continue;
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+		case NL80211_IFTYPE_MONITOR:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			ieee80211_mgd_quiesce(sdata);
+			break;
+		default:
+			break;
+		}
 
 		drv_remove_interface(local, sdata);
 	}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index a02bef35b134..d68d6cfac3b5 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -448,7 +448,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif,
 	 */
 	if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) {
 		u32 basic_rates = vif->bss_conf.basic_rates;
-		s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0;
+		s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0;
 
 		rate = &sband->bitrates[rates[0].idx];
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 83f6d29202aa..9299a38c372e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -864,7 +864,8 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx,
 	u16 sc;
 	u8 tid, ack_policy;
 
-	if (!ieee80211_is_data_qos(hdr->frame_control))
+	if (!ieee80211_is_data_qos(hdr->frame_control) ||
+	    is_multicast_ether_addr(hdr->addr1))
 		goto dont_reorder;
 
 	/*
@@ -1584,11 +1585,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	sc = le16_to_cpu(hdr->seq_ctrl);
 	frag = sc & IEEE80211_SCTL_FRAG;
 
-	if (likely((!ieee80211_has_morefrags(fc) && frag == 0) ||
-		   is_multicast_ether_addr(hdr->addr1))) {
-		/* not fragmented */
-		goto out;
+	if (is_multicast_ether_addr(hdr->addr1)) {
+		rx->local->dot11MulticastReceivedFrameCount++;
+		goto out_no_led;
 	}
+
+	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+		goto out;
+
 	I802_DEBUG_INC(rx->local->rx_handlers_fragments);
 
 	if (skb_linearize(rx->skb))
@@ -1679,12 +1683,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	status->rx_flags |= IEEE80211_RX_FRAGMENTED;
 
  out:
+	ieee80211_led_rx(rx->local);
+ out_no_led:
 	if (rx->sta)
 		rx->sta->rx_packets++;
-	if (is_multicast_ether_addr(hdr->addr1))
-		rx->local->dot11MulticastReceivedFrameCount++;
-	else
-		ieee80211_led_rx(rx->local);
 	return RX_CONTINUE;
 }
 
@@ -3002,6 +3004,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 	case NL80211_IFTYPE_ADHOC:
 		if (!bssid)
 			return 0;
+		if (ether_addr_equal(sdata->vif.addr, hdr->addr2) ||
+		    ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2))
+			return 0;
 		if (ieee80211_is_beacon(hdr->frame_control)) {
 			return 1;
 		} else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) {
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 99b103921a4b..eb03337b6545 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -202,6 +202,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 	enum ieee80211_band band;
 	int i, ielen, n_chans;
 
+	if (test_bit(SCAN_HW_CANCELLED, &local->scanning))
+		return false;
+
 	do {
 		if (local->hw_scan_band == IEEE80211_NUM_BANDS)
 			return false;
@@ -878,7 +881,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local)
 	if (!local->scan_req)
 		goto out;
 
+	/*
+	 * We have a scan running and the driver already reported completion,
+	 * but the worker hasn't run yet or is stuck on the mutex - mark it as
+	 * cancelled.
+	 */
+	if (test_bit(SCAN_HW_SCANNING, &local->scanning) &&
+	    test_bit(SCAN_COMPLETED, &local->scanning)) {
+		set_bit(SCAN_HW_CANCELLED, &local->scanning);
+		goto out;
+	}
+
 	if (test_bit(SCAN_HW_SCANNING, &local->scanning)) {
+		/*
+		 * Make sure that __ieee80211_scan_completed doesn't trigger a
+		 * scan on another band.
+		 */
+		set_bit(SCAN_HW_CANCELLED, &local->scanning);
 		if (local->ops->cancel_hw_scan)
 			drv_cancel_hw_scan(local,
 				rcu_dereference_protected(local->scan_sdata,
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 11216bc13b27..557a5760f9f6 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -270,6 +270,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
 
@@ -339,6 +340,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		return NULL;
 
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -1045,6 +1047,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1064,6 +1068,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	}
 
 	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	spin_unlock(&sta->ps_lock);
 
 	local->total_ps_buffered -= buffered;
 
@@ -1110,6 +1115,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
 	memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+	nullfunc->seq_ctrl = 0;
 
 	skb->priority = tid;
 	skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index adc30045f99e..3184b2b2853c 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -244,6 +244,7 @@ struct sta_ampdu_mlme {
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -324,10 +325,8 @@ struct sta_info {
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 43439203f4e4..9e78206bd9bb 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 
+	if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+		sta->last_rx = jiffies;
+
 	if (ieee80211_is_data_qos(mgmt->frame_control)) {
 		struct ieee80211_hdr *hdr = (void *) skb->data;
 		u8 *qc = ieee80211_get_qos_ctl(hdr);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 9972e07a2f96..10eea2326022 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -398,6 +398,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
 	if (ieee80211_has_order(hdr->frame_control))
 		return TX_CONTINUE;
 
+	if (ieee80211_is_probe_req(hdr->frame_control))
+		return TX_CONTINUE;
+
 	/* no stations in PS mode */
 	if (!atomic_read(&ps->num_sta_ps))
 		return TX_CONTINUE;
@@ -471,6 +474,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -484,6 +501,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		info->control.vif = &tx->sdata->vif;
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,
@@ -511,7 +529,6 @@ ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
 {
 	if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
 		return TX_CONTINUE;
-
 	if (tx->flags & IEEE80211_TX_UNICAST)
 		return ieee80211_tx_h_unicast_ps_buf(tx);
 	else
@@ -851,7 +868,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx,
 	}
 
 	/* adjust first fragment's length */
-	skb->len = hdrlen + per_fragm;
+	skb_trim(skb, hdrlen + per_fragm);
 	return 0;
 }
 
@@ -1100,7 +1117,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 		tx->sta = rcu_dereference(sdata->u.vlan.sta);
 		if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr)
 			return TX_DROP;
-	} else if (info->flags & IEEE80211_TX_CTL_INJECTED ||
+	} else if (info->flags & (IEEE80211_TX_CTL_INJECTED |
+				  IEEE80211_TX_INTFL_NL80211_FRAME_TX) ||
 		   tx->sdata->control_port_protocol == tx->skb->protocol) {
 		tx->sta = sta_info_get_bss(sdata, hdr->addr1);
 	}
@@ -2692,7 +2710,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 				cpu_to_le16(IEEE80211_FCTL_MOREDATA);
 		}
 
-		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
 		if (!ieee80211_tx_prepare(sdata, &tx, skb))
 			break;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 72e6292955bb..5db8eb5d56cf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2174,6 +2174,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	}
 
 	rate = cfg80211_calculate_bitrate(&ri);
+	if (WARN_ONCE(!rate,
+		      "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n",
+		      status->flag, status->rate_idx, status->vht_nss))
+		return 0;
 
 	/* rewind from end of MPDU */
 	if (status->flag & RX_FLAG_MACTIME_END)
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index afba19cb6f87..a282fddf8b00 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -153,6 +153,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		return IEEE80211_AC_BE;
 	}
 
+	if (skb->protocol == sdata->control_port_protocol) {
+		skb->priority = 7;
+		return ieee80211_downgrade_queue(sdata, skb);
+	}
+
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
 	skb->priority = cfg80211_classify8021d(skb);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 57beb1762b2d..707bc520d629 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -325,18 +325,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length)
 static void
 mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length)
 {
-	u8 i, j;
-
-	for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++)
-		;
-	h->nets[i].nets--;
-
-	if (h->nets[i].nets != 0)
-		return;
-
-	for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) {
-		h->nets[j].cidr = h->nets[j + 1].cidr;
-		h->nets[j].nets = h->nets[j + 1].nets;
+	u8 i, j, net_end = nets_length - 1;
+
+	for (i = 0; i < nets_length; i++) {
+	        if (h->nets[i].cidr != cidr)
+	                continue;
+                if (h->nets[i].nets > 1 || i == net_end ||
+                    h->nets[i + 1].nets == 0) {
+                        h->nets[i].nets--;
+                        return;
+                }
+                for (j = i; j < net_end && h->nets[j].nets; j++) {
+		        h->nets[j].cidr = h->nets[j + 1].cidr;
+		        h->nets[j].nets = h->nets[j + 1].nets;
+                }
+                h->nets[j].nets = 0;
+                return;
 	}
 }
 #endif
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a083bda322b6..90e756cf6e52 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data)
 			ip_vs_control_del(cp);
 
 		if (cp->flags & IP_VS_CONN_F_NFCT) {
-			ip_vs_conn_drop_conntrack(cp);
 			/* Do not access conntracks during subsys cleanup
 			 * because nf_conntrack_find_get can not be used after
 			 * conntrack cleanup for the net.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 23b8eb53a569..26b9a986a87f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1131,12 +1131,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	ip_vs_fill_iph_skb(af, skb, &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
-			struct sk_buff *reasm = skb_nfct_reasm(skb);
-			/* Save fw mark for coming frags */
-			reasm->ipvs_property = 1;
-			reasm->mark = skb->mark;
-		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1390,15 +1384,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	if (ipip) {
 		__be32 info = ic->un.gateway;
+		__u8 type = ic->type;
+		__u8 code = ic->code;
 
 		/* Update the MTU */
 		if (ic->type == ICMP_DEST_UNREACH &&
 		    ic->code == ICMP_FRAG_NEEDED) {
 			struct ip_vs_dest *dest = cp->dest;
 			u32 mtu = ntohs(ic->un.frag.mtu);
+			__be16 frag_off = cih->frag_off;
 
 			/* Strip outer IP and ICMP, go to IPIP header */
-			__skb_pull(skb, ihl + sizeof(_icmph));
+			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+				goto ignore_ipip;
 			offset2 -= ihl + sizeof(_icmph);
 			skb_reset_network_header(skb);
 			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1406,7 +1404,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 			ipv4_update_pmtu(skb, dev_net(skb->dev),
 					 mtu, 0, 0, 0, 0);
 			/* Client uses PMTUD? */
-			if (!(cih->frag_off & htons(IP_DF)))
+			if (!(frag_off & htons(IP_DF)))
 				goto ignore_ipip;
 			/* Prefer the resulting PMTU */
 			if (dest) {
@@ -1425,12 +1423,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		/* Strip outer IP, ICMP and IPIP, go to IP header of
 		 * original request.
 		 */
-		__skb_pull(skb, offset2);
+		if (pskb_pull(skb, offset2) == NULL)
+			goto ignore_ipip;
 		skb_reset_network_header(skb);
 		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
 			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
-			ic->type, ic->code, ntohl(info));
-		icmp_send(skb, ic->type, ic->code, info);
+			type, code, ntohl(info));
+		icmp_send(skb, type, code, info);
 		/* ICMP can be shorter but anyways, account it */
 		ip_vs_out_stats(cp, skb);
 
@@ -1606,12 +1605,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
-			struct sk_buff *reasm = skb_nfct_reasm(skb);
-			/* Save fw mark for coming frags. */
-			reasm->ipvs_property = 1;
-			reasm->mark = skb->mark;
-		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
@@ -1663,9 +1656,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		/* sorry, all this trouble for a no-hit :) */
 		IP_VS_DBG_PKT(12, af, pp, skb, 0,
 			      "ip_vs_in: packet continues traversal as normal");
-		if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+		if (iph.fragoffs) {
 			/* Fragment that couldn't be mapped to a conn entry
-			 * and don't have any pointer to a reasm skb
 			 * is missing module nf_defrag_ipv6
 			 */
 			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
@@ -1748,38 +1740,6 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
 #ifdef CONFIG_IP_VS_IPV6
 
 /*
- * AF_INET6 fragment handling
- * Copy info from first fragment, to the rest of them.
- */
-static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
-{
-	struct sk_buff *reasm = skb_nfct_reasm(skb);
-	struct net *net;
-
-	/* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
-	 * ipvs_property is set when checking first fragment
-	 * in ip_vs_in() and ip_vs_out().
-	 */
-	if (reasm)
-		IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
-	if (!reasm || !reasm->ipvs_property)
-		return NF_ACCEPT;
-
-	net = skb_net(skb);
-	if (!net_ipvs(net)->enable)
-		return NF_ACCEPT;
-
-	/* Copy stored fw mark, saved in ip_vs_{in,out} */
-	skb->mark = reasm->mark;
-
-	return NF_ACCEPT;
-}
-
-/*
  *	AF_INET6 handler in NF_INET_LOCAL_IN chain
  *	Schedule and forward packets from remote clients
  */
@@ -1916,14 +1876,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.priority	= 100,
 	},
 #ifdef CONFIG_IP_VS_IPV6
-	/* After mangle & nat fetch 2:nd fragment and following */
-	{
-		.hook		= ip_vs_preroute_frag6,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP6_PRI_NAT_DST + 1,
-	},
 	/* After packet filtering, change source only for VS/NAT */
 	{
 		.hook		= ip_vs_reply6,
@@ -1946,7 +1898,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	{
 		.hook		= ip_vs_local_reply6,
 		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
+		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
 		.priority	= NF_IP6_PRI_NAT_DST + 1,
 	},
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 9ef22bdce9f1..bed5f7042529 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff,
 static int
 ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 {
-	struct sk_buff *reasm = skb_nfct_reasm(skb);
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;
@@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	/* todo: IPv6 fragments:
 	 *       I think this only should be done for the first fragment. /HS
 	 */
-	if (reasm) {
-		skb = reasm;
-		dataoff = iph.thoff_reasm + sizeof(struct udphdr);
-	} else
-		dataoff = iph.len + sizeof(struct udphdr);
+	dataoff = iph.len + sizeof(struct udphdr);
 
 	if (dataoff >= skb->len)
 		return -EINVAL;
-	/* todo: Check if this will mess-up the reasm skb !!! /HS */
 	retc = skb_linearize(skb);
 	if (retc < 0)
 		return retc;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b75ff6429a04..1692e7534759 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	old_iph->ttl;
-	ip_select_ident(iph, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
@@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->nexthdr		=	IPPROTO_IPV6;
 	iph->payload_len	=	old_iph->payload_len;
 	be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
-	iph->priority		=	old_iph->priority;
 	memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
+	ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph));
 	iph->daddr = cp->daddr.in6;
 	iph->saddr = saddr;
 	iph->hop_limit		=	old_iph->hop_limit;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index bdebd03bc8cd..70866d192efc 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 				   flowi6_to_flowi(&fl1), false)) {
 			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
 					   flowi6_to_flowi(&fl2), false)) {
-				if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
-					    sizeof(rt1->rt6i_gateway)) &&
+				if (ipv6_addr_equal(rt6_nexthop(rt1),
+						    rt6_nexthop(rt2)) &&
 				    rt1->dst.dev == rt2->dst.dev)
 					ret = 1;
 				dst_release(&rt2->dst);
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index a99b6c3427b0..59359bec328a 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -428,7 +428,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	const char *msg;
 	u_int8_t state;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);
 
 	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
@@ -486,7 +486,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	u_int8_t type, old_state, new_state;
 	enum ct_dccp_roles role;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);
 	type = dh->dccph_type;
 
@@ -577,7 +577,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl,
 	unsigned int cscov;
 	const char *msg;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	if (dh == NULL) {
 		msg = "nf_ct_dccp: short packet ";
 		goto out_invalid;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 4d4d8f1d01fc..7dcc376eea5f 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1043,6 +1043,12 @@ static int tcp_packet(struct nf_conn *ct,
 			nf_ct_kill_acct(ct, ctinfo, skb);
 			return NF_ACCEPT;
 		}
+		/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
+		 * pickup with loose=1. Avoid large ESTABLISHED timeout.
+		 */
+		if (new_state == TCP_CONNTRACK_ESTABLISHED &&
+		    timeout > timeouts[TCP_CONNTRACK_UNACK])
+			timeout = timeouts[TCP_CONNTRACK_UNACK];
 	} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
 		   && (old_state == TCP_CONNTRACK_SYN_RECV
 		       || old_state == TCP_CONNTRACK_ESTABLISHED)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 038eee5c8f85..2bb801e3ee8c 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -487,6 +487,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -749,7 +782,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index f02b3605823e..1fb2258c3535 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb,
 			 struct nf_conntrack_expect *exp)
 {
 	char buffer[sizeof("4294967296 65635")];
+	struct nf_conn *ct = exp->master;
+	union nf_inet_addr newaddr;
 	u_int16_t port;
 	unsigned int ret;
 
 	/* Reply comes from server. */
+	newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
+
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
 	exp->dir = IP_CT_DIR_REPLY;
 	exp->expectfn = nf_nat_follow_master;
@@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb,
 	}
 
 	if (port == 0) {
-		nf_ct_helper_log(skb, exp->master, "all ports in use");
+		nf_ct_helper_log(skb, ct, "all ports in use");
 		return NF_DROP;
 	}
 
-	ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo,
-				       protoff, matchoff, matchlen, buffer,
-				       strlen(buffer));
+	/* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27
+	 * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28
+	 * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27
+	 *
+	 * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits,
+	 *                        255.255.255.255==4294967296, 10 digits)
+	 * P:         bound port (min 1 d, max 5d (65635))
+	 * F:         filename   (min 1 d )
+	 * S:         size       (min 1 d )
+	 * 0x01, \n:  terminators
+	 */
+	/* AAA = "us", ie. where server normally talks to. */
+	snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port);
+	pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
+		 buffer, &newaddr.ip, port);
+
+	ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+				       matchlen, buffer, strlen(buffer));
 	if (ret != NF_ACCEPT) {
-		nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
+		nf_ct_helper_log(skb, ct, "cannot mangle packet");
 		nf_ct_unexpect_related(exp);
 	}
+
 	return ret;
 }
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 572d87dc116f..0a03662bfbef 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -147,7 +147,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	const struct nfnetlink_subsystem *ss;
 	int type, err;
 
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	/* All the messages must at least contain nfgenmsg */
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 962e9792e317..216261dd32ae 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -45,7 +45,8 @@
 #define NFULNL_NLBUFSIZ_DEFAULT	NLMSG_GOODSIZE
 #define NFULNL_TIMEOUT_DEFAULT 	100	/* every second */
 #define NFULNL_QTHRESH_DEFAULT 	100	/* 100 packets */
-#define NFULNL_COPY_RANGE_MAX	0xFFFF	/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+#define NFULNL_COPY_RANGE_MAX	(0xFFFF - NLA_HDRLEN)
 
 #define PRINTR(x, args...)	do { if (net_ratelimit()) \
 				     printk(x, ## args); } while (0);
@@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode,
 
 	case NFULNL_COPY_PACKET:
 		inst->copy_mode = mode;
+		if (range == 0)
+			range = NFULNL_COPY_RANGE_MAX;
 		inst->copy_range = min_t(unsigned int,
 					 range, NFULNL_COPY_RANGE_MAX);
 		break;
@@ -345,26 +348,25 @@ nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size)
 	return skb;
 }
 
-static int
+static void
 __nfulnl_send(struct nfulnl_instance *inst)
 {
-	int status = -1;
-
 	if (inst->qlen > 1) {
 		struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0,
 						 NLMSG_DONE,
 						 sizeof(struct nfgenmsg),
 						 0);
-		if (!nlh)
+		if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n",
+			      inst->skb->len, skb_tailroom(inst->skb))) {
+			kfree_skb(inst->skb);
 			goto out;
+		}
 	}
-	status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
-				   MSG_DONTWAIT);
-
+	nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
+			  MSG_DONTWAIT);
+out:
 	inst->qlen = 0;
 	inst->skb = NULL;
-out:
-	return status;
 }
 
 static void
@@ -647,7 +649,8 @@ nfulnl_log_packet(struct net *net,
 		+ nla_total_size(sizeof(u_int32_t))	/* gid */
 		+ nla_total_size(plen)			/* prefix */
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
-		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp));
+		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
+		+ nla_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
 
 	if (in && skb_mac_header_was_set(skb)) {
 		size +=   nla_total_size(skb->dev->hard_header_len)
@@ -676,8 +679,7 @@ nfulnl_log_packet(struct net *net,
 		break;
 
 	case NFULNL_COPY_PACKET:
-		if (inst->copy_range == 0
-		    || inst->copy_range > skb->len)
+		if (inst->copy_range > skb->len)
 			data_len = skb->len;
 		else
 			data_len = inst->copy_range;
@@ -690,8 +692,7 @@ nfulnl_log_packet(struct net *net,
 		goto unlock_and_release;
 	}
 
-	if (inst->skb &&
-	    size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) {
+	if (inst->skb && size > skb_tailroom(inst->skb)) {
 		/* either the queue len is too high or we don't have
 		 * enough room in the skb left. flush to userspace. */
 		__nfulnl_flush(inst);
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 5352b2d2d5bf..2b8199f68785 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -227,22 +227,23 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
 	spin_unlock_bh(&queue->lock);
 }
 
-static void
+static int
 nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
 {
 	int i, j = 0;
 	int plen = 0; /* length of skb->head fragment */
+	int ret;
 	struct page *page;
 	unsigned int offset;
 
 	/* dont bother with small payloads */
-	if (len <= skb_tailroom(to)) {
-		skb_copy_bits(from, 0, skb_put(to, len), len);
-		return;
-	}
+	if (len <= skb_tailroom(to))
+		return skb_copy_bits(from, 0, skb_put(to, len), len);
 
 	if (hlen) {
-		skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		if (unlikely(ret))
+			return ret;
 		len -= hlen;
 	} else {
 		plen = min_t(int, skb_headlen(from), len);
@@ -260,6 +261,11 @@ nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
 	to->len += len + plen;
 	to->data_len += len + plen;
 
+	if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+		skb_tx_error(from);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
 		if (!len)
 			break;
@@ -270,6 +276,8 @@ nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
 		j++;
 	}
 	skb_shinfo(to)->nr_frags = j;
+
+	return 0;
 }
 
 static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet)
@@ -355,13 +363,16 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 
 	skb = nfnetlink_alloc_skb(&init_net, size, queue->peer_portid,
 				  GFP_ATOMIC);
-	if (!skb)
+	if (!skb) {
+		skb_tx_error(entskb);
 		return NULL;
+	}
 
 	nlh = nlmsg_put(skb, 0, 0,
 			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh) {
+		skb_tx_error(entskb);
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -481,13 +492,15 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 		nla->nla_type = NFQA_PAYLOAD;
 		nla->nla_len = nla_attr_size(data_len);
 
-		nfqnl_zcopy(skb, entskb, data_len, hlen);
+		if (nfqnl_zcopy(skb, entskb, data_len, hlen))
+			goto nla_put_failure;
 	}
 
 	nlh->nlmsg_len = skb->len;
 	return skb;
 
 nla_put_failure:
+	skb_tx_error(entskb);
 	kfree_skb(skb);
 	net_err_ratelimited("nf_queue: error creating packet message\n");
 	return NULL;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 57ee84d21470..afe41178c9fb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -500,7 +500,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		while (nlk->cb != NULL && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -571,7 +571,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 	 * after validation, the socket and the ring may only be used by a
 	 * single process, otherwise we fall back to copying.
 	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
+	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
 	    atomic_read(&nlk->mapped) > 1)
 		excl = false;
 
@@ -1219,7 +1219,74 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			struct user_namespace *user_ns, int cap)
+{
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *user_ns, int cap)
+{
+	return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1287,7 +1354,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 
 	/* Only superuser is allowed to listen multicasts */
 	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
@@ -1349,7 +1416,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if (nladdr->nl_groups && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -1921,7 +1988,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
@@ -2053,6 +2120,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2072,8 +2140,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2103,6 +2172,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2168,8 +2238,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
-	msg->msg_namelen = 0;
-
 	copied = data_skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
@@ -2204,7 +2272,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 393f17eea1a2..ade434b8abd8 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -592,7 +592,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
 		return -EOPNOTSUPP;
 
 	if ((ops->flags & GENL_ADMIN_PERM) &&
-	    !capable(CAP_NET_ADMIN))
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index ec0c80fde69f..13b92982a506 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sax->sax25_family = AF_NETROM;
 		skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
 			      AX25_ADDR_LEN);
+		msg->msg_namelen = sizeof(*sax);
 	}
 
-	msg->msg_namelen = sizeof(*sax);
-
 	skb_free_datagram(sk, skb);
 
 	release_sock(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 7522c3708723..86470cf54cee 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -800,8 +800,6 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	pr_debug("%p %zu\n", sk, len);
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state == LLCP_CLOSED &&
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 313bf1bc848a..5d11f4ac3ecb 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return rc;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 894b6cbdd929..c4779ca59032 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -40,6 +40,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 static int make_writable(struct sk_buff *skb, int write_len)
 {
+	if (!pskb_may_pull(skb, write_len))
+		return -ENOMEM;
+
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 
@@ -68,6 +71,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 
 	vlan_set_encap_proto(skb, vhdr);
 	skb->mac_header += VLAN_HLEN;
+	if (skb_network_offset(skb) < ETH_HLEN)
+		skb_set_network_header(skb, ETH_HLEN);
 	skb_reset_mac_len(skb);
 
 	return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a6895ab597c2..81b4b816f131 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -237,6 +237,30 @@ struct packet_skb_cb {
 static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
 static void __fanout_link(struct sock *sk, struct packet_sock *po);
 
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = rcu_dereference(po->cached_dev);
+	if (likely(dev))
+		dev_hold(dev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
+static void packet_cached_dev_assign(struct packet_sock *po,
+				     struct net_device *dev)
+{
+	rcu_assign_pointer(po->cached_dev, dev);
+}
+
+static void packet_cached_dev_reset(struct packet_sock *po)
+{
+	RCU_INIT_POINTER(po->cached_dev, NULL);
+}
+
 /* register_prot_hook must be invoked with the po->bind_lock held,
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
@@ -244,11 +268,13 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static void register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (!po->running) {
 		if (po->fanout)
 			__fanout_link(sk, po);
 		else
 			dev_add_pack(&po->prot_hook);
+
 		sock_hold(sk);
 		po->running = 1;
 	}
@@ -266,10 +292,12 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
 	struct packet_sock *po = pkt_sk(sk);
 
 	po->running = 0;
+
 	if (po->fanout)
 		__fanout_unlink(sk, po);
 	else
 		__dev_remove_pack(&po->prot_hook);
+
 	__sock_put(sk);
 
 	if (sync) {
@@ -432,9 +460,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
 
 	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
 
-	spin_lock(&rb_queue->lock);
+	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
-	spin_unlock(&rb_queue->lock);
+	spin_unlock_bh(&rb_queue->lock);
 
 	prb_del_retire_blk_timer(pkc);
 }
@@ -537,6 +565,7 @@ static void init_prb_bdqc(struct packet_sock *po,
 	p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
 	p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
 
+	p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
 	prb_init_ft_ops(p1, req_u);
 	prb_setup_retire_blk_timer(po, tx_ring);
 	prb_open_block(p1, pbd);
@@ -1775,6 +1804,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			if ((int)snaplen < 0)
 				snaplen = 0;
 		}
+	} else if (unlikely(macoff + snaplen >
+			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
+		u32 nval;
+
+		nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff;
+		pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n",
+			    snaplen, nval, macoff);
+		snaplen = nval;
+		if (unlikely((int)snaplen < 0)) {
+			snaplen = 0;
+			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);
 	h.raw = packet_current_rx_frame(po, skb,
@@ -2046,7 +2087,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	int err, reserve = 0;
 	void *ph;
 	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2058,8 +2098,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	mutex_lock(&po->pg_vec_lock);
 
-	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+	if (likely(saddr == NULL)) {
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {
@@ -2073,19 +2113,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
-
-	reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	reserve = dev->hard_header_len;
+
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
@@ -2162,8 +2200,7 @@ out_status:
 	__packet_set_status(po, ph, status);
 	kfree_skb(skb);
 out_put:
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 out:
 	mutex_unlock(&po->pg_vec_lock);
 	return err;
@@ -2201,7 +2238,6 @@ static int packet_snd(struct socket *sock,
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	unsigned char *addr;
 	int err, reserve = 0;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2216,8 +2252,8 @@ static int packet_snd(struct socket *sock,
 	 *	Get and verify the address.
 	 */
 
-	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+	if (likely(saddr == NULL)) {
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {
@@ -2229,19 +2265,17 @@ static int packet_snd(struct socket *sock,
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
-	if (dev == NULL)
+	if (unlikely(dev == NULL))
 		goto out_unlock;
-	if (sock->type == SOCK_RAW)
-		reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
-	if (!(dev->flags & IFF_UP))
+	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	if (sock->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	if (po->has_vnet_hdr) {
 		vnet_hdr_len = sizeof(vnet_hdr);
 
@@ -2375,15 +2409,14 @@ static int packet_snd(struct socket *sock,
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 
 	return len;
 
 out_free:
 	kfree_skb(skb);
 out_unlock:
-	if (dev && need_rls_dev)
+	if (dev)
 		dev_put(dev);
 out:
 	return err;
@@ -2428,6 +2461,8 @@ static int packet_release(struct socket *sock)
 
 	spin_lock(&po->bind_lock);
 	unregister_prot_hook(sk, false);
+	packet_cached_dev_reset(po);
+
 	if (po->prot_hook.dev) {
 		dev_put(po->prot_hook.dev);
 		po->prot_hook.dev = NULL;
@@ -2483,14 +2518,17 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc
 
 	spin_lock(&po->bind_lock);
 	unregister_prot_hook(sk, true);
+
 	po->num = protocol;
 	po->prot_hook.type = protocol;
 	if (po->prot_hook.dev)
 		dev_put(po->prot_hook.dev);
-	po->prot_hook.dev = dev;
 
+	po->prot_hook.dev = dev;
 	po->ifindex = dev ? dev->ifindex : 0;
 
+	packet_cached_dev_assign(po, dev);
+
 	if (protocol == 0)
 		goto out_unlock;
 
@@ -2604,6 +2642,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
 
+	packet_cached_dev_reset(po);
+
 	sk->sk_destruct = packet_sock_destruct;
 	sk_refcnt_debug_inc(sk);
 
@@ -2694,7 +2734,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
-	struct sockaddr_ll *sll;
 	int vnet_hdr_len = 0;
 
 	err = -EINVAL;
@@ -2777,22 +2816,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			goto out_free;
 	}
 
-	/*
-	 *	If the address length field is there to be filled in, we fill
-	 *	it in now.
-	 */
-
-	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	if (sock->type == SOCK_PACKET)
-		msg->msg_namelen = sizeof(struct sockaddr_pkt);
-	else
-		msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
-	/*
-	 *	You lose any data beyond the buffer you gave. If it worries a
-	 *	user program they can ask the device for its MTU anyway.
+	/* You lose any data beyond the buffer you gave. If it worries
+	 * a user program they can ask the device for its MTU
+	 * anyway.
 	 */
-
 	copied = skb->len;
 	if (copied > len) {
 		copied = len;
@@ -2805,9 +2832,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
+		/* If the address length field is there to be filled
+		 * in, we fill it in now.
+		 */
+		if (sock->type == SOCK_PACKET) {
+			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+		} else {
+			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+			msg->msg_namelen = sll->sll_halen +
+				offsetof(struct sockaddr_ll, sll_addr);
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
 		       msg->msg_namelen);
+	}
 
 	if (pkt_sk(sk)->auxdata) {
 		struct tpacket_auxdata aux;
@@ -3358,6 +3396,7 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void
 						sk->sk_error_report(sk);
 				}
 				if (msg == NETDEV_UNREGISTER) {
+					packet_cached_dev_reset(po);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
@@ -3616,6 +3655,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
 			goto out;
+		if (po->tp_version >= TPACKET_V3 &&
+		    (int)(req->tp_block_size -
+			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
 			goto out;
diff --git a/net/packet/diag.c b/net/packet/diag.c
index a9584a2f6d69..674b0a65df6c 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -127,6 +127,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct packet_diag_req *req,
+			bool may_report_filterinfo,
 			struct user_namespace *user_ns,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
 {
@@ -171,7 +172,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 		goto out_nlmsg_trim;
 
 	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
-	    sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+	    sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
 	return nlmsg_end(skb, nlh);
@@ -187,9 +189,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	struct packet_diag_req *req;
 	struct net *net;
 	struct sock *sk;
+	bool may_report_filterinfo;
 
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
+	may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
 
 	mutex_lock(&net->packet.sklist_lock);
 	sk_for_each(sk, &net->packet.sklist) {
@@ -199,6 +203,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			goto next;
 
 		if (sk_diag_fill(sk, skb, req,
+				 may_report_filterinfo,
 				 sk_user_ns(NETLINK_CB(cb->skb).sk),
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
diff --git a/net/packet/internal.h b/net/packet/internal.h
index c4e4b4561207..ca086c0c2c08 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -29,6 +29,7 @@ struct tpacket_kbdq_core {
 	char		*pkblk_start;
 	char		*pkblk_end;
 	int		kblk_size;
+	unsigned int	max_frame_len;
 	unsigned int	knum_blocks;
 	uint64_t	knxt_seq_num;
 	char		*prev;
@@ -113,6 +114,7 @@ struct packet_sock {
 	unsigned int		tp_loss:1;
 	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
+	struct net_device __rcu	*cached_dev;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
 };
 
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 12c30f3e643e..38946b26e471 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
 			MSG_CMSG_COMPAT))
 		goto out_nofree;
 
-	if (addr_len)
-		*addr_len = sizeof(sa);
-
 	skb = skb_recv_datagram(sk, flags, noblock, &rval);
 	if (skb == NULL)
 		goto out_nofree;
@@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
 
 	rval = (flags & MSG_TRUNC) ? skb->len : copylen;
 
-	if (msg->msg_name != NULL)
-		memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn));
+	if (msg->msg_name != NULL) {
+		memcpy(msg->msg_name, &sa, sizeof(sa));
+		*addr_len = sizeof(sa);
+	}
 
 out:
 	skb_free_datagram(sk, skb);
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index dc15f4300808..b64151ade6b3 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 pnaddr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
@@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 dst;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b4c8b0022fee..ba2dffeff608 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -338,7 +338,8 @@ static int rds_ib_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support iWARP devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 8eb9501e3d60..b7ebe23cdedf 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 				 struct rds_ib_refill_cache *cache)
 {
 	unsigned long flags;
-	struct list_head *old;
-	struct list_head __percpu *chpfirst;
+	struct list_head *old, *chpfirst;
 
 	local_irq_save(flags);
 
@@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	else /* put on front */
 		list_add_tail(new_item, chpfirst);
 
-	__this_cpu_write(chpfirst, new_item);
+	__this_cpu_write(cache->percpu->first, new_item);
 	__this_cpu_inc(cache->percpu->count);
 
 	if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT)
@@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	} while (old);
 
 
-	__this_cpu_write(chpfirst, NULL);
+	__this_cpu_write(cache->percpu->first, NULL);
 	__this_cpu_write(cache->percpu->count, 0);
 end:
 	local_irq_restore(flags);
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index e59094981175..37be6e226d1b 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -552,9 +552,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 	    && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
 		rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
 		scat = &rm->data.op_sg[sg];
-		ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
-		ret = min_t(int, ret, scat->length - conn->c_xmit_data_off);
-		return ret;
+		ret = max_t(int, RDS_CONG_MAP_BYTES, scat->length);
+		return sizeof(struct rds_header) + ret;
 	}
 
 	/* FIXME we may overallocate here */
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 7826d46baa70..589935661d66 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9f0f17cf6bf9..de339b24ca14 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 
 	rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
 
-	msg->msg_namelen = 0;
-
 	if (msg_flags & MSG_OOB)
 		goto out;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9c8347451597..27e6896705e6 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
-	struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
 	size_t copied;
 	unsigned char *asmptr;
 	struct sk_buff *skb;
@@ -1252,24 +1251,19 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (srose != NULL) {
-		memset(srose, 0, msg->msg_namelen);
+	if (msg->msg_name) {
+		struct sockaddr_rose *srose;
+		struct full_sockaddr_rose *full_srose = msg->msg_name;
+
+		memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+		srose = msg->msg_name;
 		srose->srose_family = AF_ROSE;
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;
 		srose->srose_ndigis = rose->dest_ndigis;
-		if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) {
-			struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name;
-			for (n = 0 ; n < rose->dest_ndigis ; n++)
-				full_srose->srose_digis[n] = rose->dest_digis[n];
-			msg->msg_namelen = sizeof(struct full_sockaddr_rose);
-		} else {
-			if (rose->dest_ndigis >= 1) {
-				srose->srose_ndigis = 1;
-				srose->srose_digi = rose->dest_digis[0];
-			}
-			msg->msg_namelen = sizeof(struct sockaddr_rose);
-		}
+		for (n = 0 ; n < rose->dest_ndigis ; n++)
+			full_srose->srose_digis[n] = rose->dest_digis[n];
+		msg->msg_namelen = sizeof(struct full_sockaddr_rose);
 	}
 
 	skb_free_datagram(sk, skb);
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4b48687c3890..898492a8d61b 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 		/* copy the peer address and timestamp */
 		if (!continue_call) {
-			if (msg->msg_name && msg->msg_namelen > 0)
+			if (msg->msg_name) {
+				size_t len =
+					sizeof(call->conn->trans->peer->srx);
 				memcpy(msg->msg_name,
-				       &call->conn->trans->peer->srx,
-				       sizeof(call->conn->trans->peer->srx));
+				       &call->conn->trans->peer->srx, len);
+				msg->msg_namelen = len;
+			}
 			sock_recv_ts_and_drops(msg, &rx->sk, skb);
 		}
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fd7072827a40..15d46b9166de 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -989,7 +989,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8e118af90973..2ea40d1877a6 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -138,7 +138,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	int err;
 	int tp_created = 0;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 51b968d3febb..2d2f07945c85 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1024,7 +1024,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1091,7 +1091,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1431,7 +1431,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 910667cbc1e3..e09b074bb8a7 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1476,7 +1476,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
 
 	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
-	cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer);
+	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
 
 	sch_tree_unlock(sch);
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 91cfd8f94a19..ca4a1a1b8e69 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -387,7 +387,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening
@@ -1213,6 +1213,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->c = new->c;
 	asoc->peer.rwnd = new->peer.rwnd;
 	asoc->peer.sack_needed = new->peer.sack_needed;
+	asoc->peer.auth_capable = new->peer.auth_capable;
 	asoc->peer.i = new->peer.i;
 	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
 			 asoc->peer.i.initial_tsn, GFP_ATOMIC);
@@ -1658,6 +1659,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 	 * ack chunk whose serial number matches that of the request.
 	 */
 	list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) {
+		if (sctp_chunk_pending(ack))
+			continue;
 		if (ack->subh.addip_hdr->serial == serial) {
 			sctp_chunk_hold(ack);
 			return ack;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index ba1dfc3f8def..bc2fae7e67be 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -393,14 +393,13 @@ nomem:
  */
 int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 {
-	struct net *net = sock_net(asoc->base.sk);
 	struct sctp_auth_bytes	*secret;
 	struct sctp_shared_key *ep_key;
 
 	/* If we don't support AUTH, or peer is not capable
 	 * we don't need to do anything.
 	 */
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	/* If the key_id is non-zero and we couldn't find an
@@ -447,16 +446,16 @@ struct sctp_shared_key *sctp_auth_get_shkey(
  */
 int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 {
-	struct net *net = sock_net(ep->base.sk);
 	struct crypto_hash *tfm = NULL;
 	__u16   id;
 
-	/* if the transforms are already allocted, we are done */
-	if (!net->sctp.auth_enable) {
+	/* If AUTH extension is disabled, we are done */
+	if (!ep->auth_enable) {
 		ep->auth_hmacs = NULL;
 		return 0;
 	}
 
+	/* If the transforms are already allocated, we are done */
 	if (ep->auth_hmacs)
 		return 0;
 
@@ -677,12 +676,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param)
 /* Check if peer requested that this chunk is authenticated */
 int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net  *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	return __sctp_auth_cid(chunk, asoc->peer.peer_chunks);
@@ -691,12 +688,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 /* Check if we requested that peer authenticate this chunk. */
 int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable)
+	if (!asoc->ep->auth_enable)
 		return 0;
 
 	return __sctp_auth_cid(chunk,
@@ -879,8 +874,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 		list_add(&cur_key->key_list, sh_keys);
 
 	cur_key->key = key;
-	sctp_auth_key_hold(key);
-
 	return 0;
 nomem:
 	if (!replace)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 5fbd7bc6bb11..e09f906514db 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -75,7 +75,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	if (!ep->digest)
 		return NULL;
 
-	if (net->sctp.auth_enable) {
+	ep->auth_enable = net->sctp.auth_enable;
+	if (ep->auth_enable) {
 		/* Allocate space for HMACS and CHUNKS authentication
 		 * variables.  There are arrays that we encode directly
 		 * into parameters to make the rest of the operations easier.
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 4b2c83146aa7..bd4fb459c63b 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -648,8 +648,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 		break;
 	case ICMP_REDIRECT:
 		sctp_icmp_redirect(sk, transport, skb);
-		err = 0;
-		break;
+		/* Fall through to out_unlock. */
 	default:
 		goto out_unlock;
 	}
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 3221d073448c..49c58eadbfa2 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -147,18 +147,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 		} else {
 			/* Nothing to do. Next chunk in the packet, please. */
 			ch = (sctp_chunkhdr_t *) chunk->chunk_end;
-
 			/* Force chunk->skb->data to chunk->chunk_end.  */
-			skb_pull(chunk->skb,
-				 chunk->chunk_end - chunk->skb->data);
-
-			/* Verify that we have at least chunk headers
-			 * worth of buffer left.
-			 */
-			if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
-				sctp_chunk_free(chunk);
-				chunk = queue->in_progress = NULL;
-			}
+			skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data);
+			/* We are guaranteed to pull a SCTP header. */
 		}
 	}
 
@@ -194,24 +185,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 
-	if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
+	if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) <
+	    skb_tail_pointer(chunk->skb)) {
 		/* This is not a singleton */
 		chunk->singleton = 0;
 	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
-		/* RFC 2960, Section 6.10  Bundling
-		 *
-		 * Partial chunks MUST NOT be placed in an SCTP packet.
-		 * If the receiver detects a partial chunk, it MUST drop
-		 * the chunk.
-		 *
-		 * Since the end of the chunk is past the end of our buffer
-		 * (which contains the whole packet, we can freely discard
-		 * the whole packet.
-		 */
-		sctp_chunk_free(chunk);
-		chunk = queue->in_progress = NULL;
-
-		return NULL;
+		/* Discard inside state machine. */
+		chunk->pdiscard = 1;
+		chunk->chunk_end = skb_tail_pointer(chunk->skb);
 	} else {
 		/* We are at the end of the packet, so mark the chunk
 		 * in case we need to send a SACK.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 391a245d5203..422d8bdacc0d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -189,7 +189,7 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		break;
 	case NDISC_REDIRECT:
 		sctp_icmp_redirect(sk, transport, skb);
-		break;
+		goto out_unlock;
 	default:
 		break;
 	}
@@ -210,45 +210,24 @@ out:
 		in6_dev_put(idev);
 }
 
-/* Based on tcp_v6_xmit() in tcp_ipv6.c. */
 static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 {
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flowi6 fl6;
-
-	memset(&fl6, 0, sizeof(fl6));
-
-	fl6.flowi6_proto = sk->sk_protocol;
-
-	/* Fill in the dest address from the route entry passed with the skb
-	 * and the source address from the transport.
-	 */
-	fl6.daddr = transport->ipaddr.v6.sin6_addr;
-	fl6.saddr = transport->saddr.v6.sin6_addr;
-
-	fl6.flowlabel = np->flow_label;
-	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
-	if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL)
-		fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id;
-	else
-		fl6.flowi6_oif = sk->sk_bound_dev_if;
-
-	if (np->opt && np->opt->srcrt) {
-		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
-		fl6.daddr = *rt0->addr;
-	}
+	struct flowi6 *fl6 = &transport->fl.u.ip6;
 
 	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n",
 			  __func__, skb, skb->len,
-			  &fl6.saddr, &fl6.daddr);
+			  &fl6->saddr, &fl6->daddr);
 
-	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
+	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
 		skb->local_df = 1;
 
-	return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
+
+	return ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 }
 
 /* Returns the dst cache entry for the given source and destination ip
@@ -261,10 +240,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct dst_entry *dst = NULL;
 	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sctp_bind_addr *bp;
+	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
 	union sctp_addr *baddr = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
+	struct in6_addr *final_p, final;
 	__u8 matchlen = 0;
 	__u8 bmatchlen;
 	sctp_scope_t scope;
@@ -287,7 +268,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr);
 	}
 
-	dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
+	final_p = fl6_update_dst(fl6, np->opt, &final);
+	dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
 	if (!asoc || saddr)
 		goto out;
 
@@ -339,10 +321,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		}
 	}
 	rcu_read_unlock();
+
 	if (baddr) {
 		fl6->saddr = baddr->v6.sin6_addr;
 		fl6->fl6_sport = baddr->v6.sin6_port;
-		dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
+		final_p = fl6_update_dst(fl6, np->opt, &final);
+		dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
 	}
 
 out:
diff --git a/net/sctp/output.c b/net/sctp/output.c
index bbef4a7a9b56..73b8ca51ba14 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -413,12 +413,12 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	sk = chunk->skb->sk;
 
 	/* Allocate the new skb.  */
-	nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
 		goto nomem;
 
 	/* Make sure the outbound skb has enough header room reserved. */
-	skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+	skb_reserve(nskb, packet->overhead + MAX_HEADER);
 
 	/* Set the owning socket so that we know where to get the
 	 * destination IP address.
@@ -547,7 +547,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	 * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
 	 */
 	if (!sctp_checksum_disable) {
-		if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) {
+		if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
+		    (dst_xfrm(dst) != NULL) || packet->ipfragok) {
 			__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
 
 			/* 3) Put the resultant value into the checksum field in the
@@ -617,7 +618,7 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index eaee00c61139..5a3c1c0a84a1 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -498,8 +498,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			continue;
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
-			fl4->saddr = laddr->a.v4.sin_addr.s_addr;
 			fl4->fl4_sport = laddr->a.v4.sin_port;
+			flowi4_update_output(fl4,
+					     asoc->base.sk->sk_bound_dev_if,
+					     RT_CONN_FLAGS(asoc->base.sk),
+					     daddr->v4.sin_addr.s_addr,
+					     laddr->a.v4.sin_addr.s_addr);
+
 			rt = ip_route_output_key(sock_net(sk), fl4);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index cf579e71cff0..29fc16f3633f 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -199,6 +199,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 			     gfp_t gfp, int vparam_len)
 {
 	struct net *net = sock_net(asoc->base.sk);
+	struct sctp_endpoint *ep = asoc->ep;
 	sctp_inithdr_t init;
 	union sctp_params addrs;
 	size_t chunksize;
@@ -258,7 +259,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	chunksize += vparam_len;
 
 	/* Account for AUTH related parameters */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		/* Add random parameter length*/
 		chunksize += sizeof(asoc->c.auth_random);
 
@@ -343,7 +344,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	}
 
 	/* Add SCTP-AUTH chunks to the parameter list */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		sctp_addto_chunk(retval, sizeof(asoc->c.auth_random),
 				 asoc->c.auth_random);
 		if (auth_hmacs)
@@ -1403,8 +1404,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk)
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);
@@ -1995,7 +1996,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
 			    /* if the peer reports AUTH, assume that he
 			     * supports AUTH.
 			     */
-			    if (net->sctp.auth_enable)
+			    if (asoc->ep->auth_enable)
 				    asoc->peer.auth_capable = 1;
 			    break;
 		    case SCTP_CID_ASCONF:
@@ -2087,6 +2088,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc,
  * 	SCTP_IERROR_NO_ERROR - continue with the chunk
  */
 static sctp_ierror_t sctp_verify_param(struct net *net,
+					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
 					union sctp_params param,
 					sctp_cid_t cid,
@@ -2137,7 +2139,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		goto fallthrough;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Secion 6.1
@@ -2154,7 +2156,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Section 3.2
@@ -2170,7 +2172,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		hmacs = (struct sctp_hmac_algo_param *)param.p;
@@ -2204,10 +2206,9 @@ fallthrough:
 }
 
 /* Verify the INIT packet before we process it.  */
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
-		     sctp_cid_t cid,
-		     sctp_init_chunk_t *peer_init,
-		     struct sctp_chunk *chunk,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+		     const struct sctp_association *asoc, sctp_cid_t cid,
+		     sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk,
 		     struct sctp_chunk **errp)
 {
 	union sctp_params param;
@@ -2250,8 +2251,8 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
 
 	/* Verify all the variable length parameters */
 	sctp_walk_params(param, peer_init, init_hdr.params) {
-
-		result = sctp_verify_param(net, asoc, param, cid, chunk, errp);
+		result = sctp_verify_param(net, ep, asoc, param, cid,
+					   chunk, errp);
 		switch (result) {
 		    case SCTP_IERROR_ABORT:
 		    case SCTP_IERROR_NOMEM:
@@ -2483,6 +2484,7 @@ static int sctp_process_param(struct sctp_association *asoc,
 	struct sctp_af *af;
 	union sctp_addr_param *addr_param;
 	struct sctp_transport *t;
+	struct sctp_endpoint *ep = asoc->ep;
 
 	/* We maintain all INIT parameters in network byte order all the
 	 * time.  This allows us to not worry about whether the parameters
@@ -2594,6 +2596,9 @@ do_addr_param:
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
 		af = sctp_get_af_specific(param_type2af(param.p->type));
+		if (af == NULL)
+			break;
+
 		af->from_addr_param(&addr, addr_param,
 				    htons(asoc->peer.port), 0);
 
@@ -2623,7 +2628,7 @@ do_addr_param:
 		goto fall_through;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's random parameter */
@@ -2636,7 +2641,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's HMAC list */
@@ -2652,7 +2657,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		asoc->peer.peer_chunks = kmemdup(param.p,
@@ -3092,50 +3097,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
 	return SCTP_ERROR_NO_ERROR;
 }
 
-/* Verify the ASCONF packet before we process it.  */
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp) {
-	sctp_addip_param_t *asconf_param;
+/* Verify the ASCONF packet before we process it. */
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp)
+{
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr;
 	union sctp_params param;
-	int length, plen;
+	bool addr_param_seen = false;
 
-	param.v = (sctp_paramhdr_t *) param_hdr;
-	while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
-		length = ntohs(param.p->length);
-		*errp = param.p;
-
-		if (param.v > chunk_end - length ||
-		    length < sizeof(sctp_paramhdr_t))
-			return 0;
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		size_t length = ntohs(param.p->length);
 
+		*errp = param.p;
 		switch (param.p->type) {
+		case SCTP_PARAM_ERR_CAUSE:
+			break;
+		case SCTP_PARAM_IPV4_ADDRESS:
+			if (length != sizeof(sctp_ipv4addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
+		case SCTP_PARAM_IPV6_ADDRESS:
+			if (length != sizeof(sctp_ipv6addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
 		case SCTP_PARAM_ADD_IP:
 		case SCTP_PARAM_DEL_IP:
 		case SCTP_PARAM_SET_PRIMARY:
-			asconf_param = (sctp_addip_param_t *)param.v;
-			plen = ntohs(asconf_param->param_hdr.length);
-			if (plen < sizeof(sctp_addip_param_t) +
-			    sizeof(sctp_paramhdr_t))
-				return 0;
+			/* In ASCONF chunks, these need to be first. */
+			if (addr_param_needed && !addr_param_seen)
+				return false;
+			length = ntohs(param.addip->param_hdr.length);
+			if (length < sizeof(sctp_addip_param_t) +
+				     sizeof(sctp_paramhdr_t))
+				return false;
 			break;
 		case SCTP_PARAM_SUCCESS_REPORT:
 		case SCTP_PARAM_ADAPTATION_LAYER_IND:
 			if (length != sizeof(sctp_addip_param_t))
-				return 0;
-
+				return false;
 			break;
 		default:
-			break;
+			/* This is unkown to us, reject! */
+			return false;
 		}
-
-		param.v += WORD_ROUND(length);
 	}
 
-	if (param.v != chunk_end)
-		return 0;
+	/* Remaining sanity checks. */
+	if (addr_param_needed && !addr_param_seen)
+		return false;
+	if (!addr_param_needed && addr_param_seen)
+		return false;
+	if (param.v != chunk->chunk_end)
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* Process an incoming ASCONF chunk with the next expected serial no. and
@@ -3144,16 +3162,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc,
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf)
 {
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr;
+	bool all_param_pass = true;
+	union sctp_params param;
 	sctp_addiphdr_t		*hdr;
 	union sctp_addr_param	*addr_param;
 	sctp_addip_param_t	*asconf_param;
 	struct sctp_chunk	*asconf_ack;
-
 	__be16	err_code;
 	int	length = 0;
 	int	chunk_len;
 	__u32	serial;
-	int	all_param_pass = 1;
 
 	chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
 	hdr = (sctp_addiphdr_t *)asconf->skb->data;
@@ -3181,9 +3200,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		goto done;
 
 	/* Process the TLVs contained within the ASCONF chunk. */
-	while (chunk_len > 0) {
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		/* Skip preceeding address parameters. */
+		if (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+		    param.p->type == SCTP_PARAM_IPV6_ADDRESS)
+			continue;
+
 		err_code = sctp_process_asconf_param(asoc, asconf,
-						     asconf_param);
+						     param.addip);
 		/* ADDIP 4.1 A7)
 		 * If an error response is received for a TLV parameter,
 		 * all TLVs with no response before the failed TLV are
@@ -3191,28 +3215,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		 * the failed response are considered unsuccessful unless
 		 * a specific success indication is present for the parameter.
 		 */
-		if (SCTP_ERROR_NO_ERROR != err_code)
-			all_param_pass = 0;
-
+		if (err_code != SCTP_ERROR_NO_ERROR)
+			all_param_pass = false;
 		if (!all_param_pass)
-			sctp_add_asconf_response(asconf_ack,
-						 asconf_param->crr_id, err_code,
-						 asconf_param);
+			sctp_add_asconf_response(asconf_ack, param.addip->crr_id,
+						 err_code, param.addip);
 
 		/* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add
 		 * an IP address sends an 'Out of Resource' in its response, it
 		 * MUST also fail any subsequent add or delete requests bundled
 		 * in the ASCONF.
 		 */
-		if (SCTP_ERROR_RSRC_LOW == err_code)
+		if (err_code == SCTP_ERROR_RSRC_LOW)
 			goto done;
-
-		/* Move to the next ASCONF param. */
-		length = ntohs(asconf_param->param_hdr.length);
-		asconf_param = (void *)asconf_param + length;
-		chunk_len -= length;
 	}
-
 done:
 	asoc->peer.addip_serial++;
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index de1a0138317f..c52763a26297 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -177,6 +177,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk,
 {
 	__u16 chunk_length = ntohs(chunk->chunk_hdr->length);
 
+	/* Previously already marked? */
+	if (unlikely(chunk->pdiscard))
+		return 0;
 	if (unlikely(chunk_length < required_length))
 		return 0;
 
@@ -364,7 +367,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -531,7 +534,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 
@@ -765,6 +768,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
 		struct sctp_chunk auth;
 		sctp_ierror_t ret;
 
+		/* Make sure that we and the peer are AUTH capable */
+		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+			sctp_association_free(new_asoc);
+			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+		}
+
 		/* set-up our fake chunk so that we can process it */
 		auth.skb = chunk->auth_chunk;
 		auth.asoc = chunk->asoc;
@@ -775,10 +784,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -1435,7 +1440,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init(
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -1780,9 +1785,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net,
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-			SCTP_STATE(SCTP_STATE_ESTABLISHED));
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	    (sctp_sstate(asoc->base.sk, CLOSING) ||
+	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
+		/* if were currently in SHUTDOWN_PENDING, but the socket
+		 * has been closed by user, don't transition to ESTABLISHED.
+		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		 */
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
+						     SCTP_ST_CHUNK(0), NULL,
+						     commands);
+	} else {
+		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
+				SCTP_STATE(SCTP_STATE_ESTABLISHED));
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	}
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem_ev:
@@ -3578,9 +3596,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	struct sctp_chunk	*asconf_ack = NULL;
 	struct sctp_paramhdr	*err_param = NULL;
 	sctp_addiphdr_t		*hdr;
-	union sctp_addr_param	*addr_param;
 	__u32			serial;
-	int			length;
 
 	if (!sctp_vtag_verify(chunk, asoc)) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
@@ -3605,17 +3621,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	hdr = (sctp_addiphdr_t *)chunk->skb->data;
 	serial = ntohl(hdr->serial);
 
-	addr_param = (union sctp_addr_param *)hdr->params;
-	length = ntohs(addr_param->p.length);
-	if (length < sizeof(sctp_paramhdr_t))
-		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
-			   (void *)addr_param, commands);
-
 	/* Verify the ASCONF chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-			    (sctp_paramhdr_t *)((void *)addr_param + length),
-			    (void *)chunk->chunk_end,
-			    &err_param))
+	if (!sctp_verify_asconf(asoc, chunk, true, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 						  (void *)err_param, commands);
 
@@ -3733,10 +3740,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
 	rcvd_serial = ntohl(addip_hdr->serial);
 
 	/* Verify the ASCONF-ACK chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-	    (sctp_paramhdr_t *)addip_hdr->params,
-	    (void *)asconf_ack->chunk_end,
-	    &err_param))
+	if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 			   (void *)err_param, commands);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6abb1caf9836..dfb9b133e662 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -71,6 +71,7 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -820,6 +821,9 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
 			goto skip_mkasconf;
 		}
 
+		if (laddr == NULL)
+			return -EINVAL;
+
 		/* We do not need RCU protection throughout this loop
 		 * because this is done under a socket lock from the
 		 * setsockopt call.
@@ -1381,11 +1385,19 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk,
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+	sctp_assoc_t	assoc_id;
+	s32		addr_num;
+	compat_uptr_t	addrs;		/* struct sockaddr * */
+};
+#endif
+
 SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len,
 					char __user *optval,
 					int __user *optlen)
@@ -1394,16 +1406,30 @@ SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len,
 	sctp_assoc_t assoc_id = 0;
 	int err = 0;
 
-	if (len < sizeof(param))
-		return -EINVAL;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		struct compat_sctp_getaddrs_old param32;
 
-	if (copy_from_user(&param, optval, sizeof(param)))
-		return -EFAULT;
+		if (len < sizeof(param32))
+			return -EINVAL;
+		if (copy_from_user(&param32, optval, sizeof(param32)))
+			return -EFAULT;
 
-	err = __sctp_setsockopt_connectx(sk,
-			(struct sockaddr __user *)param.addrs,
-			param.addr_num, &assoc_id);
+		param.assoc_id = param32.assoc_id;
+		param.addr_num = param32.addr_num;
+		param.addrs = compat_ptr(param32.addrs);
+	} else
+#endif
+	{
+		if (len < sizeof(param))
+			return -EINVAL;
+		if (copy_from_user(&param, optval, sizeof(param)))
+			return -EFAULT;
+	}
 
+	err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+					 param.addrs, param.addr_num,
+					 &assoc_id);
 	if (err == 0 || err == -EINPROGRESS) {
 		if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
 			return -EFAULT;
@@ -3292,10 +3318,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunk val;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authchunk))
@@ -3312,7 +3338,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 	}
 
 	/* add this chunk id to the endpoint */
-	return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk);
+	return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk);
 }
 
 /*
@@ -3325,12 +3351,12 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo *hmacs;
 	u32 idents;
 	int err;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen < sizeof(struct sctp_hmacalgo))
@@ -3347,7 +3373,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 		goto out;
 	}
 
-	err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs);
+	err = sctp_auth_ep_set_hmacs(ep, hmacs);
 out:
 	kfree(hmacs);
 	return err;
@@ -3363,12 +3389,12 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 				    char __user *optval,
 				    unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkey *authkey;
 	struct sctp_association *asoc;
 	int ret;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen <= sizeof(struct sctp_authkey))
@@ -3389,7 +3415,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 		goto out;
 	}
 
-	ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey);
+	ret = sctp_auth_set_key(ep, asoc, authkey);
 out:
 	kzfree(authkey);
 	return ret;
@@ -3405,11 +3431,11 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3421,8 +3447,7 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc,
-					val.scact_keynumber);
+	return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
 }
 
 /*
@@ -3434,11 +3459,11 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 				   char __user *optval,
 				   unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3450,8 +3475,7 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc,
-				    val.scact_keynumber);
+	return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
 
 }
 
@@ -5342,16 +5366,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len,
 static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo  __user *p = (void __user *)optval;
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
-	hmacs = sctp_sk(sk)->ep->auth_hmacs_list;
+	hmacs = ep->auth_hmacs_list;
 	data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t);
 
 	if (len < sizeof(struct sctp_hmacalgo) + data_len)
@@ -5372,11 +5396,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 static int sctp_getsockopt_active_key(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authkeyid))
@@ -5391,7 +5415,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 	if (asoc)
 		val.scact_keynumber = asoc->active_key_id;
 	else
-		val.scact_keynumber = sctp_sk(sk)->ep->active_key_id;
+		val.scact_keynumber = ep->active_key_id;
 
 	len = sizeof(struct sctp_authkeyid);
 	if (put_user(len, optlen))
@@ -5405,7 +5429,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5413,7 +5437,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5449,7 +5473,7 @@ num:
 static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5457,7 +5481,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5474,7 +5498,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	if (asoc)
 		ch = (struct sctp_chunks_param*)asoc->c.auth_chunks;
 	else
-		ch = sctp_sk(sk)->ep->auth_chunk_list;
+		ch = ep->auth_chunk_list;
 
 	if (!ch)
 		goto num;
@@ -6193,7 +6217,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	/* Is there any exceptional events?  */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
 		mask |= POLLERR |
-			sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0;
+			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= POLLRDHUP | POLLIN | POLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -6556,6 +6580,46 @@ static void __sctp_write_space(struct sctp_association *asoc)
 	}
 }
 
+static void sctp_wake_up_waiters(struct sock *sk,
+				 struct sctp_association *asoc)
+{
+	struct sctp_association *tmp = asoc;
+
+	/* We do accounting for the sndbuf space per association,
+	 * so we only need to wake our own association.
+	 */
+	if (asoc->ep->sndbuf_policy)
+		return __sctp_write_space(asoc);
+
+	/* If association goes down and is just flushing its
+	 * outq, then just normally notify others.
+	 */
+	if (asoc->base.dead)
+		return sctp_write_space(sk);
+
+	/* Accounting for the sndbuf space is per socket, so we
+	 * need to wake up others, try to be fair and in case of
+	 * other associations, let them have a go first instead
+	 * of just doing a sctp_write_space() call.
+	 *
+	 * Note that we reach sctp_wake_up_waiters() only when
+	 * associations free up queued chunks, thus we are under
+	 * lock and the list of associations on a socket is
+	 * guaranteed not to change.
+	 */
+	for (tmp = list_next_entry(tmp, asocs); 1;
+	     tmp = list_next_entry(tmp, asocs)) {
+		/* Manually skip the head element. */
+		if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs))
+			continue;
+		/* Wake up association. */
+		__sctp_write_space(tmp);
+		/* We've reached the end. */
+		if (tmp == asoc)
+			break;
+	}
+}
+
 /* Do accounting for the sndbuf space.
  * Decrement the used sndbuf space of the corresponding association by the
  * data size which was just transmitted(freed).
@@ -6583,7 +6647,7 @@ static void sctp_wfree(struct sk_buff *skb)
 	sk_mem_uncharge(sk, skb->truesize);
 
 	sock_wfree(skb);
-	__sctp_write_space(asoc);
+	sctp_wake_up_waiters(sk, asoc);
 
 	sctp_association_put(asoc);
 }
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index bf3c6e8fc401..29299dcabfbb 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -65,8 +65,11 @@ extern int sysctl_sctp_wmem[3];
 static int proc_sctp_do_hmac_alg(ctl_table *ctl,
 				int write,
 				void __user *buffer, size_t *lenp,
-
 				loff_t *ppos);
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos);
+
 static ctl_table sctp_table[] = {
 	{
 		.procname	= "sctp_mem",
@@ -267,7 +270,7 @@ static ctl_table sctp_net_table[] = {
 		.data		= &init_net.sctp.auth_enable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_sctp_do_auth,
 	},
 	{
 		.procname	= "addr_scope_policy",
@@ -348,6 +351,36 @@ static int proc_sctp_do_hmac_alg(ctl_table *ctl,
 	return ret;
 }
 
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct ctl_table tbl;
+	int new_value, ret;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.auth_enable;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		net->sctp.auth_enable = new_value;
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->ep->auth_enable = new_value;
+		release_sock(sk);
+	}
+
+	return ret;
+}
+
 int sctp_sysctl_net_register(struct net *net)
 {
 	struct ctl_table *table;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 10c018a5b9fe..ca907f2f5e5a 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -373,9 +373,10 @@ fail:
  * specification [SCTP] and any extensions for a list of possible
  * error formats.
  */
-struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
-	const struct sctp_association *asoc, struct sctp_chunk *chunk,
-	__u16 flags, gfp_t gfp)
+struct sctp_ulpevent *
+sctp_ulpevent_make_remote_error(const struct sctp_association *asoc,
+				struct sctp_chunk *chunk, __u16 flags,
+				gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
 	struct sctp_remote_error *sre;
@@ -394,8 +395,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	/* Copy the skb to a new skb with room for us to prepend
 	 * notification with.
 	 */
-	skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
-			      0, gfp);
+	skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp);
 
 	/* Pull off the rest of the cause TLV from the chunk.  */
 	skb_pull(chunk->skb, elen);
@@ -406,62 +406,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	event = sctp_skb2event(skb);
 	sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
 
-	sre = (struct sctp_remote_error *)
-		skb_push(skb, sizeof(struct sctp_remote_error));
+	sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre));
 
 	/* Trim the buffer to the right length.  */
-	skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+	skb_trim(skb, sizeof(*sre) + elen);
 
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_type:
-	 *   It should be SCTP_REMOTE_ERROR.
-	 */
+	/* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */
+	memset(sre, 0, sizeof(*sre));
 	sre->sre_type = SCTP_REMOTE_ERROR;
-
-	/*
-	 * Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_flags: 16 bits (unsigned integer)
-	 *   Currently unused.
-	 */
 	sre->sre_flags = 0;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_length: sizeof (__u32)
-	 *
-	 * This field is the total length of the notification data,
-	 * including the notification header.
-	 */
 	sre->sre_length = skb->len;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_error: 16 bits (unsigned integer)
-	 * This value represents one of the Operational Error causes defined in
-	 * the SCTP specification, in network byte order.
-	 */
 	sre->sre_error = cause;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association id field, holds the identifier for the association.
-	 * All notifications for a given association have the same association
-	 * identifier.  For TCP style socket, this field is ignored.
-	 */
 	sctp_ulpevent_set_owner(event, asoc);
 	sre->sre_assoc_id = sctp_assoc2id(asoc);
 
 	return event;
-
 fail:
 	return NULL;
 }
@@ -906,7 +865,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event)
 	return notification->sn_header.sn_type;
 }
 
-/* Copy out the sndrcvinfo into a msghdr.  */
+/* RFC6458, Section 5.3.2. SCTP Header Information Structure
+ * (SCTP_SNDRCV, DEPRECATED)
+ */
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *msghdr)
 {
@@ -915,74 +876,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 	if (sctp_ulpevent_is_notification(event))
 		return;
 
-	/* Sockets API Extensions for SCTP
-	 * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
-	 *
-	 * sinfo_stream: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() the SCTP stack places the message's stream number in
-	 * this value.
-	*/
+	memset(&sinfo, 0, sizeof(sinfo));
 	sinfo.sinfo_stream = event->stream;
-	/* sinfo_ssn: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() this value contains the stream sequence number that
-	 * the remote endpoint placed in the DATA chunk.  For fragmented
-	 * messages this is the same number for all deliveries of the message
-	 * (if more than one recvmsg() is needed to read the message).
-	 */
 	sinfo.sinfo_ssn = event->ssn;
-	/* sinfo_ppid: 32 bits (unsigned integer)
-	 *
-	 * In recvmsg() this value is
-	 * the same information that was passed by the upper layer in the peer
-	 * application.  Please note that byte order issues are NOT accounted
-	 * for and this information is passed opaquely by the SCTP stack from
-	 * one end to the other.
-	 */
 	sinfo.sinfo_ppid = event->ppid;
-	/* sinfo_flags: 16 bits (unsigned integer)
-	 *
-	 * This field may contain any of the following flags and is composed of
-	 * a bitwise OR of these values.
-	 *
-	 * recvmsg() flags:
-	 *
-	 * SCTP_UNORDERED - This flag is present when the message was sent
-	 *                 non-ordered.
-	 */
 	sinfo.sinfo_flags = event->flags;
-	/* sinfo_tsn: 32 bit (unsigned integer)
-	 *
-	 * For the receiving side, this field holds a TSN that was
-	 * assigned to one of the SCTP Data Chunks.
-	 */
 	sinfo.sinfo_tsn = event->tsn;
-	/* sinfo_cumtsn: 32 bit (unsigned integer)
-	 *
-	 * This field will hold the current cumulative TSN as
-	 * known by the underlying SCTP layer.  Note this field is
-	 * ignored when sending and only valid for a receive
-	 * operation when sinfo_flags are set to SCTP_UNORDERED.
-	 */
 	sinfo.sinfo_cumtsn = event->cumtsn;
-	/* sinfo_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association handle field, sinfo_assoc_id, holds the identifier
-	 * for the association announced in the COMMUNICATION_UP notification.
-	 * All notifications for a given association have the same identifier.
-	 * Ignored for one-to-one style sockets.
-	 */
 	sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
-
-	/* context value that is set via SCTP_CONTEXT socket option. */
+	/* Context value that is set via SCTP_CONTEXT socket option. */
 	sinfo.sinfo_context = event->asoc->default_rcv_context;
-
 	/* These fields are not used while receiving. */
 	sinfo.sinfo_timetolive = 0;
 
 	put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
-		 sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+		 sizeof(sinfo), &sinfo);
 }
 
 /* Do accounting for bytes received and hold a reference to the association
diff --git a/net/socket.c b/net/socket.c
index 4ca1526db756..fc90b4f0da3c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -215,12 +215,13 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
 	int err;
 	int len;
 
+	BUG_ON(klen > sizeof(struct sockaddr_storage));
 	err = get_user(len, ulen);
 	if (err)
 		return err;
 	if (len > klen)
 		len = klen;
-	if (len < 0 || len > sizeof(struct sockaddr_storage))
+	if (len < 0)
 		return -EINVAL;
 	if (len) {
 		if (audit_sockaddr(klen, kaddr))
@@ -1832,8 +1833,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	msg.msg_iov = &iov;
 	iov.iov_len = size;
 	iov.iov_base = ubuf;
-	msg.msg_name = (struct sockaddr *)&address;
-	msg.msg_namelen = sizeof(address);
+	/* Save some cycles and don't copy the address if not needed */
+	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg.msg_namelen = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, size, flags);
@@ -1956,6 +1959,20 @@ struct used_address {
 	unsigned int name_len;
 };
 
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+				 struct msghdr __user *umsg)
+{
+	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
+	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
+	return 0;
+}
+
 static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
 			 struct msghdr *msg_sys, unsigned int flags,
 			 struct used_address *used_address)
@@ -1974,8 +1991,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
 	if (MSG_CMSG_COMPAT & flags) {
 		if (get_compat_msghdr(msg_sys, msg_compat))
 			return -EFAULT;
-	} else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
-		return -EFAULT;
+	} else {
+		err = copy_msghdr_from_user(msg_sys, msg);
+		if (err)
+			return err;
+	}
 
 	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
 		err = -EMSGSIZE;
@@ -2183,8 +2203,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	if (MSG_CMSG_COMPAT & flags) {
 		if (get_compat_msghdr(msg_sys, msg_compat))
 			return -EFAULT;
-	} else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
-		return -EFAULT;
+	} else {
+		err = copy_msghdr_from_user(msg_sys, msg);
+		if (err)
+			return err;
+	}
 
 	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
 		err = -EMSGSIZE;
@@ -2197,16 +2220,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 			goto out;
 	}
 
-	/*
-	 *      Save the user-mode address (verify_iovec will change the
-	 *      kernel msghdr to use the kernel address space)
+	/* Save the user-mode address (verify_iovec will change the
+	 * kernel msghdr to use the kernel address space)
 	 */
-
 	uaddr = (__force void __user *)msg_sys->msg_name;
 	uaddr_len = COMPAT_NAMELEN(msg);
-	if (MSG_CMSG_COMPAT & flags) {
+	if (MSG_CMSG_COMPAT & flags)
 		err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
-	} else
+	else
 		err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
 	if (err < 0)
 		goto out_freeiov;
@@ -2215,6 +2236,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
 
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg_sys->msg_namelen = 0;
+
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index af7ffd447fee..f1eb0d16666c 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -213,6 +213,26 @@ static int gssp_call(struct net *net, struct rpc_message *msg)
 	return status;
 }
 
+static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
+{
+	int i;
+
+	for (i = 0; i < arg->npages && arg->pages[i]; i++)
+		__free_page(arg->pages[i]);
+}
+
+static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg)
+{
+	arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE);
+	arg->pages = kzalloc(arg->npages * sizeof(struct page *), GFP_KERNEL);
+	/*
+	 * XXX: actual pages are allocated by xdr layer in
+	 * xdr_partial_copy_from_skb.
+	 */
+	if (!arg->pages)
+		return -ENOMEM;
+	return 0;
+}
 
 /*
  * Public functions
@@ -261,10 +281,16 @@ int gssp_accept_sec_context_upcall(struct net *net,
 		arg.context_handle = &ctxh;
 	res.output_token->len = GSSX_max_output_token_sz;
 
+	ret = gssp_alloc_receive_pages(&arg);
+	if (ret)
+		return ret;
+
 	/* use nfs/ for targ_name ? */
 
 	ret = gssp_call(net, &msg);
 
+	gssp_free_receive_pages(&arg);
+
 	/* we need to fetch all data even in case of error so
 	 * that we can free special strctures is they have been allocated */
 	data->major_status = res.status.major_status;
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 3c85d1c8a028..f0f78c5f1c7d 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -166,14 +166,15 @@ static int dummy_dec_opt_array(struct xdr_stream *xdr,
 	return 0;
 }
 
-static int get_s32(void **p, void *max, s32 *res)
+static int get_host_u32(struct xdr_stream *xdr, u32 *res)
 {
-	void *base = *p;
-	void *next = (void *)((char *)base + sizeof(s32));
-	if (unlikely(next > max || next < base))
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (!p)
 		return -EINVAL;
-	memcpy(res, base, sizeof(s32));
-	*p = next;
+	/* Contents of linux creds are all host-endian: */
+	memcpy(res, p, sizeof(u32));
 	return 0;
 }
 
@@ -182,9 +183,9 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr,
 {
 	u32 length;
 	__be32 *p;
-	void *q, *end;
-	s32 tmp;
-	int N, i, err;
+	u32 tmp;
+	u32 N;
+	int i, err;
 
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(p == NULL))
@@ -192,33 +193,28 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr,
 
 	length = be32_to_cpup(p);
 
-	/* FIXME: we do not want to use the scratch buffer for this one
-	 * may need to use functions that allows us to access an io vector
-	 * directly */
-	p = xdr_inline_decode(xdr, length);
-	if (unlikely(p == NULL))
+	if (length > (3 + NGROUPS_MAX) * sizeof(u32))
 		return -ENOSPC;
 
-	q = p;
-	end = q + length;
-
 	/* uid */
-	err = get_s32(&q, end, &tmp);
+	err = get_host_u32(xdr, &tmp);
 	if (err)
 		return err;
 	creds->cr_uid = make_kuid(&init_user_ns, tmp);
 
 	/* gid */
-	err = get_s32(&q, end, &tmp);
+	err = get_host_u32(xdr, &tmp);
 	if (err)
 		return err;
 	creds->cr_gid = make_kgid(&init_user_ns, tmp);
 
 	/* number of additional gid's */
-	err = get_s32(&q, end, &tmp);
+	err = get_host_u32(xdr, &tmp);
 	if (err)
 		return err;
 	N = tmp;
+	if ((3 + N) * sizeof(u32) != length)
+		return -EINVAL;
 	creds->cr_group_info = groups_alloc(N);
 	if (creds->cr_group_info == NULL)
 		return -ENOMEM;
@@ -226,7 +222,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr,
 	/* gid's */
 	for (i = 0; i < N; i++) {
 		kgid_t kgid;
-		err = get_s32(&q, end, &tmp);
+		err = get_host_u32(xdr, &tmp);
 		if (err)
 			goto out_free_groups;
 		err = -EINVAL;
@@ -784,6 +780,9 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req,
 	/* arg->options */
 	err = dummy_enc_opt_array(xdr, &arg->options);
 
+	xdr_inline_pages(&req->rq_rcv_buf,
+		PAGE_SIZE/2 /* pretty arbitrary */,
+		arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE);
 done:
 	if (err)
 		dprintk("RPC:       gssx_enc_accept_sec_context: %d\n", err);
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h
index 1c98b27d870c..685a688f3d8a 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.h
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h
@@ -147,6 +147,8 @@ struct gssx_arg_accept_sec_context {
 	struct gssx_cb *input_cb;
 	u32 ret_deleg_cred;
 	struct gssx_option_array options;
+	struct page **pages;
+	unsigned int npages;
 };
 
 struct gssx_res_accept_sec_context {
@@ -240,7 +242,8 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 			     2 * GSSX_max_princ_sz + \
 			     8 + 8 + 4 + 4 + 4)
 #define GSSX_max_output_token_sz 1024
-#define GSSX_max_creds_sz (4 + 4 + 4 + NGROUPS_MAX * 4)
+/* grouplist not included; we allocate separate pages for that: */
+#define GSSX_max_creds_sz (4 + 4 + 4 /* + NGROUPS_MAX*4 */)
 #define GSSX_RES_accept_sec_context_sz (GSSX_default_status_sz + \
 					GSSX_default_ctx_sz + \
 					GSSX_max_output_token_sz + \
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 426f8fcc4c6c..3524a8b50046 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1402,14 +1402,18 @@ call_refreshresult(struct rpc_task *task)
 	task->tk_action = call_refresh;
 	switch (status) {
 	case 0:
-		if (rpcauth_uptodatecred(task))
+		if (rpcauth_uptodatecred(task)) {
 			task->tk_action = call_allocate;
-		return;
+			return;
+		}
+		/* Use rate-limiting and a max number of retries if refresh
+		 * had status 0 but failed to update the cred.
+		 */
 	case -ETIMEDOUT:
 		rpc_delay(task, 3*HZ);
-	case -EKEYEXPIRED:
 	case -EAGAIN:
 		status = -EACCES;
+	case -EKEYEXPIRED:
 		if (!task->tk_cred_retry)
 			break;
 		task->tk_cred_retry--;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640f329b..b9aad4723a9d 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -730,6 +730,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt)
 			svc_add_new_temp_xprt(serv, newxpt);
+		else
+			module_put(xprt->xpt_class->xcl_owner);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 305374d4fb98..5c62c5e89b46 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -683,6 +683,7 @@ static struct svc_xprt_class svc_udp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_udp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
+	.xcl_ident = XPRT_TRANSPORT_UDP,
 };
 
 static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
@@ -1275,6 +1276,7 @@ static struct svc_xprt_class svc_tcp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_tcp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_TCP,
 };
 
 void svc_init_xprt_sock(void)
@@ -1393,6 +1395,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	return svsk;
 }
 
+bool svc_alien_sock(struct net *net, int fd)
+{
+	int err;
+	struct socket *sock = sockfd_lookup(fd, &err);
+	bool ret = false;
+
+	if (!sock)
+		goto out;
+	if (sock_net(sock->sk) != net)
+		ret = true;
+	sockfd_put(sock);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(svc_alien_sock);
+
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 095363eee764..42ce6bfc729d 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1290,7 +1290,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 		}
 	}
 	spin_unlock(&xprt_list_lock);
-	printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident);
+	dprintk("RPC: transport (%d) not supported\n", args->ident);
 	return ERR_PTR(-EIO);
 
 found:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 62e4f9bcc387..ed36cb52cd86 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -89,6 +89,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ffd50348a509..fc47165dc254 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -391,8 +391,10 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen,
 	return kernel_sendmsg(sock, &msg, NULL, 0, 0);
 }
 
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
 {
+	ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
+			int offset, size_t size, int flags);
 	struct page **ppage;
 	unsigned int remainder;
 	int err, sent = 0;
@@ -401,6 +403,9 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
 	base += xdr->page_base;
 	ppage = xdr->pages + (base >> PAGE_SHIFT);
 	base &= ~PAGE_MASK;
+	do_sendpage = sock->ops->sendpage;
+	if (!zerocopy)
+		do_sendpage = sock_no_sendpage;
 	for(;;) {
 		unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
 		int flags = XS_SENDMSG_FLAGS;
@@ -408,7 +413,7 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
 		remainder -= len;
 		if (remainder != 0 || more)
 			flags |= MSG_MORE;
-		err = sock->ops->sendpage(sock, *ppage, base, len, flags);
+		err = do_sendpage(sock, *ppage, base, len, flags);
 		if (remainder == 0 || err != len)
 			break;
 		sent += err;
@@ -429,9 +434,10 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
  * @addrlen: UDP only -- length of destination address
  * @xdr: buffer containing this request
  * @base: starting position in the buffer
+ * @zerocopy: true if it is safe to use sendpage()
  *
  */
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
 {
 	unsigned int remainder = xdr->len - base;
 	int err, sent = 0;
@@ -459,7 +465,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 	if (base < xdr->page_len) {
 		unsigned int len = xdr->page_len - base;
 		remainder -= len;
-		err = xs_send_pagedata(sock, xdr, base, remainder != 0);
+		err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
 		if (remainder == 0 || err != len)
 			goto out;
 		sent += err;
@@ -496,6 +502,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -513,7 +520,7 @@ static int xs_nospace(struct rpc_task *task)
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -523,6 +530,9 @@ static int xs_nospace(struct rpc_task *task)
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }
 
@@ -562,7 +572,7 @@ static int xs_local_send_request(struct rpc_task *task)
 			req->rq_svec->iov_base, req->rq_svec->iov_len);
 
 	status = xs_sendpages(transport->sock, NULL, 0,
-						xdr, req->rq_bytes_sent);
+						xdr, req->rq_bytes_sent, true);
 	dprintk("RPC:       %s(%u) = %d\n",
 			__func__, xdr->len - req->rq_bytes_sent, status);
 	if (likely(status >= 0)) {
@@ -618,7 +628,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 	status = xs_sendpages(transport->sock,
 			      xs_addr(xprt),
 			      xprt->addrlen, xdr,
-			      req->rq_bytes_sent);
+			      req->rq_bytes_sent, true);
 
 	dprintk("RPC:       xs_udp_send_request(%u) = %d\n",
 			xdr->len - req->rq_bytes_sent, status);
@@ -689,6 +699,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
+	bool zerocopy = true;
 	int status;
 
 	xs_encode_stream_record_marker(&req->rq_snd_buf);
@@ -696,13 +707,20 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	xs_pktdump("packet data:",
 				req->rq_svec->iov_base,
 				req->rq_svec->iov_len);
+	/* Don't use zero copy if this is a resend. If the RPC call
+	 * completes while the socket holds a reference to the pages,
+	 * then we may end up resending corrupted data.
+	 */
+	if (task->tk_flags & RPC_TASK_SENT)
+		zerocopy = false;
 
 	/* Continue transmitting the packet/record. We must be careful
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
 	while (1) {
 		status = xs_sendpages(transport->sock,
-					NULL, 0, xdr, req->rq_bytes_sent);
+					NULL, 0, xdr, req->rq_bytes_sent,
+					zerocopy);
 
 		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
 				xdr->len - req->rq_bytes_sent, status);
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index 9bc6db04be3e..e7000be321b0 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -47,12 +47,12 @@ static int net_ctl_permissions(struct ctl_table_header *head,
 
 	/* Allow network administrator to have same access as root. */
 	if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
-	    uid_eq(root_uid, current_uid())) {
+	    uid_eq(root_uid, current_euid())) {
 		int mode = (table->mode >> 6) & 7;
 		return (mode << 6) | (mode << 3) | mode;
 	}
 	/* Allow netns root group to have the same access as the root group */
-	if (gid_eq(root_gid, current_gid())) {
+	if (in_egroup_p(root_gid)) {
 		int mode = (table->mode >> 3) & 7;
 		return (mode << 3) | mode;
 	}
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index e5f3da507823..bf2755419ec6 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -531,6 +531,7 @@ receive:
 
 		buf = node->bclink.deferred_head;
 		node->bclink.deferred_head = buf->next;
+		buf->next = NULL;
 		node->bclink.deferred_size--;
 		goto receive;
 	}
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 8bcd4985d0fb..1e6081fb6078 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
 	u16 cmd;
 
-	if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+	if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
 		cmd = TIPC_CMD_NOT_NET_ADMIN;
 	else
 		cmd = req_userhdr->cmd;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7e26ad416af1..2b1d7c2d677d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -905,9 +905,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 restart:
 
@@ -1017,9 +1014,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 826e09938bff..75e198d029d2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -160,9 +160,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 
 static inline unsigned int unix_hash_fold(__wsum n)
 {
-	unsigned int hash = (__force unsigned int)n;
+	unsigned int hash = (__force unsigned int)csum_fold(n);
 
-	hash ^= hash>>16;
 	hash ^= hash>>8;
 	return hash&(UNIX_HASH_SIZE-1);
 }
@@ -529,13 +528,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
 static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *,
 				  struct msghdr *, size_t, int);
 
-static void unix_set_peek_off(struct sock *sk, int val)
+static int unix_set_peek_off(struct sock *sk, int val)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	mutex_lock(&u->readlock);
+	if (mutex_lock_interruptible(&u->readlock))
+		return -EINTR;
+
 	sk->sk_peek_off = val;
 	mutex_unlock(&u->readlock);
+
+	return 0;
 }
 
 
@@ -713,7 +716,9 @@ static int unix_autobind(struct socket *sock)
 	int err;
 	unsigned int retries = 0;
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err)
+		return err;
 
 	err = 0;
 	if (u->addr)
@@ -872,7 +877,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err)
+		goto out;
 
 	err = -EINVAL;
 	if (u->addr)
@@ -1245,6 +1252,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
 	return 0;
 }
 
+static void unix_sock_inherit_flags(const struct socket *old,
+				    struct socket *new)
+{
+	if (test_bit(SOCK_PASSCRED, &old->flags))
+		set_bit(SOCK_PASSCRED, &new->flags);
+	if (test_bit(SOCK_PASSSEC, &old->flags))
+		set_bit(SOCK_PASSSEC, &new->flags);
+}
+
 static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
 {
 	struct sock *sk = sock->sk;
@@ -1279,6 +1295,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
 	/* attach accepted sock to socket */
 	unix_state_lock(tsk);
 	newsock->state = SS_CONNECTED;
+	unix_sock_inherit_flags(sock, newsock);
 	sock_graft(tsk, newsock);
 	unix_state_unlock(tsk);
 	return 0;
@@ -1751,7 +1768,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	msg->msg_namelen = 0;
 	if (u->addr) {
 		msg->msg_namelen = u->addr->len;
 		memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1775,11 +1791,12 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
@@ -1899,6 +1916,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = msg->msg_name;
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;
@@ -1914,9 +1932,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
-
-	msg->msg_namelen = 0;
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
@@ -1928,8 +1944,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index d591091603bf..86fa0f3b2caf 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	rep->udiag_family = AF_UNIX;
 	rep->udiag_type = sk->sk_type;
 	rep->udiag_state = sk->sk_state;
+	rep->pad = 0;
 	rep->udiag_ino = sk_ino;
 	sock_diag_save_cookie(sk, rep->udiag_cookie);
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 3f77f42a3b58..9b88693bcc99 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1670,8 +1670,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb,
 	vsk = vsock_sk(sk);
 	err = 0;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state != SS_CONNECTED) {
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index daff75200e25..62bbf7d73980 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
 	if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	/* Retrieve the head sk_buff from the socket's receive queue. */
 	err = 0;
 	skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index d80e47194d49..e62c1ad4e4c9 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -269,6 +269,8 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 				if (chan->flags & IEEE80211_CHAN_DISABLED)
 					continue;
 				wdev->wext.ibss.chandef.chan = chan;
+				wdev->wext.ibss.chandef.center_freq1 =
+					chan->center_freq;
 				break;
 			}
 
@@ -353,6 +355,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 	if (chan) {
 		wdev->wext.ibss.chandef.chan = chan;
 		wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
+		wdev->wext.ibss.chandef.center_freq1 = freq;
 		wdev->wext.ibss.channel_fixed = true;
 	} else {
 		/* cfg80211_ibss_wext_join will pick one if needed */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 448c034184e2..62aebed7c6e2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6568,6 +6568,9 @@ int cfg80211_testmode_reply(struct sk_buff *skb)
 	void *hdr = ((void **)skb->cb)[1];
 	struct nlattr *data = ((void **)skb->cb)[2];
 
+	/* clear CB data for netlink core to own from now on */
+	memset(skb->cb, 0, sizeof(skb->cb));
+
 	if (WARN_ON(!rdev->testmode_info)) {
 		kfree_skb(skb);
 		return -EINVAL;
@@ -6594,6 +6597,9 @@ void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
 	void *hdr = ((void **)skb->cb)[1];
 	struct nlattr *data = ((void **)skb->cb)[2];
 
+	/* clear CB data for netlink core to own from now on */
+	memset(skb->cb, 0, sizeof(skb->cb));
+
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);
 	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 7d604c06c3dc..722da616438c 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init(
 	struct ieee80211_radiotap_header *radiotap_header,
 	int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns)
 {
+	/* check the radiotap header can actually be present */
+	if (max_length < sizeof(struct ieee80211_radiotap_header))
+		return -EINVAL;
+
 	/* Linux only supports version 0 radiotap format */
 	if (radiotap_header->it_version)
 		return -EINVAL;
@@ -120,6 +124,10 @@ int ieee80211_radiotap_iterator_init(
 	/* find payload start allowing for extended bitmap(s) */
 
 	if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) {
+		if ((unsigned long)iterator->_arg -
+		    (unsigned long)iterator->_rtheader + sizeof(uint32_t) >
+		    (unsigned long)iterator->_max_length)
+			return -EINVAL;
 		while (get_unaligned_le32(iterator->_arg) &
 					(1 << IEEE80211_RADIOTAP_EXT)) {
 			iterator->_arg += sizeof(uint32_t);
@@ -131,7 +139,8 @@ int ieee80211_radiotap_iterator_init(
 			 */
 
 			if ((unsigned long)iterator->_arg -
-			    (unsigned long)iterator->_rtheader >
+			    (unsigned long)iterator->_rtheader +
+			    sizeof(uint32_t) >
 			    (unsigned long)iterator->_max_length)
 				return -EINVAL;
 		}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index fd99ea495b7e..81019ee3ddc8 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -253,10 +253,10 @@ void __cfg80211_sched_scan_results(struct work_struct *wk)
 	rdev = container_of(wk, struct cfg80211_registered_device,
 			    sched_scan_results_wk);
 
-	request = rdev->sched_scan_req;
-
 	mutex_lock(&rdev->sched_scan_mtx);
 
+	request = rdev->sched_scan_req;
+
 	/* we don't have sched_scan_req anymore if the scan is stopping */
 	if (request) {
 		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5755bc14abbd..bc5a75b1aef8 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1972,7 +1972,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure,
 		MAC_ASSIGN(addr, addr);
 		__entry->key_type = key_type;
 		__entry->key_id = key_id;
-		memcpy(__entry->tsc, tsc, 6);
+		if (tsc)
+			memcpy(__entry->tsc, tsc, 6);
 	),
 	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm",
 		  NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 22c88d2e6846..f96af3b96322 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sx25) {
 		sx25->sx25_family = AF_X25;
 		sx25->sx25_addr   = x25->dest_addr;
+		msg->msg_namelen = sizeof(*sx25);
 	}
 
-	msg->msg_namelen = sizeof(struct sockaddr_x25);
-
 	x25_check_rbuf(sk);
 	rc = copied;
 out_free_dgram:
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 3f565e495ac6..7a70a5a5671a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2362,7 +2362,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	link = &xfrm_dispatch[type];
 
 	/* All operations require privileges, even GET */
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst
index 182084d728c8..8ccf83056a7a 100644
--- a/scripts/Makefile.headersinst
+++ b/scripts/Makefile.headersinst
@@ -47,18 +47,24 @@ header-y      := $(filter-out $(generic-y), $(header-y))
 all-files     := $(header-y) $(genhdr-y) $(wrapper-files)
 output-files  := $(addprefix $(installdir)/, $(all-files))
 
-input-files   := $(foreach hdr, $(header-y), \
+input-files1  := $(foreach hdr, $(header-y), \
 		   $(if $(wildcard $(srcdir)/$(hdr)), \
-			$(wildcard $(srcdir)/$(hdr)), \
+			$(wildcard $(srcdir)/$(hdr))) \
+		   )
+input-files1-name := $(notdir $(input-files1))
+input-files2  := $(foreach hdr, $(header-y), \
+		   $(if  $(wildcard $(srcdir)/$(hdr)),, \
 			$(if $(wildcard $(oldsrcdir)/$(hdr)), \
 				$(wildcard $(oldsrcdir)/$(hdr)), \
 				$(error Missing UAPI file $(srcdir)/$(hdr))) \
-		   )) \
-		 $(foreach hdr, $(genhdr-y), \
+		   ))
+input-files2-name := $(notdir $(input-files2))
+input-files3  := $(foreach hdr, $(genhdr-y), \
 		   $(if	$(wildcard $(gendir)/$(hdr)), \
 			$(wildcard $(gendir)/$(hdr)), \
 			$(error Missing generated UAPI file $(gendir)/$(hdr)) \
 		   ))
+input-files3-name := $(notdir $(input-files3))
 
 # Work out what needs to be removed
 oldheaders    := $(patsubst $(installdir)/%,%,$(wildcard $(installdir)/*.h))
@@ -72,7 +78,9 @@ printdir = $(patsubst $(INSTALL_HDR_PATH)/%/,%,$(dir $@))
 quiet_cmd_install = INSTALL $(printdir) ($(words $(all-files))\
                             file$(if $(word 2, $(all-files)),s))
       cmd_install = \
-        $(CONFIG_SHELL) $< $(installdir) $(input-files); \
+        $(CONFIG_SHELL) $< $(installdir) $(srcdir) $(input-files1-name); \
+        $(CONFIG_SHELL) $< $(installdir) $(oldsrcdir) $(input-files2-name); \
+        $(CONFIG_SHELL) $< $(installdir) $(gendir) $(input-files3-name); \
         for F in $(wrapper-files); do                                   \
                 echo "\#include <asm-generic/$$F>" > $(installdir)/$$F;    \
         done;                                                           \
@@ -98,7 +106,7 @@ __headersinst: $(subdirs) $(install-file)
 	@:
 
 targets += $(install-file)
-$(install-file): scripts/headers_install.sh $(input-files) FORCE
+$(install-file): scripts/headers_install.sh $(input-files1) $(input-files2) $(input-files3) FORCE
 	$(if $(unwanted),$(call cmd,remove),)
 	$(if $(wildcard $(dir $@)),,$(shell mkdir -p $(dir $@)))
 	$(call if_changed,install)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f97869f1f09b..c4b37f6b5478 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -152,6 +152,7 @@ ld_flags       = $(LDFLAGS) $(ldflags-y)
 dtc_cpp_flags  = -Wp,-MD,$(depfile).pre.tmp -nostdinc                    \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts                   \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts/include           \
+		 -I$(srctree)/include                                    \
 		 -undef -D__DTS__
 
 # Finds the multi-part object the current object will be linked into
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index 643764f53ea7..5de5660cb708 100644
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -2,7 +2,7 @@
 
 if [ $# -lt 1 ]
 then
-	echo "Usage: headers_install.sh OUTDIR [FILES...]
+	echo "Usage: headers_install.sh OUTDIR SRCDIR [FILES...]
 	echo
 	echo "Prepares kernel header files for use by user space, by removing"
 	echo "all compiler.h definitions and #includes, removing any"
@@ -10,6 +10,7 @@ then
 	echo "asm/inline/volatile keywords."
 	echo
 	echo "OUTDIR: directory to write each userspace header FILE to."
+	echo "SRCDIR: source directory where files are picked."
 	echo "FILES:  list of header files to operate on."
 
 	exit 1
@@ -19,6 +20,8 @@ fi
 
 OUTDIR="$1"
 shift
+SRCDIR="$1"
+shift
 
 # Iterate through files listed on command line
 
@@ -34,7 +37,7 @@ do
 		-e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \
 		-e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \
 		-e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \
-		"$i" > "$OUTDIR/$FILE.sed" || exit 1
+		"$SRCDIR/$i" > "$OUTDIR/$FILE.sed" || exit 1
 	scripts/unifdef -U__KERNEL__ -D__EXPORTED_HEADERS__ "$OUTDIR/$FILE.sed" \
 		> "$OUTDIR/$FILE"
 	[ $? -gt 1 ] && exit 1
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 487ac6f37ca2..9a11f9f799f4 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -55,6 +55,7 @@ static struct sym_entry *table;
 static unsigned int table_size, table_cnt;
 static int all_symbols = 0;
 static char symbol_prefix_char = '\0';
+static unsigned long long kernel_start_addr = 0;
 
 int token_profit[0x10000];
 
@@ -65,7 +66,10 @@ unsigned char best_table_len[256];
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--symbol-prefix=<prefix char>] < in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
+			"[--symbol-prefix=<prefix char>] "
+			"[--page-offset=<CONFIG_PAGE_OFFSET>] "
+			"< in.map > out.S\n");
 	exit(1);
 }
 
@@ -194,6 +198,9 @@ static int symbol_valid(struct sym_entry *s)
 	int i;
 	int offset = 1;
 
+	if (s->addr < kernel_start_addr)
+		return 0;
+
 	/* skip prefix char */
 	if (symbol_prefix_char && *(s->sym + 1) == symbol_prefix_char)
 		offset++;
@@ -646,6 +653,9 @@ int main(int argc, char **argv)
 				if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\''))
 					p++;
 				symbol_prefix_char = *p;
+			} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
+				const char *p = &argv[i][14];
+				kernel_start_addr = strtoull(p, NULL, 16);
 			} else
 				usage();
 		}
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 4305b2f2ec5e..8c0e07b7a70b 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1750,7 +1750,7 @@ sub dump_struct($$) {
 	# strip kmemcheck_bitfield_{begin,end}.*;
 	$members =~ s/kmemcheck_bitfield_.*?;//gos;
 	# strip attributes
-	$members =~ s/__aligned\s*\(.+\)//gos;
+	$members =~ s/__aligned\s*\([^;]*\)//gos;
 
 	create_parameterlist($members, ';', $file);
 	check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested);
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 014994936b1c..32b10f53d0b4 100644
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -82,6 +82,8 @@ kallsyms()
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
+	kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
+
 	local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL}               \
 		      ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}"
 
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index e66d4d258e1a..5e74595f2e85 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -174,6 +174,9 @@ int main(void)
 	DEVID_FIELD(x86_cpu_id, model);
 	DEVID_FIELD(x86_cpu_id, vendor);
 
+	DEVID(cpu_feature);
+	DEVID_FIELD(cpu_feature, feature);
+
 	DEVID(mei_cl_device_id);
 	DEVID_FIELD(mei_cl_device_id, name);
 
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 45f9a3377dcd..09632f04576b 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -208,8 +208,8 @@ static void do_usb_entry(void *symval,
 				range_lo < 0x9 ? "[%X-9" : "[%X",
 				range_lo);
 			sprintf(alias + strlen(alias),
-				range_hi > 0xA ? "a-%X]" : "%X]",
-				range_lo);
+				range_hi > 0xA ? "A-%X]" : "%X]",
+				range_hi);
 		}
 	}
 	if (bcdDevice_initial_digits < (sizeof(bcdDevice_lo) * 2 - 1))
@@ -1133,6 +1133,16 @@ static int do_x86cpu_entry(const char *filename, void *symval,
 }
 ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);
 
+/* LOOKS like cpu:type:*:feature:*FEAT* */
+static int do_cpu_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD(symval, cpu_feature, feature);
+
+	sprintf(alias, "cpu:type:*:feature:*%04X*", feature);
+	return 1;
+}
+ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);
+
 /* Looks like: mei:S */
 static int do_mei_entry(const char *filename, void *symval,
 			char *alias)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index a4be8e112bb6..a2c361c86e75 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -573,12 +573,16 @@ static int ignore_undef_symbol(struct elf_info *info, const char *symname)
 		if (strncmp(symname, "_restgpr_", sizeof("_restgpr_") - 1) == 0 ||
 		    strncmp(symname, "_savegpr_", sizeof("_savegpr_") - 1) == 0 ||
 		    strncmp(symname, "_rest32gpr_", sizeof("_rest32gpr_") - 1) == 0 ||
-		    strncmp(symname, "_save32gpr_", sizeof("_save32gpr_") - 1) == 0)
+		    strncmp(symname, "_save32gpr_", sizeof("_save32gpr_") - 1) == 0 ||
+		    strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
+		    strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0)
 			return 1;
 	if (info->hdr->e_machine == EM_PPC64)
 		/* Special register function linked on all modules during final link of .ko */
 		if (strncmp(symname, "_restgpr0_", sizeof("_restgpr0_") - 1) == 0 ||
-		    strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0)
+		    strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0 ||
+		    strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
+		    strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0)
 			return 1;
 	/* Do not ignore this symbol */
 	return 0;
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index acb86507828a..3001ec5ae07d 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -62,7 +62,7 @@ create_package() {
 	fi
 
 	# Create the package
-	dpkg-gencontrol -isp $forcearch -p$pname -P"$pdir"
+	dpkg-gencontrol -isp $forcearch -Vkernel:debarch="${debarch:-$(dpkg --print-architecture)}" -p$pname -P"$pdir"
 	dpkg --build "$pdir" ..
 }
 
@@ -252,15 +252,14 @@ mkdir -p "$destdir"
 (cd $objtree; tar -c -f - -T "$objtree/debian/hdrobjfiles") | (cd $destdir; tar -xf -)
 ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
 rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
-arch=$(dpkg --print-architecture)
 
 cat <<EOF >> debian/control
 
 Package: $kernel_headers_packagename
 Provides: linux-headers, linux-headers-2.6
-Architecture: $arch
-Description: Linux kernel headers for $KERNELRELEASE on $arch
- This package provides kernel header files for $KERNELRELEASE on $arch
+Architecture: any
+Description: Linux kernel headers for $KERNELRELEASE on \${kernel:debarch}
+ This package provides kernel header files for $KERNELRELEASE on \${kernel:debarch}
  .
  This is useful for people who need to build external modules
 EOF
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 9c22317778eb..e11aa4a156d2 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -40,6 +40,11 @@
 #define R_METAG_NONE                     3
 #endif
 
+#ifndef EM_AARCH64
+#define EM_AARCH64	183
+#define R_AARCH64_ABS64	257
+#endif
+
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
@@ -347,6 +352,8 @@ do_file(char const *const fname)
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
+	case EM_AARCH64:
+			 reltype = R_AARCH64_ABS64; gpfx = '_'; break;
 	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
 	case EM_METAG:	 reltype = R_METAG_ADDR32;
 			 altmcount = "_mcount_wrapper";
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 9d1421e63ff8..49b582a225b0 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -163,11 +163,11 @@ static int mcount_adjust = 0;
 
 static int MIPS_is_fake_mcount(Elf_Rel const *rp)
 {
-	static Elf_Addr old_r_offset;
+	static Elf_Addr old_r_offset = ~(Elf_Addr)0;
 	Elf_Addr current_r_offset = _w(rp->r_offset);
 	int is_fake;
 
-	is_fake = old_r_offset &&
+	is_fake = (old_r_offset != ~(Elf_Addr)0) &&
 		(current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET);
 	old_r_offset = current_r_offset;
 
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 858966ab019c..151739b4e481 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -279,6 +279,11 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_ARM_(CALL|PC24|THM_CALL)" .
 			"\\s+(__gnu_mcount_nc|mcount)\$";
 
+} elsif ($arch eq "arm64") {
+    $alignment = 3;
+    $section_type = '%progbits';
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$";
+    $type = ".quad";
 } elsif ($arch eq "ia64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
     $type = "data8";
diff --git a/security/commoncap.c b/security/commoncap.c
index c44b6fe6648e..c9219a66b7c6 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -421,6 +421,9 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
 		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
 	}
 
+	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
 	return 0;
 }
 
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index cdbde1762189..b980a6ce5c79 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -275,12 +275,23 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name,
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!xattr_value_len)
+			return -EINVAL;
+		if (xattr_data->type != EVM_IMA_XATTR_DIGSIG)
+			return -EPERM;
+	}
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index a02e0791cf15..9da974c0f958 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -24,6 +24,36 @@
 
 static struct crypto_shash *ima_shash_tfm;
 
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op->read && !file->f_op->aio_read)
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else
+		ret = do_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
 int ima_init_crypto(void)
 {
 	long rc;
@@ -70,7 +100,7 @@ int ima_calc_file_hash(struct file *file, char *digest)
 	while (offset < i_size) {
 		int rbuf_len;
 
-		rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
 		if (rbuf_len < 0) {
 			rc = rbuf_len;
 			break;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 399433ad614e..a9c3d3cd1990 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -73,7 +73,6 @@ static struct ima_rule_entry default_rules[] = {
 	{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
-	{.action = DONT_MEASURE,.fsmagic = RAMFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = DEVPTS_SUPER_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = BINFMTFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 9e1e005c7596..c4c8df4b214d 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -1018,10 +1018,13 @@ static int __init init_encrypted(void)
 	ret = encrypted_shash_alloc();
 	if (ret < 0)
 		return ret;
+	ret = aes_get_sizes();
+	if (ret < 0)
+		goto out;
 	ret = register_key_type(&key_type_encrypted);
 	if (ret < 0)
 		goto out;
-	return aes_get_sizes();
+	return 0;
 out:
 	encrypted_shash_release();
 	return ret;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5c6f2cd2d095..fdd6e4f8be39 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -53,6 +53,7 @@
 #include <net/ip.h>		/* for local_port_range[] */
 #include <net/sock.h>
 #include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
+#include <net/inet_connection_sock.h>
 #include <net/net_namespace.h>
 #include <net/netlabel.h>
 #include <linux/uaccess.h>
@@ -218,6 +219,14 @@ static int inode_alloc_security(struct inode *inode)
 	return 0;
 }
 
+static void inode_free_rcu(struct rcu_head *head)
+{
+	struct inode_security_struct *isec;
+
+	isec = container_of(head, struct inode_security_struct, rcu);
+	kmem_cache_free(sel_inode_cache, isec);
+}
+
 static void inode_free_security(struct inode *inode)
 {
 	struct inode_security_struct *isec = inode->i_security;
@@ -228,8 +237,16 @@ static void inode_free_security(struct inode *inode)
 		list_del_init(&isec->list);
 	spin_unlock(&sbsec->isec_lock);
 
-	inode->i_security = NULL;
-	kmem_cache_free(sel_inode_cache, isec);
+	/*
+	 * The inode may still be referenced in a path walk and
+	 * a call to selinux_inode_permission() can be made
+	 * after inode_free_security() is called. Ideally, the VFS
+	 * wouldn't do this, but fixing that is a much harder
+	 * job. For now, simply free the i_security via RCU, and
+	 * leave the current inode->i_security pointer intact.
+	 * The inode will be freed after the RCU grace period too.
+	 */
+	call_rcu(&isec->rcu, inode_free_rcu);
 }
 
 static int file_alloc_security(struct file *file)
@@ -420,6 +437,7 @@ next_inode:
 				list_entry(sbsec->isec_head.next,
 					   struct inode_security_struct, list);
 		struct inode *inode = isec->inode;
+		list_del_init(&isec->list);
 		spin_unlock(&sbsec->isec_lock);
 		inode = igrab(inode);
 		if (inode) {
@@ -428,7 +446,6 @@ next_inode:
 			iput(inode);
 		}
 		spin_lock(&sbsec->isec_lock);
-		list_del_init(&isec->list);
 		goto next_inode;
 	}
 	spin_unlock(&sbsec->isec_lock);
@@ -1344,15 +1361,33 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		isec->sid = sbsec->sid;
 
 		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
-			if (opt_dentry) {
-				isec->sclass = inode_mode_to_security_class(inode->i_mode);
-				rc = selinux_proc_get_sid(opt_dentry,
-							  isec->sclass,
-							  &sid);
-				if (rc)
-					goto out_unlock;
-				isec->sid = sid;
-			}
+			/* We must have a dentry to determine the label on
+			 * procfs inodes */
+			if (opt_dentry)
+				/* Called from d_instantiate or
+				 * d_splice_alias. */
+				dentry = dget(opt_dentry);
+			else
+				/* Called from selinux_complete_init, try to
+				 * find a dentry. */
+				dentry = d_find_alias(inode);
+			/*
+			 * This can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as
+			 * these will get fixed up the next time we go through
+			 * inode_doinit() with a dentry, before these inodes
+			 * could be used again by userspace.
+			 */
+			if (!dentry)
+				goto out_unlock;
+			isec->sclass = inode_mode_to_security_class(inode->i_mode);
+			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+			dput(dentry);
+			if (rc)
+				goto out_unlock;
+			isec->sid = sid;
 		}
 		break;
 	}
@@ -3722,7 +3757,7 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	u32 nlbl_sid;
 	u32 nlbl_type;
 
-	selinux_skb_xfrm_sid(skb, &xfrm_sid);
+	selinux_xfrm_skb_sid(skb, &xfrm_sid);
 	selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
 
 	err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid);
@@ -3736,6 +3771,30 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	return 0;
 }
 
+/**
+ * selinux_conn_sid - Determine the child socket label for a connection
+ * @sk_sid: the parent socket's SID
+ * @skb_sid: the packet's SID
+ * @conn_sid: the resulting connection SID
+ *
+ * If @skb_sid is valid then the user:role:type information from @sk_sid is
+ * combined with the MLS information from @skb_sid in order to create
+ * @conn_sid.  If @skb_sid is not valid then then @conn_sid is simply a copy
+ * of @sk_sid.  Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid)
+{
+	int err = 0;
+
+	if (skb_sid != SECSID_NULL)
+		err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid);
+	else
+		*conn_sid = sk_sid;
+
+	return err;
+}
+
 /* socket security operations */
 
 static int socket_sockcreate_sid(const struct task_security_struct *tsec,
@@ -4203,8 +4262,10 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		}
 		err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
 				   PEER__RECV, &ad);
-		if (err)
+		if (err) {
 			selinux_netlbl_err(skb, err, 0);
+			return err;
+		}
 	}
 
 	if (secmark_active) {
@@ -4342,7 +4403,7 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	struct sk_security_struct *sksec = sk->sk_security;
 	int err;
 	u16 family = sk->sk_family;
-	u32 newsid;
+	u32 connsid;
 	u32 peersid;
 
 	/* handle mapped IPv4 packets arriving via IPv6 sockets */
@@ -4352,16 +4413,11 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	err = selinux_skb_peerlbl_sid(skb, family, &peersid);
 	if (err)
 		return err;
-	if (peersid == SECSID_NULL) {
-		req->secid = sksec->sid;
-		req->peer_secid = SECSID_NULL;
-	} else {
-		err = security_sid_mls_copy(sksec->sid, peersid, &newsid);
-		if (err)
-			return err;
-		req->secid = newsid;
-		req->peer_secid = peersid;
-	}
+	err = selinux_conn_sid(sksec->sid, peersid, &connsid);
+	if (err)
+		return err;
+	req->secid = connsid;
+	req->peer_secid = peersid;
 
 	return selinux_netlbl_inet_conn_request(req, family);
 }
@@ -4621,6 +4677,7 @@ static unsigned int selinux_ipv6_forward(unsigned int hooknum,
 static unsigned int selinux_ip_output(struct sk_buff *skb,
 				      u16 family)
 {
+	struct sock *sk;
 	u32 sid;
 
 	if (!netlbl_enabled())
@@ -4629,8 +4686,27 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
 	/* we do this in the LOCAL_OUT path and not the POST_ROUTING path
 	 * because we want to make sure we apply the necessary labeling
 	 * before IPsec is applied so we can leverage AH protection */
-	if (skb->sk) {
-		struct sk_security_struct *sksec = skb->sk->sk_security;
+	sk = skb->sk;
+	if (sk) {
+		struct sk_security_struct *sksec;
+
+		if (sk->sk_state == TCP_LISTEN)
+			/* if the socket is the listening state then this
+			 * packet is a SYN-ACK packet which means it needs to
+			 * be labeled based on the connection/request_sock and
+			 * not the parent socket.  unfortunately, we can't
+			 * lookup the request_sock yet as it isn't queued on
+			 * the parent socket until after the SYN-ACK is sent.
+			 * the "solution" is to simply pass the packet as-is
+			 * as any IP option based labeling should be copied
+			 * from the initial connection request (in the IP
+			 * layer).  it is far from ideal, but until we get a
+			 * security label in the packet itself this is the
+			 * best we can do. */
+			return NF_ACCEPT;
+
+		/* standard practice, label using the parent socket */
+		sksec = sk->sk_security;
 		sid = sksec->sid;
 	} else
 		sid = SECINITSID_KERNEL;
@@ -4700,27 +4776,37 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	 * as fast and as clean as possible. */
 	if (!selinux_policycap_netpeer)
 		return selinux_ip_postroute_compat(skb, ifindex, family);
+
+	secmark_active = selinux_secmark_enabled();
+	peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+	if (!secmark_active && !peerlbl_active)
+		return NF_ACCEPT;
+
+	sk = skb->sk;
+
 #ifdef CONFIG_XFRM
 	/* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec
 	 * packet transformation so allow the packet to pass without any checks
 	 * since we'll have another chance to perform access control checks
 	 * when the packet is on it's final way out.
 	 * NOTE: there appear to be some IPv6 multicast cases where skb->dst
-	 *       is NULL, in this case go ahead and apply access control. */
-	if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL)
+	 *       is NULL, in this case go ahead and apply access control.
+	 *       is NULL, in this case go ahead and apply access control.
+	 * NOTE: if this is a local socket (skb->sk != NULL) that is in the
+	 *       TCP listening state we cannot wait until the XFRM processing
+	 *       is done as we will miss out on the SA label if we do;
+	 *       unfortunately, this means more work, but it is only once per
+	 *       connection. */
+	if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL &&
+	    !(sk != NULL && sk->sk_state == TCP_LISTEN))
 		return NF_ACCEPT;
 #endif
-	secmark_active = selinux_secmark_enabled();
-	peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
-	if (!secmark_active && !peerlbl_active)
-		return NF_ACCEPT;
 
-	/* if the packet is being forwarded then get the peer label from the
-	 * packet itself; otherwise check to see if it is from a local
-	 * application or the kernel, if from an application get the peer label
-	 * from the sending socket, otherwise use the kernel's sid */
-	sk = skb->sk;
 	if (sk == NULL) {
+		/* Without an associated socket the packet is either coming
+		 * from the kernel or it is being forwarded; check the packet
+		 * to determine which and if the packet is being forwarded
+		 * query the packet directly to determine the security label. */
 		if (skb->skb_iif) {
 			secmark_perm = PACKET__FORWARD_OUT;
 			if (selinux_skb_peerlbl_sid(skb, family, &peer_sid))
@@ -4729,7 +4815,45 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 			secmark_perm = PACKET__SEND;
 			peer_sid = SECINITSID_KERNEL;
 		}
+	} else if (sk->sk_state == TCP_LISTEN) {
+		/* Locally generated packet but the associated socket is in the
+		 * listening state which means this is a SYN-ACK packet.  In
+		 * this particular case the correct security label is assigned
+		 * to the connection/request_sock but unfortunately we can't
+		 * query the request_sock as it isn't queued on the parent
+		 * socket until after the SYN-ACK packet is sent; the only
+		 * viable choice is to regenerate the label like we do in
+		 * selinux_inet_conn_request().  See also selinux_ip_output()
+		 * for similar problems. */
+		u32 skb_sid;
+		struct sk_security_struct *sksec = sk->sk_security;
+		if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+			return NF_DROP;
+		/* At this point, if the returned skb peerlbl is SECSID_NULL
+		 * and the packet has been through at least one XFRM
+		 * transformation then we must be dealing with the "final"
+		 * form of labeled IPsec packet; since we've already applied
+		 * all of our access controls on this packet we can safely
+		 * pass the packet. */
+		if (skb_sid == SECSID_NULL) {
+			switch (family) {
+			case PF_INET:
+				if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+				break;
+			case PF_INET6:
+				if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+			default:
+				return NF_DROP_ERR(-ECONNREFUSED);
+			}
+		}
+		if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
+			return NF_DROP;
+		secmark_perm = PACKET__SEND;
 	} else {
+		/* Locally generated packet, fetch the security label from the
+		 * associated socket. */
 		struct sk_security_struct *sksec = sk->sk_security;
 		peer_sid = sksec->sid;
 		secmark_perm = PACKET__SEND;
@@ -5393,11 +5517,11 @@ static int selinux_setprocattr(struct task_struct *p,
 		/* Check for ptracing, and update the task SID if ok.
 		   Otherwise, leave SID unchanged and fail. */
 		ptsid = 0;
-		task_lock(p);
+		rcu_read_lock();
 		tracer = ptrace_parent(p);
 		if (tracer)
 			ptsid = task_sid(tracer);
-		task_unlock(p);
+		rcu_read_unlock();
 
 		if (tracer) {
 			error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index aa47bcabb5f6..6fd9dd256a62 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -38,7 +38,10 @@ struct task_security_struct {
 
 struct inode_security_struct {
 	struct inode *inode;	/* back pointer to inode object */
-	struct list_head list;	/* list of inode_security_struct */
+	union {
+		struct list_head list;	/* list of inode_security_struct */
+		struct rcu_head rcu;	/* for freeing the inode_security_struct */
+	};
 	u32 task_sid;		/* SID of creating task */
 	u32 sid;		/* SID of this object */
 	u16 sclass;		/* security class of this object */
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 65f67cb0aefb..3ffdadc9960f 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -47,6 +47,7 @@ int selinux_xfrm_sock_rcv_skb(u32 sid, struct sk_buff *skb,
 int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
 			struct common_audit_data *ad, u8 proto);
 int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid);
 
 static inline void selinux_xfrm_notify_policyload(void)
 {
@@ -80,12 +81,12 @@ static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int
 static inline void selinux_xfrm_notify_policyload(void)
 {
 }
-#endif
 
-static inline void selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
+static inline int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
 {
-	int err = selinux_xfrm_decode_session(skb, sid, 0);
-	BUG_ON(err);
+	*sid = SECSID_NULL;
+	return 0;
 }
+#endif
 
 #endif /* _SELINUX_XFRM_H_ */
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index da4b8b233280..6235d052338b 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -442,8 +442,7 @@ int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr)
 	    sksec->nlbl_state != NLBL_CONNLABELED)
 		return 0;
 
-	local_bh_disable();
-	bh_lock_sock_nested(sk);
+	lock_sock(sk);
 
 	/* connected sockets are allowed to disconnect when the address family
 	 * is set to AF_UNSPEC, if that is what is happening we want to reset
@@ -464,7 +463,6 @@ int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr)
 		sksec->nlbl_state = NLBL_CONNLABELED;
 
 socket_connect_return:
-	bh_unlock_sock(sk);
-	local_bh_enable();
+	release_sock(sk);
 	return rc;
 }
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 9cd9b7c661ec..bcdca73033f3 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -1941,7 +1941,19 @@ static int filename_trans_read(struct policydb *p, void *fp)
 		if (rc)
 			goto out;
 
-		hashtab_insert(p->filename_trans, ft, otype);
+		rc = hashtab_insert(p->filename_trans, ft, otype);
+		if (rc) {
+			/*
+			 * Do not return -EEXIST to the caller, or the system
+			 * will not boot.
+			 */
+			if (rc != -EEXIST)
+				goto out;
+			/* But free memory to avoid memory leak. */
+			kfree(ft);
+			kfree(name);
+			kfree(otype);
+		}
 	}
 	hash_eval(p->filename_trans, "filenametr");
 	return 0;
@@ -3246,10 +3258,10 @@ static int filename_write_helper(void *key, void *data, void *ptr)
 	if (rc)
 		return rc;
 
-	buf[0] = ft->stype;
-	buf[1] = ft->ttype;
-	buf[2] = ft->tclass;
-	buf[3] = otype->otype;
+	buf[0] = cpu_to_le32(ft->stype);
+	buf[1] = cpu_to_le32(ft->ttype);
+	buf[2] = cpu_to_le32(ft->tclass);
+	buf[3] = cpu_to_le32(otype->otype);
 
 	rc = put_entry(buf, sizeof(u32), 4, fp);
 	if (rc)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index b4feecc3fe01..18caa16de27b 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1231,6 +1231,10 @@ static int security_context_to_sid_core(const char *scontext, u32 scontext_len,
 	struct context context;
 	int rc = 0;
 
+	/* An empty security context is never valid. */
+	if (!scontext_len)
+		return -EINVAL;
+
 	if (!ss_initialized) {
 		int i;
 
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index d03081886214..78504a18958a 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -152,21 +152,13 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *
 	return rc;
 }
 
-/*
- * LSM hook implementation that checks and/or returns the xfrm sid for the
- * incoming packet.
- */
-
-int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb,
+					u32 *sid, int ckall)
 {
-	struct sec_path *sp;
+	struct sec_path *sp = skb->sp;
 
 	*sid = SECSID_NULL;
 
-	if (skb == NULL)
-		return 0;
-
-	sp = skb->sp;
 	if (sp) {
 		int i, sid_set = 0;
 
@@ -190,6 +182,45 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
 	return 0;
 }
 
+static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x;
+
+	if (dst == NULL)
+		return SECSID_NULL;
+	x = dst->xfrm;
+	if (x == NULL || !selinux_authorizable_xfrm(x))
+		return SECSID_NULL;
+
+	return x->security->ctx_sid;
+}
+
+/*
+ * LSM hook implementation that checks and/or returns the xfrm sid for the
+ * incoming packet.
+ */
+
+int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+{
+	if (skb == NULL) {
+		*sid = SECSID_NULL;
+		return 0;
+	}
+	return selinux_xfrm_skb_sid_ingress(skb, sid, ckall);
+}
+
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
+{
+	int rc;
+
+	rc = selinux_xfrm_skb_sid_ingress(skb, sid, 0);
+	if (rc == 0 && *sid == SECSID_NULL)
+		*sid = selinux_xfrm_skb_sid_egress(skb);
+
+	return rc;
+}
+
 /*
  * Security blob allocation for xfrm_policy and xfrm_state
  * CTX does not have a meaningful value on input
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 98969541cbcc..3fdf998ad057 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -133,7 +133,7 @@ static int snd_compr_open(struct inode *inode, struct file *f)
 		kfree(data);
 	}
 	snd_card_unref(compr->card);
-	return 0;
+	return ret;
 }
 
 static int snd_compr_free(struct inode *inode, struct file *f)
@@ -668,14 +668,48 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 		return -EPERM;
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
 	if (!retval) {
-		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
-		wake_up(&stream->runtime->sleep);
+		snd_compr_drain_notify(stream);
 		stream->runtime->total_bytes_available = 0;
 		stream->runtime->total_bytes_transferred = 0;
 	}
 	return retval;
 }
 
+static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
+{
+	int ret;
+
+	/*
+	 * We are called with lock held. So drop the lock while we wait for
+	 * drain complete notfication from the driver
+	 *
+	 * It is expected that driver will notify the drain completion and then
+	 * stream will be moved to SETUP state, even if draining resulted in an
+	 * error. We can trigger next track after this.
+	 */
+	stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+	mutex_unlock(&stream->device->lock);
+
+	/* we wait for drain to complete here, drain can return when
+	 * interruption occurred, wait returned error or success.
+	 * For the first two cases we don't do anything different here and
+	 * return after waking up
+	 */
+
+	ret = wait_event_interruptible(stream->runtime->sleep,
+			(stream->runtime->state != SNDRV_PCM_STATE_DRAINING));
+	if (ret == -ERESTARTSYS)
+		pr_debug("wait aborted by a signal");
+	else if (ret)
+		pr_debug("wait for drain failed with %d\n", ret);
+
+
+	wake_up(&stream->runtime->sleep);
+	mutex_lock(&stream->device->lock);
+
+	return ret;
+}
+
 static int snd_compr_drain(struct snd_compr_stream *stream)
 {
 	int retval;
@@ -683,12 +717,15 @@ static int snd_compr_drain(struct snd_compr_stream *stream)
 	if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
 			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
 		return -EPERM;
+
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
-	if (!retval) {
-		stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+	if (retval) {
+		pr_debug("SND_COMPR_TRIGGER_DRAIN failed %d\n", retval);
 		wake_up(&stream->runtime->sleep);
+		return retval;
 	}
-	return retval;
+
+	return snd_compress_wait_for_drain(stream);
 }
 
 static int snd_compr_next_track(struct snd_compr_stream *stream)
@@ -724,9 +761,14 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 		return -EPERM;
 
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
+	if (retval) {
+		pr_debug("Partial drain returned failure\n");
+		wake_up(&stream->runtime->sleep);
+		return retval;
+	}
 
 	stream->next_track = false;
-	return retval;
+	return snd_compress_wait_for_drain(stream);
 }
 
 static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
@@ -837,7 +879,8 @@ static int snd_compress_dev_disconnect(struct snd_device *device)
 	struct snd_compr *compr;
 
 	compr = device->device_data;
-	snd_unregister_device(compr->direction, compr->card, compr->device);
+	snd_unregister_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card,
+		compr->device);
 	return 0;
 }
 
diff --git a/sound/core/control.c b/sound/core/control.c
index d8aa206e8bde..98a29b26c5f4 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card,
 {
 	struct snd_kcontrol *kctl;
 
+	/* Make sure that the ids assigned to the control do not wrap around */
+	if (card->last_numid >= UINT_MAX - count)
+		card->last_numid = 0;
+
 	list_for_each_entry(kctl, &card->controls, list) {
 		if (kctl->id.numid < card->last_numid + 1 + count &&
 		    kctl->id.numid + kctl->count > card->last_numid + 1) {
@@ -331,6 +335,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 {
 	struct snd_ctl_elem_id id;
 	unsigned int idx;
+	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
@@ -338,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
 	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		goto error;
+
 	down_write(&card->controls_rwsem);
 	if (snd_ctl_find_id(card, &id)) {
 		up_write(&card->controls_rwsem);
@@ -359,8 +367,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -389,6 +398,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol,
 		    bool add_on_replace)
 {
 	struct snd_ctl_elem_id id;
+	unsigned int count;
 	unsigned int idx;
 	struct snd_kcontrol *old;
 	int ret;
@@ -424,8 +434,9 @@ add:
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -898,9 +909,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file,
 			result = kctl->put(kctl, control);
 		}
 		if (result > 0) {
+			struct snd_ctl_elem_id id = control->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
-				       &control->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
 			return 0;
 		}
 	}
@@ -992,6 +1003,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file,
 
 struct user_element {
 	struct snd_ctl_elem_info info;
+	struct snd_card *card;
 	void *elem_data;		/* element data */
 	unsigned long elem_data_size;	/* size of element data in bytes */
 	void *tlv_data;			/* TLV data */
@@ -1035,7 +1047,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol,
 {
 	struct user_element *ue = kcontrol->private_data;
 
+	mutex_lock(&ue->card->user_ctl_lock);
 	memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return 0;
 }
 
@@ -1044,10 +1058,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol,
 {
 	int change;
 	struct user_element *ue = kcontrol->private_data;
-	
+
+	mutex_lock(&ue->card->user_ctl_lock);
 	change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
 	if (change)
 		memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return change;
 }
 
@@ -1067,19 +1083,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol,
 		new_data = memdup_user(tlv, size);
 		if (IS_ERR(new_data))
 			return PTR_ERR(new_data);
+		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
 			change = memcmp(ue->tlv_data, new_data, size);
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
+		mutex_unlock(&ue->card->user_ctl_lock);
 	} else {
-		if (! ue->tlv_data_size || ! ue->tlv_data)
-			return -ENXIO;
-		if (size < ue->tlv_data_size)
-			return -ENOSPC;
+		int ret = 0;
+
+		mutex_lock(&ue->card->user_ctl_lock);
+		if (!ue->tlv_data_size || !ue->tlv_data) {
+			ret = -ENXIO;
+			goto err_unlock;
+		}
+		if (size < ue->tlv_data_size) {
+			ret = -ENOSPC;
+			goto err_unlock;
+		}
 		if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
-			return -EFAULT;
+			ret = -EFAULT;
+err_unlock:
+		mutex_unlock(&ue->card->user_ctl_lock);
+		if (ret)
+			return ret;
 	}
 	return change;
 }
@@ -1137,8 +1166,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	struct user_element *ue;
 	int idx, err;
 
-	if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
-		return -ENOMEM;
 	if (info->count < 1)
 		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
@@ -1147,21 +1174,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 				 SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
 	info->id.numid = 0;
 	memset(&kctl, 0, sizeof(kctl));
-	down_write(&card->controls_rwsem);
-	_kctl = snd_ctl_find_id(card, &info->id);
-	err = 0;
-	if (_kctl) {
-		if (replace)
-			err = snd_ctl_remove(card, _kctl);
-		else
-			err = -EBUSY;
-	} else {
-		if (replace)
-			err = -ENOENT;
+
+	if (replace) {
+		err = snd_ctl_remove_user_ctl(file, &info->id);
+		if (err)
+			return err;
 	}
-	up_write(&card->controls_rwsem);
-	if (err < 0)
-		return err;
+
+	if (card->user_ctl_count >= MAX_USER_CONTROLS)
+		return -ENOMEM;
+
 	memcpy(&kctl.id, &info->id, sizeof(info->id));
 	kctl.count = info->owner ? info->owner : 1;
 	access |= SNDRV_CTL_ELEM_ACCESS_USER;
@@ -1211,6 +1233,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
 	if (ue == NULL)
 		return -ENOMEM;
+	ue->card = card;
 	ue->info = *info;
 	ue->info.access = 0;
 	ue->elem_data = (char *)ue + sizeof(*ue);
@@ -1322,8 +1345,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
 		}
 		err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
 		if (err > 0) {
+			struct snd_ctl_elem_id id = kctl->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
 			return 0;
 		}
 	} else {
diff --git a/sound/core/info.c b/sound/core/info.c
index e79baa11b60e..08070e1eefeb 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -679,7 +679,7 @@ int snd_info_card_free(struct snd_card *card)
  * snd_info_get_line - read one line from the procfs buffer
  * @buffer: the procfs buffer
  * @line: the buffer to store
- * @len: the max. buffer size - 1
+ * @len: the max. buffer size
  *
  * Reads one line from the buffer and stores the string.
  *
@@ -699,7 +699,7 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len)
 			buffer->stop = 1;
 		if (c == '\n')
 			break;
-		if (len) {
+		if (len > 1) {
 			len--;
 			*line++ = c;
 		}
diff --git a/sound/core/init.c b/sound/core/init.c
index 6ef06400dfc8..27791a58e448 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -208,6 +208,7 @@ int snd_card_create(int idx, const char *xid,
 	INIT_LIST_HEAD(&card->devices);
 	init_rwsem(&card->controls_rwsem);
 	rwlock_init(&card->ctl_files_rwlock);
+	mutex_init(&card->user_ctl_lock);
 	INIT_LIST_HEAD(&card->controls);
 	INIT_LIST_HEAD(&card->ctl_files);
 	spin_lock_init(&card->files_lock);
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 17f45e8aa89c..e1e9e0c999fe 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -49,6 +49,8 @@ static struct snd_pcm *snd_pcm_get(struct snd_card *card, int device)
 	struct snd_pcm *pcm;
 
 	list_for_each_entry(pcm, &snd_pcm_devices, list) {
+		if (pcm->internal)
+			continue;
 		if (pcm->card == card && pcm->device == device)
 			return pcm;
 	}
@@ -60,6 +62,8 @@ static int snd_pcm_next(struct snd_card *card, int device)
 	struct snd_pcm *pcm;
 
 	list_for_each_entry(pcm, &snd_pcm_devices, list) {
+		if (pcm->internal)
+			continue;
 		if (pcm->card == card && pcm->device > device)
 			return pcm->device;
 		else if (pcm->card->number > card->number)
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index af49721ba0e3..c4ac3c1e19af 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -206,6 +206,8 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream,
 	if (err < 0)
 		return err;
 
+	if (clear_user(src, sizeof(*src)))
+		return -EFAULT;
 	if (put_user(status.state, &src->state) ||
 	    compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) ||
 	    compat_put_timespec(&status.tstamp, &src->tstamp) ||
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 41b3dfe68698..8eddece217bb 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1782,14 +1782,16 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream,
 {
 	struct snd_pcm_hw_params *params = arg;
 	snd_pcm_format_t format;
-	int channels, width;
+	int channels;
+	ssize_t frame_size;
 
 	params->fifo_size = substream->runtime->hw.fifo_size;
 	if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) {
 		format = params_format(params);
 		channels = params_channels(params);
-		width = snd_pcm_format_physical_width(format);
-		params->fifo_size /= width * channels;
+		frame_size = snd_pcm_format_size(format, channels);
+		if (frame_size > 0)
+			params->fifo_size /= (unsigned)frame_size;
 	}
 	return 0;
 }
@@ -1936,6 +1938,8 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 		case SNDRV_PCM_STATE_DISCONNECTED:
 			err = -EBADFD;
 			goto _endloop;
+		case SNDRV_PCM_STATE_PAUSED:
+			continue;
 		}
 		if (!tout) {
 			snd_printd("%s write error (DMA or IRQ trouble?)\n",
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f92818155958..175dca44c97e 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3197,7 +3197,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = {
 
 #ifndef ARCH_HAS_DMA_MMAP_COHERENT
 /* This should be defined / handled globally! */
-#ifdef CONFIG_ARM
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 #define ARCH_HAS_DMA_MMAP_COHERENT
 #endif
 #endif
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index ddabb406b14c..3a7946ebbe23 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -73,9 +73,11 @@
 #ifdef MSND_CLASSIC
 #  include "msnd_classic.h"
 #  define LOGNAME			"msnd_classic"
+#  define DEV_NAME			"msnd-classic"
 #else
 #  include "msnd_pinnacle.h"
 #  define LOGNAME			"snd_msnd_pinnacle"
+#  define DEV_NAME			"msnd-pinnacle"
 #endif
 
 static void set_default_audio_parameters(struct snd_msnd *chip)
@@ -1068,8 +1070,6 @@ static int snd_msnd_isa_remove(struct device *pdev, unsigned int dev)
 	return 0;
 }
 
-#define DEV_NAME "msnd-pinnacle"
-
 static struct isa_driver snd_msnd_driver = {
 	.match		= snd_msnd_isa_match,
 	.probe		= snd_msnd_isa_probe,
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index fe6fa93a6262..3397ddbdfc0c 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -30,6 +30,7 @@ config SND_ALS300
 	select SND_PCM
 	select SND_AC97_CODEC
 	select SND_OPL3_LIB
+	select ZONE_DMA
 	help
 	  Say 'Y' or 'M' to include support for Avance Logic ALS300/ALS300+
 
@@ -54,6 +55,7 @@ config SND_ALI5451
 	tristate "ALi M5451 PCI Audio Controller"
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for the integrated AC97 sound
 	  device on motherboards using the ALi M5451 Audio Controller
@@ -158,6 +160,7 @@ config SND_AZT3328
 	select SND_PCM
 	select SND_RAWMIDI
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for Aztech AZF3328 (PCI168)
 	  soundcards.
@@ -463,6 +466,7 @@ config SND_EMU10K1
 	select SND_HWDEP
 	select SND_RAWMIDI
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y to include support for Sound Blaster PCI 512, Live!,
 	  Audigy and E-mu APS (partially supported) soundcards.
@@ -478,6 +482,7 @@ config SND_EMU10K1X
 	tristate "Emu10k1X (Dell OEM Version)"
 	select SND_AC97_CODEC
 	select SND_RAWMIDI
+	select ZONE_DMA
 	help
 	  Say Y here to include support for the Dell OEM version of the
 	  Sound Blaster Live!.
@@ -511,6 +516,7 @@ config SND_ES1938
 	select SND_OPL3_LIB
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on ESS Solo-1
 	  (ES1938, ES1946, ES1969) chips.
@@ -522,6 +528,7 @@ config SND_ES1968
 	tristate "ESS ES1968/1978 (Maestro-1/2/2E)"
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on ESS Maestro
 	  1/2/2E chips.
@@ -603,6 +610,7 @@ config SND_ICE1712
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
 	select BITREVERSE
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on the
 	  ICE1712 (Envy24) chip.
@@ -690,6 +698,7 @@ config SND_LX6464ES
 config SND_MAESTRO3
 	tristate "ESS Allegro/Maestro3"
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on ESS Maestro 3
 	  (Allegro) chips.
@@ -786,6 +795,7 @@ config SND_SIS7019
 	tristate "SiS 7019 Audio Accelerator"
 	depends on X86 && !X86_64
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for the SiS 7019 Audio Accelerator.
 
@@ -797,6 +807,7 @@ config SND_SONICVIBES
 	select SND_OPL3_LIB
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on the S3
 	  SonicVibes chip.
@@ -808,6 +819,7 @@ config SND_TRIDENT
 	tristate "Trident 4D-Wave DX/NX; SiS 7018"
 	select SND_MPU401_UART
 	select SND_AC97_CODEC
+	select ZONE_DMA
 	help
 	  Say Y here to include support for soundcards based on Trident
 	  4D-Wave DX/NX or SiS 7018 chips.
@@ -844,8 +856,8 @@ config SND_VIRTUOSO
 	select SND_JACK if INPUT=y || INPUT=SND
 	help
 	  Say Y here to include support for sound cards based on the
-	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS,
-	  Essence ST (Deluxe), and Essence STX.
+	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX,
+	  Essence ST (Deluxe), and Essence STX (II).
 	  Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental;
 	  for the Xense, missing.
 
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index cae36597aa71..0a34b5f1c475 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux)
  * get more voice for pcm
  *
  * terminate most inactive voice and give it as a pcm voice.
+ *
+ * voice_lock is already held.
  */
 int
 snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
@@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 	struct snd_emux *emu;
 	struct snd_emux_voice *vp;
 	struct best_voice best[V_END];
-	unsigned long flags;
 	int i;
 
 	emu = hw->synth;
 
-	spin_lock_irqsave(&emu->voice_lock, flags);
 	lookup_voices(emu, hw, best, 1); /* no OFF voices */
 	for (i = 0; i < V_END; i++) {
 		if (best[i].voice >= 0) {
@@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 			vp->emu->num_voices--;
 			vp->ch = -1;
 			vp->state = SNDRV_EMUX_ST_OFF;
-			spin_unlock_irqrestore(&emu->voice_lock, flags);
 			return ch;
 		}
 	}
-	spin_unlock_irqrestore(&emu->voice_lock, flags);
 
 	/* not found */
 	return -ENOMEM;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 55108b5fb291..83a0f9b4452b 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -327,8 +327,10 @@ int snd_hda_get_sub_nodes(struct hda_codec *codec, hda_nid_t nid,
 	unsigned int parm;
 
 	parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT);
-	if (parm == -1)
+	if (parm == -1) {
+		*start_id = 0;
 		return 0;
+	}
 	*start_id = (parm >> 16) & 0x7fff;
 	return (int)(parm & 0x7fff);
 }
@@ -2517,9 +2519,6 @@ int snd_hda_codec_reset(struct hda_codec *codec)
 	cancel_delayed_work_sync(&codec->jackpoll_work);
 #ifdef CONFIG_PM
 	cancel_delayed_work_sync(&codec->power_work);
-	codec->power_on = 0;
-	codec->power_transition = 0;
-	codec->power_jiffies = jiffies;
 	flush_workqueue(bus->workq);
 #endif
 	snd_hda_ctls_clear(codec);
@@ -3927,6 +3926,10 @@ static void hda_call_codec_resume(struct hda_codec *codec)
 	 * in the resume / power-save sequence
 	 */
 	hda_keep_power_on(codec);
+	if (codec->pm_down_notified) {
+		codec->pm_down_notified = 0;
+		hda_call_pm_notify(codec->bus, true);
+	}
 	hda_set_power_state(codec, AC_PWRST_D0);
 	restore_shutup_pins(codec);
 	hda_exec_init_verbs(codec);
@@ -4789,8 +4792,8 @@ static void hda_power_work(struct work_struct *work)
 	spin_unlock(&codec->power_lock);
 
 	state = hda_call_codec_suspend(codec, true);
-	codec->pm_down_notified = 0;
-	if (!bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) {
+	if (!codec->pm_down_notified &&
+	    !bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) {
 		codec->pm_down_notified = 1;
 		hda_call_pm_notify(bus, false);
 	}
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index ad22decad02b..cb4d3700f330 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -468,6 +468,20 @@ static void invalidate_nid_path(struct hda_codec *codec, int idx)
 	memset(path, 0, sizeof(*path));
 }
 
+/* return a DAC if paired to the given pin by codec driver */
+static hda_nid_t get_preferred_dac(struct hda_codec *codec, hda_nid_t pin)
+{
+	struct hda_gen_spec *spec = codec->spec;
+	const hda_nid_t *list = spec->preferred_dacs;
+
+	if (!list)
+		return 0;
+	for (; *list; list += 2)
+		if (*list == pin)
+			return list[1];
+	return 0;
+}
+
 /* look for an empty DAC slot */
 static hda_nid_t look_for_dac(struct hda_codec *codec, hda_nid_t pin,
 			      bool is_digital)
@@ -786,10 +800,10 @@ static void set_pin_eapd(struct hda_codec *codec, hda_nid_t pin, bool enable)
 	if (spec->own_eapd_ctl ||
 	    !(snd_hda_query_pin_caps(codec, pin) & AC_PINCAP_EAPD))
 		return;
-	if (codec->inv_eapd)
-		enable = !enable;
 	if (spec->keep_eapd_on && !enable)
 		return;
+	if (codec->inv_eapd)
+		enable = !enable;
 	snd_hda_codec_update_cache(codec, pin, 0,
 				   AC_VERB_SET_EAPD_BTLENABLE,
 				   enable ? 0x02 : 0x00);
@@ -1134,7 +1148,14 @@ static int try_assign_dacs(struct hda_codec *codec, int num_outs,
 			continue;
 		}
 
-		dacs[i] = look_for_dac(codec, pin, false);
+		dacs[i] = get_preferred_dac(codec, pin);
+		if (dacs[i]) {
+			if (is_dac_already_used(codec, dacs[i]))
+				badness += bad->shared_primary;
+		}
+
+		if (!dacs[i])
+			dacs[i] = look_for_dac(codec, pin, false);
 		if (!dacs[i] && !i) {
 			/* try to steal the DAC of surrounds for the front */
 			for (j = 1; j < num_outs; j++) {
@@ -2445,12 +2466,8 @@ static int create_out_jack_modes(struct hda_codec *codec, int num_pins,
 
 	for (i = 0; i < num_pins; i++) {
 		hda_nid_t pin = pins[i];
-		if (pin == spec->hp_mic_pin) {
-			int ret = create_hp_mic_jack_mode(codec, pin);
-			if (ret < 0)
-				return ret;
+		if (pin == spec->hp_mic_pin)
 			continue;
-		}
 		if (get_out_jack_num_items(codec, pin) > 1) {
 			struct snd_kcontrol_new *knew;
 			char name[44];
@@ -2703,7 +2720,7 @@ static int hp_mic_jack_mode_put(struct snd_kcontrol *kcontrol,
 			val &= ~(AC_PINCTL_VREFEN | PIN_HP);
 			val |= get_vref_idx(vref_caps, idx) | PIN_IN;
 		} else
-			val = snd_hda_get_default_vref(codec, nid);
+			val = snd_hda_get_default_vref(codec, nid) | PIN_IN;
 	}
 	snd_hda_set_pin_ctl_cache(codec, nid, val);
 	call_hp_automute(codec, NULL);
@@ -2723,9 +2740,6 @@ static int create_hp_mic_jack_mode(struct hda_codec *codec, hda_nid_t pin)
 	struct hda_gen_spec *spec = codec->spec;
 	struct snd_kcontrol_new *knew;
 
-	if (get_out_jack_num_items(codec, pin) <= 1 &&
-	    get_in_jack_num_items(codec, pin) <= 1)
-		return 0; /* no need */
 	knew = snd_hda_gen_add_kctl(spec, "Headphone Mic Jack Mode",
 				    &hp_mic_jack_mode_enum);
 	if (!knew)
@@ -2754,6 +2768,44 @@ static int add_loopback_list(struct hda_gen_spec *spec, hda_nid_t mix, int idx)
 	return 0;
 }
 
+/* return true if either a volume or a mute amp is found for the given
+ * aamix path; the amp has to be either in the mixer node or its direct leaf
+ */
+static bool look_for_mix_leaf_ctls(struct hda_codec *codec, hda_nid_t mix_nid,
+				   hda_nid_t pin, unsigned int *mix_val,
+				   unsigned int *mute_val)
+{
+	int idx, num_conns;
+	const hda_nid_t *list;
+	hda_nid_t nid;
+
+	idx = snd_hda_get_conn_index(codec, mix_nid, pin, true);
+	if (idx < 0)
+		return false;
+
+	*mix_val = *mute_val = 0;
+	if (nid_has_volume(codec, mix_nid, HDA_INPUT))
+		*mix_val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
+	if (nid_has_mute(codec, mix_nid, HDA_INPUT))
+		*mute_val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
+	if (*mix_val && *mute_val)
+		return true;
+
+	/* check leaf node */
+	num_conns = snd_hda_get_conn_list(codec, mix_nid, &list);
+	if (num_conns < idx)
+		return false;
+	nid = list[idx];
+	if (!*mix_val && nid_has_volume(codec, nid, HDA_OUTPUT) &&
+	    !is_ctl_associated(codec, nid, HDA_OUTPUT, 0, NID_PATH_VOL_CTL))
+		*mix_val = HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_OUTPUT);
+	if (!*mute_val && nid_has_mute(codec, nid, HDA_OUTPUT) &&
+	    !is_ctl_associated(codec, nid, HDA_OUTPUT, 0, NID_PATH_MUTE_CTL))
+		*mute_val = HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_OUTPUT);
+
+	return *mix_val || *mute_val;
+}
+
 /* create input playback/capture controls for the given pin */
 static int new_analog_input(struct hda_codec *codec, int input_idx,
 			    hda_nid_t pin, const char *ctlname, int ctlidx,
@@ -2761,12 +2813,11 @@ static int new_analog_input(struct hda_codec *codec, int input_idx,
 {
 	struct hda_gen_spec *spec = codec->spec;
 	struct nid_path *path;
-	unsigned int val;
+	unsigned int mix_val, mute_val;
 	int err, idx;
 
-	if (!nid_has_volume(codec, mix_nid, HDA_INPUT) &&
-	    !nid_has_mute(codec, mix_nid, HDA_INPUT))
-		return 0; /* no need for analog loopback */
+	if (!look_for_mix_leaf_ctls(codec, mix_nid, pin, &mix_val, &mute_val))
+		return 0;
 
 	path = snd_hda_add_new_path(codec, pin, mix_nid, 0);
 	if (!path)
@@ -2775,20 +2826,18 @@ static int new_analog_input(struct hda_codec *codec, int input_idx,
 	spec->loopback_paths[input_idx] = snd_hda_get_path_idx(codec, path);
 
 	idx = path->idx[path->depth - 1];
-	if (nid_has_volume(codec, mix_nid, HDA_INPUT)) {
-		val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
-		err = __add_pb_vol_ctrl(spec, HDA_CTL_WIDGET_VOL, ctlname, ctlidx, val);
+	if (mix_val) {
+		err = __add_pb_vol_ctrl(spec, HDA_CTL_WIDGET_VOL, ctlname, ctlidx, mix_val);
 		if (err < 0)
 			return err;
-		path->ctls[NID_PATH_VOL_CTL] = val;
+		path->ctls[NID_PATH_VOL_CTL] = mix_val;
 	}
 
-	if (nid_has_mute(codec, mix_nid, HDA_INPUT)) {
-		val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
-		err = __add_pb_sw_ctrl(spec, HDA_CTL_WIDGET_MUTE, ctlname, ctlidx, val);
+	if (mute_val) {
+		err = __add_pb_sw_ctrl(spec, HDA_CTL_WIDGET_MUTE, ctlname, ctlidx, mute_val);
 		if (err < 0)
 			return err;
-		path->ctls[NID_PATH_MUTE_CTL] = val;
+		path->ctls[NID_PATH_MUTE_CTL] = mute_val;
 	}
 
 	path->active = true;
@@ -3474,7 +3523,7 @@ static int create_capture_mixers(struct hda_codec *codec)
 		if (!multi)
 			err = create_single_cap_vol_ctl(codec, n, vol, sw,
 							inv_dmic);
-		else if (!multi_cap_vol)
+		else if (!multi_cap_vol && !inv_dmic)
 			err = create_bind_cap_vol_ctl(codec, n, vol, sw);
 		else
 			err = create_multi_cap_vol_ctl(codec);
@@ -4175,6 +4224,26 @@ static unsigned int snd_hda_gen_path_power_filter(struct hda_codec *codec,
 	return AC_PWRST_D3;
 }
 
+/* mute all aamix inputs initially; parse up to the first leaves */
+static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix)
+{
+	int i, nums;
+	const hda_nid_t *conn;
+	bool has_amp;
+
+	nums = snd_hda_get_conn_list(codec, mix, &conn);
+	has_amp = nid_has_mute(codec, mix, HDA_INPUT);
+	for (i = 0; i < nums; i++) {
+		if (has_amp)
+			snd_hda_codec_amp_stereo(codec, mix,
+						 HDA_INPUT, i,
+						 0xff, HDA_AMP_MUTE);
+		else if (nid_has_volume(codec, conn[i], HDA_OUTPUT))
+			snd_hda_codec_amp_stereo(codec, conn[i],
+						 HDA_OUTPUT, 0,
+						 0xff, HDA_AMP_MUTE);
+	}
+}
 
 /*
  * Parse the given BIOS configuration and set up the hda_gen_spec
@@ -4287,6 +4356,17 @@ int snd_hda_gen_parse_auto_config(struct hda_codec *codec,
 	if (err < 0)
 		return err;
 
+	/* create "Headphone Mic Jack Mode" if no input selection is
+	 * available (or user specifies add_jack_modes hint)
+	 */
+	if (spec->hp_mic_pin &&
+	    (spec->auto_mic || spec->input_mux.num_items == 1 ||
+	     spec->add_jack_modes)) {
+		err = create_hp_mic_jack_mode(codec, spec->hp_mic_pin);
+		if (err < 0)
+			return err;
+	}
+
 	if (spec->add_jack_modes) {
 		if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) {
 			err = create_out_jack_modes(codec, cfg->line_outs,
@@ -4302,6 +4382,10 @@ int snd_hda_gen_parse_auto_config(struct hda_codec *codec,
 		}
 	}
 
+	/* mute all aamix input initially */
+	if (spec->mixer_nid)
+		mute_all_mixer_nid(codec, spec->mixer_nid);
+
  dig_only:
 	parse_digital(codec);
 
@@ -4383,9 +4467,11 @@ int snd_hda_gen_build_controls(struct hda_codec *codec)
 					    true, &spec->vmaster_mute.sw_kctl);
 		if (err < 0)
 			return err;
-		if (spec->vmaster_mute.hook)
+		if (spec->vmaster_mute.hook) {
 			snd_hda_add_vmaster_hook(codec, &spec->vmaster_mute,
 						 spec->vmaster_mute_enum);
+			snd_hda_sync_vmaster_hook(&spec->vmaster_mute);
+		}
 	}
 
 	free_kctls(spec); /* no longer needed */
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 76200314ee95..a18a1005002f 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -241,6 +241,9 @@ struct hda_gen_spec {
 	const struct badness_table *main_out_badness;
 	const struct badness_table *extra_out_badness;
 
+	/* preferred pin/DAC pairs; an array of paired NIDs */
+	const hda_nid_t *preferred_dacs;
+
 	/* loopback mixing mode */
 	bool aamix_mode;
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 624e6c044a44..1800db643a16 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -3332,6 +3332,10 @@ static void check_probe_mask(struct azx *chip, int dev)
  * white/black-list for enable_msi
  */
 static struct snd_pci_quirk msi_black_list[] = {
+	SND_PCI_QUIRK(0x103c, 0x2191, "HP", 0), /* AMD Hudson */
+	SND_PCI_QUIRK(0x103c, 0x2192, "HP", 0), /* AMD Hudson */
+	SND_PCI_QUIRK(0x103c, 0x21f7, "HP", 0), /* AMD Hudson */
+	SND_PCI_QUIRK(0x103c, 0x21fa, "HP", 0), /* AMD Hudson */
 	SND_PCI_QUIRK(0x1043, 0x81f2, "ASUS", 0), /* Athlon64 X2 + nvidia */
 	SND_PCI_QUIRK(0x1043, 0x81f6, "ASUS", 0), /* nvidia */
 	SND_PCI_QUIRK(0x1043, 0x822d, "ASUS", 0), /* Athlon64 X2 + nvidia MCP55 */
@@ -3852,6 +3856,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	/* Lynx Point */
 	{ PCI_DEVICE(0x8086, 0x8c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	/* 9 Series */
+	{ PCI_DEVICE(0x8086, 0x8ca0),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Wellsburg */
 	{ PCI_DEVICE(0x8086, 0x8d20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index d97f0d61a15b..290e09825b82 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -1197,8 +1197,12 @@ static int alloc_ad_spec(struct hda_codec *codec)
 static void ad_fixup_inv_jack_detect(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
-	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+	struct ad198x_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		codec->inv_jack_detect = 1;
+		spec->gen.keep_eapd_on = 1;
+	}
 }
 
 enum {
@@ -1223,6 +1227,14 @@ static int ad1986a_parse_auto_config(struct hda_codec *codec)
 {
 	int err;
 	struct ad198x_spec *spec;
+	static hda_nid_t preferred_pairs[] = {
+		0x1a, 0x03,
+		0x1b, 0x03,
+		0x1c, 0x04,
+		0x1d, 0x05,
+		0x1e, 0x03,
+		0
+	};
 
 	err = alloc_ad_spec(codec);
 	if (err < 0)
@@ -1243,6 +1255,8 @@ static int ad1986a_parse_auto_config(struct hda_codec *codec)
 	 * So, let's disable the shared stream.
 	 */
 	spec->gen.multiout.no_share_stream = 1;
+	/* give fixed DAC/pin pairs */
+	spec->gen.preferred_dacs = preferred_pairs;
 
 	snd_hda_pick_fixup(codec, NULL, ad1986a_fixup_tbl, ad1986a_fixups);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -1666,6 +1680,7 @@ static int ad1983_parse_auto_config(struct hda_codec *codec)
 		return err;
 	spec = codec->spec;
 
+	spec->gen.mixer_nid = 0x0e;
 	spec->gen.beep_nid = 0x10;
 	set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
 	err = ad198x_parse_auto_config(codec);
@@ -3652,6 +3667,7 @@ static int ad1884_parse_auto_config(struct hda_codec *codec)
 	spec = codec->spec;
 
 	spec->gen.mixer_nid = 0x20;
+	spec->gen.mixer_merge_nid = 0x21;
 	spec->gen.beep_nid = 0x10;
 	set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
 
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 90ff7a3f72df..4126f3d9edb6 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -2662,60 +2662,6 @@ static bool dspload_wait_loaded(struct hda_codec *codec)
 }
 
 /*
- * PCM stuffs
- */
-static void ca0132_setup_stream(struct hda_codec *codec, hda_nid_t nid,
-				 u32 stream_tag,
-				 int channel_id, int format)
-{
-	unsigned int oldval, newval;
-
-	if (!nid)
-		return;
-
-	snd_printdd(
-		   "ca0132_setup_stream: NID=0x%x, stream=0x%x, "
-		   "channel=%d, format=0x%x\n",
-		   nid, stream_tag, channel_id, format);
-
-	/* update the format-id if changed */
-	oldval = snd_hda_codec_read(codec, nid, 0,
-				    AC_VERB_GET_STREAM_FORMAT,
-				    0);
-	if (oldval != format) {
-		msleep(20);
-		snd_hda_codec_write(codec, nid, 0,
-				    AC_VERB_SET_STREAM_FORMAT,
-				    format);
-	}
-
-	oldval = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
-	newval = (stream_tag << 4) | channel_id;
-	if (oldval != newval) {
-		snd_hda_codec_write(codec, nid, 0,
-				    AC_VERB_SET_CHANNEL_STREAMID,
-				    newval);
-	}
-}
-
-static void ca0132_cleanup_stream(struct hda_codec *codec, hda_nid_t nid)
-{
-	unsigned int val;
-
-	if (!nid)
-		return;
-
-	snd_printdd(KERN_INFO "ca0132_cleanup_stream: NID=0x%x\n", nid);
-
-	val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
-	if (!val)
-		return;
-
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_STREAM_FORMAT, 0);
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0);
-}
-
-/*
  * PCM callbacks
  */
 static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
@@ -2726,7 +2672,7 @@ static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 {
 	struct ca0132_spec *spec = codec->spec;
 
-	ca0132_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
+	snd_hda_codec_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
 
 	return 0;
 }
@@ -2745,7 +2691,7 @@ static int ca0132_playback_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
 		msleep(50);
 
-	ca0132_cleanup_stream(codec, spec->dacs[0]);
+	snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
 
 	return 0;
 }
@@ -2822,10 +2768,8 @@ static int ca0132_capture_pcm_prepare(struct hda_pcm_stream *hinfo,
 					unsigned int format,
 					struct snd_pcm_substream *substream)
 {
-	struct ca0132_spec *spec = codec->spec;
-
-	ca0132_setup_stream(codec, spec->adcs[substream->number],
-			    stream_tag, 0, format);
+	snd_hda_codec_setup_stream(codec, hinfo->nid,
+				   stream_tag, 0, format);
 
 	return 0;
 }
@@ -2839,7 +2783,7 @@ static int ca0132_capture_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	if (spec->dsp_state == DSP_DOWNLOADING)
 		return 0;
 
-	ca0132_cleanup_stream(codec, hinfo->nid);
+	snd_hda_codec_cleanup_stream(codec, hinfo->nid);
 	return 0;
 }
 
@@ -4435,6 +4379,9 @@ static void ca0132_download_dsp(struct hda_codec *codec)
 	return; /* NOP */
 #endif
 
+	if (spec->dsp_state == DSP_DOWNLOAD_FAILED)
+		return; /* don't retry failures */
+
 	chipio_enable_clocks(codec);
 	spec->dsp_state = DSP_DOWNLOADING;
 	if (!ca0132_download_dsp_images(codec))
@@ -4611,7 +4558,8 @@ static int ca0132_init(struct hda_codec *codec)
 	struct auto_pin_cfg *cfg = &spec->autocfg;
 	int i;
 
-	spec->dsp_state = DSP_DOWNLOAD_INIT;
+	if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
+		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
 	snd_hda_power_up(codec);
@@ -4722,6 +4670,7 @@ static int patch_ca0132(struct hda_codec *codec)
 	codec->spec = spec;
 	spec->codec = codec;
 
+	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
 	spec->mixers[0] = ca0132_mixer;
 
@@ -4742,6 +4691,8 @@ static int patch_ca0132(struct hda_codec *codec)
 		return err;
 
 	codec->patch_ops = ca0132_patch_ops;
+	codec->pcm_format_first = 1;
+	codec->no_sticky_stream = 1;
 
 	return 0;
 }
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index b314d3e6d7fa..1868d3a6e310 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3225,6 +3225,7 @@ enum {
 	CXT_PINCFG_LEMOTE_A1205,
 	CXT_FIXUP_STEREO_DMIC,
 	CXT_FIXUP_INC_MIC_BOOST,
+	CXT_FIXUP_GPIO1,
 };
 
 static void cxt_fixup_stereo_dmic(struct hda_codec *codec,
@@ -3303,6 +3304,15 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt5066_increase_mic_boost,
 	},
+	[CXT_FIXUP_GPIO1] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{ 0x01, AC_VERB_SET_GPIO_MASK, 0x01 },
+			{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01 },
+			{ 0x01, AC_VERB_SET_GPIO_DATA, 0x01 },
+			{ }
+		},
+	},
 };
 
 static const struct snd_pci_quirk cxt5051_fixups[] = {
@@ -3312,6 +3322,7 @@ static const struct snd_pci_quirk cxt5051_fixups[] = {
 
 static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x215f, "Lenovo T510", CXT_PINCFG_LENOVO_TP410),
@@ -3480,6 +3491,8 @@ static const struct hda_codec_preset snd_hda_preset_conexant[] = {
 	  .patch = patch_conexant_auto },
 	{ .id = 0x14f15115, .name = "CX20757",
 	  .patch = patch_conexant_auto },
+	{ .id = 0x14f151d7, .name = "CX20952",
+	  .patch = patch_conexant_auto },
 	{} /* terminator */
 };
 
@@ -3506,6 +3519,7 @@ MODULE_ALIAS("snd-hda-codec-id:14f15111");
 MODULE_ALIAS("snd-hda-codec-id:14f15113");
 MODULE_ALIAS("snd-hda-codec-id:14f15114");
 MODULE_ALIAS("snd-hda-codec-id:14f15115");
+MODULE_ALIAS("snd-hda-codec-id:14f151d7");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Conexant HD-audio codec");
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index b5375ed022d7..ba442d24257a 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -86,6 +86,9 @@ struct hdmi_spec {
 	unsigned int channels_max; /* max over all cvts */
 
 	struct hdmi_eld temp_eld;
+
+	bool dyn_pin_out;
+
 	/*
 	 * Non-generic ATI/NVIDIA specific
 	 */
@@ -450,15 +453,25 @@ static void hdmi_write_dip_byte(struct hda_codec *codec, hda_nid_t pin_nid,
 
 static void hdmi_init_pin(struct hda_codec *codec, hda_nid_t pin_nid)
 {
+	struct hdmi_spec *spec = codec->spec;
+	int pin_out;
+
 	/* Unmute */
 	if (get_wcaps(codec, pin_nid) & AC_WCAP_OUT_AMP)
 		snd_hda_codec_write(codec, pin_nid, 0,
 				AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
-	/* Enable pin out: some machines with GM965 gets broken output when
-	 * the pin is disabled or changed while using with HDMI
-	 */
+
+	if (spec->dyn_pin_out)
+		/* Disable pin out until stream is active */
+		pin_out = 0;
+	else
+		/* Enable pin out: some machines with GM965 gets broken output
+		 * when the pin is disabled or changed while using with HDMI
+		 */
+		pin_out = PIN_OUT;
+
 	snd_hda_codec_write(codec, pin_nid, 0,
-			    AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+			    AC_VERB_SET_PIN_WIDGET_CONTROL, pin_out);
 }
 
 static int hdmi_get_channel_count(struct hda_codec *codec, hda_nid_t cvt_nid)
@@ -738,9 +751,10 @@ static int hdmi_manual_setup_channel_mapping(struct hda_codec *codec,
 static void hdmi_setup_fake_chmap(unsigned char *map, int ca)
 {
 	int i;
+	int ordered_ca = get_channel_allocation_order(ca);
 	for (i = 0; i < 8; i++) {
-		if (i < channel_allocations[ca].channels)
-			map[i] = from_cea_slot((hdmi_channel_mapping[ca][i] >> 4) & 0x0f);
+		if (i < channel_allocations[ordered_ca].channels)
+			map[i] = from_cea_slot(hdmi_channel_mapping[ca][i] & 0x0f);
 		else
 			map[i] = 0;
 	}
@@ -930,6 +944,14 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 	}
 
 	/*
+	 * always configure channel mapping, it may have been changed by the
+	 * user in the meantime
+	 */
+	hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
+				   channels, per_pin->chmap,
+				   per_pin->chmap_set);
+
+	/*
 	 * sizeof(ai) is used instead of sizeof(*hdmi_ai) or
 	 * sizeof(*dp_ai) to avoid partial match/update problems when
 	 * the user switches between HDMI/DP monitors.
@@ -940,20 +962,10 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 			    "pin=%d channels=%d\n",
 			    pin_nid,
 			    channels);
-		hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
-					   channels, per_pin->chmap,
-					   per_pin->chmap_set);
 		hdmi_stop_infoframe_trans(codec, pin_nid);
 		hdmi_fill_audio_infoframe(codec, pin_nid,
 					    ai.bytes, sizeof(ai));
 		hdmi_start_infoframe_trans(codec, pin_nid);
-	} else {
-		/* For non-pcm audio switch, setup new channel mapping
-		 * accordingly */
-		if (per_pin->non_pcm != non_pcm)
-			hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
-						   channels, per_pin->chmap,
-						   per_pin->chmap_set);
 	}
 
 	per_pin->non_pcm = non_pcm;
@@ -1474,6 +1486,7 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
 	hda_nid_t pin_nid = per_pin->pin_nid;
 	bool non_pcm;
+	int pinctl;
 
 	non_pcm = check_non_pcm_per_cvt(codec, cvt_nid);
 	per_pin->channels = substream->runtime->channels;
@@ -1483,6 +1496,14 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 
 	hdmi_setup_audio_infoframe(codec, per_pin, non_pcm);
 
+	if (spec->dyn_pin_out) {
+		pinctl = snd_hda_codec_read(codec, pin_nid, 0,
+					    AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_codec_write(codec, pin_nid, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL,
+				    pinctl | PIN_OUT);
+	}
+
 	return hdmi_setup_stream(codec, cvt_nid, pin_nid, stream_tag, format);
 }
 
@@ -1502,6 +1523,7 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 	int cvt_idx, pin_idx;
 	struct hdmi_spec_per_cvt *per_cvt;
 	struct hdmi_spec_per_pin *per_pin;
+	int pinctl;
 
 	if (hinfo->nid) {
 		cvt_idx = cvt_nid_to_cvt_index(spec, hinfo->nid);
@@ -1518,6 +1540,14 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 			return -EINVAL;
 		per_pin = get_pin(spec, pin_idx);
 
+		if (spec->dyn_pin_out) {
+			pinctl = snd_hda_codec_read(codec, per_pin->pin_nid, 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+			snd_hda_codec_write(codec, per_pin->pin_nid, 0,
+					    AC_VERB_SET_PIN_WIDGET_CONTROL,
+					    pinctl & ~PIN_OUT);
+		}
+
 		snd_hda_spdif_ctls_unassign(codec, pin_idx);
 		per_pin->chmap_set = false;
 		memset(per_pin->chmap, 0, sizeof(per_pin->chmap));
@@ -2002,8 +2032,9 @@ static int simple_playback_build_controls(struct hda_codec *codec)
 	int err;
 
 	per_cvt = get_cvt(spec, 0);
-	err = snd_hda_create_spdif_out_ctls(codec, per_cvt->cvt_nid,
-					    per_cvt->cvt_nid);
+	err = snd_hda_create_dig_out_ctls(codec, per_cvt->cvt_nid,
+					  per_cvt->cvt_nid,
+					  HDA_PCM_TYPE_HDMI);
 	if (err < 0)
 		return err;
 	return simple_hdmi_build_jack(codec, 0);
@@ -2476,6 +2507,21 @@ static int patch_nvhdmi_8ch_7x(struct hda_codec *codec)
 	return 0;
 }
 
+static int patch_nvhdmi(struct hda_codec *codec)
+{
+	struct hdmi_spec *spec;
+	int err;
+
+	err = patch_generic_hdmi(codec);
+	if (err)
+		return err;
+
+	spec = codec->spec;
+	spec->dyn_pin_out = true;
+
+	return 0;
+}
+
 /*
  * ATI-specific implementations
  *
@@ -2548,30 +2594,30 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0005, .name = "MCP77/78 HDMI",	.patch = patch_nvhdmi_8ch_7x },
 { .id = 0x10de0006, .name = "MCP77/78 HDMI",	.patch = patch_nvhdmi_8ch_7x },
 { .id = 0x10de0007, .name = "MCP79/7A HDMI",	.patch = patch_nvhdmi_8ch_7x },
-{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de000c, .name = "MCP89 HDMI",	.patch = patch_generic_hdmi },
-{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de000c, .name = "MCP89 HDMI",	.patch = patch_nvhdmi },
+{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP",	.patch = patch_nvhdmi },
 /* 17 is known to be absent */
-{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0051, .name = "GPU 51 HDMI/DP",	.patch = patch_generic_hdmi },
-{ .id = 0x10de0060, .name = "GPU 60 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0051, .name = "GPU 51 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0060, .name = "GPU 60 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 458cf89b1643..4008034b6ebe 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -175,6 +175,8 @@ static void alc_fix_pll(struct hda_codec *codec)
 			    spec->pll_coef_idx);
 	val = snd_hda_codec_read(codec, spec->pll_nid, 0,
 				 AC_VERB_GET_PROC_COEF, 0);
+	if (val == -1)
+		return;
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
 			    spec->pll_coef_idx);
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF,
@@ -316,6 +318,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 		case 0x10ec0885:
 		case 0x10ec0887:
 		/*case 0x10ec0889:*/ /* this causes an SPDIF problem */
+		case 0x10ec0900:
 			alc889_coef_init(codec);
 			break;
 		case 0x10ec0888:
@@ -937,6 +940,7 @@ static int alc_codec_rename_from_preset(struct hda_codec *codec)
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
+	SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x8376, "EeePC", 1),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1),
@@ -1037,6 +1041,7 @@ enum {
 	ALC880_FIXUP_UNIWILL,
 	ALC880_FIXUP_UNIWILL_DIG,
 	ALC880_FIXUP_Z71V,
+	ALC880_FIXUP_ASUS_W5A,
 	ALC880_FIXUP_3ST_BASE,
 	ALC880_FIXUP_3ST,
 	ALC880_FIXUP_3ST_DIG,
@@ -1207,6 +1212,26 @@ static const struct hda_fixup alc880_fixups[] = {
 			{ }
 		}
 	},
+	[ALC880_FIXUP_ASUS_W5A] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			/* set up the whole pins as BIOS is utterly broken */
+			{ 0x14, 0x0121411f }, /* HP */
+			{ 0x15, 0x411111f0 }, /* N/A */
+			{ 0x16, 0x411111f0 }, /* N/A */
+			{ 0x17, 0x411111f0 }, /* N/A */
+			{ 0x18, 0x90a60160 }, /* mic */
+			{ 0x19, 0x411111f0 }, /* N/A */
+			{ 0x1a, 0x411111f0 }, /* N/A */
+			{ 0x1b, 0x411111f0 }, /* N/A */
+			{ 0x1c, 0x411111f0 }, /* N/A */
+			{ 0x1d, 0x411111f0 }, /* N/A */
+			{ 0x1e, 0xb743111e }, /* SPDIF out */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC880_FIXUP_GPIO1,
+	},
 	[ALC880_FIXUP_3ST_BASE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -1328,6 +1353,7 @@ static const struct hda_fixup alc880_fixups[] = {
 
 static const struct snd_pci_quirk alc880_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1019, 0x0f69, "Coeus G610P", ALC880_FIXUP_W810),
+	SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS W5A", ALC880_FIXUP_ASUS_W5A),
 	SND_PCI_QUIRK(0x1043, 0x1964, "ASUS Z71V", ALC880_FIXUP_Z71V),
 	SND_PCI_QUIRK_VENDOR(0x1043, "ASUS", ALC880_FIXUP_GPIO1),
 	SND_PCI_QUIRK(0x1558, 0x5401, "Clevo GPIO2", ALC880_FIXUP_GPIO2),
@@ -1473,6 +1499,7 @@ enum {
 	ALC260_FIXUP_KN1,
 	ALC260_FIXUP_FSC_S7020,
 	ALC260_FIXUP_FSC_S7020_JWSE,
+	ALC260_FIXUP_VAIO_PINS,
 };
 
 static void alc260_gpio1_automute(struct hda_codec *codec)
@@ -1566,12 +1593,10 @@ static const struct hda_fixup alc260_fixups[] = {
 	[ALC260_FIXUP_COEF] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
-			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
-			{ 0x20, AC_VERB_SET_PROC_COEF,  0x3040 },
+			{ 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+			{ 0x1a, AC_VERB_SET_PROC_COEF,  0x3040 },
 			{ }
 		},
-		.chained = true,
-		.chain_id = ALC260_FIXUP_HP_PIN_0F,
 	},
 	[ALC260_FIXUP_GPIO1] = {
 		.type = HDA_FIXUP_VERBS,
@@ -1586,8 +1611,8 @@ static const struct hda_fixup alc260_fixups[] = {
 	[ALC260_FIXUP_REPLACER] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
-			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
-			{ 0x20, AC_VERB_SET_PROC_COEF,  0x3050 },
+			{ 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+			{ 0x1a, AC_VERB_SET_PROC_COEF,  0x3050 },
 			{ }
 		},
 		.chained = true,
@@ -1613,6 +1638,24 @@ static const struct hda_fixup alc260_fixups[] = {
 		.chained = true,
 		.chain_id = ALC260_FIXUP_FSC_S7020,
 	},
+	[ALC260_FIXUP_VAIO_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			/* Pin configs are missing completely on some VAIOs */
+			{ 0x0f, 0x01211020 },
+			{ 0x10, 0x0001003f },
+			{ 0x11, 0x411111f0 },
+			{ 0x12, 0x01a15930 },
+			{ 0x13, 0x411111f0 },
+			{ 0x14, 0x411111f0 },
+			{ 0x15, 0x411111f0 },
+			{ 0x16, 0x411111f0 },
+			{ 0x17, 0x411111f0 },
+			{ 0x18, 0x411111f0 },
+			{ 0x19, 0x411111f0 },
+			{ }
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc260_fixup_tbl[] = {
@@ -1621,6 +1664,8 @@ static const struct snd_pci_quirk alc260_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x008f, "Acer", ALC260_FIXUP_GPIO1),
 	SND_PCI_QUIRK(0x103c, 0x280a, "HP dc5750", ALC260_FIXUP_HP_DC5750),
 	SND_PCI_QUIRK(0x103c, 0x30ba, "HP Presario B1900", ALC260_FIXUP_HP_B1900),
+	SND_PCI_QUIRK(0x104d, 0x81bb, "Sony VAIO", ALC260_FIXUP_VAIO_PINS),
+	SND_PCI_QUIRK(0x104d, 0x81e2, "Sony VAIO TX", ALC260_FIXUP_HP_PIN_0F),
 	SND_PCI_QUIRK(0x10cf, 0x1326, "FSC LifeBook S7020", ALC260_FIXUP_FSC_S7020),
 	SND_PCI_QUIRK(0x1509, 0x4540, "Favorit 100XS", ALC260_FIXUP_GPIO1),
 	SND_PCI_QUIRK(0x152d, 0x0729, "Quanta KN1", ALC260_FIXUP_KN1),
@@ -1720,8 +1765,12 @@ enum {
 	ALC889_FIXUP_DAC_ROUTE,
 	ALC889_FIXUP_MBP_VREF,
 	ALC889_FIXUP_IMAC91_VREF,
+	ALC889_FIXUP_MBA11_VREF,
+	ALC889_FIXUP_MBA21_VREF,
+	ALC889_FIXUP_MP11_VREF,
 	ALC882_FIXUP_INV_DMIC,
 	ALC882_FIXUP_NO_PRIMARY_HP,
+	ALC887_FIXUP_ASUS_BASS,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1822,17 +1871,13 @@ static void alc889_fixup_mbp_vref(struct hda_codec *codec,
 	}
 }
 
-/* Set VREF on speaker pins on imac91 */
-static void alc889_fixup_imac91_vref(struct hda_codec *codec,
-				     const struct hda_fixup *fix, int action)
+static void alc889_fixup_mac_pins(struct hda_codec *codec,
+				  const hda_nid_t *nids, int num_nids)
 {
 	struct alc_spec *spec = codec->spec;
-	static hda_nid_t nids[2] = { 0x18, 0x1a };
 	int i;
 
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
-	for (i = 0; i < ARRAY_SIZE(nids); i++) {
+	for (i = 0; i < num_nids; i++) {
 		unsigned int val;
 		val = snd_hda_codec_get_pin_target(codec, nids[i]);
 		val |= AC_PINCTL_VREF_50;
@@ -1841,6 +1886,36 @@ static void alc889_fixup_imac91_vref(struct hda_codec *codec,
 	spec->gen.keep_vref_in_automute = 1;
 }
 
+/* Set VREF on speaker pins on imac91 */
+static void alc889_fixup_imac91_vref(struct hda_codec *codec,
+				     const struct hda_fixup *fix, int action)
+{
+	static hda_nid_t nids[2] = { 0x18, 0x1a };
+
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
+/* Set VREF on speaker pins on mba11 */
+static void alc889_fixup_mba11_vref(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	static hda_nid_t nids[1] = { 0x18 };
+
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
+/* Set VREF on speaker pins on mba21 */
+static void alc889_fixup_mba21_vref(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	static hda_nid_t nids[2] = { 0x18, 0x19 };
+
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
 /* Don't take HP output as primary
  * Strangely, the speaker output doesn't work on Vaio Z and some Vaio
  * all-in-one desktop PCs (for example VGC-LN51JGB) through DAC 0x05
@@ -2035,6 +2110,24 @@ static const struct hda_fixup alc882_fixups[] = {
 		.chained = true,
 		.chain_id = ALC882_FIXUP_GPIO1,
 	},
+	[ALC889_FIXUP_MBA11_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mba11_vref,
+		.chained = true,
+		.chain_id = ALC889_FIXUP_MBP_VREF,
+	},
+	[ALC889_FIXUP_MBA21_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mba21_vref,
+		.chained = true,
+		.chain_id = ALC889_FIXUP_MBP_VREF,
+	},
+	[ALC889_FIXUP_MP11_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mba11_vref,
+		.chained = true,
+		.chain_id = ALC885_FIXUP_MACPRO_GPIO,
+	},
 	[ALC882_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic_0x12,
@@ -2043,6 +2136,13 @@ static const struct hda_fixup alc882_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc882_fixup_no_primary_hp,
 	},
+	[ALC887_FIXUP_ASUS_BASS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{0x16, 0x99130130}, /* bass speaker */
+			{}
+		},
+	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2076,6 +2176,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1873, "ASUS W90V", ALC882_FIXUP_ASUS_W90V),
 	SND_PCI_QUIRK(0x1043, 0x1971, "Asus W2JC", ALC882_FIXUP_ASUS_W2JC),
 	SND_PCI_QUIRK(0x1043, 0x835f, "Asus Eee 1601", ALC888_FIXUP_EEE1601),
+	SND_PCI_QUIRK(0x1043, 0x84bc, "ASUS ET2700", ALC887_FIXUP_ASUS_BASS),
 	SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
 	SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
@@ -2084,14 +2185,14 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x00a1, "Macbook", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x00a4, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
-	SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC885_FIXUP_MACPRO_GPIO),
+	SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC889_FIXUP_MP11_VREF),
 	SND_PCI_QUIRK(0x106b, 0x1000, "iMac 24", ALC885_FIXUP_MACPRO_GPIO),
 	SND_PCI_QUIRK(0x106b, 0x2800, "AppleTV", ALC885_FIXUP_MACPRO_GPIO),
 	SND_PCI_QUIRK(0x106b, 0x2c00, "MacbookPro rev3", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3000, "iMac", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3200, "iMac 7,1 Aluminum", ALC882_FIXUP_EAPD),
-	SND_PCI_QUIRK(0x106b, 0x3400, "MacBookAir 1,1", ALC889_FIXUP_MBP_VREF),
-	SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBP_VREF),
+	SND_PCI_QUIRK(0x106b, 0x3400, "MacBookAir 1,1", ALC889_FIXUP_MBA11_VREF),
+	SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBA21_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3600, "Macbook 3,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3800, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3e00, "iMac 24 Aluminum", ALC885_FIXUP_MACPRO_GPIO),
@@ -2152,6 +2253,7 @@ static int patch_alc882(struct hda_codec *codec)
 	switch (codec->vendor_id) {
 	case 0x10ec0882:
 	case 0x10ec0885:
+	case 0x10ec0900:
 		break;
 	default:
 		/* ALC883 and variants */
@@ -2380,6 +2482,7 @@ static const struct hda_verb alc268_beep_init_verbs[] = {
 enum {
 	ALC268_FIXUP_INV_DMIC,
 	ALC268_FIXUP_HP_EAPD,
+	ALC268_FIXUP_SPDIF,
 };
 
 static const struct hda_fixup alc268_fixups[] = {
@@ -2394,6 +2497,13 @@ static const struct hda_fixup alc268_fixups[] = {
 			{}
 		}
 	},
+	[ALC268_FIXUP_SPDIF] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1e, 0x014b1180 }, /* enable SPDIF out */
+			{}
+		}
+	},
 };
 
 static const struct hda_model_fixup alc268_fixup_models[] = {
@@ -2403,6 +2513,7 @@ static const struct hda_model_fixup alc268_fixup_models[] = {
 };
 
 static const struct snd_pci_quirk alc268_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1025, 0x0139, "Acer TravelMate 6293", ALC268_FIXUP_SPDIF),
 	SND_PCI_QUIRK(0x1025, 0x015b, "Acer AOA 150 (ZG5)", ALC268_FIXUP_INV_DMIC),
 	/* below is codec SSID since multiple Toshiba laptops have the
 	 * same PCI SSID 1179:ff00
@@ -2531,6 +2642,7 @@ enum {
 	ALC269_TYPE_ALC282,
 	ALC269_TYPE_ALC284,
 	ALC269_TYPE_ALC286,
+	ALC269_TYPE_ALC255,
 };
 
 /*
@@ -2555,6 +2667,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	case ALC269_TYPE_ALC269VD:
 	case ALC269_TYPE_ALC282:
 	case ALC269_TYPE_ALC286:
+	case ALC269_TYPE_ALC255:
 		ssids = alc269_ssids;
 		break;
 	default:
@@ -2568,6 +2681,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
 {
 	int val = alc_read_coef_idx(codec, 0x04);
+	if (val == -1)
+		return;
 	if (power_up)
 		val |= 1 << 11;
 	else
@@ -2748,12 +2863,30 @@ static void alc269_fixup_mic_mute_hook(void *private_data, int enabled)
 
 	if (spec->mute_led_polarity)
 		enabled = !enabled;
-	pinval = AC_PINCTL_IN_EN |
-		(enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80);
+	pinval = snd_hda_codec_get_pin_target(codec, spec->mute_led_nid);
+	pinval &= ~AC_PINCTL_VREFEN;
+	pinval |= enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80;
 	if (spec->mute_led_nid)
 		snd_hda_set_pin_ctl_cache(codec, spec->mute_led_nid, pinval);
 }
 
+/* Make sure the led works even in runtime suspend */
+static unsigned int led_power_filter(struct hda_codec *codec,
+						  hda_nid_t nid,
+						  unsigned int power_state)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (power_state != AC_PWRST_D3 || nid != spec->mute_led_nid)
+		return power_state;
+
+	/* Set pin ctl again, it might have just been set to 0 */
+	snd_hda_set_pin_ctl(codec, nid,
+			    snd_hda_codec_get_pin_target(codec, nid));
+
+	return AC_PWRST_D0;
+}
+
 static void alc269_fixup_hp_mute_led(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
@@ -2773,6 +2906,7 @@ static void alc269_fixup_hp_mute_led(struct hda_codec *codec,
 		spec->mute_led_nid = pin - 0x0a + 0x18;
 		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
 		spec->gen.vmaster_mute_enum = 1;
+		codec->power_filter = led_power_filter;
 		snd_printd("Detected mute LED for %x:%d\n", spec->mute_led_nid,
 			   spec->mute_led_polarity);
 		break;
@@ -2788,6 +2922,7 @@ static void alc269_fixup_hp_mute_led_mic1(struct hda_codec *codec,
 		spec->mute_led_nid = 0x18;
 		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
 		spec->gen.vmaster_mute_enum = 1;
+		codec->power_filter = led_power_filter;
 	}
 }
 
@@ -2800,6 +2935,7 @@ static void alc269_fixup_hp_mute_led_mic2(struct hda_codec *codec,
 		spec->mute_led_nid = 0x19;
 		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
 		spec->gen.vmaster_mute_enum = 1;
+		codec->power_filter = led_power_filter;
 	}
 }
 
@@ -2958,6 +3094,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		alc_write_coef_idx(codec, 0x18, 0x7388);
 		break;
 	case 0x10ec0668:
+		alc_write_coef_idx(codec, 0x11, 0x0001);
 		alc_write_coef_idx(codec, 0x15, 0x0d60);
 		alc_write_coef_idx(codec, 0xc3, 0x0000);
 		break;
@@ -2980,6 +3117,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		alc_write_coef_idx(codec, 0x18, 0x7388);
 		break;
 	case 0x10ec0668:
+		alc_write_coef_idx(codec, 0x11, 0x0001);
 		alc_write_coef_idx(codec, 0x15, 0x0d50);
 		alc_write_coef_idx(codec, 0xc3, 0x0000);
 		break;
@@ -3040,8 +3178,10 @@ static void alc_update_headset_mode(struct hda_codec *codec)
 	else
 		new_headset_mode = ALC_HEADSET_MODE_HEADPHONE;
 
-	if (new_headset_mode == spec->current_headset_mode)
+	if (new_headset_mode == spec->current_headset_mode) {
+		snd_hda_gen_update_outputs(codec);
 		return;
+	}
 
 	switch (new_headset_mode) {
 	case ALC_HEADSET_MODE_UNPLUGGED:
@@ -3200,6 +3340,15 @@ static void alc269_fixup_limit_int_mic_boost(struct hda_codec *codec,
 	}
 }
 
+static void alc290_fixup_mono_speakers(struct hda_codec *codec,
+				       const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		/* Remove DAC node 0x03, as it seems to be
+		   giving mono output */
+		snd_hda_override_wcaps(codec, 0x03, 0);
+}
+
 enum {
 	ALC269_FIXUP_SONY_VAIO,
 	ALC275_FIXUP_SONY_VAIO_GPIO2,
@@ -3213,6 +3362,7 @@ enum {
 	ALC269_FIXUP_STEREO_DMIC,
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
+	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -3223,9 +3373,12 @@ enum {
 	ALC269_FIXUP_HP_GPIO_LED,
 	ALC269_FIXUP_INV_DMIC,
 	ALC269_FIXUP_LENOVO_DOCK,
+	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
+	ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+	ALC290_FIXUP_MONO_SPEAKERS,
 	ALC269_FIXUP_HEADSET_MODE,
 	ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC269_FIXUP_ASUS_X101_FUNC,
@@ -3317,6 +3470,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_QUANTA_MUTE
 	},
+	[ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -3412,6 +3572,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
 	},
+	[ALC269_FIXUP_DELL3_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+	},
 	[ALC269_FIXUP_HEADSET_MODE] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode,
@@ -3420,6 +3589,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode_no_hp_mic,
 	},
+	[ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_ASUS_X101_FUNC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_x101_headset_mic,
@@ -3477,9 +3653,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_limit_int_mic_boost,
 	},
+	[ALC290_FIXUP_MONO_SPEAKERS] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc290_fixup_mono_speakers,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1028, 0x05bd, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -3511,6 +3694,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
 	SND_PCI_QUIRK(0x103c, 0x18e6, "HP", ALC269_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -3529,6 +3715,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x8516, "ASUS X101CH", ALC269_FIXUP_ASUS_X101),
+	SND_PCI_QUIRK(0x104d, 0x90b5, "Sony VAIO Pro 11", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x104d, 0x90b6, "Sony VAIO Pro 13", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x104d, 0x9073, "Sony VAIO", ALC275_FIXUP_SONY_VAIO_GPIO2),
 	SND_PCI_QUIRK(0x104d, 0x907b, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
@@ -3539,6 +3727,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
@@ -3639,27 +3828,30 @@ static void alc269_fill_coef(struct hda_codec *codec)
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x017) {
 		val = alc_read_coef_idx(codec, 0x04);
 		/* Power up output pin */
-		alc_write_coef_idx(codec, 0x04, val | (1<<11));
+		if (val != -1)
+			alc_write_coef_idx(codec, 0x04, val | (1<<11));
 	}
 
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x018) {
 		val = alc_read_coef_idx(codec, 0xd);
-		if ((val & 0x0c00) >> 10 != 0x1) {
+		if (val != -1 && (val & 0x0c00) >> 10 != 0x1) {
 			/* Capless ramp up clock control */
 			alc_write_coef_idx(codec, 0xd, val | (1<<10));
 		}
 		val = alc_read_coef_idx(codec, 0x17);
-		if ((val & 0x01c0) >> 6 != 0x4) {
+		if (val != -1 && (val & 0x01c0) >> 6 != 0x4) {
 			/* Class D power on reset */
 			alc_write_coef_idx(codec, 0x17, val | (1<<7));
 		}
 	}
 
 	val = alc_read_coef_idx(codec, 0xd); /* Class D */
-	alc_write_coef_idx(codec, 0xd, val | (1<<14));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0xd, val | (1<<14));
 
 	val = alc_read_coef_idx(codec, 0x4); /* HP */
-	alc_write_coef_idx(codec, 0x4, val | (1<<11));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0x4, val | (1<<11));
 }
 
 /*
@@ -3727,8 +3919,12 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC284;
 		break;
 	case 0x10ec0286:
+	case 0x10ec0288:
 		spec->codec_variant = ALC269_TYPE_ALC286;
 		break;
+	case 0x10ec0255:
+		spec->codec_variant = ALC269_TYPE_ALC255;
+		break;
 	}
 
 	/* automatic parse from the BIOS config */
@@ -3771,6 +3967,7 @@ enum {
 	ALC861_FIXUP_AMP_VREF_0F,
 	ALC861_FIXUP_NO_JACK_DETECT,
 	ALC861_FIXUP_ASUS_A6RP,
+	ALC660_FIXUP_ASUS_W7J,
 };
 
 /* On some laptops, VREF of pin 0x0f is abused for controlling the main amp */
@@ -3820,10 +4017,22 @@ static const struct hda_fixup alc861_fixups[] = {
 		.v.func = alc861_fixup_asus_amp_vref_0f,
 		.chained = true,
 		.chain_id = ALC861_FIXUP_NO_JACK_DETECT,
+	},
+	[ALC660_FIXUP_ASUS_W7J] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* ASUS W7J needs a magic pin setup on unused NID 0x10
+			 * for enabling outputs
+			 */
+			{0x10, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24},
+			{ }
+		},
 	}
 };
 
 static const struct snd_pci_quirk alc861_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1043, 0x1253, "ASUS W7J", ALC660_FIXUP_ASUS_W7J),
+	SND_PCI_QUIRK(0x1043, 0x1263, "ASUS Z35HL", ALC660_FIXUP_ASUS_W7J),
 	SND_PCI_QUIRK(0x1043, 0x1393, "ASUS A6Rp", ALC861_FIXUP_ASUS_A6RP),
 	SND_PCI_QUIRK_VENDOR(0x1043, "ASUS laptop", ALC861_FIXUP_AMP_VREF_0F),
 	SND_PCI_QUIRK(0x1462, 0x7254, "HP DX2200", ALC861_FIXUP_NO_JACK_DETECT),
@@ -4216,6 +4425,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
+	SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_ASUS_MODE4),
+	SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_ASUS_MODE4),
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
 	SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2),
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
@@ -4376,6 +4587,7 @@ static int patch_alc662(struct hda_codec *codec)
 		case 0x10ec0272:
 		case 0x10ec0663:
 		case 0x10ec0665:
+		case 0x10ec0668:
 			set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
 			break;
 		case 0x10ec0273:
@@ -4433,7 +4645,9 @@ static int patch_alc680(struct hda_codec *codec)
  */
 static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0221, .name = "ALC221", .patch = patch_alc269 },
+	{ .id = 0x10ec0231, .name = "ALC231", .patch = patch_alc269 },
 	{ .id = 0x10ec0233, .name = "ALC233", .patch = patch_alc269 },
+	{ .id = 0x10ec0255, .name = "ALC255", .patch = patch_alc269 },
 	{ .id = 0x10ec0260, .name = "ALC260", .patch = patch_alc260 },
 	{ .id = 0x10ec0262, .name = "ALC262", .patch = patch_alc262 },
 	{ .id = 0x10ec0267, .name = "ALC267", .patch = patch_alc268 },
@@ -4448,6 +4662,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0283, .name = "ALC283", .patch = patch_alc269 },
 	{ .id = 0x10ec0284, .name = "ALC284", .patch = patch_alc269 },
 	{ .id = 0x10ec0286, .name = "ALC286", .patch = patch_alc269 },
+	{ .id = 0x10ec0288, .name = "ALC288", .patch = patch_alc269 },
 	{ .id = 0x10ec0290, .name = "ALC290", .patch = patch_alc269 },
 	{ .id = 0x10ec0292, .name = "ALC292", .patch = patch_alc269 },
 	{ .id = 0x10ec0861, .rev = 0x100340, .name = "ALC660",
@@ -4467,6 +4682,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
 	{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
 	{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+	{ .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
 	{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
 	{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
 	{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index dc4833f47a2b..4ae5767a2cf5 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -83,6 +83,8 @@ enum {
 	STAC_DELL_M6_BOTH,
 	STAC_DELL_EQ,
 	STAC_ALIENWARE_M17X,
+	STAC_92HD89XX_HP_FRONT_JACK,
+	STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
 	STAC_92HD73XX_MODELS
 };
 
@@ -97,6 +99,7 @@ enum {
 	STAC_92HD83XXX_HP_LED,
 	STAC_92HD83XXX_HP_INV_LED,
 	STAC_92HD83XXX_HP_MIC_LED,
+	STAC_HP_LED_GPIO10,
 	STAC_92HD83XXX_HEADSET_JACK,
 	STAC_92HD83XXX_HP,
 	STAC_HP_ENVY_BASS,
@@ -536,8 +539,8 @@ static void stac_init_power_map(struct hda_codec *codec)
 		if (snd_hda_jack_tbl_get(codec, nid))
 			continue;
 		if (def_conf == AC_JACK_PORT_COMPLEX &&
-		    !(spec->vref_mute_led_nid == nid ||
-		      is_jack_detectable(codec, nid))) {
+		    spec->vref_mute_led_nid != nid &&
+		    is_jack_detectable(codec, nid)) {
 			snd_hda_jack_detect_enable_callback(codec, nid,
 							    STAC_PWR_EVENT,
 							    jack_update_power);
@@ -570,9 +573,9 @@ static void stac_store_hints(struct hda_codec *codec)
 			spec->gpio_mask;
 	}
 	if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir))
-		spec->gpio_mask &= spec->gpio_mask;
-	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
 		spec->gpio_dir &= spec->gpio_mask;
+	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
+		spec->gpio_data &= spec->gpio_mask;
 	if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask))
 		spec->eapd_mask &= spec->gpio_mask;
 	if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute))
@@ -1775,6 +1778,17 @@ static const struct hda_pintbl intel_dg45id_pin_configs[] = {
 	{}
 };
 
+static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
+	{ 0x0a, 0x02214030 },
+	{ 0x0b, 0x02A19010 },
+	{}
+};
+
+static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = {
+	{ 0x0e, 0x400000f0 },
+	{}
+};
+
 static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -1893,6 +1907,14 @@ static const struct hda_fixup stac92hd73xx_fixups[] = {
 	[STAC_92HD73XX_NO_JD] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd73xx_fixup_no_jd,
+	},
+	[STAC_92HD89XX_HP_FRONT_JACK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = stac92hd89xx_hp_front_jack_pin_configs,
+	},
+	[STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
 	}
 };
 
@@ -1953,6 +1975,10 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = {
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
 		      "Alienware M17x R3", STAC_DELL_EQ),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927,
+				"HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
+				"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
 	{} /* terminator */
 };
 
@@ -2094,6 +2120,17 @@ static void stac92hd83xxx_fixup_hp_mic_led(struct hda_codec *codec,
 		spec->mic_mute_led_gpio = 0x08; /* GPIO3 */
 }
 
+static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec,
+				   const struct hda_fixup *fix, int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gpio_led = 0x10; /* GPIO4 */
+		spec->default_polarity = 0;
+	}
+}
+
 static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -2160,6 +2197,12 @@ static const struct hda_fixup stac92hd83xxx_fixups[] = {
 		.chained = true,
 		.chain_id = STAC_92HD83XXX_HP,
 	},
+	[STAC_HP_LED_GPIO10] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = stac92hd83xxx_fixup_hp_led_gpio10,
+		.chained = true,
+		.chain_id = STAC_92HD83XXX_HP,
+	},
 	[STAC_92HD83XXX_HEADSET_JACK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd83xxx_fixup_headset_jack,
@@ -2231,6 +2274,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = {
 			  "HP", STAC_92HD83XXX_HP_cNB11_INTQUAD),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888,
 			  "HP Envy Spectre", STAC_HP_ENVY_BASS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899,
+			  "HP Folio 13", STAC_HP_LED_GPIO10),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df,
 			  "HP Folio", STAC_92HD83XXX_HP_MIC_LED),
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xff00, 0x1900,
@@ -3602,11 +3647,18 @@ static int stac_parse_auto_config(struct hda_codec *codec)
 			return err;
 	}
 
-	stac_init_power_map(codec);
-
 	return 0;
 }
 
+static int stac_build_controls(struct hda_codec *codec)
+{
+	int err = snd_hda_gen_build_controls(codec);
+
+	if (err < 0)
+		return err;
+	stac_init_power_map(codec);
+	return 0;
+}
 
 static int stac_init(struct hda_codec *codec)
 {
@@ -3749,7 +3801,7 @@ static void stac_set_power_state(struct hda_codec *codec, hda_nid_t fg,
 #endif /* CONFIG_PM */
 
 static const struct hda_codec_ops stac_patch_ops = {
-	.build_controls = snd_hda_gen_build_controls,
+	.build_controls = stac_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = stac_init,
 	.free = stac_free,
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 806407a3973e..e6b70e35f628 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -685,9 +685,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pointer(struct snd_pcm_substream *
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1))
 		return 0;
 	ptr = runtime->buffer_size - inw(ice->ddma_port + 4);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream)
@@ -704,9 +705,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substrea
 		addr = ICE1712_DSC_ADDR0;
 	ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) -
 		ice->playback_con_virt_addr[substream->number];
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream)
@@ -717,9 +719,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *s
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1))
 		return 0;
 	ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr;
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback = {
@@ -1113,9 +1116,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pro_pointer(struct snd_pcm_substre
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START))
 		return 0;
 	ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream)
@@ -1126,9 +1130,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substrea
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW))
 		return 0;
 	ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback_pro = {
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 64b9fda5f04a..dbbbacfd535e 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = {
 	{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
+	{ OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
 	{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
 	{ }
 };
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index 77acd790ea47..eb7ad7706205 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -294,6 +294,16 @@ static int output_switch_put(struct snd_kcontrol *ctl,
 		oxygen_write16_masked(chip, OXYGEN_GPIO_DATA,
 				      data->output_sel == 1 ? GPIO_HP_REAR : 0,
 				      GPIO_HP_REAR);
+		oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING,
+				     data->output_sel == 0 ?
+				     OXYGEN_PLAY_MUTE01 :
+				     OXYGEN_PLAY_MUTE23 |
+				     OXYGEN_PLAY_MUTE45 |
+				     OXYGEN_PLAY_MUTE67,
+				     OXYGEN_PLAY_MUTE01 |
+				     OXYGEN_PLAY_MUTE23 |
+				     OXYGEN_PLAY_MUTE45 |
+				     OXYGEN_PLAY_MUTE67);
 	}
 	mutex_unlock(&chip->mutex);
 	return changed;
@@ -596,7 +606,7 @@ struct oxygen_model model_xonar_dg = {
 	.model_data_size = sizeof(struct dg),
 	.device_config = PLAYBACK_0_TO_I2S |
 			 PLAYBACK_1_TO_SPDIF |
-			 CAPTURE_0_FROM_I2S_2 |
+			 CAPTURE_0_FROM_I2S_1 |
 			 CAPTURE_1_FROM_SPDIF,
 	.dac_channels_pcm = 6,
 	.dac_channels_mixer = 0,
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index c8c7f2c9b355..e02605931669 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -100,8 +100,8 @@
  */
 
 /*
- * Xonar Essence ST (Deluxe)/STX
- * -----------------------------
+ * Xonar Essence ST (Deluxe)/STX (II)
+ * ----------------------------------
  *
  * CMI8788:
  *
@@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip,
 		chip->model.resume = xonar_stx_resume;
 		chip->model.set_dac_params = set_pcm1796_params;
 		break;
+	case 0x85f4:
+		chip->model = model_xonar_st;
+		/* TODO: daughterboard support */
+		chip->model.shortname = "Xonar STX II";
+		chip->model.init = xonar_stx_init;
+		chip->model.resume = xonar_stx_resume;
+		chip->model.set_dac_params = set_pcm1796_params;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 773a67fff4cd..431bf6897dd6 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -285,7 +285,7 @@ static char channel_map_9636_ds[26] = {
 	/* ADAT channels are remapped */
 	1, 3, 5, 7, 9, 11, 13, 15,
 	/* channels 8 and 9 are S/PDIF */
-	24, 25
+	24, 25,
 	/* others don't exist */
 	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
 };
diff --git a/sound/soc/blackfin/bf5xx-i2s.c b/sound/soc/blackfin/bf5xx-i2s.c
index dd0c2a4f83a3..e0869aaa1e93 100644
--- a/sound/soc/blackfin/bf5xx-i2s.c
+++ b/sound/soc/blackfin/bf5xx-i2s.c
@@ -111,6 +111,7 @@ static int bf5xx_i2s_hw_params(struct snd_pcm_substream *substream,
 		bf5xx_i2s->tcr2 |= 7;
 		bf5xx_i2s->rcr2 |= 7;
 		sport_handle->wdsize = 1;
+		break;
 	case SNDRV_PCM_FORMAT_S16_LE:
 		bf5xx_i2s->tcr2 |= 15;
 		bf5xx_i2s->rcr2 |= 15;
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 60159c07448d..6fd174be3bdf 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -351,6 +351,9 @@ static int snd_soc_put_volsw_2r_st(struct snd_kcontrol *kcontrol,
 	val = ucontrol->value.integer.value[0];
 	val2 = ucontrol->value.integer.value[1];
 
+	if (val >= ARRAY_SIZE(st_table) || val2 >= ARRAY_SIZE(st_table))
+		return -EINVAL;
+
 	err = snd_soc_update_bits(codec, reg, 0x3f, st_table[val].m);
 	if (err < 0)
 		return err;
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index a153b168129b..bce45c197e1d 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -1225,13 +1225,18 @@ static int anc_status_control_put(struct snd_kcontrol *kcontrol,
 	struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev);
 	struct device *dev = codec->dev;
 	bool apply_fir, apply_iir;
-	int req, status;
+	unsigned int req;
+	int status;
 
 	dev_dbg(dev, "%s: Enter.\n", __func__);
 
 	mutex_lock(&drvdata->anc_lock);
 
 	req = ucontrol->value.integer.value[0];
+	if (req >= ARRAY_SIZE(enum_anc_state)) {
+		status = -EINVAL;
+		goto cleanup;
+	}
 	if (req != ANC_APPLY_FIR_IIR && req != ANC_APPLY_FIR &&
 		req != ANC_APPLY_IIR) {
 		dev_err(dev, "%s: ERROR: Unsupported status to set '%s'!\n",
diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c
index dafdbe87edeb..0c499c638692 100644
--- a/sound/soc/codecs/adau1701.c
+++ b/sound/soc/codecs/adau1701.c
@@ -64,7 +64,7 @@
 
 #define ADAU1701_SEROCTL_WORD_LEN_24	0x0000
 #define ADAU1701_SEROCTL_WORD_LEN_20	0x0001
-#define ADAU1701_SEROCTL_WORD_LEN_16	0x0010
+#define ADAU1701_SEROCTL_WORD_LEN_16	0x0002
 #define ADAU1701_SEROCTL_WORD_LEN_MASK	0x0003
 
 #define ADAU1701_AUXNPOW_VBPD		0x40
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 2d0378709702..687565d08d9c 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -257,7 +257,7 @@ static int ak4642_dai_startup(struct snd_pcm_substream *substream,
 		 * This operation came from example code of
 		 * "ASAHI KASEI AK4642" (japanese) manual p94.
 		 */
-		snd_soc_write(codec, SG_SL1, PMMP | MGAIN0);
+		snd_soc_update_bits(codec, SG_SL1, PMMP | MGAIN0, PMMP | MGAIN0);
 		snd_soc_write(codec, TIMER, ZTM(0x3) | WTM(0x3));
 		snd_soc_write(codec, ALC_CTL1, ALC | LMTH0);
 		snd_soc_update_bits(codec, PW_MGMT1, PMADL, PMADL);
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 389f23253831..663a2a748626 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1455,6 +1455,8 @@ static void arizona_enable_fll(struct arizona_fll *fll,
 	try_wait_for_completion(&fll->ok);
 
 	regmap_update_bits(arizona->regmap, fll->base + 1,
+			   ARIZONA_FLL1_FREERUN, 0);
+	regmap_update_bits(arizona->regmap, fll->base + 1,
 			   ARIZONA_FLL1_ENA, ARIZONA_FLL1_ENA);
 	if (fll->ref_src >= 0 && fll->sync_src >= 0 &&
 	    fll->ref_src != fll->sync_src)
@@ -1473,6 +1475,8 @@ static void arizona_disable_fll(struct arizona_fll *fll)
 	struct arizona *arizona = fll->arizona;
 	bool change;
 
+	regmap_update_bits(arizona->regmap, fll->base + 1,
+			   ARIZONA_FLL1_FREERUN, ARIZONA_FLL1_FREERUN);
 	regmap_update_bits_check(arizona->regmap, fll->base + 1,
 				 ARIZONA_FLL1_ENA, 0, &change);
 	regmap_update_bits(arizona->regmap, fll->base + 0x11,
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 1e0fa3b5f79a..e1dfebbea650 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -124,9 +124,8 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol,
 
 static const DECLARE_TLV_DB_SCALE(adc_pcm_tlv, -5150, 50, 0);
 static const DECLARE_TLV_DB_SCALE(tone_tlv, -1050, 150, 0);
-/* This is a lie. after -102 db, it stays at -102 */
-/* maybe a range would be better */
-static const DECLARE_TLV_DB_SCALE(aout_tlv, -11550, 50, 0);
+
+static const DECLARE_TLV_DB_SCALE(aout_tlv, -10200, 50, 0);
 
 static const DECLARE_TLV_DB_SCALE(boost_tlv, 1600, 1600, 0);
 static const char *chan_mix[] = {
@@ -141,7 +140,7 @@ static const struct soc_enum cs42l51_chan_mix =
 static const struct snd_kcontrol_new cs42l51_snd_controls[] = {
 	SOC_DOUBLE_R_SX_TLV("PCM Playback Volume",
 			CS42L51_PCMA_VOL, CS42L51_PCMB_VOL,
-			6, 0x19, 0x7F, adc_pcm_tlv),
+			0, 0x19, 0x7F, adc_pcm_tlv),
 	SOC_DOUBLE_R("PCM Playback Switch",
 			CS42L51_PCMA_VOL, CS42L51_PCMB_VOL, 7, 1, 1),
 	SOC_DOUBLE_R_SX_TLV("Analog Playback Volume",
@@ -149,7 +148,7 @@ static const struct snd_kcontrol_new cs42l51_snd_controls[] = {
 			0, 0x34, 0xE4, aout_tlv),
 	SOC_DOUBLE_R_SX_TLV("ADC Mixer Volume",
 			CS42L51_ADCA_VOL, CS42L51_ADCB_VOL,
-			6, 0x19, 0x7F, adc_pcm_tlv),
+			0, 0x19, 0x7F, adc_pcm_tlv),
 	SOC_DOUBLE_R("ADC Mixer Switch",
 			CS42L51_ADCA_VOL, CS42L51_ADCB_VOL, 7, 1, 1),
 	SOC_SINGLE("Playback Deemphasis Switch", CS42L51_DAC_CTL, 3, 1, 0),
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index ee25f325d65c..b99af6362de6 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -350,7 +350,7 @@ static const char * const right_swap_text[] = {
 static const unsigned int swap_values[] = { 0, 1, 3 };
 
 static const struct soc_enum adca_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 3,
 			      ARRAY_SIZE(left_swap_text),
 			      left_swap_text,
 			      swap_values);
@@ -359,7 +359,7 @@ static const struct snd_kcontrol_new adca_mixer =
 	SOC_DAPM_ENUM("Route", adca_swap_enum);
 
 static const struct soc_enum pcma_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 3,
 			      ARRAY_SIZE(left_swap_text),
 			      left_swap_text,
 			      swap_values);
@@ -368,7 +368,7 @@ static const struct snd_kcontrol_new pcma_mixer =
 	SOC_DAPM_ENUM("Route", pcma_swap_enum);
 
 static const struct soc_enum adcb_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 3,
 			      ARRAY_SIZE(right_swap_text),
 			      right_swap_text,
 			      swap_values);
@@ -377,7 +377,7 @@ static const struct snd_kcontrol_new adcb_mixer =
 	SOC_DAPM_ENUM("Route", adcb_swap_enum);
 
 static const struct soc_enum pcmb_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 3,
 			      ARRAY_SIZE(right_swap_text),
 			      right_swap_text,
 			      swap_values);
diff --git a/sound/soc/codecs/cs42l52.h b/sound/soc/codecs/cs42l52.h
index 4277012c4719..a935d7381af6 100644
--- a/sound/soc/codecs/cs42l52.h
+++ b/sound/soc/codecs/cs42l52.h
@@ -179,7 +179,7 @@
 #define CS42L52_MICB_CTL			0x11
 #define	CS42L52_MIC_CTL_MIC_SEL_MASK		0xBF
 #define	CS42L52_MIC_CTL_MIC_SEL_SHIFT		6
-#define CS42L52_MIC_CTL_TYPE_MASK		0xDF
+#define CS42L52_MIC_CTL_TYPE_MASK		0x20
 #define CS42L52_MIC_CTL_TYPE_SHIFT		5
 
 
diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c
index 3b20c86cdb01..eade6e2d883d 100644
--- a/sound/soc/codecs/cs42l73.c
+++ b/sound/soc/codecs/cs42l73.c
@@ -325,7 +325,7 @@ static const char * const cs42l73_mono_mix_texts[] = {
 static const unsigned int cs42l73_mono_mix_values[] = { 0, 1, 2 };
 
 static const struct soc_enum spk_asp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
@@ -343,7 +343,7 @@ static const struct snd_kcontrol_new spk_xsp_mixer =
 	SOC_DAPM_ENUM("Route", spk_xsp_enum);
 
 static const struct soc_enum esl_asp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 5,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
@@ -352,7 +352,7 @@ static const struct snd_kcontrol_new esl_asp_mixer =
 	SOC_DAPM_ENUM("Route", esl_asp_enum);
 
 static const struct soc_enum esl_xsp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 7,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index dc0284dc9e6f..76fdf0a598bc 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -1268,11 +1268,23 @@ static struct snd_soc_dai_driver da732x_dai[] = {
 	},
 };
 
+static bool da732x_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case DA732X_REG_HPL_DAC_OFF_CNTL:
+	case DA732X_REG_HPR_DAC_OFF_CNTL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct regmap_config da732x_regmap = {
 	.reg_bits		= 8,
 	.val_bits		= 8,
 
 	.max_register		= DA732X_MAX_REG,
+	.volatile_reg		= da732x_volatile,
 	.reg_defaults		= da732x_reg_cache,
 	.num_reg_defaults	= ARRAY_SIZE(da732x_reg_cache),
 	.cache_type		= REGCACHE_RBTREE,
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 8d14a76c7249..be8de7ce1cda 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = {
 static bool max98090_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case M98090_REG_SOFTWARE_RESET:
 	case M98090_REG_DEVICE_STATUS:
 	case M98090_REG_JACK_STATUS:
 	case M98090_REG_REVISION_ID:
@@ -336,6 +337,7 @@ static bool max98090_readable_register(struct device *dev, unsigned int reg)
 	case M98090_REG_RECORD_TDM_SLOT:
 	case M98090_REG_SAMPLE_RATE:
 	case M98090_REG_DMIC34_BIQUAD_BASE ... M98090_REG_DMIC34_BIQUAD_BASE + 0x0E:
+	case M98090_REG_REVISION_ID:
 		return true;
 	default:
 		return false;
@@ -1362,8 +1364,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
 	{"STENL Mux", "Sidetone Left", "DMICL"},
 	{"STENR Mux", "Sidetone Right", "ADCR"},
 	{"STENR Mux", "Sidetone Right", "DMICR"},
-	{"DACL", "NULL", "STENL Mux"},
-	{"DACR", "NULL", "STENL Mux"},
+	{"DACL", NULL, "STENL Mux"},
+	{"DACR", NULL, "STENL Mux"},
 
 	{"AIFINL", NULL, "SHDN"},
 	{"AIFINR", NULL, "SHDN"},
@@ -1755,16 +1757,6 @@ static int max98090_set_bias_level(struct snd_soc_codec *codec,
 
 	switch (level) {
 	case SND_SOC_BIAS_ON:
-		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
-			ret = regcache_sync(max98090->regmap);
-
-			if (ret != 0) {
-				dev_err(codec->dev,
-					"Failed to sync cache: %d\n", ret);
-				return ret;
-			}
-		}
-
 		if (max98090->jack_state == M98090_JACK_STATE_HEADSET) {
 			/*
 			 * Set to normal bias level.
@@ -1778,6 +1770,16 @@ static int max98090_set_bias_level(struct snd_soc_codec *codec,
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
+		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
+			ret = regcache_sync(max98090->regmap);
+			if (ret != 0) {
+				dev_err(codec->dev,
+					"Failed to sync cache: %d\n", ret);
+				return ret;
+			}
+		}
+		break;
+
 	case SND_SOC_BIAS_OFF:
 		/* Set internal pull-up to lowest power mode */
 		snd_soc_update_bits(codec, M98090_REG_JACK_DETECT,
@@ -2232,7 +2234,7 @@ static int max98090_probe(struct snd_soc_codec *codec)
 	/* Register for interrupts */
 	dev_dbg(codec->dev, "irq = %d\n", max98090->irq);
 
-	ret = request_threaded_irq(max98090->irq, NULL,
+	ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL,
 		max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 		"max98090_interrupt", codec);
 	if (ret < 0) {
@@ -2342,6 +2344,8 @@ static int max98090_runtime_resume(struct device *dev)
 
 	regcache_cache_only(max98090->regmap, false);
 
+	max98090_reset(max98090);
+
 	regcache_sync(max98090->regmap);
 
 	return 0;
diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c
index 41cdd1642970..8dbcacd44e6a 100644
--- a/sound/soc/codecs/max98095.c
+++ b/sound/soc/codecs/max98095.c
@@ -1863,7 +1863,7 @@ static int max98095_put_eq_enum(struct snd_kcontrol *kcontrol,
 	struct max98095_pdata *pdata = max98095->pdata;
 	int channel = max98095_get_eq_channel(kcontrol->id.name);
 	struct max98095_cdata *cdata;
-	int sel = ucontrol->value.integer.value[0];
+	unsigned int sel = ucontrol->value.integer.value[0];
 	struct max98095_eq_cfg *coef_set;
 	int fs, best, best_val, i;
 	int regmask, regsave;
@@ -2016,7 +2016,7 @@ static int max98095_put_bq_enum(struct snd_kcontrol *kcontrol,
 	struct max98095_pdata *pdata = max98095->pdata;
 	int channel = max98095_get_bq_channel(codec, kcontrol->id.name);
 	struct max98095_cdata *cdata;
-	int sel = ucontrol->value.integer.value[0];
+	unsigned int sel = ucontrol->value.integer.value[0];
 	struct max98095_biquad_cfg *coef_set;
 	int fs, best, best_val, i;
 	int regmask, regsave;
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index ea479388fb5c..23670737116e 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1317,8 +1317,7 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 
 	/* enable small pop, introduce 400ms delay in turning off */
 	snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL,
-				SGTL5000_SMALL_POP,
-				SGTL5000_SMALL_POP);
+				SGTL5000_SMALL_POP, 1);
 
 	/* disable short cut detector */
 	snd_soc_write(codec, SGTL5000_CHIP_SHORT_CTRL, 0);
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index d3a68bbfea00..0bd6e1cd8200 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -275,7 +275,7 @@
 #define SGTL5000_BIAS_CTRL_MASK			0x000e
 #define SGTL5000_BIAS_CTRL_SHIFT		1
 #define SGTL5000_BIAS_CTRL_WIDTH		3
-#define SGTL5000_SMALL_POP			0x0001
+#define SGTL5000_SMALL_POP			0
 
 /*
  * SGTL5000_CHIP_MIC_CTRL
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index 4068f2491232..bb3878c9625f 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -176,6 +176,13 @@ static int _process_sigma_firmware(struct device *dev,
 		goto done;
 	}
 
+	if (ssfw_head->version != 1) {
+		dev_err(dev,
+			"Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n",
+			ssfw_head->version);
+		goto done;
+	}
+
 	crc = crc32(0, fw->data + sizeof(*ssfw_head),
 			fw->size - sizeof(*ssfw_head));
 	pr_debug("%s: crc=%x\n", __func__, crc);
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index cfb55fe35e98..8517e70bc24b 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -187,42 +187,42 @@ static const unsigned int sta32x_limiter_drc_release_tlv[] = {
 	13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0),
 };
 
-static const struct soc_enum sta32x_drc_ac_enum =
-	SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
-			2, sta32x_drc_ac);
-static const struct soc_enum sta32x_auto_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
-			3, sta32x_auto_eq_mode);
-static const struct soc_enum sta32x_auto_gc_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
-			4, sta32x_auto_gc_mode);
-static const struct soc_enum sta32x_auto_xo_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
-			16, sta32x_auto_xo_mode);
-static const struct soc_enum sta32x_preset_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
-			32, sta32x_preset_eq_mode);
-static const struct soc_enum sta32x_limiter_ch1_enum =
-	SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch2_enum =
-	SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch3_enum =
-	SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter1_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter2_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter1_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
-static const struct soc_enum sta32x_limiter2_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum,
+			    STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
+			    sta32x_drc_ac);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
+			    sta32x_auto_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
+			    sta32x_auto_gc_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum,
+			    STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
+			    sta32x_auto_xo_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum,
+			    STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
+			    sta32x_preset_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum,
+			    STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum,
+			    STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum,
+			    STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum,
+			    STA32X_L1AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum,
+			    STA32X_L2AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum,
+			    STA32X_L1AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum,
+			    STA32X_L2AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
 
 /* byte array controls for setting biquad, mixer, scaling coefficients;
  * for biquads all five coefficients need to be set in one go,
@@ -331,7 +331,7 @@ static int sta32x_sync_coef_shadow(struct snd_soc_codec *codec)
 
 static int sta32x_cache_sync(struct snd_soc_codec *codec)
 {
-	struct sta32x_priv *sta32x = codec->control_data;
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
 	unsigned int mute;
 	int rc;
 
@@ -432,7 +432,7 @@ SOC_SINGLE_TLV("Treble Tone Control", STA32X_TONE, STA32X_TONE_TTC_SHIFT, 15, 0,
 SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum),
 SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum),
 SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
-SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
+SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum),
 
 /* depending on mode, the attack/release thresholds have
  * two different enum definitions; provide both
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 88ad7db52dde..3775394c9c8b 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -37,6 +37,95 @@ struct wm5110_priv {
 	struct arizona_fll fll[2];
 };
 
+static const struct reg_default wm5110_sysclk_revd_patch[] = {
+	{ 0x3093, 0x1001 },
+	{ 0x30E3, 0x1301 },
+	{ 0x3133, 0x1201 },
+	{ 0x3183, 0x1501 },
+	{ 0x31D3, 0x1401 },
+	{ 0x0049, 0x01ea },
+	{ 0x004a, 0x01f2 },
+	{ 0x0057, 0x01e7 },
+	{ 0x0058, 0x01fb },
+	{ 0x33ce, 0xc4f5 },
+	{ 0x33cf, 0x1361 },
+	{ 0x33d0, 0x0402 },
+	{ 0x33d1, 0x4700 },
+	{ 0x33d2, 0x026d },
+	{ 0x33d3, 0xff00 },
+	{ 0x33d4, 0x026d },
+	{ 0x33d5, 0x0101 },
+	{ 0x33d6, 0xc4f5 },
+	{ 0x33d7, 0x0361 },
+	{ 0x33d8, 0x0402 },
+	{ 0x33d9, 0x6701 },
+	{ 0x33da, 0xc4f5 },
+	{ 0x33db, 0x136f },
+	{ 0x33dc, 0xc4f5 },
+	{ 0x33dd, 0x134f },
+	{ 0x33de, 0xc4f5 },
+	{ 0x33df, 0x131f },
+	{ 0x33e0, 0x026d },
+	{ 0x33e1, 0x4f01 },
+	{ 0x33e2, 0x026d },
+	{ 0x33e3, 0xf100 },
+	{ 0x33e4, 0x026d },
+	{ 0x33e5, 0x0001 },
+	{ 0x33e6, 0xc4f5 },
+	{ 0x33e7, 0x0361 },
+	{ 0x33e8, 0x0402 },
+	{ 0x33e9, 0x6601 },
+	{ 0x33ea, 0xc4f5 },
+	{ 0x33eb, 0x136f },
+	{ 0x33ec, 0xc4f5 },
+	{ 0x33ed, 0x134f },
+	{ 0x33ee, 0xc4f5 },
+	{ 0x33ef, 0x131f },
+	{ 0x33f0, 0x026d },
+	{ 0x33f1, 0x4e01 },
+	{ 0x33f2, 0x026d },
+	{ 0x33f3, 0xf000 },
+	{ 0x33f6, 0xc4f5 },
+	{ 0x33f7, 0x1361 },
+	{ 0x33f8, 0x0402 },
+	{ 0x33f9, 0x4600 },
+	{ 0x33fa, 0x026d },
+	{ 0x33fb, 0xfe00 },
+};
+
+static int wm5110_sysclk_ev(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = w->codec;
+	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
+	struct regmap *regmap = codec->control_data;
+	const struct reg_default *patch = NULL;
+	int i, patch_size;
+
+	switch (arizona->rev) {
+	case 3:
+		patch = wm5110_sysclk_revd_patch;
+		patch_size = ARRAY_SIZE(wm5110_sysclk_revd_patch);
+		break;
+	default:
+		return 0;
+	}
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		if (patch)
+			for (i = 0; i < patch_size; i++)
+				regmap_write(regmap, patch[i].reg,
+					     patch[i].def);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
 static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
 static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
@@ -386,7 +475,7 @@ static const struct snd_kcontrol_new wm5110_aec_loopback_mux =
 
 static const struct snd_soc_dapm_widget wm5110_dapm_widgets[] = {
 SND_SOC_DAPM_SUPPLY("SYSCLK", ARIZONA_SYSTEM_CLOCK_1, ARIZONA_SYSCLK_ENA_SHIFT,
-		    0, NULL, 0),
+		    0, wm5110_sysclk_ev, SND_SOC_DAPM_POST_PMU),
 SND_SOC_DAPM_SUPPLY("ASYNCCLK", ARIZONA_ASYNC_CLOCK_1,
 		    ARIZONA_ASYNC_CLK_ENA_SHIFT, 0, NULL, 0),
 SND_SOC_DAPM_SUPPLY("OPCLK", ARIZONA_OUTPUT_SYSTEM_CLOCK,
@@ -856,7 +945,7 @@ static const struct snd_soc_dapm_route wm5110_dapm_routes[] = {
 	{ "HPOUT2R", NULL, "OUT2R" },
 
 	{ "HPOUT3L", NULL, "OUT3L" },
-	{ "HPOUT3R", NULL, "OUT3L" },
+	{ "HPOUT3R", NULL, "OUT3R" },
 
 	{ "SPKOUTLN", NULL, "OUT4L" },
 	{ "SPKOUTLP", NULL, "OUT4L" },
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 5276062d6c79..10d492b6a5b4 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -407,10 +407,10 @@ static int wm8731_set_dai_fmt(struct snd_soc_dai *codec_dai,
 		iface |= 0x0001;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
-		iface |= 0x0003;
+		iface |= 0x0013;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
-		iface |= 0x0013;
+		iface |= 0x0003;
 		break;
 	default:
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c
index 89a18d82f303..5bce21013485 100644
--- a/sound/soc/codecs/wm8770.c
+++ b/sound/soc/codecs/wm8770.c
@@ -196,8 +196,8 @@ static const char *ain_text[] = {
 	"AIN5", "AIN6", "AIN7", "AIN8"
 };
 
-static const struct soc_enum ain_enum =
-	SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text);
+static SOC_ENUM_DOUBLE_DECL(ain_enum,
+			    WM8770_ADCMUX, 0, 4, ain_text);
 
 static const struct snd_kcontrol_new ain_mux =
 	SOC_DAPM_ENUM("Capture Mux", ain_enum);
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 3ff195c541db..af62f843a691 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1449,7 +1449,7 @@ static int wm8904_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
-		aif1 |= WM8904_AIF_LRCLK_INV;
+		aif1 |= 0x3 | WM8904_AIF_LRCLK_INV;
 	case SND_SOC_DAIFMT_DSP_A:
 		aif1 |= 0x3;
 		break;
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b0710d817a65..754f88e1fdab 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -153,7 +153,7 @@ static int wm8958_dsp2_fw(struct snd_soc_codec *codec, const char *name,
 
 			data32 &= 0xffffff;
 
-			wm8994_bulk_write(codec->control_data,
+			wm8994_bulk_write(wm8994->wm8994,
 					  data32 & 0xffffff,
 					  block_len / 2,
 					  (void *)(data + 8));
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 730dd0c0f0ab..1ae1f8bd9c36 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -153,6 +153,7 @@ static struct reg_default wm8962_reg[] = {
 	{ 40, 0x0000 },   /* R40    - SPKOUTL volume */
 	{ 41, 0x0000 },   /* R41    - SPKOUTR volume */
 
+	{ 49, 0x0010 },   /* R49    - Class D Control 1 */
 	{ 51, 0x0003 },   /* R51    - Class D Control 2 */
 
 	{ 56, 0x0506 },   /* R56    - Clocking 4 */
@@ -794,7 +795,6 @@ static bool wm8962_volatile_register(struct device *dev, unsigned int reg)
 	case WM8962_ALC2:
 	case WM8962_THERMAL_SHUTDOWN_STATUS:
 	case WM8962_ADDITIONAL_CONTROL_4:
-	case WM8962_CLASS_D_CONTROL_1:
 	case WM8962_DC_SERVO_6:
 	case WM8962_INTERRUPT_STATUS_1:
 	case WM8962_INTERRUPT_STATUS_2:
@@ -2901,13 +2901,22 @@ static int wm8962_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
 static int wm8962_mute(struct snd_soc_dai *dai, int mute)
 {
 	struct snd_soc_codec *codec = dai->codec;
-	int val;
+	int val, ret;
 
 	if (mute)
-		val = WM8962_DAC_MUTE;
+		val = WM8962_DAC_MUTE | WM8962_DAC_MUTE_ALT;
 	else
 		val = 0;
 
+	/**
+	 * The DAC mute bit is mirrored in two registers, update both to keep
+	 * the register cache consistent.
+	 */
+	ret = snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_1,
+				  WM8962_DAC_MUTE_ALT, val);
+	if (ret < 0)
+		return ret;
+
 	return snd_soc_update_bits(codec, WM8962_ADC_DAC_CONTROL_1,
 				   WM8962_DAC_MUTE, val);
 }
@@ -3686,6 +3695,8 @@ static int wm8962_i2c_probe(struct i2c_client *i2c,
 	if (ret < 0)
 		goto err_enable;
 
+	regcache_cache_only(wm8962->regmap, true);
+
 	/* The drivers should power up as needed */
 	regulator_bulk_disable(ARRAY_SIZE(wm8962->supplies), wm8962->supplies);
 
diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h
index a1a5d5294c19..910aafd09d21 100644
--- a/sound/soc/codecs/wm8962.h
+++ b/sound/soc/codecs/wm8962.h
@@ -1954,6 +1954,10 @@
 #define WM8962_SPKOUTL_ENA_MASK                 0x0040  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_SHIFT                     6  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_WIDTH                     1  /* SPKOUTL_ENA */
+#define WM8962_DAC_MUTE_ALT                     0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_MASK                0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_SHIFT                    4  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_WIDTH                    1  /* DAC_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE                 0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_MASK            0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_SHIFT                1  /* SPKOUTL_PGA_MUTE */
diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 837978e16e9d..ded9ed854a1f 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -1264,6 +1264,8 @@ static int wm8990_set_bias_level(struct snd_soc_codec *codec,
 
 		/* disable POBCTRL, SOFT_ST and BUFDCOPEN */
 		snd_soc_write(codec, WM8990_ANTIPOP2, 0x0);
+
+		codec->cache_sync = 1;
 		break;
 	}
 
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 3470b649c0b2..d785e46be47c 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -964,6 +964,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 			  file, blocks, pos - firmware->size);
 
 out_fw:
+	regmap_async_complete(regmap);
 	release_firmware(firmware);
 	wm_adsp_buf_free(&buf_list);
 out:
@@ -1073,13 +1074,17 @@ static int wm_adsp2_ena(struct wm_adsp *dsp)
 		return ret;
 
 	/* Wait for the RAM to start, should be near instantaneous */
-	count = 0;
-	do {
+	for (count = 0; count < 10; ++count) {
 		ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1,
 				  &val);
 		if (ret != 0)
 			return ret;
-	} while (!(val & ADSP2_RAM_RDY) && ++count < 10);
+
+		if (val & ADSP2_RAM_RDY)
+			break;
+
+		msleep(1);
+	}
 
 	if (!(val & ADSP2_RAM_RDY)) {
 		adsp_err(dsp, "Failed to start DSP RAM\n");
@@ -1280,3 +1285,5 @@ int wm_adsp2_init(struct wm_adsp *adsp, bool dvfs)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index f5d81b948759..7a0466eb7ede 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -530,6 +530,7 @@ static int hp_supply_event(struct snd_soc_dapm_widget *w,
 				hubs->hp_startup_mode);
 			break;
 		}
+		break;
 
 	case SND_SOC_DAPM_PRE_PMD:
 		snd_soc_update_bits(codec, WM8993_CHARGE_PUMP_1,
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 81490febac6d..ade9d6379c1b 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -632,8 +632,17 @@ static int davinci_config_channel_size(struct davinci_audio_dev *dev,
 {
 	u32 fmt;
 	u32 tx_rotate = (word_length / 4) & 0x7;
-	u32 rx_rotate = (32 - word_length) / 4;
 	u32 mask = (1ULL << word_length) - 1;
+	/*
+	 * For captured data we should not rotate, inversion and masking is
+	 * enoguh to get the data to the right position:
+	 * Format	  data from bus		after reverse (XRBUF)
+	 * S16_LE:	|LSB|MSB|xxx|xxx|	|xxx|xxx|MSB|LSB|
+	 * S24_3LE:	|LSB|DAT|MSB|xxx|	|xxx|MSB|DAT|LSB|
+	 * S24_LE:	|LSB|DAT|MSB|xxx|	|xxx|MSB|DAT|LSB|
+	 * S32_LE:	|LSB|DAT|DAT|MSB|	|MSB|DAT|DAT|LSB|
+	 */
+	u32 rx_rotate = 0;
 
 	/*
 	 * if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv()
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index 593a3ea12d4c..489a9abf112b 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -263,6 +263,19 @@ static void dw_i2s_shutdown(struct snd_pcm_substream *substream,
 	snd_soc_dai_set_dma_data(dai, substream, NULL);
 }
 
+static int dw_i2s_prepare(struct snd_pcm_substream *substream,
+			  struct snd_soc_dai *dai)
+{
+	struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		i2s_write_reg(dev->i2s_base, TXFFR, 1);
+	else
+		i2s_write_reg(dev->i2s_base, RXFFR, 1);
+
+	return 0;
+}
+
 static int dw_i2s_trigger(struct snd_pcm_substream *substream,
 		int cmd, struct snd_soc_dai *dai)
 {
@@ -294,6 +307,7 @@ static struct snd_soc_dai_ops dw_i2s_dai_ops = {
 	.startup	= dw_i2s_startup,
 	.shutdown	= dw_i2s_shutdown,
 	.hw_params	= dw_i2s_hw_params,
+	.prepare	= dw_i2s_prepare,
 	.trigger	= dw_i2s_trigger,
 };
 
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 670b96b0ce2f..dcfd0fae0b35 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -42,7 +42,8 @@ struct imx_pcm_runtime_data {
 	struct hrtimer hrt;
 	int poll_time_ns;
 	struct snd_pcm_substream *substream;
-	atomic_t running;
+	atomic_t playing;
+	atomic_t capturing;
 };
 
 static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt)
@@ -54,7 +55,7 @@ static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt)
 	struct pt_regs regs;
 	unsigned long delta;
 
-	if (!atomic_read(&iprtd->running))
+	if (!atomic_read(&iprtd->playing) && !atomic_read(&iprtd->capturing))
 		return HRTIMER_NORESTART;
 
 	get_fiq_regs(&regs);
@@ -122,7 +123,6 @@ static int snd_imx_pcm_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int fiq_enable;
 static int imx_pcm_fiq;
 
 static int snd_imx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
@@ -134,23 +134,27 @@ static int snd_imx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		atomic_set(&iprtd->running, 1);
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			atomic_set(&iprtd->playing, 1);
+		else
+			atomic_set(&iprtd->capturing, 1);
 		hrtimer_start(&iprtd->hrt, ns_to_ktime(iprtd->poll_time_ns),
 		      HRTIMER_MODE_REL);
-		if (++fiq_enable == 1)
-			enable_fiq(imx_pcm_fiq);
-
+		enable_fiq(imx_pcm_fiq);
 		break;
 
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		atomic_set(&iprtd->running, 0);
-
-		if (--fiq_enable == 0)
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			atomic_set(&iprtd->playing, 0);
+		else
+			atomic_set(&iprtd->capturing, 0);
+		if (!atomic_read(&iprtd->playing) &&
+				!atomic_read(&iprtd->capturing))
 			disable_fiq(imx_pcm_fiq);
-
 		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -198,7 +202,8 @@ static int snd_imx_open(struct snd_pcm_substream *substream)
 
 	iprtd->substream = substream;
 
-	atomic_set(&iprtd->running, 0);
+	atomic_set(&iprtd->playing, 0);
+	atomic_set(&iprtd->capturing, 0);
 	hrtimer_init(&iprtd->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	iprtd->hrt.function = snd_hrtimer_callback;
 
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 6f4dd7543e82..95a9b07bbe96 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -757,9 +757,7 @@ static int pxa_ssp_remove(struct snd_soc_dai *dai)
 			  SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 |	\
 			  SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
 
-#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
-			    SNDRV_PCM_FMTBIT_S24_LE |	\
-			    SNDRV_PCM_FMTBIT_S32_LE)
+#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE)
 
 static const struct snd_soc_dai_ops pxa_ssp_dai_ops = {
 	.startup	= pxa_ssp_startup,
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 82ebb1a51479..5c9b5e4f94c3 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -853,11 +853,9 @@ static int i2s_suspend(struct snd_soc_dai *dai)
 {
 	struct i2s_dai *i2s = to_info(dai);
 
-	if (dai->active) {
-		i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
-		i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
-		i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
-	}
+	i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
+	i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
+	i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
 
 	return 0;
 }
@@ -866,11 +864,9 @@ static int i2s_resume(struct snd_soc_dai *dai)
 {
 	struct i2s_dai *i2s = to_info(dai);
 
-	if (dai->active) {
-		writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
-		writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
-		writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
-	}
+	writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
+	writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
+	writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
 
 	return 0;
 }
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 06a8000aa07b..5e9690c85d8f 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -24,6 +24,7 @@
 #include <sound/compress_driver.h>
 #include <sound/soc.h>
 #include <sound/initval.h>
+#include <sound/soc-dpcm.h>
 
 static int soc_compr_open(struct snd_compr_stream *cstream)
 {
@@ -75,6 +76,98 @@ out:
 	return ret;
 }
 
+static int soc_compr_open_fe(struct snd_compr_stream *cstream)
+{
+	struct snd_soc_pcm_runtime *fe = cstream->private_data;
+	struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream;
+	struct snd_soc_platform *platform = fe->platform;
+	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
+	struct snd_soc_dai *codec_dai = fe->codec_dai;
+	struct snd_soc_dpcm *dpcm;
+	struct snd_soc_dapm_widget_list *list;
+	int stream;
+	int ret = 0;
+
+	if (cstream->direction == SND_COMPRESS_PLAYBACK)
+		stream = SNDRV_PCM_STREAM_PLAYBACK;
+	else
+		stream = SNDRV_PCM_STREAM_CAPTURE;
+
+	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+	if (platform->driver->compr_ops && platform->driver->compr_ops->open) {
+		ret = platform->driver->compr_ops->open(cstream);
+		if (ret < 0) {
+			pr_err("compress asoc: can't open platform %s\n", platform->name);
+			goto out;
+		}
+	}
+
+	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->startup) {
+		ret = fe->dai_link->compr_ops->startup(cstream);
+		if (ret < 0) {
+			pr_err("compress asoc: %s startup failed\n", fe->dai_link->name);
+			goto machine_err;
+		}
+	}
+
+	fe->dpcm[stream].runtime = fe_substream->runtime;
+
+	if (dpcm_path_get(fe, stream, &list) <= 0) {
+		dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
+			fe->dai_link->name, stream ? "capture" : "playback");
+	}
+
+	/* calculate valid and active FE <-> BE dpcms */
+	dpcm_process_paths(fe, stream, &list, 1);
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_startup(fe, stream);
+	if (ret < 0) {
+		/* clean up all links */
+		list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+			dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+		dpcm_be_disconnect(fe, stream);
+		fe->dpcm[stream].runtime = NULL;
+		goto fe_err;
+	}
+
+	dpcm_clear_pending_state(fe, stream);
+	dpcm_path_put(&list);
+
+	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_OPEN;
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+
+	if (cstream->direction == SND_COMPRESS_PLAYBACK) {
+		cpu_dai->playback_active++;
+		codec_dai->playback_active++;
+	} else {
+		cpu_dai->capture_active++;
+		codec_dai->capture_active++;
+	}
+
+	cpu_dai->active++;
+	codec_dai->active++;
+	fe->codec->active++;
+
+	mutex_unlock(&fe->card->mutex);
+
+	return 0;
+
+fe_err:
+	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
+		fe->dai_link->compr_ops->shutdown(cstream);
+machine_err:
+	if (platform->driver->compr_ops && platform->driver->compr_ops->free)
+		platform->driver->compr_ops->free(cstream);
+out:
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	mutex_unlock(&fe->card->mutex);
+	return ret;
+}
+
 /*
  * Power down the audio subsystem pmdown_time msecs after close is called.
  * This is to ensure there are no pops or clicks in between any music tracks
@@ -149,8 +242,9 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 					SND_SOC_DAPM_STREAM_STOP);
 		} else {
 			rtd->pop_wait = 1;
-			schedule_delayed_work(&rtd->delayed_work,
-				msecs_to_jiffies(rtd->pmdown_time));
+			queue_delayed_work(system_power_efficient_wq,
+					   &rtd->delayed_work,
+					   msecs_to_jiffies(rtd->pmdown_time));
 		}
 	} else {
 		/* capture streams can be powered down now */
@@ -163,6 +257,65 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 	return 0;
 }
 
+static int soc_compr_free_fe(struct snd_compr_stream *cstream)
+{
+	struct snd_soc_pcm_runtime *fe = cstream->private_data;
+	struct snd_soc_platform *platform = fe->platform;
+	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
+	struct snd_soc_dai *codec_dai = fe->codec_dai;
+	struct snd_soc_dpcm *dpcm;
+	int stream, ret;
+
+	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+	if (cstream->direction == SND_COMPRESS_PLAYBACK) {
+		stream = SNDRV_PCM_STREAM_PLAYBACK;
+		cpu_dai->playback_active--;
+		codec_dai->playback_active--;
+	} else {
+		stream = SNDRV_PCM_STREAM_CAPTURE;
+		cpu_dai->capture_active--;
+		codec_dai->capture_active--;
+	}
+
+	cpu_dai->active--;
+	codec_dai->active--;
+	fe->codec->active--;
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_hw_free(fe, stream);
+	if (ret < 0)
+		dev_err(fe->dev, "compressed hw_free failed %d\n", ret);
+
+	ret = dpcm_be_dai_shutdown(fe, stream);
+
+	/* mark FE's links ready to prune */
+	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+		dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+		dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
+	else
+		dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
+
+	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+
+	dpcm_be_disconnect(fe, stream);
+
+	fe->dpcm[stream].runtime = NULL;
+
+	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
+		fe->dai_link->compr_ops->shutdown(cstream);
+
+	if (platform->driver->compr_ops && platform->driver->compr_ops->free)
+		platform->driver->compr_ops->free(cstream);
+
+	mutex_unlock(&fe->card->mutex);
+	return 0;
+}
+
 static int soc_compr_trigger(struct snd_compr_stream *cstream, int cmd)
 {
 
@@ -193,6 +346,59 @@ out:
 	return ret;
 }
 
+static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
+{
+	struct snd_soc_pcm_runtime *fe = cstream->private_data;
+	struct snd_soc_platform *platform = fe->platform;
+	int ret = 0, stream;
+
+	if (cmd == SND_COMPR_TRIGGER_PARTIAL_DRAIN ||
+		cmd == SND_COMPR_TRIGGER_DRAIN) {
+
+		if (platform->driver->compr_ops &&
+			platform->driver->compr_ops->trigger)
+		return platform->driver->compr_ops->trigger(cstream, cmd);
+	}
+
+	if (cstream->direction == SND_COMPRESS_PLAYBACK)
+		stream = SNDRV_PCM_STREAM_PLAYBACK;
+	else
+		stream = SNDRV_PCM_STREAM_CAPTURE;
+
+
+	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+	if (platform->driver->compr_ops && platform->driver->compr_ops->trigger) {
+		ret = platform->driver->compr_ops->trigger(cstream, cmd);
+		if (ret < 0)
+			goto out;
+	}
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_trigger(fe, stream, cmd);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		fe->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		fe->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
+		break;
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED;
+		break;
+	}
+
+out:
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	mutex_unlock(&fe->card->mutex);
+	return ret;
+}
+
 static int soc_compr_set_params(struct snd_compr_stream *cstream,
 					struct snd_compr_params *params)
 {
@@ -240,6 +446,64 @@ err:
 	return ret;
 }
 
+static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
+					struct snd_compr_params *params)
+{
+	struct snd_soc_pcm_runtime *fe = cstream->private_data;
+	struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream;
+	struct snd_soc_platform *platform = fe->platform;
+	int ret = 0, stream;
+
+	if (cstream->direction == SND_COMPRESS_PLAYBACK)
+		stream = SNDRV_PCM_STREAM_PLAYBACK;
+	else
+		stream = SNDRV_PCM_STREAM_CAPTURE;
+
+	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+	if (platform->driver->compr_ops && platform->driver->compr_ops->set_params) {
+		ret = platform->driver->compr_ops->set_params(cstream, params);
+		if (ret < 0)
+			goto out;
+	}
+
+	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->set_params) {
+		ret = fe->dai_link->compr_ops->set_params(cstream);
+		if (ret < 0)
+			goto out;
+	}
+
+	/*
+	 * Create an empty hw_params for the BE as the machine driver must
+	 * fix this up to match DSP decoder and ASRC configuration.
+	 * I.e. machine driver fixup for compressed BE is mandatory.
+	 */
+	memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
+		sizeof(struct snd_pcm_hw_params));
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_hw_params(fe, stream);
+	if (ret < 0)
+		goto out;
+
+	ret = dpcm_be_dai_prepare(fe, stream);
+	if (ret < 0)
+		goto out;
+
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+		dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
+	else
+		dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
+
+	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE;
+
+out:
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	mutex_unlock(&fe->card->mutex);
+	return ret;
+}
+
 static int soc_compr_get_params(struct snd_compr_stream *cstream,
 					struct snd_codec *params)
 {
@@ -334,7 +598,7 @@ static int soc_compr_copy(struct snd_compr_stream *cstream,
 	return ret;
 }
 
-static int sst_compr_set_metadata(struct snd_compr_stream *cstream,
+static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
 				struct snd_compr_metadata *metadata)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
@@ -347,7 +611,7 @@ static int sst_compr_set_metadata(struct snd_compr_stream *cstream,
 	return ret;
 }
 
-static int sst_compr_get_metadata(struct snd_compr_stream *cstream,
+static int soc_compr_get_metadata(struct snd_compr_stream *cstream,
 				struct snd_compr_metadata *metadata)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
@@ -359,13 +623,14 @@ static int sst_compr_get_metadata(struct snd_compr_stream *cstream,
 
 	return ret;
 }
+
 /* ASoC Compress operations */
 static struct snd_compr_ops soc_compr_ops = {
 	.open		= soc_compr_open,
 	.free		= soc_compr_free,
 	.set_params	= soc_compr_set_params,
-	.set_metadata   = sst_compr_set_metadata,
-	.get_metadata	= sst_compr_get_metadata,
+	.set_metadata   = soc_compr_set_metadata,
+	.get_metadata	= soc_compr_get_metadata,
 	.get_params	= soc_compr_get_params,
 	.trigger	= soc_compr_trigger,
 	.pointer	= soc_compr_pointer,
@@ -374,6 +639,21 @@ static struct snd_compr_ops soc_compr_ops = {
 	.get_codec_caps = soc_compr_get_codec_caps
 };
 
+/* ASoC Dynamic Compress operations */
+static struct snd_compr_ops soc_compr_dyn_ops = {
+	.open		= soc_compr_open_fe,
+	.free		= soc_compr_free_fe,
+	.set_params	= soc_compr_set_params_fe,
+	.get_params	= soc_compr_get_params,
+	.set_metadata   = soc_compr_set_metadata,
+	.get_metadata	= soc_compr_get_metadata,
+	.trigger	= soc_compr_trigger_fe,
+	.pointer	= soc_compr_pointer,
+	.ack		= soc_compr_ack,
+	.get_caps	= soc_compr_get_caps,
+	.get_codec_caps = soc_compr_get_codec_caps
+};
+
 /* create a new compress */
 int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 {
@@ -382,6 +662,7 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_compr *compr;
+	struct snd_pcm *be_pcm;
 	char new_name[64];
 	int ret = 0, direction = 0;
 
@@ -409,7 +690,26 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 		ret = -ENOMEM;
 		goto compr_err;
 	}
-	memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
+
+	if (rtd->dai_link->dynamic) {
+		snprintf(new_name, sizeof(new_name), "(%s)",
+			rtd->dai_link->stream_name);
+
+		ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num,
+				1, 0, &be_pcm);
+		if (ret < 0) {
+			dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n",
+				rtd->dai_link->name);
+			goto compr_err;
+		}
+
+		rtd->pcm = be_pcm;
+		rtd->fe_compr = 1;
+		be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
+		be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
+		memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops));
+	} else
+		memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
 
 	/* Add copy callback for not memory mapped DSPs */
 	if (platform->driver->compr_ops && platform->driver->compr_ops->copy)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 360638362e98..c2ecb4e01597 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1797,7 +1797,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file,
 				w->active ? "active" : "inactive");
 
 	list_for_each_entry(p, &w->sources, list_sink) {
-		if (p->connected && !p->connected(w, p->sink))
+		if (p->connected && !p->connected(w, p->source))
 			continue;
 
 		if (p->connect)
diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index 0bb5cccd7766..7aa26b5178aa 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -263,7 +263,7 @@ static irqreturn_t gpio_handler(int irq, void *data)
 	if (device_may_wakeup(dev))
 		pm_wakeup_event(dev, gpio->debounce_time + 50);
 
-	schedule_delayed_work(&gpio->work,
+	queue_delayed_work(system_power_efficient_wq, &gpio->work,
 			      msecs_to_jiffies(gpio->debounce_time));
 
 	return IRQ_HANDLED;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index ccb6be4d658d..7b4bf0cc1f19 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -34,7 +34,7 @@
 #define DPCM_MAX_BE_USERS	8
 
 /* DPCM stream event, send event to FE and all active BEs. */
-static int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
+int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
 	int event)
 {
 	struct snd_soc_dpcm *dpcm;
@@ -408,8 +408,9 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 		} else {
 			/* start delayed pop wq here for playback streams */
 			rtd->pop_wait = 1;
-			schedule_delayed_work(&rtd->delayed_work,
-				msecs_to_jiffies(rtd->pmdown_time));
+			queue_delayed_work(system_power_efficient_wq,
+					   &rtd->delayed_work,
+					   msecs_to_jiffies(rtd->pmdown_time));
 		}
 	} else {
 		/* capture streams can be powered down now */
@@ -757,7 +758,7 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe,
 }
 
 /* disconnect a BE and FE */
-static void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
+void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm, *d;
 
@@ -853,7 +854,7 @@ static int widget_in_list(struct snd_soc_dapm_widget_list *list,
 	return 0;
 }
 
-static int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
+int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
 	int stream, struct snd_soc_dapm_widget_list **list_)
 {
 	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
@@ -875,11 +876,6 @@ static int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
 	return paths;
 }
 
-static inline void dpcm_path_put(struct snd_soc_dapm_widget_list **list)
-{
-	kfree(*list);
-}
-
 static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream,
 	struct snd_soc_dapm_widget_list **list_)
 {
@@ -949,7 +945,7 @@ static int dpcm_add_paths(struct snd_soc_pcm_runtime *fe, int stream,
 			continue;
 
 		/* don't connect if FE is not running */
-		if (!fe->dpcm[stream].runtime)
+		if (!fe->dpcm[stream].runtime && !fe->fe_compr)
 			continue;
 
 		/* newly connected FE and BE */
@@ -974,7 +970,7 @@ static int dpcm_add_paths(struct snd_soc_pcm_runtime *fe, int stream,
  * Find the corresponding BE DAIs that source or sink audio to this
  * FE substream.
  */
-static int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
+int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
 	int stream, struct snd_soc_dapm_widget_list **list, int new)
 {
 	if (new)
@@ -983,7 +979,7 @@ static int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
 		return dpcm_prune_paths(fe, stream, list);
 }
 
-static void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
+void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 
@@ -1021,7 +1017,7 @@ static void dpcm_be_dai_startup_unwind(struct snd_soc_pcm_runtime *fe,
 	}
 }
 
-static int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 	int err, count = 0;
@@ -1163,7 +1159,7 @@ be_err:
 	return ret;
 }
 
-static int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 
@@ -1224,7 +1220,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 
@@ -1289,7 +1285,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 	int ret;
@@ -1419,7 +1415,7 @@ static int dpcm_do_trigger(struct snd_soc_dpcm *dpcm,
 	return ret;
 }
 
-static int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
+int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 			       int cmd)
 {
 	struct snd_soc_dpcm *dpcm;
@@ -1587,7 +1583,7 @@ out:
 	return ret;
 }
 
-static int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
 	int ret = 0;
@@ -1886,6 +1882,7 @@ int soc_dpcm_runtime_update(struct snd_soc_dapm_widget *widget)
 			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
 		}
 
+		dpcm_path_put(&list);
 capture:
 		/* skip if FE doesn't have capture capability */
 		if (!fe->cpu_dai->driver->capture.channels_min)
diff --git a/sound/soc/tegra/tegra20_i2s.c b/sound/soc/tegra/tegra20_i2s.c
index 52af7f6fb37f..540832e9e684 100644
--- a/sound/soc/tegra/tegra20_i2s.c
+++ b/sound/soc/tegra/tegra20_i2s.c
@@ -74,7 +74,7 @@ static int tegra20_i2s_set_fmt(struct snd_soc_dai *dai,
 				unsigned int fmt)
 {
 	struct tegra20_i2s *i2s = snd_soc_dai_get_drvdata(dai);
-	unsigned int mask, val;
+	unsigned int mask = 0, val = 0;
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
 	case SND_SOC_DAIFMT_NB_NF:
@@ -83,10 +83,10 @@ static int tegra20_i2s_set_fmt(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	mask = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+	mask |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBS_CFS:
-		val = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+		val |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
 		break;
 	case SND_SOC_DAIFMT_CBM_CFM:
 		break;
diff --git a/sound/soc/tegra/tegra20_spdif.c b/sound/soc/tegra/tegra20_spdif.c
index 551b3c93ce93..2e7d4aca3d7d 100644
--- a/sound/soc/tegra/tegra20_spdif.c
+++ b/sound/soc/tegra/tegra20_spdif.c
@@ -67,15 +67,15 @@ static int tegra20_spdif_hw_params(struct snd_pcm_substream *substream,
 {
 	struct device *dev = dai->dev;
 	struct tegra20_spdif *spdif = snd_soc_dai_get_drvdata(dai);
-	unsigned int mask, val;
+	unsigned int mask = 0, val = 0;
 	int ret, spdifclock;
 
-	mask = TEGRA20_SPDIF_CTRL_PACK |
-	       TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
+	mask |= TEGRA20_SPDIF_CTRL_PACK |
+		TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_S16_LE:
-		val = TEGRA20_SPDIF_CTRL_PACK |
-		      TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
+		val |= TEGRA20_SPDIF_CTRL_PACK |
+		       TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
 		break;
 	default:
 		return -EINVAL;
diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c
index a5432b10eaca..5c6520b8ec0e 100644
--- a/sound/soc/tegra/tegra30_i2s.c
+++ b/sound/soc/tegra/tegra30_i2s.c
@@ -117,7 +117,7 @@ static int tegra30_i2s_set_fmt(struct snd_soc_dai *dai,
 				unsigned int fmt)
 {
 	struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
-	unsigned int mask, val;
+	unsigned int mask = 0, val = 0;
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
 	case SND_SOC_DAIFMT_NB_NF:
@@ -126,10 +126,10 @@ static int tegra30_i2s_set_fmt(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	mask = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+	mask |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBS_CFS:
-		val = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+		val |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
 		break;
 	case SND_SOC_DAIFMT_CBM_CFM:
 		break;
diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c
index 4394ae796356..0716ba691398 100644
--- a/sound/usb/6fire/chip.c
+++ b/sound/usb/6fire/chip.c
@@ -101,7 +101,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf,
 			usb_set_intfdata(intf, chips[i]);
 			mutex_unlock(&register_mutex);
 			return 0;
-		} else if (regidx < 0)
+		} else if (!devices[i] && regidx < 0)
 			regidx = i;
 	}
 	if (regidx < 0) {
diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index 225dfd737265..ba2664200d14 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -14,6 +14,7 @@ config SND_USB_AUDIO
 	select SND_HWDEP
 	select SND_RAWMIDI
 	select SND_PCM
+	select BITREVERSE
 	help
 	  Say Y here to include support for USB audio and USB MIDI
 	  devices.
diff --git a/sound/usb/card.h b/sound/usb/card.h
index bf2889a2cae5..82c2d80c8228 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -90,6 +90,7 @@ struct snd_usb_endpoint {
 	unsigned int curframesize;      /* current packet size in frames (for capture) */
 	unsigned int syncmaxsize;	/* sync endpoint packet size */
 	unsigned int fill_max:1;	/* fill max packet size always */
+	unsigned int udh01_fb_quirk:1;	/* corrupted feedback data */
 	unsigned int datainterval;      /* log_2 of data packet interval */
 	unsigned int syncinterval;	/* P for adaptive mode, 0 otherwise */
 	unsigned char silence_value;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 659950e5b94f..308c02b2a597 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -467,6 +467,10 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip,
 			ep->syncinterval = 3;
 
 		ep->syncmaxsize = le16_to_cpu(get_endpoint(alts, 1)->wMaxPacketSize);
+
+		if (chip->usb_id == USB_ID(0x0644, 0x8038) /* TEAC UD-H01 */ &&
+		    ep->syncmaxsize == 4)
+			ep->udh01_fb_quirk = 1;
 	}
 
 	list_add_tail(&ep->list, &chip->ep_list);
@@ -1075,7 +1079,16 @@ void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep,
 	if (f == 0)
 		return;
 
-	if (unlikely(ep->freqshift == INT_MIN)) {
+	if (unlikely(sender->udh01_fb_quirk)) {
+		/*
+		 * The TEAC UD-H01 firmware sometimes changes the feedback value
+		 * by +/- 0x1.0000.
+		 */
+		if (f < ep->freqn - 0x8000)
+			f += 0x10000;
+		else if (f > ep->freqn + 0x8000)
+			f -= 0x10000;
+	} else if (unlikely(ep->freqshift == INT_MIN)) {
 		/*
 		 * The first time we see a feedback value, determine its format
 		 * by shifting it left or right until it matches the nominal
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 8e01fa4991c5..93249133aeec 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -364,6 +364,8 @@ static void snd_usbmidi_error_timer(unsigned long data)
 		if (in && in->error_resubmit) {
 			in->error_resubmit = 0;
 			for (j = 0; j < INPUT_URBS; ++j) {
+				if (atomic_read(&in->urbs[j]->use_count))
+					continue;
 				in->urbs[j]->dev = umidi->dev;
 				snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC);
 			}
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 95558ef4a7a0..be4db47cb2d9 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -883,6 +883,7 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 		}
 		break;
 
+	case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
 	case USB_ID(0x046d, 0x0808):
 	case USB_ID(0x046d, 0x0809):
 	case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index cc2dd1f0decb..4df31b0f94a3 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -322,6 +322,14 @@ static struct usbmix_name_map hercules_usb51_map[] = {
 	{ 0 }				/* terminator */
 };
 
+/* some (all?) SCMS USB3318 devices are affected by a firmware lock up
+ * when anything attempts to access FU 10 (control)
+ */
+static const struct usbmix_name_map scms_usb3318_map[] = {
+	{ 10, NULL },
+	{ 0 }
+};
+
 /*
  * Control map entries
  */
@@ -409,6 +417,16 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.id = USB_ID(0x200c, 0x1018),
 		.map = ebox44_map,
 	},
+	{
+		/* KEF X300A */
+		.id = USB_ID(0x27ac, 0x1000),
+		.map = scms_usb3318_map,
+	},
+	{
+		/* Arcam rPAC */
+		.id = USB_ID(0x25c4, 0x0003),
+		.map = scms_usb3318_map,
+	},
 	{ 0 } /* terminator */
 };
 
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index ebe91440a068..c89a5bf5c00e 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -799,6 +799,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl,
 	return changed;
 }
 
+static void kctl_private_value_free(struct snd_kcontrol *kctl)
+{
+	kfree((void *)kctl->private_value);
+}
+
 static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
 	int validx, int bUnitID)
 {
@@ -833,6 +838,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
 		return -ENOMEM;
 	}
 
+	kctl->private_free = kctl_private_value_free;
 	err = snd_ctl_add(mixer->chip->card, kctl);
 	if (err < 0)
 		return err;
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 93b6e32cfead..0d7a872dab36 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1420,7 +1420,8 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 	 * on two reads of a counter updated every ms.
 	 */
 	if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
-		snd_printk(KERN_DEBUG "delay: estimated %d, actual %d\n",
+		dev_dbg_ratelimited(&subs->dev->dev,
+			"delay: estimated %d, actual %d\n",
 			est_delay, subs->last_delay);
 
 	if (!subs->running) {
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 8b75bcf136f6..d5bed1d25713 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -386,6 +386,36 @@ YAMAHA_DEVICE(0x105d, NULL),
 	}
 },
 {
+	USB_DEVICE(0x0499, 0x1509),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		/* .vendor_name = "Yamaha", */
+		/* .product_name = "Steinberg UR22", */
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_YAMAHA
+			},
+			{
+				.ifnum = 4,
+				.type = QUIRK_IGNORE_INTERFACE
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	USB_DEVICE(0x0499, 0x150a),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
 		/* .vendor_name = "Yamaha", */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3879eae7e874..734c6579b194 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -914,6 +914,20 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		mdelay(20);
+
+	/* Marantz/Denon devices with USB DAC functionality need a delay
+	 * after each class compliant request
+	 */
+	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) &&
+	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+
+		switch (le16_to_cpu(dev->descriptor.idProduct)) {
+		case 0x3005: /* Marantz HD-DAC1 */
+		case 0x3006: /* Marantz SA-14S1 */
+			mdelay(20);
+			break;
+		}
+	}
 }
 
 /*
diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index d0323a693ba2..999550bbad40 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -262,7 +262,9 @@ static int usb_stream_hwdep_mmap(struct snd_hwdep *hw,
 	}
 
 	area->vm_ops = &usb_stream_hwdep_vm_ops;
-	area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	area->vm_flags |= VM_DONTDUMP;
+	if (!read)
+		area->vm_flags |= VM_DONTEXPAND;
 	area->vm_private_data = us122l;
 	atomic_inc(&us122l->mmap_count);
 out:
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index 0ce903375eaf..cd69a80b5ca9 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -299,19 +299,6 @@ static void usX2Y_error_urb_status(struct usX2Ydev *usX2Y,
 	usX2Y_clients_stop(usX2Y);
 }
 
-static void usX2Y_error_sequence(struct usX2Ydev *usX2Y,
-				 struct snd_usX2Y_substream *subs, struct urb *urb)
-{
-	snd_printk(KERN_ERR
-"Sequence Error!(hcd_frame=%i ep=%i%s;wait=%i,frame=%i).\n"
-"Most probably some urb of usb-frame %i is still missing.\n"
-"Cause could be too long delays in usb-hcd interrupt handling.\n",
-		   usb_get_current_frame_number(usX2Y->dev),
-		   subs->endpoint, usb_pipein(urb->pipe) ? "in" : "out",
-		   usX2Y->wait_iso_frame, urb->start_frame, usX2Y->wait_iso_frame);
-	usX2Y_clients_stop(usX2Y);
-}
-
 static void i_usX2Y_urb_complete(struct urb *urb)
 {
 	struct snd_usX2Y_substream *subs = urb->context;
@@ -328,12 +315,9 @@ static void i_usX2Y_urb_complete(struct urb *urb)
 		usX2Y_error_urb_status(usX2Y, subs, urb);
 		return;
 	}
-	if (likely((urb->start_frame & 0xFFFF) == (usX2Y->wait_iso_frame & 0xFFFF)))
-		subs->completed_urb = urb;
-	else {
-		usX2Y_error_sequence(usX2Y, subs, urb);
-		return;
-	}
+
+	subs->completed_urb = urb;
+
 	{
 		struct snd_usX2Y_substream *capsubs = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE],
 			*playbacksubs = usX2Y->subs[SNDRV_PCM_STREAM_PLAYBACK];
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index f2a1acdc4d83..814d0e887c62 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -244,13 +244,8 @@ static void i_usX2Y_usbpcm_urb_complete(struct urb *urb)
 		usX2Y_error_urb_status(usX2Y, subs, urb);
 		return;
 	}
-	if (likely((urb->start_frame & 0xFFFF) == (usX2Y->wait_iso_frame & 0xFFFF)))
-		subs->completed_urb = urb;
-	else {
-		usX2Y_error_sequence(usX2Y, subs, urb);
-		return;
-	}
 
+	subs->completed_urb = urb;
 	capsubs = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE];
 	capsubs2 = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE + 2];
 	playbacksubs = usX2Y->subs[SNDRV_PCM_STREAM_PLAYBACK];
diff --git a/tools/gator/daemon/Android.mk b/tools/gator/daemon/Android.mk
new file mode 100644
index 000000000000..970ac6946150
--- /dev/null
+++ b/tools/gator/daemon/Android.mk
@@ -0,0 +1,76 @@
+LOCAL_PATH := $(call my-dir)
+include $(CLEAR_VARS)
+
+XML_H := $(shell cd $(LOCAL_PATH) && make events_xml.h defaults_xml.h)
+
+LOCAL_SRC_FILES := \
+	AnnotateListener.cpp \
+	Buffer.cpp \
+	CCNDriver.cpp \
+	CPUFreqDriver.cpp \
+	CapturedXML.cpp \
+	Child.cpp \
+	Command.cpp \
+	ConfigurationXML.cpp \
+	DiskIODriver.cpp \
+	Driver.cpp \
+	DriverSource.cpp \
+	DynBuf.cpp \
+	EventsXML.cpp \
+	ExternalSource.cpp \
+	FSDriver.cpp \
+	Fifo.cpp \
+	FtraceDriver.cpp \
+	FtraceSource.cpp \
+	HwmonDriver.cpp \
+	KMod.cpp \
+	LocalCapture.cpp \
+	Logging.cpp \
+	main.cpp \
+	MaliVideoDriver.cpp \
+	MemInfoDriver.cpp\
+	Monitor.cpp \
+	NetDriver.cpp \
+	OlySocket.cpp \
+	OlyUtility.cpp \
+	PerfBuffer.cpp \
+	PerfDriver.cpp \
+	PerfGroup.cpp \
+	PerfSource.cpp \
+	Proc.cpp \
+	Sender.cpp \
+	SessionData.cpp \
+	SessionXML.cpp \
+	Setup.cpp \
+	Source.cpp \
+	StreamlineSetup.cpp \
+	UEvent.cpp \
+	UserSpaceSource.cpp \
+	libsensors/access.c \
+	libsensors/conf-lex.c \
+	libsensors/conf-parse.c \
+	libsensors/data.c \
+	libsensors/error.c \
+	libsensors/general.c \
+	libsensors/init.c \
+	libsensors/sysfs.c \
+	mxml/mxml-attr.c \
+	mxml/mxml-entity.c \
+	mxml/mxml-file.c \
+	mxml/mxml-get.c \
+	mxml/mxml-index.c \
+	mxml/mxml-node.c \
+	mxml/mxml-private.c \
+	mxml/mxml-search.c \
+	mxml/mxml-set.c \
+	mxml/mxml-string.c
+
+LOCAL_CFLAGS += -Wall -O3 -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors -fPIE
+LOCAL_LDFLAGS += -fPIE -pie
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)
+
+LOCAL_MODULE := gatord
+LOCAL_MODULE_TAGS := optional
+
+include $(BUILD_EXECUTABLE)
diff --git a/tools/gator/daemon/AnnotateListener.cpp b/tools/gator/daemon/AnnotateListener.cpp
new file mode 100644
index 000000000000..50110b4dc84c
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.cpp
@@ -0,0 +1,69 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "AnnotateListener.h"
+
+#include <unistd.h>
+
+#include "OlySocket.h"
+
+struct AnnotateClient {
+	AnnotateClient *next;
+	int fd;
+};
+
+AnnotateListener::AnnotateListener() : mClients(NULL), mSock(NULL) {
+}
+
+AnnotateListener::~AnnotateListener() {
+	close();
+	delete mSock;
+}
+
+void AnnotateListener::setup() {
+	mSock = new OlyServerSocket(8082);
+}
+
+int AnnotateListener::getFd() {
+	return mSock->getFd();
+}
+
+void AnnotateListener::handle() {
+	AnnotateClient *const client = new AnnotateClient();
+	client->fd = mSock->acceptConnection();
+	client->next = mClients;
+	mClients = client;
+}
+
+void AnnotateListener::close() {
+	mSock->closeServerSocket();
+	while (mClients != NULL) {
+		::close(mClients->fd);
+		AnnotateClient *next = mClients->next;
+		delete mClients;
+		mClients = next;
+	}
+}
+
+void AnnotateListener::signal() {
+	const char ch = 0;
+	AnnotateClient **ptr = &mClients;
+	AnnotateClient *client = mClients;
+	while (client != NULL) {
+		if (write(client->fd, &ch, sizeof(ch)) != 1) {
+			::close(client->fd);
+			AnnotateClient *next = client->next;
+			delete client;
+			*ptr = next;
+			client = next;
+			continue;
+		}
+		ptr = &client->next;
+		client = client->next;
+	}
+}
diff --git a/tools/gator/daemon/AnnotateListener.h b/tools/gator/daemon/AnnotateListener.h
new file mode 100644
index 000000000000..cdefef12db22
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+class AnnotateClient;
+class OlyServerSocket;
+
+class AnnotateListener {
+public:
+	AnnotateListener();
+	~AnnotateListener();
+
+	void setup();
+	int getFd();
+
+	void handle();
+	void close();
+	void signal();
+
+private:
+	AnnotateClient *mClients;
+	OlyServerSocket *mSock;
+
+	// Intentionally unimplemented
+	AnnotateListener(const AnnotateListener &);
+	AnnotateListener &operator=(const AnnotateListener &);
+};
diff --git a/tools/gator/daemon/Application.mk b/tools/gator/daemon/Application.mk
new file mode 100644
index 000000000000..3ada471cac19
--- /dev/null
+++ b/tools/gator/daemon/Application.mk
@@ -0,0 +1,3 @@
+APP_PLATFORM := android-8
+# Replace armeabi-v7a with arm64-v8a to build an arm64 gatord or with armeabi to build an ARM11 gatord
+APP_ABI := armeabi-v7a
diff --git a/tools/gator/daemon/Buffer.cpp b/tools/gator/daemon/Buffer.cpp
new file mode 100644
index 000000000000..8fa628015069
--- /dev/null
+++ b/tools/gator/daemon/Buffer.cpp
@@ -0,0 +1,428 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Buffer.h"
+
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+#define mask (mSize - 1)
+
+enum {
+	CODE_PEA         = 1,
+	CODE_KEYS        = 2,
+	CODE_FORMAT      = 3,
+	CODE_MAPS        = 4,
+	CODE_COMM        = 5,
+	CODE_KEYS_OLD    = 6,
+	CODE_ONLINE_CPU  = 7,
+	CODE_OFFLINE_CPU = 8,
+	CODE_KALLSYMS    = 9,
+};
+
+// Summary Frame Messages
+enum {
+	MESSAGE_SUMMARY = 1,
+	MESSAGE_CORE_NAME = 3,
+};
+
+// From gator_marshaling.c
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mBuf(new char[size]), mReaderSem(readerSem), mCommitTime(gSessionData->mLiveRate), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mCore(core), mBufType(buftype) {
+	if ((mSize & mask) != 0) {
+		logg->logError(__FILE__, __LINE__, "Buffer size is not a power of 2");
+		handleException();
+	}
+	sem_init(&mWriterSem, 0, 0);
+	frame();
+}
+
+Buffer::~Buffer() {
+	delete [] mBuf;
+	sem_destroy(&mWriterSem);
+}
+
+void Buffer::write(Sender *const sender) {
+	if (!commitReady()) {
+		return;
+	}
+
+	// commit and read are updated by the writer, only read them once
+	int commitPos = mCommitPos;
+	int readPos = mReadPos;
+
+	// determine the size of two halves
+	int length1 = commitPos - readPos;
+	char *buffer1 = mBuf + readPos;
+	int length2 = 0;
+	char *buffer2 = mBuf;
+	if (length1 < 0) {
+		length1 = mSize - readPos;
+		length2 = commitPos;
+	}
+
+	logg->logMessage("Sending data length1: %i length2: %i", length1, length2);
+
+	// start, middle or end
+	if (length1 > 0) {
+		sender->writeData(buffer1, length1, RESPONSE_APC_DATA);
+	}
+
+	// possible wrap around
+	if (length2 > 0) {
+		sender->writeData(buffer2, length2, RESPONSE_APC_DATA);
+	}
+
+	mReadPos = commitPos;
+
+	// send a notification that space is available
+	sem_post(&mWriterSem);
+}
+
+bool Buffer::commitReady() const {
+	return mCommitPos != mReadPos;
+}
+
+int Buffer::bytesAvailable() const {
+	int filled = mWritePos - mReadPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+
+	int remaining = mSize - filled;
+
+	if (mAvailable) {
+		// Give some extra room; also allows space to insert the overflow error packet
+		remaining -= 200;
+	} else {
+		// Hysteresis, prevents multiple overflow messages
+		remaining -= 2000;
+	}
+
+	return remaining;
+}
+
+bool Buffer::checkSpace(const int bytes) {
+	const int remaining = bytesAvailable();
+
+	if (remaining < bytes) {
+		mAvailable = false;
+	} else {
+		mAvailable = true;
+	}
+
+	return mAvailable;
+}
+
+int Buffer::contiguousSpaceAvailable() const {
+	int remaining = bytesAvailable();
+	int contiguous = mSize - mWritePos;
+	if (remaining < contiguous) {
+		return remaining;
+	} else {
+		return contiguous;
+	}
+}
+
+void Buffer::commit(const uint64_t time) {
+	// post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+	int length = mWritePos - mCommitPos;
+	if (length < 0) {
+		length += mSize;
+	}
+	length = length - typeLength - sizeof(int32_t);
+	for (size_t byte = 0; byte < sizeof(int32_t); byte++) {
+		mBuf[(mCommitPos + typeLength + byte) & mask] = (length >> byte * 8) & 0xFF;
+	}
+
+	logg->logMessage("Committing data mReadPos: %i mWritePos: %i mCommitPos: %i", mReadPos, mWritePos, mCommitPos);
+	mCommitPos = mWritePos;
+
+	if (gSessionData->mLiveRate > 0) {
+		while (time > mCommitTime) {
+			mCommitTime += gSessionData->mLiveRate;
+		}
+	}
+
+	if (!mIsDone) {
+		frame();
+	}
+
+	// send a notification that data is ready
+	sem_post(mReaderSem);
+}
+
+void Buffer::check(const uint64_t time) {
+	int filled = mWritePos - mCommitPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+	if (filled >= ((mSize * 3) / 4) || (gSessionData->mLiveRate > 0 && time >= mCommitTime)) {
+		commit(time);
+	}
+}
+
+void Buffer::packInt(char *const buf, const int size, int &writePos, int32_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt(int32_t x) {
+	packInt(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::packInt64(char *const buf, const int size, int &writePos, int64_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt64(int64_t x) {
+	packInt64(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::writeBytes(const void *const data, size_t count) {
+	size_t i;
+	for (i = 0; i < count; ++i) {
+		mBuf[(mWritePos + i) & mask] = static_cast<const char *>(data)[i];
+	}
+
+	mWritePos = (mWritePos + i) & mask;
+}
+
+void Buffer::writeString(const char *const str) {
+	const int len = strlen(str);
+	packInt(len);
+	writeBytes(str, len);
+}
+
+void Buffer::frame() {
+	if (!gSessionData->mLocalCapture) {
+		packInt(RESPONSE_APC_DATA);
+	}
+	// Reserve space for the length
+	mWritePos += sizeof(int32_t);
+	packInt(mBufType);
+	if ((mBufType == FRAME_BLOCK_COUNTER) || (mBufType == FRAME_PERF_ATTRS) || (mBufType == FRAME_PERF)) {
+		packInt(mCore);
+	}
+}
+
+void Buffer::summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname) {
+	packInt(MESSAGE_SUMMARY);
+	writeString(NEWLINE_CANARY);
+	packInt64(timestamp);
+	packInt64(uptime);
+	packInt64(monotonicDelta);
+	writeString("uname");
+	writeString(uname);
+	writeString("");
+	check(currTime);
+}
+
+void Buffer::coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name) {
+	if (checkSpace(3 * MAXSIZE_PACK32 + 0x100)) {
+		packInt(MESSAGE_CORE_NAME);
+		packInt(core);
+		packInt(cpuid);
+		writeString(name);
+	}
+	check(currTime);
+}
+
+bool Buffer::eventHeader(const uint64_t curr_time) {
+	bool retval = false;
+	if (checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		// key of zero indicates a timestamp
+		packInt(0);
+		packInt64(curr_time);
+		retval = true;
+	}
+
+	return retval;
+}
+
+bool Buffer::eventTid(const int tid) {
+	bool retval = false;
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		// key of 1 indicates a tid
+		packInt(1);
+		packInt(tid);
+		retval = true;
+	}
+
+	return retval;
+}
+
+void Buffer::event(const int key, const int32_t value) {
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt(value);
+	}
+}
+
+void Buffer::event64(const int key, const int64_t value) {
+	if (checkSpace(MAXSIZE_PACK64 + MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt64(value);
+	}
+}
+
+void Buffer::pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + pea->size)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_PEA);
+	writeBytes(pea, pea->size);
+	packInt(key);
+	check(currTime);
+}
+
+void Buffer::keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS);
+	packInt(count);
+	for (int i = 0; i < count; ++i) {
+		packInt64(ids[i]);
+		packInt(keys[i]);
+	}
+	check(currTime);
+}
+
+void Buffer::keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf) {
+	while (!checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS_OLD);
+	packInt(keyCount);
+	for (int i = 0; i < keyCount; ++i) {
+		packInt(keys[i]);
+	}
+	writeBytes(buf, bytes);
+	check(currTime);
+}
+
+void Buffer::format(const uint64_t currTime, const int length, const char *const format) {
+	while (!checkSpace(MAXSIZE_PACK32 + length + 1)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_FORMAT);
+	writeBytes(format, length + 1);
+	check(currTime);
+}
+
+void Buffer::maps(const uint64_t currTime, const int pid, const int tid, const char *const maps) {
+	const int mapsLen = strlen(maps) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_MAPS);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(maps, mapsLen);
+	check(currTime);
+}
+
+void Buffer::comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm) {
+	const int imageLen = strlen(image) + 1;
+	const int commLen = strlen(comm) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_COMM);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(image, imageLen);
+	writeBytes(comm, commLen);
+	check(currTime);
+}
+
+void Buffer::onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_ONLINE_CPU);
+	packInt64(time);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_OFFLINE_CPU);
+	packInt64(time);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::kallsyms(const uint64_t currTime, const char *const kallsyms) {
+	const int kallsymsLen = strlen(kallsyms) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + kallsymsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KALLSYMS);
+	writeBytes(kallsyms, kallsymsLen);
+	check(currTime);
+}
+
+void Buffer::setDone() {
+	mIsDone = true;
+	commit(0);
+}
+
+bool Buffer::isDone() const {
+	return mIsDone && mReadPos == mCommitPos && mCommitPos == mWritePos;
+}
diff --git a/tools/gator/daemon/Buffer.h b/tools/gator/daemon/Buffer.h
new file mode 100644
index 000000000000..6cffd8e39a36
--- /dev/null
+++ b/tools/gator/daemon/Buffer.h
@@ -0,0 +1,106 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef BUFFER_H
+#define BUFFER_H
+
+#include <stdint.h>
+#include <semaphore.h>
+
+#include "k/perf_event.h"
+
+class Sender;
+
+enum {
+	FRAME_SUMMARY       =  1,
+	FRAME_BLOCK_COUNTER =  5,
+	FRAME_EXTERNAL      = 10,
+	FRAME_PERF_ATTRS    = 11,
+	FRAME_PERF          = 12,
+};
+
+class Buffer {
+public:
+	static const size_t MAXSIZE_PACK32 = 5;
+	static const size_t MAXSIZE_PACK64 = 10;
+
+	Buffer(int32_t core, int32_t buftype, const int size, sem_t *const readerSem);
+	~Buffer();
+
+	void write(Sender *sender);
+
+	int bytesAvailable() const;
+	int contiguousSpaceAvailable() const;
+	void commit(const uint64_t time);
+	void check(const uint64_t time);
+
+	// Summary messages
+	void summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname);
+	void coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name);
+
+	// Block Counter messages
+	bool eventHeader(uint64_t curr_time);
+	bool eventTid(int tid);
+	void event(int key, int32_t value);
+	void event64(int key, int64_t value);
+
+	// Perf Attrs messages
+	void pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key);
+	void keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys);
+	void keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf);
+	void format(const uint64_t currTime, const int length, const char *const format);
+	void maps(const uint64_t currTime, const int pid, const int tid, const char *const maps);
+	void comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm);
+	void onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu);
+	void offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu);
+	void kallsyms(const uint64_t currTime, const char *const kallsyms);
+
+	void setDone();
+	bool isDone() const;
+
+	// Prefer a new member to using these functions if possible
+	char *getWritePos() { return mBuf + mWritePos; }
+	void advanceWrite(int bytes) { mWritePos = (mWritePos + bytes) & /*mask*/(mSize - 1); }
+	static void packInt(char *const buf, const int size, int &writePos, int32_t x);
+	void packInt(int32_t x);
+	static void packInt64(char *const buf, const int size, int &writePos, int64_t x);
+	void packInt64(int64_t x);
+	void writeBytes(const void *const data, size_t count);
+	void writeString(const char *const str);
+
+	static void writeLEInt(unsigned char *buf, int v) {
+		buf[0] = (v >> 0) & 0xFF;
+		buf[1] = (v >> 8) & 0xFF;
+		buf[2] = (v >> 16) & 0xFF;
+		buf[3] = (v >> 24) & 0xFF;
+	}
+
+private:
+	void frame();
+	bool commitReady() const;
+	bool checkSpace(int bytes);
+
+	char *const mBuf;
+	sem_t *const mReaderSem;
+	uint64_t mCommitTime;
+	sem_t mWriterSem;
+	const int mSize;
+	int mReadPos;
+	int mWritePos;
+	int mCommitPos;
+	bool mAvailable;
+	bool mIsDone;
+	const int32_t mCore;
+	const int32_t mBufType;
+
+	// Intentionally unimplemented
+	Buffer(const Buffer &);
+	Buffer &operator=(const Buffer &);
+};
+
+#endif // BUFFER_H
diff --git a/tools/gator/daemon/CCNDriver.cpp b/tools/gator/daemon/CCNDriver.cpp
new file mode 100644
index 000000000000..dd1a2b133842
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.cpp
@@ -0,0 +1,295 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CCNDriver.h"
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "k/perf_event.h"
+
+#include "Config.h"
+#include "DriverSource.h"
+#include "Logging.h"
+
+static const char TAG_CATEGORY[] = "category";
+static const char TAG_COUNTER_SET[] = "counter_set";
+static const char TAG_EVENT[] = "event";
+static const char TAG_OPTION[] = "option";
+static const char TAG_OPTION_SET[] = "option_set";
+
+static const char ATTR_AVERAGE_SELECTION[] = "average_selection";
+static const char ATTR_COUNTER[] = "counter";
+static const char ATTR_COUNTER_SET[] = "counter_set";
+static const char ATTR_COUNT[] = "count";
+static const char ATTR_DESCRIPTION[] = "description";
+static const char ATTR_DISPLAY[] = "display";
+static const char ATTR_EVENT[] = "event";
+static const char ATTR_EVENT_DELTA[] = "event_delta";
+static const char ATTR_NAME[] = "name";
+static const char ATTR_OPTION_SET[] = "option_set";
+static const char ATTR_TITLE[] = "title";
+static const char ATTR_UNITS[] = "units";
+
+static const char XP_REGION[] = "XP_Region";
+static const char HNF_REGION[] = "HN-F_Region";
+static const char RNI_REGION[] = "RN-I_Region";
+static const char SBAS_REGION[] = "SBAS_Region";
+static const char CCN_5XX[] = "CCN-5xx";
+#define ARM_CCN_5XX "ARM_CCN_5XX_"
+
+static const char *const VC_TYPES[] = { "REQ", "RSP", "SNP", "DAT" };
+static const char *const XP_EVENT_NAMES[] = { NULL, "H-bit", "S-bit", "P-Cnt", "TknV" };
+static const char *const XP_EVENT_DESCRIPTIONS[] = { NULL, "Set H-bit, signaled when this XP sets the H-bit.", "Set S-bit, signaled when this XP sets the S-bit.", "Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC.", "No TknV, signaled when this XP transmits a valid packet." };
+static const char *const HNF_EVENT_NAMES[] = { NULL, "Cache Miss", "L3 SF Cache Access", "Cache Fill", "POCQ Retry", "POCQ Reqs Recvd", "SF Hit", "SF Evictions", "Snoops Sent", "Snoops Broadcast", "L3 Eviction", "L3 Fill Invalid Way", "MC Retries", "MC Reqs", "QOS HH Retry" };
+static const char *const HNF_EVENT_DESCRIPTIONS[] = { NULL, "Counts the total cache misses. This is the first time lookup result, and is high priority.", "Counts the number of cache accesses. This is the first time access, and is high priority.", "Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache.", "Counts the number of requests that have been retried.", "Counts the number of requests received by HN.", "Counts the number of snoop filter hits.", "Counts the number of snoop filter evictions. Cache invalidations are initiated.", "Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops.", "Counts the number of snoop broadcasts sent.", "Counts the number of L3 evictions.", "Counts the number of L3 fills to an invalid way.", "Counts the number of transactions retried by the memory controller.", "Counts the number of requests to the memory controller.", "Counts the number of times a highest-priority QoS class was retried at the HN-F." };
+static const char *const RNI_EVENT_NAMES[] = { NULL, "S0 RDataBeats", "S1 RDataBeats", "S2 RDataBeats", "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const RNI_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", "S1 RDataBeats.", "S2 RDataBeats.", "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+static const char *const SBAS_EVENT_NAMES[] = { NULL, "S0 RDataBeats", NULL, NULL, "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const SBAS_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", NULL, NULL, "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+
+// This class is used only to poll for CCN-5xx configuration and emit events XML for it. All other operations are handled by PerfDriver
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static unsigned int getConfig(unsigned int node, unsigned int type, unsigned int event, unsigned int port, unsigned int vc) {
+  return
+    ((node  & 0xff) <<  0) |
+    ((type  & 0xff) <<  8) |
+    ((event & 0xff) << 16) |
+    ((port  & 0x03) << 24) |
+    ((vc    & 0x07) << 26) |
+    0;
+}
+
+static bool perfPoll(struct perf_event_attr *const pea) {
+	int fd = sys_perf_event_open(pea, -1, 0, -1, 0);
+	if (fd < 0) {
+		return false;
+	}
+	close(fd);
+	return true;
+}
+
+CCNDriver::CCNDriver() : mNodeTypes(NULL), mXpCount(0) {
+}
+
+CCNDriver::~CCNDriver() {
+	delete mNodeTypes;
+}
+
+bool CCNDriver::claimCounter(const Counter &) const {
+	// Handled by PerfDriver
+	return false;
+}
+
+void CCNDriver::resetCounters() {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::setupCounter(Counter &) {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::readEvents(mxml_node_t *const) {
+	struct stat st;
+	if (stat("/sys/bus/event_source/devices/ccn", &st) != 0) {
+		// Not found
+		return;
+	}
+
+	int type;
+	if (DriverSource::readIntDriver("/sys/bus/event_source/devices/ccn/type", &type) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to read CCN-5xx type");
+		handleException();
+	}
+
+	// Detect number of xps
+	struct perf_event_attr pea;
+	memset(&pea, 0, sizeof(pea));
+	pea.type = type;
+	pea.size = sizeof(pea);
+
+	mXpCount = 1;
+	while (true) {
+		pea.config = getConfig(0, 0x08, 1, 0, 1) | mXpCount;
+		if (!perfPoll(&pea)) {
+			break;
+		}
+		mXpCount *= 2;
+	};
+	{
+		int lower = mXpCount/2 + 1;
+		while (lower < mXpCount) {
+			int mid = (lower + mXpCount)/2;
+			pea.config = getConfig(0, 0x08, 1, 0, 1) | mid;
+			if (perfPoll(&pea)) {
+				lower = mid + 1;
+			} else {
+				mXpCount = mid;
+			}
+		}
+	}
+
+	mNodeTypes = new NodeType[2*mXpCount];
+
+	// Detect node types
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		pea.config = getConfig(0, 0x04, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_HNF;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x16, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_RNI;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x10, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_SBAS;
+			continue;
+		}
+
+		mNodeTypes[i] = NT_UNKNOWN;
+	}
+}
+
+int CCNDriver::writeCounters(mxml_node_t *const) const {
+	// Handled by PerfDriver
+	return 0;
+}
+
+void CCNDriver::writeEvents(mxml_node_t *const root) const {
+	mxml_node_t *const counter_set = mxmlNewElement(root, TAG_COUNTER_SET);
+	mxmlElementSetAttr(counter_set, ATTR_NAME, ARM_CCN_5XX "cnt");
+	mxmlElementSetAttr(counter_set, ATTR_COUNT, "8");
+
+	mxml_node_t *const category = mxmlNewElement(root, TAG_CATEGORY);
+	mxmlElementSetAttr(category, ATTR_NAME, CCN_5XX);
+	mxmlElementSetAttr(category, TAG_COUNTER_SET, ARM_CCN_5XX "cnt");
+
+	mxml_node_t *const clock_event = mxmlNewElement(category, TAG_EVENT);
+	mxmlElementSetAttr(clock_event, ATTR_COUNTER, ARM_CCN_5XX "ccnt");
+	mxmlElementSetAttr(clock_event, ATTR_EVENT, "0xff00");
+	mxmlElementSetAttr(clock_event, ATTR_TITLE, "CCN-5xx Clock");
+	mxmlElementSetAttr(clock_event, ATTR_NAME, "Cycles");
+	mxmlElementSetAttr(clock_event, ATTR_DISPLAY, "hertz");
+	mxmlElementSetAttr(clock_event, ATTR_UNITS, "Hz");
+	mxmlElementSetAttr(clock_event, ATTR_AVERAGE_SELECTION, "yes");
+	mxmlElementSetAttr(clock_event, ATTR_DESCRIPTION, "The number of core clock cycles");
+
+	mxml_node_t *const xp_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(xp_option_set, ATTR_NAME, XP_REGION);
+
+	for (int i = 0; i < mXpCount; ++i) {
+		mxml_node_t *const option = mxmlNewElement(xp_option_set, TAG_OPTION);
+		mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+		mxmlElementSetAttrf(option, ATTR_NAME, "XP %i", i);
+		mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Crosspoint %i", i);
+	}
+
+	for (int vc = 0; vc < ARRAY_LENGTH(VC_TYPES); ++vc) {
+		if (VC_TYPES[vc] == NULL) {
+			continue;
+		}
+		for (int bus = 0; bus < 2; ++bus) {
+			for (int eventId = 0; eventId < ARRAY_LENGTH(XP_EVENT_NAMES); ++eventId) {
+				if (XP_EVENT_NAMES[eventId] == NULL) {
+					continue;
+				}
+				mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+				mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x08, eventId, bus, vc));
+				mxmlElementSetAttr(event, ATTR_OPTION_SET, XP_REGION);
+				mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+				mxmlElementSetAttrf(event, ATTR_NAME, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_NAMES[eventId]);
+				mxmlElementSetAttrf(event, ATTR_DESCRIPTION, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_DESCRIPTIONS[eventId]);
+			}
+		}
+	}
+
+	mxml_node_t *const hnf_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(hnf_option_set, ATTR_NAME, HNF_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(HNF_EVENT_NAMES); ++eventId) {
+		if (HNF_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x04, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, HNF_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, HNF_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, HNF_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const rni_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(rni_option_set, ATTR_NAME, RNI_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(RNI_EVENT_NAMES); ++eventId) {
+		if (RNI_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x16, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, RNI_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, RNI_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, RNI_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const sbas_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(sbas_option_set, ATTR_NAME, SBAS_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(SBAS_EVENT_NAMES); ++eventId) {
+		if (SBAS_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x10, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, SBAS_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, SBAS_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, SBAS_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		switch (mNodeTypes[i]) {
+		case NT_HNF: {
+			mxml_node_t *const option = mxmlNewElement(hnf_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "HN-F %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Fully-coherent Home Node %i", i);
+			break;
+		}
+		case NT_RNI: {
+			mxml_node_t *const option = mxmlNewElement(rni_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "RN-I %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "I/O-coherent Requesting Node %i", i);
+			break;
+		}
+		case NT_SBAS: {
+			mxml_node_t *const option = mxmlNewElement(sbas_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "SBAS %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "ACE master to CHI protocol bridge %i", i);
+			break;
+		}
+		default:
+			continue;
+		}
+	}
+}
diff --git a/tools/gator/daemon/CCNDriver.h b/tools/gator/daemon/CCNDriver.h
new file mode 100644
index 000000000000..fb4c717e969a
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CCNDRIVER_H
+#define CCNDRIVER_H
+
+#include "Driver.h"
+
+class CCNDriver : public Driver {
+public:
+	CCNDriver();
+	~CCNDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	void readEvents(mxml_node_t *const);
+	int writeCounters(mxml_node_t *const root) const;
+	void writeEvents(mxml_node_t *const) const;
+
+private:
+	enum NodeType {
+		NT_UNKNOWN,
+		NT_HNF,
+		NT_RNI,
+		NT_SBAS,
+	};
+
+	NodeType *mNodeTypes;
+	int mXpCount;
+
+	// Intentionally unimplemented
+	CCNDriver(const CCNDriver &);
+	CCNDriver &operator=(const CCNDriver &);
+};
+
+#endif // CCNDRIVER_H
diff --git a/tools/gator/daemon/CPUFreqDriver.cpp b/tools/gator/daemon/CPUFreqDriver.cpp
new file mode 100644
index 000000000000..41f9d6f2b3f4
--- /dev/null
+++ b/tools/gator/daemon/CPUFreqDriver.cpp
@@ -0,0 +1,58 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CPUFreqDriver.h"
+
+#include "Buffer.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+CPUFreqDriver::CPUFreqDriver() : mPrev() {
+}
+
+CPUFreqDriver::~CPUFreqDriver() {
+}
+
+void CPUFreqDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new DriverCounter(getCounters(), strdup("Linux_power_cpu_freq")));
+}
+
+void CPUFreqDriver::read(Buffer *const buffer) {
+	char buf[64];
+	const DriverCounter *const counter = getCounters();
+	if ((counter == NULL) || !counter->isEnabled()) {
+		return;
+	}
+
+	const int key = getCounters()->getKey();
+	bool resetCores = false;
+	for (int i = 0; i < gSessionData->mCores; ++i) {
+		snprintf(buf, sizeof(buf), "/sys/devices/system/cpu/cpu%i/cpufreq/cpuinfo_cur_freq", i);
+		int64_t freq;
+		if (DriverSource::readInt64Driver(buf, &freq) != 0) {
+			freq = 0;
+		}
+		if (mPrev[i] != freq) {
+			mPrev[i] = freq;
+			// Change cores
+			buffer->event64(2, i);
+			resetCores = true;
+			buffer->event64(key, 1000*freq);
+		}
+	}
+	if (resetCores) {
+		// Revert cores, UserSpaceSource is all on core 0
+		buffer->event64(2, 0);
+	}
+}
diff --git a/tools/gator/daemon/CPUFreqDriver.h b/tools/gator/daemon/CPUFreqDriver.h
new file mode 100644
index 000000000000..ad8c9aaa9e7d
--- /dev/null
+++ b/tools/gator/daemon/CPUFreqDriver.h
@@ -0,0 +1,34 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CPUFREQDRIVER_H
+#define CPUFREQDRIVER_H
+
+#include "Config.h"
+#include "Driver.h"
+
+class CPUFreqDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	CPUFreqDriver();
+	~CPUFreqDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void read(Buffer *const buffer);
+
+private:
+	int64_t mPrev[NR_CPUS];
+
+	// Intentionally unimplemented
+	CPUFreqDriver(const CPUFreqDriver &);
+	CPUFreqDriver &operator=(const CPUFreqDriver &);
+};
+
+#endif // CPUFREQDRIVER_H
diff --git a/tools/gator/daemon/CapturedXML.cpp b/tools/gator/daemon/CapturedXML.cpp
new file mode 100644
index 000000000000..0b5802c893bb
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.cpp
@@ -0,0 +1,145 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CapturedXML.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+
+CapturedXML::CapturedXML() {
+}
+
+CapturedXML::~CapturedXML() {
+}
+
+mxml_node_t* CapturedXML::getTree(bool includeTime) {
+	mxml_node_t *xml;
+	mxml_node_t *captured;
+	mxml_node_t *target;
+	int x;
+
+	xml = mxmlNewXML("1.0");
+
+	captured = mxmlNewElement(xml, "captured");
+	mxmlElementSetAttr(captured, "version", "1");
+	if (gSessionData->perf.isSetup()) {
+		mxmlElementSetAttr(captured, "type", "Perf");
+		mxmlElementSetAttr(captured, "perf_beta", "yes");
+	}
+	mxmlElementSetAttrf(captured, "protocol", "%d", PROTOCOL_VERSION);
+	if (includeTime) { // Send the following only after the capture is complete
+		if (time(NULL) > 1267000000) { // If the time is reasonable (after Feb 23, 2010)
+			mxmlElementSetAttrf(captured, "created", "%lu", time(NULL)); // Valid until the year 2038
+		}
+	}
+
+	target = mxmlNewElement(captured, "target");
+	mxmlElementSetAttr(target, "name", gSessionData->mCoreName);
+	mxmlElementSetAttrf(target, "sample_rate", "%d", gSessionData->mSampleRate);
+	mxmlElementSetAttrf(target, "cores", "%d", gSessionData->mCores);
+	mxmlElementSetAttrf(target, "cpuid", "0x%x", gSessionData->mMaxCpuId);
+
+	if (!gSessionData->mOneShot && (gSessionData->mSampleRate > 0)) {
+		mxmlElementSetAttr(target, "supports_live", "yes");
+	}
+
+	if (gSessionData->mLocalCapture) {
+		mxmlElementSetAttr(target, "local_capture", "yes");
+	}
+
+	mxml_node_t *counters = NULL;
+	for (x = 0; x < MAX_PERFORMANCE_COUNTERS; x++) {
+		const Counter & counter = gSessionData->mCounters[x];
+		if (counter.isEnabled()) {
+			if (counters == NULL) {
+				counters = mxmlNewElement(captured, "counters");
+			}
+			mxml_node_t *const node = mxmlNewElement(counters, "counter");
+			mxmlElementSetAttrf(node, "key", "0x%x", counter.getKey());
+			mxmlElementSetAttr(node, "type", counter.getType());
+			if (counter.getEvent() != -1) {
+				mxmlElementSetAttrf(node, "event", "0x%x", counter.getEvent());
+			}
+			if (counter.getCount() > 0) {
+				mxmlElementSetAttrf(node, "count", "%d", counter.getCount());
+			}
+			if (counter.getCores() > 0) {
+				mxmlElementSetAttrf(node, "cores", "%d", counter.getCores());
+			}
+		}
+	}
+
+	return xml;
+}
+
+char* CapturedXML::getXML(bool includeTime) {
+	char* xml_string;
+	mxml_node_t *xml = getTree(includeTime);
+	xml_string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+	return xml_string;
+}
+
+void CapturedXML::write(char* path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/captured.xml", path);
+
+	char* xml = getXML(true);
+	if (util->writeToDisk(file, xml) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(xml);
+}
+
+// whitespace callback utility function used with mini-xml
+const char * mxmlWhitespaceCB(mxml_node_t *node, int loc) {
+	const char *name;
+
+	name = mxmlGetElement(node);
+
+	if (loc == MXML_WS_BEFORE_OPEN) {
+		// Single indentation
+		if (!strcmp(name, "target") || !strcmp(name, "counters"))
+			return "\n  ";
+
+		// Double indentation
+		if (!strcmp(name, "counter"))
+			return "\n    ";
+
+		// Avoid a carriage return on the first line of the xml file
+		if (!strncmp(name, "?xml", 4))
+			return NULL;
+
+		// Default - no indentation
+		return "\n";
+	}
+
+	if (loc == MXML_WS_BEFORE_CLOSE) {
+		// No indentation
+		if (!strcmp(name, "captured"))
+			return "\n";
+
+		// Single indentation
+		if (!strcmp(name, "counters"))
+			return "\n  ";
+
+		// Default - no carriage return
+		return NULL;
+	}
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/CapturedXML.h b/tools/gator/daemon/CapturedXML.h
new file mode 100644
index 000000000000..b704f6e53bb5
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CAPTURED_XML_H__
+#define __CAPTURED_XML_H__
+
+#include "mxml/mxml.h"
+
+class CapturedXML {
+public:
+	CapturedXML();
+	~CapturedXML();
+	char* getXML(bool includeTime); // the string should be freed by the caller
+	void write(char* path);
+private:
+	mxml_node_t* getTree(bool includeTime);
+};
+
+const char * mxmlWhitespaceCB(mxml_node_t *node, int where);
+
+#endif //__CAPTURED_XML_H__
diff --git a/tools/gator/daemon/Child.cpp b/tools/gator/daemon/Child.cpp
new file mode 100644
index 000000000000..6b5bbb3bf6af
--- /dev/null
+++ b/tools/gator/daemon/Child.cpp
@@ -0,0 +1,392 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Child.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "CapturedXML.h"
+#include "Command.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "DriverSource.h"
+#include "ExternalSource.h"
+#include "FtraceSource.h"
+#include "LocalCapture.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "PerfSource.h"
+#include "Sender.h"
+#include "SessionData.h"
+#include "StreamlineSetup.h"
+#include "UserSpaceSource.h"
+
+static sem_t haltPipeline, senderThreadStarted, startProfile, senderSem; // Shared by Child and spawned threads
+static Source *primarySource = NULL;
+static Source *externalSource = NULL;
+static Source *userSpaceSource = NULL;
+static Source *ftraceSource = NULL;
+static Sender* sender = NULL;        // Shared by Child.cpp and spawned threads
+Child* child = NULL;                 // shared by Child.cpp and main.cpp
+
+extern void cleanUp();
+void handleException() {
+	if (child && child->numExceptions++ > 0) {
+		// it is possible one of the below functions itself can cause an exception, thus allow only one exception
+		logg->logMessage("Received multiple exceptions, terminating the child");
+		exit(1);
+	}
+	fprintf(stderr, "%s", logg->getLastError());
+
+	if (child && child->socket) {
+		if (sender) {
+			// send the error, regardless of the command sent by Streamline
+			sender->writeData(logg->getLastError(), strlen(logg->getLastError()), RESPONSE_ERROR);
+
+			// cannot close the socket before Streamline issues the command, so wait for the command before exiting
+			if (gSessionData->mWaitingOnCommand) {
+				char discard;
+				child->socket->receiveNBytes(&discard, 1);
+			}
+
+			// Ensure all data is flushed
+			child->socket->shutdownConnection();
+
+			// this indirectly calls close socket which will ensure the data has been sent
+			delete sender;
+		}
+	}
+
+	if (gSessionData->mLocalCapture)
+		cleanUp();
+
+	exit(1);
+}
+
+// CTRL C Signal Handler for child process
+static void child_handler(int signum) {
+	static bool beenHere = false;
+	if (beenHere == true) {
+		logg->logMessage("Gator is being forced to shut down.");
+		exit(1);
+	}
+	beenHere = true;
+	logg->logMessage("Gator is shutting down.");
+	if (signum == SIGALRM || !primarySource) {
+		exit(1);
+	} else {
+		child->endSession();
+		alarm(5); // Safety net in case endSession does not complete within 5 seconds
+	}
+}
+
+static void *durationThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-duration", 0, 0, 0);
+	sem_wait(&startProfile);
+	if (gSessionData->mSessionIsActive) {
+		// Time out after duration seconds
+		// Add a second for host-side filtering
+		sleep(gSessionData->mDuration + 1);
+		if (gSessionData->mSessionIsActive) {
+			logg->logMessage("Duration expired.");
+			child->endSession();
+		}
+	}
+	logg->logMessage("Exit duration thread");
+	return 0;
+}
+
+static void *stopThread(void *) {
+	OlySocket* socket = child->socket;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-stopper", 0, 0, 0);
+	while (gSessionData->mSessionIsActive) {
+		// This thread will stall until the APC_STOP or PING command is received over the socket or the socket is disconnected
+		unsigned char header[5];
+		const int result = socket->receiveNBytes((char*)&header, sizeof(header));
+		const char type = header[0];
+		const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+		if (result == -1) {
+			child->endSession();
+		} else if (result > 0) {
+			if ((type != COMMAND_APC_STOP) && (type != COMMAND_PING)) {
+				logg->logMessage("INVESTIGATE: Received unknown command type %d", type);
+			} else {
+				// verify a length of zero
+				if (length == 0) {
+					if (type == COMMAND_APC_STOP) {
+						logg->logMessage("Stop command received.");
+						child->endSession();
+					} else {
+						// Ping is used to make sure gator is alive and requires an ACK as the response
+						logg->logMessage("Ping command received.");
+						sender->writeData(NULL, 0, RESPONSE_ACK);
+					}
+				} else {
+					logg->logMessage("INVESTIGATE: Received stop command but with length = %d", length);
+				}
+			}
+		}
+	}
+
+	logg->logMessage("Exit stop thread");
+	return 0;
+}
+
+static void *senderThread(void *) {
+	char end_sequence[] = {RESPONSE_APC_DATA, 0, 0, 0, 0};
+
+	sem_post(&senderThreadStarted);
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sender", 0, 0, 0);
+	sem_wait(&haltPipeline);
+
+	while (!primarySource->isDone() ||
+	       !externalSource->isDone() ||
+	       (userSpaceSource != NULL && !userSpaceSource->isDone()) ||
+	       (ftraceSource != NULL && !ftraceSource->isDone())) {
+		sem_wait(&senderSem);
+
+		primarySource->write(sender);
+		externalSource->write(sender);
+		if (userSpaceSource != NULL) {
+			userSpaceSource->write(sender);
+		}
+		if (ftraceSource != NULL) {
+			ftraceSource->write(sender);
+		}
+	}
+
+	// write end-of-capture sequence
+	if (!gSessionData->mLocalCapture) {
+		sender->writeData(end_sequence, sizeof(end_sequence), RESPONSE_APC_DATA);
+	}
+
+	logg->logMessage("Exit sender thread");
+	return 0;
+}
+
+Child::Child() {
+	initialization();
+	gSessionData->mLocalCapture = true;
+}
+
+Child::Child(OlySocket* sock, int conn) {
+	initialization();
+	socket = sock;
+	mNumConnections = conn;
+}
+
+Child::~Child() {
+}
+
+void Child::initialization() {
+	// Set up different handlers for signals
+	gSessionData->mSessionIsActive = true;
+	signal(SIGINT, child_handler);
+	signal(SIGTERM, child_handler);
+	signal(SIGABRT, child_handler);
+	signal(SIGALRM, child_handler);
+	socket = NULL;
+	numExceptions = 0;
+	mNumConnections = 0;
+
+	// Initialize semaphores
+	sem_init(&senderThreadStarted, 0, 0);
+	sem_init(&startProfile, 0, 0);
+	sem_init(&senderSem, 0, 0);
+}
+
+void Child::endSession() {
+	gSessionData->mSessionIsActive = false;
+	primarySource->interrupt();
+	externalSource->interrupt();
+	if (userSpaceSource != NULL) {
+		userSpaceSource->interrupt();
+	}
+	if (ftraceSource != NULL) {
+		ftraceSource->interrupt();
+	}
+	sem_post(&haltPipeline);
+}
+
+void Child::run() {
+	LocalCapture* localCapture = NULL;
+	pthread_t durationThreadID, stopThreadID, senderThreadID;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-child", 0, 0, 0);
+
+	// Disable line wrapping when generating xml files; carriage returns and indentation to be added manually
+	mxmlSetWrapMargin(0);
+
+	// Instantiate the Sender - must be done first, after which error messages can be sent
+	sender = new Sender(socket);
+
+	if (mNumConnections > 1) {
+		logg->logError(__FILE__, __LINE__, "Session already in progress");
+		handleException();
+	}
+
+	// Populate gSessionData with the configuration
+	{ ConfigurationXML configuration; }
+
+	// Set up the driver; must be done after gSessionData->mPerfCounterType[] is populated
+	if (!gSessionData->perf.isSetup()) {
+		primarySource = new DriverSource(&senderSem, &startProfile);
+	} else {
+		primarySource = new PerfSource(&senderSem, &startProfile);
+	}
+
+	// Initialize all drivers
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->resetCounters();
+	}
+
+	// Set up counters using the associated driver's setup function
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			counter.getDriver()->setupCounter(counter);
+		}
+	}
+
+	// Start up and parse session xml
+	if (socket) {
+		// Respond to Streamline requests
+		StreamlineSetup ss(socket);
+	} else {
+		char* xmlString;
+		xmlString = util->readFromDisk(gSessionData->mSessionXMLPath);
+		if (xmlString == 0) {
+			logg->logError(__FILE__, __LINE__, "Unable to read session xml file: %s", gSessionData->mSessionXMLPath);
+			handleException();
+		}
+		gSessionData->parseSessionXML(xmlString);
+		localCapture = new LocalCapture();
+		localCapture->createAPCDirectory(gSessionData->mTargetPath);
+		localCapture->copyImages(gSessionData->mImages);
+		localCapture->write(xmlString);
+		sender->createDataFile(gSessionData->mAPCDir);
+		free(xmlString);
+	}
+
+	if (gSessionData->kmod.isMaliCapture() && (gSessionData->mSampleRate == 0)) {
+		logg->logError(__FILE__, __LINE__, "Mali counters are not supported with Sample Rate: None.");
+		handleException();
+	}
+
+	// Must be after session XML is parsed
+	if (!primarySource->prepare()) {
+		if (gSessionData->perf.isSetup()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare gator driver for capture");
+		} else {
+			logg->logError(__FILE__, __LINE__, "Unable to communicate with the perf API, please ensure that CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER are enabled. Please refer to README_Streamline.txt for more information.");
+		}
+		handleException();
+	}
+
+	// Sender thread shall be halted until it is signaled for one shot mode
+	sem_init(&haltPipeline, 0, gSessionData->mOneShot ? 0 : 2);
+
+	// Must be initialized before senderThread is started as senderThread checks externalSource
+	externalSource = new ExternalSource(&senderSem);
+	if (!externalSource->prepare()) {
+		logg->logError(__FILE__, __LINE__, "Unable to prepare external source for capture");
+		handleException();
+	}
+	externalSource->start();
+
+	// Create the duration, stop, and sender threads
+	bool thread_creation_success = true;
+	if (gSessionData->mDuration > 0 && pthread_create(&durationThreadID, NULL, durationThread, NULL)) {
+		thread_creation_success = false;
+	} else if (socket && pthread_create(&stopThreadID, NULL, stopThread, NULL)) {
+		thread_creation_success = false;
+	} else if (pthread_create(&senderThreadID, NULL, senderThread, NULL)) {
+		thread_creation_success = false;
+	}
+
+	bool startUSSource = false;
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+		if (gSessionData->usDrivers[i]->countersEnabled()) {
+			startUSSource = true;
+		}
+	}
+	if (startUSSource) {
+		userSpaceSource = new UserSpaceSource(&senderSem);
+		if (!userSpaceSource->prepare()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture");
+			handleException();
+		}
+		userSpaceSource->start();
+	}
+
+	if (gSessionData->ftraceDriver.countersEnabled()) {
+		ftraceSource = new FtraceSource(&senderSem);
+		if (!ftraceSource->prepare()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture");
+			handleException();
+		}
+		ftraceSource->start();
+	}
+
+	if (gSessionData->mAllowCommands && (gSessionData->mCaptureCommand != NULL)) {
+		pthread_t thread;
+		if (pthread_create(&thread, NULL, commandThread, NULL)) {
+			thread_creation_success = false;
+		}
+	}
+
+	if (!thread_creation_success) {
+		logg->logError(__FILE__, __LINE__, "Failed to create gator threads");
+		handleException();
+	}
+
+	// Wait until thread has started
+	sem_wait(&senderThreadStarted);
+
+	// Start profiling
+	primarySource->run();
+
+	if (ftraceSource != NULL) {
+		ftraceSource->join();
+	}
+	if (userSpaceSource != NULL) {
+		userSpaceSource->join();
+	}
+	externalSource->join();
+
+	// Wait for the other threads to exit
+	pthread_join(senderThreadID, NULL);
+
+	// Shutting down the connection should break the stop thread which is stalling on the socket recv() function
+	if (socket) {
+		logg->logMessage("Waiting on stop thread");
+		socket->shutdownConnection();
+		pthread_join(stopThreadID, NULL);
+	}
+
+	// Write the captured xml file
+	if (gSessionData->mLocalCapture) {
+		CapturedXML capturedXML;
+		capturedXML.write(gSessionData->mAPCDir);
+	}
+
+	logg->logMessage("Profiling ended.");
+
+	delete ftraceSource;
+	delete userSpaceSource;
+	delete externalSource;
+	delete primarySource;
+	delete sender;
+	delete localCapture;
+}
diff --git a/tools/gator/daemon/Child.h b/tools/gator/daemon/Child.h
new file mode 100644
index 000000000000..cc78202ceb5c
--- /dev/null
+++ b/tools/gator/daemon/Child.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CHILD_H__
+#define __CHILD_H__
+
+class OlySocket;
+
+class Child {
+public:
+	Child();
+	Child(OlySocket* sock, int numConnections);
+	~Child();
+	void run();
+	OlySocket *socket;
+	void endSession();
+	int numExceptions;
+private:
+	int mNumConnections;
+
+	void initialization();
+
+	// Intentionally unimplemented
+	Child(const Child &);
+	Child &operator=(const Child &);
+};
+
+#endif //__CHILD_H__
diff --git a/tools/gator/daemon/Command.cpp b/tools/gator/daemon/Command.cpp
new file mode 100644
index 000000000000..28d73cf5a905
--- /dev/null
+++ b/tools/gator/daemon/Command.cpp
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Command.h"
+
+#include <fcntl.h>
+#include <pwd.h>
+#include <stdio.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+static int getUid(const char *const name, char *const shPath, const char *const tmpDir) {
+	// Lookups may fail when using a different libc or a statically compiled executable
+	char gatorTemp[32];
+	snprintf(gatorTemp, sizeof(gatorTemp), "%s/gator_temp", tmpDir);
+
+	const int fd = open(gatorTemp, 600, O_CREAT | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+	close(fd);
+
+	char cmd[128];
+	snprintf(cmd, sizeof(cmd), "chown %s %s || rm %s", name, gatorTemp, gatorTemp);
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError(__FILE__, __LINE__, "fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		char cargv1[] = "-c";
+		char *cargv[] = {
+			shPath,
+			cargv1,
+			cmd,
+			NULL,
+		};
+
+		execv(cargv[0], cargv);
+		exit(-1);
+	}
+	while ((waitpid(pid, NULL, 0) < 0) && (errno == EINTR));
+
+	struct stat st;
+	int result = -1;
+	if (stat(gatorTemp, &st) == 0) {
+		result = st.st_uid;
+	}
+	unlink(gatorTemp);
+	return result;
+}
+
+static int getUid(const char *const name) {
+	// Look up the username
+	struct passwd *const user = getpwnam(name);
+	if (user != NULL) {
+		return user->pw_uid;
+	}
+
+
+	// Are we on Linux
+	char cargv0l[] = "/bin/sh";
+	if ((access(cargv0l, X_OK) == 0) && (access("/tmp", W_OK) == 0)) {
+		return getUid(name, cargv0l, "/tmp");
+	}
+
+	// Are we on android
+	char cargv0a[] = "/system/bin/sh";
+	if ((access(cargv0a, X_OK) == 0) && (access("/data", W_OK) == 0)) {
+		return getUid(name, cargv0a, "/data");
+	}
+
+	return -1;
+}
+
+void *commandThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-command", 0, 0, 0);
+
+	const char *const name = gSessionData->mCaptureUser == NULL ? "nobody" : gSessionData->mCaptureUser;
+	const int uid = getUid(name);
+	if (uid < 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to lookup the user %s, please double check that the user exists", name);
+		handleException();
+	}
+
+	sleep(3);
+
+	char buf[128];
+	int pipefd[2];
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError(__FILE__, __LINE__, "fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		char cargv0l[] = "/bin/sh";
+		char cargv0a[] = "/system/bin/sh";
+		char cargv1[] = "-c";
+		char *cargv[] = {
+			cargv0l,
+			cargv1,
+			gSessionData->mCaptureCommand,
+			NULL,
+		};
+
+		buf[0] = '\0';
+		close(pipefd[0]);
+
+		// Gator runs at a high priority, reset the priority to the default
+		if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+			snprintf(buf, sizeof(buf), "setpriority failed");
+			goto fail_exit;
+		}
+
+		if (setuid(uid) != 0) {
+			snprintf(buf, sizeof(buf), "setuid failed");
+			goto fail_exit;
+		}
+
+		{
+			const char *const path = gSessionData->mCaptureWorkingDir == NULL ? "/" : gSessionData->mCaptureWorkingDir;
+			if (chdir(path) != 0) {
+				snprintf(buf, sizeof(buf), "Unable to cd to %s, please verify the directory exists and is accessable to %s", path, name);
+				goto fail_exit;
+			}
+		}
+
+		execv(cargv[0], cargv);
+		cargv[0] = cargv0a;
+		execv(cargv[0], cargv);
+		snprintf(buf, sizeof(buf), "execv failed");
+
+	fail_exit:
+		if (buf[0] != '\0') {
+			const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+			// Can't do anything if this fails
+			(void)bytes;
+		}
+
+		exit(-1);
+	}
+
+	close(pipefd[1]);
+	const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+	if (bytes > 0) {
+		logg->logError(__FILE__, __LINE__, buf);
+		handleException();
+	}
+	close(pipefd[0]);
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/Command.h b/tools/gator/daemon/Command.h
new file mode 100644
index 000000000000..17244b7aaebc
--- /dev/null
+++ b/tools/gator/daemon/Command.h
@@ -0,0 +1,14 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COMMAND_H
+#define COMMAND_H
+
+void *commandThread(void *);
+
+#endif // COMMAND_H
diff --git a/tools/gator/daemon/Config.h b/tools/gator/daemon/Config.h
new file mode 100644
index 000000000000..bee383a1c797
--- /dev/null
+++ b/tools/gator/daemon/Config.h
@@ -0,0 +1,28 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CONFIG_H
+#define CONFIG_H
+
+#define ARRAY_LENGTH(A) static_cast<int>(sizeof(A)/sizeof((A)[0]))
+#define ACCESS_ONCE(x) (*(volatile typeof(x)*)&(x))
+
+#define MAX_PERFORMANCE_COUNTERS 50
+#define NR_CPUS 32
+
+template<typename T>
+static inline T min(const T a, const T b) {
+	return (a < b ? a : b);
+}
+
+template<typename T>
+static inline T max(const T a, const T b) {
+	return (a > b ? a : b);
+}
+
+#endif // CONFIG_H
diff --git a/tools/gator/daemon/ConfigurationXML.cpp b/tools/gator/daemon/ConfigurationXML.cpp
new file mode 100644
index 000000000000..6590dd389196
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.cpp
@@ -0,0 +1,217 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ConfigurationXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <dirent.h>
+
+#include "Driver.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char* ATTR_COUNTER            = "counter";
+static const char* ATTR_REVISION           = "revision";
+static const char* ATTR_EVENT              = "event";
+static const char* ATTR_COUNT              = "count";
+static const char* ATTR_CORES              = "cores";
+
+ConfigurationXML::ConfigurationXML() {
+	const char * configuration_xml;
+	unsigned int configuration_xml_len;
+	getDefaultConfigurationXml(configuration_xml, configuration_xml_len);
+
+	char path[PATH_MAX];
+
+	getPath(path);
+	mConfigurationXML = util->readFromDisk(path);
+
+	for (int retryCount = 0; retryCount < 2; ++retryCount) {
+		if (mConfigurationXML == NULL) {
+			logg->logMessage("Unable to locate configuration.xml, using default in binary");
+			// null-terminate configuration_xml
+			mConfigurationXML = (char*)malloc(configuration_xml_len + 1);
+			memcpy(mConfigurationXML, (const void*)configuration_xml, configuration_xml_len);
+			mConfigurationXML[configuration_xml_len] = 0;
+		}
+
+		int ret = parse(mConfigurationXML);
+		if (ret == 1) {
+			remove();
+
+			// Free the current configuration and reload
+			free((void*)mConfigurationXML);
+			mConfigurationXML = NULL;
+			continue;
+		}
+
+		break;
+	}
+
+	validate();
+}
+
+ConfigurationXML::~ConfigurationXML() {
+	if (mConfigurationXML) {
+		free((void*)mConfigurationXML);
+	}
+}
+
+int ConfigurationXML::parse(const char* configurationXML) {
+	mxml_node_t *tree, *node;
+	int ret;
+
+	// clear counter overflow
+	gSessionData->mCounterOverflow = 0;
+	gSessionData->mIsEBS = false;
+	mIndex = 0;
+
+	// disable all counters prior to parsing the configuration xml
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		gSessionData->mCounters[i].setEnabled(false);
+	}
+
+	tree = mxmlLoadString(NULL, configurationXML, MXML_NO_CALLBACK);
+
+	node = mxmlGetFirstChild(tree);
+	while (node && mxmlGetType(node) != MXML_ELEMENT)
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+
+	ret = configurationsTag(node);
+
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		configurationTag(node);
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+
+	mxmlDelete(tree);
+
+	return ret;
+}
+
+void ConfigurationXML::validate(void) {
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		const Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			if (strcmp(counter.getType(), "") == 0) {
+				logg->logError(__FILE__, __LINE__, "Invalid required attribute in configuration.xml:\n  counter=\"%s\"\n  event=%d\n", counter.getType(), counter.getEvent());
+				handleException();
+			}
+
+			// iterate through the remaining enabled performance counters
+			for (int j = i + 1; j < MAX_PERFORMANCE_COUNTERS; j++) {
+				const Counter & counter2 = gSessionData->mCounters[j];
+				if (counter2.isEnabled()) {
+					// check if the types are the same
+					if (strcmp(counter.getType(), counter2.getType()) == 0) {
+						logg->logError(__FILE__, __LINE__, "Duplicate performance counter type in configuration.xml: %s", counter.getType());
+						handleException();
+					}
+				}
+			}
+		}
+	}
+}
+
+#define CONFIGURATION_REVISION 3
+int ConfigurationXML::configurationsTag(mxml_node_t *node) {
+	const char* revision_string;
+
+	revision_string = mxmlElementGetAttr(node, ATTR_REVISION);
+	if (!revision_string) {
+		return 1; //revision issue;
+	}
+
+	int revision = strtol(revision_string, NULL, 10);
+	if (revision < CONFIGURATION_REVISION) {
+		return 1; // revision issue
+	}
+
+	// A revision >= CONFIGURATION_REVISION is okay
+	// Greater than can occur when Streamline is newer than gator
+
+	return 0;
+}
+
+void ConfigurationXML::configurationTag(mxml_node_t *node) {
+	// handle all other performance counters
+	if (mIndex >= MAX_PERFORMANCE_COUNTERS) {
+		mIndex++;
+		gSessionData->mCounterOverflow = mIndex;
+		return;
+	}
+
+	// read attributes
+	Counter & counter = gSessionData->mCounters[mIndex];
+	counter.clear();
+	if (mxmlElementGetAttr(node, ATTR_COUNTER)) counter.setType(mxmlElementGetAttr(node, ATTR_COUNTER));
+	if (mxmlElementGetAttr(node, ATTR_EVENT)) counter.setEvent(strtol(mxmlElementGetAttr(node, ATTR_EVENT), NULL, 16));
+	if (mxmlElementGetAttr(node, ATTR_COUNT)) counter.setCount(strtol(mxmlElementGetAttr(node, ATTR_COUNT), NULL, 10));
+	if (mxmlElementGetAttr(node, ATTR_CORES)) counter.setCores(strtol(mxmlElementGetAttr(node, ATTR_CORES), NULL, 10));
+	if (counter.getCount() > 0) {
+		gSessionData->mIsEBS = true;
+	}
+	counter.setEnabled(true);
+
+	// Associate a driver with each counter
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		if (driver->claimCounter(counter)) {
+			if (counter.getDriver() != NULL) {
+				logg->logError(__FILE__, __LINE__, "More than one driver has claimed %s:%i", counter.getType(), counter.getEvent());
+				handleException();
+			}
+			counter.setDriver(driver);
+		}
+	}
+
+	// If no driver is associated with the counter, disable it
+	if (counter.getDriver() == NULL) {
+		logg->logMessage("No driver has claimed %s:%i", counter.getType(), counter.getEvent());
+		counter.setEnabled(false);
+	}
+
+	if (counter.isEnabled()) {
+		// update counter index
+		mIndex++;
+	}
+}
+
+void ConfigurationXML::getDefaultConfigurationXml(const char * & xml, unsigned int & len) {
+#include "defaults_xml.h" // defines and initializes char defaults_xml[] and int defaults_xml_len
+	xml = (const char *)defaults_xml;
+	len = defaults_xml_len;
+}
+
+void ConfigurationXML::getPath(char* path) {
+	if (gSessionData->mConfigurationXMLPath) {
+		strncpy(path, gSessionData->mConfigurationXMLPath, PATH_MAX);
+	} else {
+		if (util->getApplicationFullPath(path, PATH_MAX) != 0) {
+			logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+		}
+		strncat(path, "configuration.xml", PATH_MAX - strlen(path) - 1);
+	}
+}
+
+void ConfigurationXML::remove() {
+	char path[PATH_MAX];
+	getPath(path);
+
+	if (::remove(path) != 0) {
+		logg->logError(__FILE__, __LINE__, "Invalid configuration.xml file detected and unable to delete it. To resolve, delete configuration.xml on disk");
+		handleException();
+	}
+	logg->logMessage("Invalid configuration.xml file detected and removed");
+}
diff --git a/tools/gator/daemon/ConfigurationXML.h b/tools/gator/daemon/ConfigurationXML.h
new file mode 100644
index 000000000000..efa415e508b6
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTERS_H
+#define COUNTERS_H
+
+#include "mxml/mxml.h"
+
+class ConfigurationXML {
+public:
+	static void getDefaultConfigurationXml(const char * & xml, unsigned int & len);
+	static void getPath(char* path);
+	static void remove();
+
+	ConfigurationXML();
+	~ConfigurationXML();
+	const char* getConfigurationXML() {return mConfigurationXML;}
+	void validate(void);
+
+private:
+	char* mConfigurationXML;
+	int mIndex;
+
+	int parse(const char* xmlFile);
+	int configurationsTag(mxml_node_t *node);
+	void configurationTag(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	ConfigurationXML(const ConfigurationXML &);
+	ConfigurationXML &operator=(const ConfigurationXML &);
+};
+
+#endif // COUNTERS_H
diff --git a/tools/gator/daemon/Counter.h b/tools/gator/daemon/Counter.h
new file mode 100644
index 000000000000..5202aa046362
--- /dev/null
+++ b/tools/gator/daemon/Counter.h
@@ -0,0 +1,65 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTER_H
+#define COUNTER_H
+
+#include <string.h>
+
+class Driver;
+
+class Counter {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+	static const size_t MAX_DESCRIPTION_LEN = 400;
+
+	Counter () {
+		clear();
+	}
+
+	void clear () {
+		mType[0] = '\0';
+		mEnabled = false;
+		mEvent = -1;
+		mCount = 0;
+		mCores = -1;
+		mKey = 0;
+		mDriver = NULL;
+	}
+
+	void setType(const char *const type) { strncpy(mType, type, sizeof(mType)); mType[sizeof(mType) - 1] = '\0'; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	void setEvent(const int event) { mEvent = event; }
+	void setCount(const int count) { mCount = count; }
+	void setCores(const int cores) { mCores = cores; }
+	void setKey(const int key) { mKey = key; }
+	void setDriver(Driver *const driver) { mDriver = driver; }
+
+	const char *getType() const { return mType;}
+	bool isEnabled() const { return mEnabled; }
+	int getEvent() const { return mEvent; }
+	int getCount() const { return mCount; }
+	int getCores() const { return mCores; }
+	int getKey() const { return mKey; }
+	Driver *getDriver() const { return mDriver; }
+
+private:
+	// Intentionally unimplemented
+	Counter(const Counter &);
+	Counter & operator=(const Counter &);
+
+	char mType[MAX_STRING_LEN];
+	bool mEnabled;
+	int mEvent;
+	int mCount;
+	int mCores;
+	int mKey;
+	Driver *mDriver;
+};
+
+#endif // COUNTER_H
diff --git a/tools/gator/daemon/DiskIODriver.cpp b/tools/gator/daemon/DiskIODriver.cpp
new file mode 100644
index 000000000000..5deb0f375f3a
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.cpp
@@ -0,0 +1,125 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DiskIODriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class DiskIOCounter : public DriverCounter {
+public:
+	DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~DiskIOCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	DiskIOCounter(const DiskIOCounter &);
+	DiskIOCounter &operator=(const DiskIOCounter &);
+};
+
+DiskIOCounter::DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+DiskIOCounter::~DiskIOCounter() {
+}
+
+int64_t DiskIOCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	// Kernel assumes a sector is 512 bytes
+	return result << 9;
+}
+
+DiskIODriver::DiskIODriver() : mBuf(), mReadBytes(0), mWriteBytes(0) {
+}
+
+DiskIODriver::~DiskIODriver() {
+}
+
+void DiskIODriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_rd"), &mReadBytes));
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_wr"), &mWriteBytes));
+}
+
+void DiskIODriver::doRead() {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/diskstats")) {
+		logg->logError(__FILE__, __LINE__, "Unable to read /proc/diskstats");
+		handleException();
+	}
+
+	mReadBytes = 0;
+	mWriteBytes = 0;
+
+	char *lastName = NULL;
+	int lastNameLen = -1;
+	char *start = mBuf.getBuf();
+	while (*start != '\0') {
+		char *end = strchr(start, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+
+		int nameStart = -1;
+		int nameEnd = -1;
+		int64_t readBytes = -1;
+		int64_t writeBytes = -1;
+		const int count = sscanf(start, "%*d %*d %n%*s%n %*u %*u %" SCNu64 " %*u %*u %*u %" SCNu64, &nameStart, &nameEnd, &readBytes, &writeBytes);
+		if (count != 2) {
+			logg->logError(__FILE__, __LINE__, "Unable to parse /proc/diskstats");
+			handleException();
+		}
+
+		// Skip partitions which are identified if the name is a substring of the last non-partition
+		if ((lastName == NULL) || (strncmp(lastName, start + nameStart, lastNameLen) != 0)) {
+			lastName = start + nameStart;
+			lastNameLen = nameEnd - nameStart;
+			mReadBytes += readBytes;
+			mWriteBytes += writeBytes;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		start = end + 1;
+	}
+}
+
+void DiskIODriver::start() {
+	doRead();
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void DiskIODriver::read(Buffer *const buffer) {
+	doRead();
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/DiskIODriver.h b/tools/gator/daemon/DiskIODriver.h
new file mode 100644
index 000000000000..d0db18c77d04
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DISKIODRIVER_H
+#define DISKIODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class DiskIODriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	DiskIODriver();
+	~DiskIODriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	void doRead();
+
+	DynBuf mBuf;
+	int64_t mReadBytes;
+	int64_t mWriteBytes;
+
+	// Intentionally unimplemented
+	DiskIODriver(const DiskIODriver &);
+	DiskIODriver &operator=(const DiskIODriver &);
+};
+
+#endif // DISKIODRIVER_H
diff --git a/tools/gator/daemon/Driver.cpp b/tools/gator/daemon/Driver.cpp
new file mode 100644
index 000000000000..275da31c7a0d
--- /dev/null
+++ b/tools/gator/daemon/Driver.cpp
@@ -0,0 +1,96 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Driver.h"
+
+#include "Buffer.h"
+#include "SessionData.h"
+
+DriverCounter::DriverCounter(DriverCounter *const next, const char *const name) : mNext(next), mName(name), mKey(getEventKey()), mEnabled(false) {
+}
+
+DriverCounter::~DriverCounter() {
+	delete mName;
+}
+
+Driver *Driver::head = NULL;
+
+Driver::Driver() : next(head) {
+	head = this;
+}
+
+SimpleDriver::~SimpleDriver() {
+	DriverCounter *counters = mCounters;
+	while (counters != NULL) {
+		DriverCounter *counter = counters;
+		counters = counter->getNext();
+		delete counter;
+	}
+}
+
+DriverCounter *SimpleDriver::findCounter(const Counter &counter) const {
+	for (DriverCounter *driverCounter = mCounters; driverCounter != NULL; driverCounter = driverCounter->getNext()) {
+		if (strcmp(driverCounter->getName(), counter.getType()) == 0) {
+			return driverCounter;
+		}
+	}
+
+	return NULL;
+}
+
+bool SimpleDriver::claimCounter(const Counter &counter) const {
+	return findCounter(counter) != NULL;
+}
+
+bool SimpleDriver::countersEnabled() const {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		if (counter->isEnabled()) {
+			return true;
+		}
+	}
+	return false;
+}
+
+void SimpleDriver::resetCounters() {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		counter->setEnabled(false);
+	}
+}
+
+void SimpleDriver::setupCounter(Counter &counter) {
+	DriverCounter *const driverCounter = findCounter(counter);
+	if (driverCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+	driverCounter->setEnabled(true);
+	counter.setKey(driverCounter->getKey());
+}
+
+int SimpleDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		mxml_node_t *node = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(node, "name", counter->getName());
+		++count;
+	}
+
+	return count;
+}
+
+PolledDriver::~PolledDriver() {
+}
+
+void PolledDriver::read(Buffer *const buffer) {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		buffer->event64(counter->getKey(), counter->read());
+	}
+}
diff --git a/tools/gator/daemon/Driver.h b/tools/gator/daemon/Driver.h
new file mode 100644
index 000000000000..72870e3dbca1
--- /dev/null
+++ b/tools/gator/daemon/Driver.h
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVER_H
+#define DRIVER_H
+
+#include <stdint.h>
+
+#include "mxml/mxml.h"
+
+class Buffer;
+class Counter;
+
+class DriverCounter {
+public:
+	DriverCounter(DriverCounter *const next, const char *const name);
+	virtual ~DriverCounter();
+
+	DriverCounter *getNext() const { return mNext; }
+	const char *getName() const { return mName; }
+	int getKey() const { return mKey; }
+	bool isEnabled() const { return mEnabled; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	virtual int64_t read() { return -1; }
+
+private:
+	DriverCounter *const mNext;
+	const char *const mName;
+	const int mKey;
+	bool mEnabled;
+
+	// Intentionally unimplemented
+	DriverCounter(const DriverCounter &);
+	DriverCounter &operator=(const DriverCounter &);
+};
+
+class Driver {
+public:
+	static Driver *getHead() { return head; }
+
+	virtual ~Driver() {}
+
+	// Returns true if this driver can manage the counter
+	virtual bool claimCounter(const Counter &counter) const = 0;
+	// Clears and disables all counters
+	virtual void resetCounters() = 0;
+	// Enables and prepares the counter for capture
+	virtual void setupCounter(Counter &counter) = 0;
+
+	// Performs any actions needed for setup or based on eventsXML
+	virtual void readEvents(mxml_node_t *const) {}
+	// Emits available counters
+	virtual int writeCounters(mxml_node_t *const root) const = 0;
+	// Emits possible dynamically generated events/counters
+	virtual void writeEvents(mxml_node_t *const) const {}
+
+	Driver *getNext() const { return next; }
+
+protected:
+	Driver();
+
+private:
+	static Driver *head;
+	Driver *next;
+
+	// Intentionally unimplemented
+	Driver(const Driver &);
+	Driver &operator=(const Driver &);
+};
+
+class SimpleDriver : public Driver {
+public:
+	virtual ~SimpleDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	bool countersEnabled() const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+	int writeCounters(mxml_node_t *root) const;
+
+protected:
+	SimpleDriver() : mCounters(NULL) {}
+
+	DriverCounter *getCounters() const { return mCounters; }
+	void setCounters(DriverCounter *const counter) { mCounters = counter; }
+
+	DriverCounter *findCounter(const Counter &counter) const;
+
+private:
+	DriverCounter *mCounters;
+
+	// Intentionally unimplemented
+	SimpleDriver(const SimpleDriver &);
+	SimpleDriver &operator=(const SimpleDriver &);
+};
+
+class PolledDriver : public SimpleDriver {
+public:
+	virtual ~PolledDriver();
+
+	virtual void start() {}
+	virtual void read(Buffer *const buffer);
+
+protected:
+	PolledDriver() {}
+
+private:
+	// Intentionally unimplemented
+	PolledDriver(const PolledDriver &);
+	PolledDriver &operator=(const PolledDriver &);
+};
+
+#endif // DRIVER_H
diff --git a/tools/gator/daemon/DriverSource.cpp b/tools/gator/daemon/DriverSource.cpp
new file mode 100644
index 000000000000..7f299b646952
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.cpp
@@ -0,0 +1,322 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DriverSource.h"
+
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Child.h"
+#include "DynBuf.h"
+#include "Fifo.h"
+#include "Logging.h"
+#include "Proc.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+DriverSource::DriverSource(sem_t *senderSem, sem_t *startProfile) : mBuffer(NULL), mFifo(NULL), mSenderSem(senderSem), mStartProfile(startProfile), mBufferSize(0), mBufferFD(0), mLength(1) {
+	int driver_version = 0;
+
+	mBuffer = new Buffer(0, FRAME_PERF_ATTRS, 4*1024*1024, senderSem);
+	if (readIntDriver("/dev/gator/version", &driver_version) == -1) {
+		logg->logError(__FILE__, __LINE__, "Error reading gator driver version");
+		handleException();
+	}
+
+	// Verify the driver version matches the daemon version
+	if (driver_version != PROTOCOL_VERSION) {
+		if ((driver_version > PROTOCOL_DEV) || (PROTOCOL_VERSION > PROTOCOL_DEV)) {
+			// One of the mismatched versions is development version
+			logg->logError(__FILE__, __LINE__,
+				"DEVELOPMENT BUILD MISMATCH: gator driver version \"%d\" is not in sync with gator daemon version \"%d\".\n"
+				">> The following must be synchronized from engineering repository:\n"
+				">> * gator driver\n"
+				">> * gator daemon\n"
+				">> * Streamline", driver_version, PROTOCOL_VERSION);
+			handleException();
+		} else {
+			// Release version mismatch
+			logg->logError(__FILE__, __LINE__,
+				"gator driver version \"%d\" is different than gator daemon version \"%d\".\n"
+				">> Please upgrade the driver and daemon to the latest versions.", driver_version, PROTOCOL_VERSION);
+			handleException();
+		}
+	}
+
+	int enable = -1;
+	if (readIntDriver("/dev/gator/enable", &enable) != 0 || enable != 0) {
+		logg->logError(__FILE__, __LINE__, "Driver already enabled, possibly a session is already in progress.");
+		handleException();
+	}
+
+	readIntDriver("/dev/gator/cpu_cores", &gSessionData->mCores);
+	if (gSessionData->mCores == 0) {
+		gSessionData->mCores = 1;
+	}
+
+	if (readIntDriver("/dev/gator/buffer_size", &mBufferSize) || mBufferSize <= 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to read the driver buffer size");
+		handleException();
+	}
+}
+
+DriverSource::~DriverSource() {
+	delete mFifo;
+
+	// Write zero for safety, as a zero should have already been written
+	writeDriver("/dev/gator/enable", "0");
+
+	// Calls event_buffer_release in the driver
+	if (mBufferFD) {
+		close(mBufferFD);
+	}
+}
+
+bool DriverSource::prepare() {
+	// Create user-space buffers, add 5 to the size to account for the 1-byte type and 4-byte length
+	logg->logMessage("Created %d MB collector buffer with a %d-byte ragged end", gSessionData->mTotalBufferSize, mBufferSize);
+	mFifo = new Fifo(mBufferSize + 5, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+	return true;
+}
+
+void DriverSource::bootstrapThread() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	DynBuf printb;
+	DynBuf b1;
+	DynBuf b2;
+	const uint64_t currTime = getTime();
+
+	if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+		logg->logError(__FILE__, __LINE__, "readProcComms failed");
+		handleException();
+	}
+
+	mBuffer->commit(currTime);
+	mBuffer->setDone();
+}
+
+void *DriverSource::bootstrapThreadStatic(void *arg) {
+	static_cast<DriverSource *>(arg)->bootstrapThread();
+	return NULL;
+}
+
+void DriverSource::run() {
+	// Get the initial pointer to the collect buffer
+	char *collectBuffer = mFifo->start();
+	int bytesCollected = 0;
+
+	logg->logMessage("********** Profiling started **********");
+
+	// Set the maximum backtrace depth
+	if (writeReadDriver("/dev/gator/backtrace_depth", &gSessionData->mBacktraceDepth)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver backtrace depth");
+		handleException();
+	}
+
+	// open the buffer which calls userspace_buffer_open() in the driver
+	mBufferFD = open("/dev/gator/buffer", O_RDONLY | O_CLOEXEC);
+	if (mBufferFD < 0) {
+		logg->logError(__FILE__, __LINE__, "The gator driver did not set up properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	// set the tick rate of the profiling timer
+	if (writeReadDriver("/dev/gator/tick", &gSessionData->mSampleRate) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver tick");
+		handleException();
+	}
+
+	// notify the kernel of the response type
+	int response_type = gSessionData->mLocalCapture ? 0 : RESPONSE_APC_DATA;
+	if (writeDriver("/dev/gator/response_type", response_type)) {
+		logg->logError(__FILE__, __LINE__, "Unable to write the response type");
+		handleException();
+	}
+
+	// Set the live rate
+	if (writeReadDriver("/dev/gator/live_rate", &gSessionData->mLiveRate)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver live rate");
+		handleException();
+	}
+
+	logg->logMessage("Start the driver");
+
+	// This command makes the driver start profiling by calling gator_op_start() in the driver
+	if (writeDriver("/dev/gator/enable", "1") != 0) {
+		logg->logError(__FILE__, __LINE__, "The gator driver did not start properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	lseek(mBufferFD, 0, SEEK_SET);
+
+	sem_post(mStartProfile);
+
+	pthread_t bootstrapThreadID;
+	if (pthread_create(&bootstrapThreadID, NULL, bootstrapThreadStatic, this) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to start the gator_bootstrap thread");
+		handleException();
+	}
+
+	// Collect Data
+	do {
+		// This command will stall until data is received from the driver
+		// Calls event_buffer_read in the driver
+		errno = 0;
+		bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+
+		// If read() returned due to an interrupt signal, re-read to obtain the last bit of collected data
+		if (bytesCollected == -1 && errno == EINTR) {
+			bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+		}
+
+		// return the total bytes written
+		logg->logMessage("Driver read of %d bytes", bytesCollected);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			if (bytesCollected == -1 || mFifo->willFill(bytesCollected)) {
+				logg->logMessage("One shot");
+				child->endSession();
+			}
+		}
+		collectBuffer = mFifo->write(bytesCollected);
+	} while (bytesCollected > 0);
+
+	logg->logMessage("Exit collect data loop");
+
+	pthread_join(bootstrapThreadID, NULL);
+}
+
+void DriverSource::interrupt() {
+	// This command should cause the read() function in collect() to return and stop the driver from profiling
+	if (writeDriver("/dev/gator/enable", "0") != 0) {
+		logg->logMessage("Stopping kernel failed");
+	}
+}
+
+bool DriverSource::isDone() {
+	return mLength <= 0 && (mBuffer == NULL || mBuffer->isDone());
+}
+
+void DriverSource::write(Sender *sender) {
+	char *data = mFifo->read(&mLength);
+	if (data != NULL) {
+		sender->writeData(data, mLength, RESPONSE_APC_DATA);
+		mFifo->release();
+		// Assume the summary packet is in the first block received from the driver
+		gSessionData->mSentSummary = true;
+	}
+	if (mBuffer != NULL && !mBuffer->isDone()) {
+		mBuffer->write(sender);
+		if (mBuffer->isDone()) {
+			Buffer *buf = mBuffer;
+			mBuffer = NULL;
+			delete buf;
+		}
+	}
+}
+
+int DriverSource::readIntDriver(const char *fullpath, int *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtol(data, &endptr, 10);
+	if (errno != 0 || *endptr != '\n') {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtoll(data, &endptr, 10);
+	if (errno != 0 || (*endptr != '\n' && *endptr != '\0')) {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *fullpath, const char *data) {
+	int fd = open(fullpath, O_WRONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+	if (::write(fd, data, strlen(data)) < 0) {
+		close(fd);
+		logg->logMessage("Opened but could not write to %s", fullpath);
+		return -1;
+	}
+	close(fd);
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *path, int value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%d", value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeDriver(const char *path, int64_t value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%" PRIi64, value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeReadDriver(const char *path, int *value) {
+	if (writeDriver(path, *value) || readIntDriver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
+
+int DriverSource::writeReadDriver(const char *path, int64_t *value) {
+	if (writeDriver(path, *value) || readInt64Driver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/gator/daemon/DriverSource.h b/tools/gator/daemon/DriverSource.h
new file mode 100644
index 000000000000..ec27b0815bbf
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVERSOURCE_H
+#define DRIVERSOURCE_H
+
+#include <semaphore.h>
+#include <stdint.h>
+
+#include "Source.h"
+
+class Buffer;
+class Fifo;
+
+class DriverSource : public Source {
+public:
+	DriverSource(sem_t *senderSem, sem_t *startProfile);
+	~DriverSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+	static int readIntDriver(const char *fullpath, int *value);
+	static int readInt64Driver(const char *fullpath, int64_t *value);
+	static int writeDriver(const char *fullpath, const char *data);
+	static int writeDriver(const char *path, int value);
+	static int writeDriver(const char *path, int64_t value);
+	static int writeReadDriver(const char *path, int *value);
+	static int writeReadDriver(const char *path, int64_t *value);
+
+private:
+	static void *bootstrapThreadStatic(void *arg);
+	void bootstrapThread();
+
+	Buffer *mBuffer;
+	Fifo *mFifo;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mBufferSize;
+	int mBufferFD;
+	int mLength;
+
+	// Intentionally unimplemented
+	DriverSource(const DriverSource &);
+	DriverSource &operator=(const DriverSource &);
+};
+
+#endif // DRIVERSOURCE_H
diff --git a/tools/gator/daemon/DynBuf.cpp b/tools/gator/daemon/DynBuf.cpp
new file mode 100644
index 000000000000..df20713ad63c
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.cpp
@@ -0,0 +1,139 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "DynBuf.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+// Pick an aggressive size as buffer is primarily used for disk IO
+#define MIN_BUFFER_FREE (1 << 12)
+
+int DynBuf::resize(const size_t minCapacity) {
+	size_t scaledCapacity = 2 * capacity;
+	if (scaledCapacity < minCapacity) {
+		scaledCapacity = minCapacity;
+	}
+	if (scaledCapacity < 2 * MIN_BUFFER_FREE) {
+		scaledCapacity = 2 * MIN_BUFFER_FREE;
+	}
+	capacity = scaledCapacity;
+
+	buf = static_cast<char *>(realloc(buf, capacity));
+	if (buf == NULL) {
+		return -errno;
+	}
+
+	return 0;
+}
+
+bool DynBuf::read(const char *const path) {
+	int result = false;
+
+	const int fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	length = 0;
+
+	for (;;) {
+		const size_t minCapacity = length + MIN_BUFFER_FREE + 1;
+		if (capacity < minCapacity) {
+			if (resize(minCapacity) != 0) {
+				logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+		}
+
+		const ssize_t bytes = ::read(fd, buf + length, capacity - length - 1);
+		if (bytes < 0) {
+			logg->logMessage("%s(%s:%i): read failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		} else if (bytes == 0) {
+			break;
+		}
+		length += bytes;
+	}
+
+	buf[length] = '\0';
+	result = true;
+
+ fail:
+	close(fd);
+
+	return result;
+}
+
+int DynBuf::readlink(const char *const path) {
+	ssize_t bytes = MIN_BUFFER_FREE;
+
+	for (;;) {
+		if (static_cast<size_t>(bytes) >= capacity) {
+			const int err = resize(2 * bytes);
+			if (err != 0) {
+				return err;
+			}
+		}
+		bytes = ::readlink(path, buf, capacity);
+		if (bytes < 0) {
+			return -errno;
+		} else if (static_cast<size_t>(bytes) < capacity) {
+			break;
+		}
+	}
+
+	length = bytes;
+	buf[bytes] = '\0';
+
+	return 0;
+}
+
+bool DynBuf::printf(const char *format, ...) {
+	va_list ap;
+
+	if (capacity <= 0) {
+		if (resize(2 * MIN_BUFFER_FREE) != 0) {
+			logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	va_start(ap, format);
+	int bytes = vsnprintf(buf, capacity, format, ap);
+	va_end(ap);
+	if (bytes < 0) {
+		logg->logMessage("%s(%s:%i): fsnprintf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (static_cast<size_t>(bytes) > capacity) {
+		if (resize(bytes + 1) != 0) {
+			logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		va_start(ap, format);
+		bytes = vsnprintf(buf, capacity, format, ap);
+		va_end(ap);
+		if (bytes < 0) {
+			logg->logMessage("%s(%s:%i): fsnprintf failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	length = bytes;
+
+	return true;
+}
diff --git a/tools/gator/daemon/DynBuf.h b/tools/gator/daemon/DynBuf.h
new file mode 100644
index 000000000000..2f4554ab2e49
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.h
@@ -0,0 +1,52 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DYNBUF_H
+#define DYNBUF_H
+
+#include <stdlib.h>
+
+class DynBuf {
+public:
+	DynBuf() : capacity(0), length(0), buf(NULL) {}
+	~DynBuf() {
+		reset();
+	}
+
+	inline void reset() {
+		capacity = 0;
+		length = 0;
+		if (buf != NULL) {
+			free(buf);
+			buf = NULL;
+		}
+	}
+
+	bool read(const char *const path);
+	// On error instead of printing the error and returning false, this returns -errno
+	int readlink(const char *const path);
+	__attribute__ ((format(printf, 2, 3)))
+	bool printf(const char *format, ...);
+
+	size_t getLength() const { return length; }
+	const char *getBuf() const { return buf; }
+	char *getBuf() { return buf; }
+
+private:
+	int resize(const size_t minCapacity);
+
+	size_t capacity;
+	size_t length;
+	char *buf;
+
+	// Intentionally undefined
+	DynBuf(const DynBuf &);
+	DynBuf &operator=(const DynBuf &);
+};
+
+#endif // DYNBUF_H
diff --git a/tools/gator/daemon/EventsXML.cpp b/tools/gator/daemon/EventsXML.cpp
new file mode 100644
index 000000000000..d905bbabe988
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.cpp
@@ -0,0 +1,76 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "EventsXML.h"
+
+#include "CapturedXML.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+mxml_node_t *EventsXML::getTree() {
+#include "events_xml.h" // defines and initializes char events_xml[] and int events_xml_len
+	char path[PATH_MAX];
+	mxml_node_t *xml;
+	FILE *fl;
+
+	// Avoid unused variable warning
+	(void)events_xml_len;
+
+	// Load the provided or default events xml
+	if (gSessionData->mEventsXMLPath) {
+		strncpy(path, gSessionData->mEventsXMLPath, PATH_MAX);
+	} else {
+		util->getApplicationFullPath(path, PATH_MAX);
+		strncat(path, "events.xml", PATH_MAX - strlen(path) - 1);
+	}
+	fl = fopen(path, "r");
+	if (fl) {
+		xml = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+		fclose(fl);
+	} else {
+		logg->logMessage("Unable to locate events.xml, using default");
+		xml = mxmlLoadString(NULL, (const char *)events_xml, MXML_NO_CALLBACK);
+	}
+
+	return xml;
+}
+
+char *EventsXML::getXML() {
+	mxml_node_t *xml = getTree();
+
+	// Add dynamic events from the drivers
+	mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+	if (!events) {
+		logg->logError(__FILE__, __LINE__, "Unable to find <events> node in the events.xml");
+		handleException();
+	}
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->writeEvents(events);
+	}
+
+	char *string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+
+	return string;
+}
+
+void EventsXML::write(const char *path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/events.xml", path);
+
+	char *buf = getXML();
+	if (util->writeToDisk(file, buf) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(buf);
+}
diff --git a/tools/gator/daemon/EventsXML.h b/tools/gator/daemon/EventsXML.h
new file mode 100644
index 000000000000..ff7a02fd3c78
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EVENTS_XML
+#define EVENTS_XML
+
+#include "mxml/mxml.h"
+
+class EventsXML {
+public:
+	mxml_node_t *getTree();
+	char *getXML();
+	void write(const char* path);
+};
+
+#endif // EVENTS_XML
diff --git a/tools/gator/daemon/ExternalSource.cpp b/tools/gator/daemon/ExternalSource.cpp
new file mode 100644
index 000000000000..8f5e6b684c53
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.cpp
@@ -0,0 +1,260 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ExternalSource.h"
+
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+static const char MALI_VIDEO[] = "\0mali-video";
+static const char MALI_VIDEO_STARTUP[] = "\0mali-video-startup";
+static const char MALI_VIDEO_V1[] = "MALI_VIDEO 1\n";
+static const char MALI_GRAPHICS[] = "\0mali_thirdparty_server";
+static const char MALI_GRAPHICS_STARTUP[] = "\0mali_thirdparty_client";
+static const char MALI_GRAPHICS_V1[] = "MALI_GRAPHICS 1\n";
+
+static bool setNonblock(const int fd) {
+	int flags;
+
+	flags = fcntl(fd, F_GETFL);
+	if (flags < 0) {
+		logg->logMessage("fcntl getfl failed");
+		return false;
+	}
+
+	if (fcntl(fd, F_SETFL, flags | O_NONBLOCK) != 0) {
+		logg->logMessage("fcntl setfl failed");
+		return false;
+	}
+
+	return true;
+}
+
+ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mMaliStartupUds(MALI_GRAPHICS_STARTUP, sizeof(MALI_GRAPHICS_STARTUP)), mAnnotate(8083), mInterruptFd(-1), mMaliUds(-1), mMveUds(-1) {
+	sem_init(&mBufferSem, 0, 0);
+}
+
+ExternalSource::~ExternalSource() {
+}
+
+void ExternalSource::waitFor(const int bytes) {
+	while (mBuffer.bytesAvailable() <= bytes) {
+		sem_wait(&mBufferSem);
+	}
+}
+
+void ExternalSource::configureConnection(const int fd, const char *const handshake, size_t size) {
+	if (!setNonblock(fd)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set nonblock on fh");
+		handleException();
+	}
+
+	if (!mMonitor.add(fd)) {
+		logg->logError(__FILE__, __LINE__, "Unable to add fh to monitor");
+		handleException();
+	}
+
+	// Write the handshake to the circular buffer
+	waitFor(Buffer::MAXSIZE_PACK32 + size - 1);
+	mBuffer.packInt(fd);
+	mBuffer.writeBytes(handshake, size - 1);
+	mBuffer.commit(1);
+}
+
+bool ExternalSource::connectMali() {
+	mMaliUds = OlySocket::connect(MALI_GRAPHICS, sizeof(MALI_GRAPHICS));
+	if (mMaliUds < 0) {
+		return false;
+	}
+
+	configureConnection(mMaliUds, MALI_GRAPHICS_V1, sizeof(MALI_GRAPHICS_V1));
+
+	return true;
+}
+
+bool ExternalSource::connectMve() {
+	if (!gSessionData->maliVideo.countersEnabled()) {
+		return true;
+	}
+
+	mMveUds = OlySocket::connect(MALI_VIDEO, sizeof(MALI_VIDEO));
+	if (mMveUds < 0) {
+		return false;
+	}
+
+	if (!gSessionData->maliVideo.start(mMveUds)) {
+		return false;
+	}
+
+	configureConnection(mMveUds, MALI_VIDEO_V1, sizeof(MALI_VIDEO_V1));
+
+	return true;
+}
+
+bool ExternalSource::prepare() {
+	if (!mMonitor.init() ||
+			!setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd()) ||
+			!setNonblock(mMaliStartupUds.getFd()) || !mMonitor.add(mMaliStartupUds.getFd()) ||
+			!setNonblock(mAnnotate.getFd()) || !mMonitor.add(mAnnotate.getFd()) ||
+			false) {
+		return false;
+	}
+
+	connectMali();
+	connectMve();
+
+	return true;
+}
+
+void ExternalSource::run() {
+	int pipefd[2];
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-external", 0, 0, 0);
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError(__FILE__, __LINE__, "Monitor::add failed");
+		handleException();
+	}
+
+	// Notify annotate clients to retry connecting to gatord
+	gSessionData->annotateListener.signal();
+
+	while (gSessionData->mSessionIsActive) {
+		struct epoll_event events[16];
+		// Clear any pending sem posts
+		while (sem_trywait(&mBufferSem) == 0);
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), -1);
+		if (ready < 0) {
+			logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+			handleException();
+		}
+
+		const uint64_t currTime = getTime();
+
+		for (int i = 0; i < ready; ++i) {
+			const int fd = events[i].data.fd;
+			if (fd == mMveStartupUds.getFd()) {
+				// Mali Video Engine says it's alive
+				int client = mMveStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali-V500
+				close(client);
+				if (!connectMve()) {
+					logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali video connection");
+					handleException();
+				}
+			} else if (fd == mMaliStartupUds.getFd()) {
+				// Mali Graphics says it's alive
+				int client = mMaliStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali Graphics
+				close(client);
+				if (!connectMali()) {
+					logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali graphics connection");
+					handleException();
+				}
+			} else if (fd == mAnnotate.getFd()) {
+				int client = mAnnotate.acceptConnection();
+				if (!setNonblock(client) || !mMonitor.add(client)) {
+					logg->logError(__FILE__, __LINE__, "Unable to set socket options on incoming annotation connection");
+					handleException();
+				}
+			} else if (fd == pipefd[0]) {
+				// Means interrupt has been called and mSessionIsActive should be reread
+			} else {
+				/* This can result in some starvation if there are multiple
+				 * threads which are annotating heavily, but it is not
+				 * recommended that threads annotate that much as it can also
+				 * starve out the gator data.
+				 */
+				while (gSessionData->mSessionIsActive) {
+					// Wait until there is enough room for the fd, two headers and two ints
+					waitFor(7*Buffer::MAXSIZE_PACK32 + 2*sizeof(uint32_t));
+					mBuffer.packInt(fd);
+					const int contiguous = mBuffer.contiguousSpaceAvailable();
+					const int bytes = read(fd, mBuffer.getWritePos(), contiguous);
+					if (bytes < 0) {
+						if (errno == EAGAIN) {
+							// Nothing left to read
+							mBuffer.commit(currTime);
+							break;
+						}
+						// Something else failed, close the socket
+						mBuffer.commit(currTime);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						mBuffer.commit(currTime);
+						close(fd);
+						break;
+					} else if (bytes == 0) {
+						// The other side is closed
+						mBuffer.commit(currTime);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						mBuffer.commit(currTime);
+						close(fd);
+						break;
+					}
+
+					mBuffer.advanceWrite(bytes);
+					mBuffer.commit(currTime);
+
+					// Short reads also mean nothing is left to read
+					if (bytes < contiguous) {
+						break;
+					}
+				}
+			}
+		}
+	}
+
+	mBuffer.setDone();
+
+	if (mMveUds >= 0) {
+		gSessionData->maliVideo.stop(mMveUds);
+	}
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+void ExternalSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError(__FILE__, __LINE__, "write failed");
+			handleException();
+		}
+	}
+}
+
+bool ExternalSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void ExternalSource::write(Sender *sender) {
+	// Don't send external data until the summary packet is sent so that monotonic delta is available
+	if (!gSessionData->mSentSummary) {
+		return;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+		sem_post(&mBufferSem);
+	}
+}
diff --git a/tools/gator/daemon/ExternalSource.h b/tools/gator/daemon/ExternalSource.h
new file mode 100644
index 000000000000..919e75e8a41a
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.h
@@ -0,0 +1,53 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXTERNALSOURCE_H
+#define EXTERNALSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "Source.h"
+
+// Counters from external sources like graphics drivers and annotations
+class ExternalSource : public Source {
+public:
+	ExternalSource(sem_t *senderSem);
+	~ExternalSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	void waitFor(const int bytes);
+	void configureConnection(const int fd, const char *const handshake, size_t size);
+	bool connectMali();
+	bool connectMve();
+
+	sem_t mBufferSem;
+	Buffer mBuffer;
+	Monitor mMonitor;
+	OlyServerSocket mMveStartupUds;
+	OlyServerSocket mMaliStartupUds;
+	OlyServerSocket mAnnotate;
+	int mInterruptFd;
+	int mMaliUds;
+	int mMveUds;
+
+	// Intentionally unimplemented
+	ExternalSource(const ExternalSource &);
+	ExternalSource &operator=(const ExternalSource &);
+};
+
+#endif // EXTERNALSOURCE_H
diff --git a/tools/gator/daemon/FSDriver.cpp b/tools/gator/daemon/FSDriver.cpp
new file mode 100644
index 000000000000..dd8eb804dc99
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FSDriver.h"
+
+#include <fcntl.h>
+#include <regex.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+
+class FSCounter : public DriverCounter {
+public:
+	FSCounter(DriverCounter *next, char *name, char *path, const char *regex);
+	~FSCounter();
+
+	const char *getPath() const { return mPath; }
+
+	int64_t read();
+
+private:
+	char *const mPath;
+	regex_t mReg;
+	bool mUseRegex;
+
+	// Intentionally unimplemented
+	FSCounter(const FSCounter &);
+	FSCounter &operator=(const FSCounter &);
+};
+
+FSCounter::FSCounter(DriverCounter *next, char *name, char *path, const char *regex) : DriverCounter(next, name), mPath(path), mUseRegex(regex != NULL) {
+	if (mUseRegex) {
+		int result = regcomp(&mReg, regex, REG_EXTENDED);
+		if (result != 0) {
+			char buf[128];
+			regerror(result, &mReg, buf, sizeof(buf));
+			logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf);
+			handleException();
+		}
+	}
+}
+
+FSCounter::~FSCounter() {
+	free(mPath);
+	if (mUseRegex) {
+		regfree(&mReg);
+	}
+}
+
+int64_t FSCounter::read() {
+	int64_t value;
+	if (mUseRegex) {
+		char buf[4096];
+		size_t pos = 0;
+		const int fd = open(mPath, O_RDONLY | O_CLOEXEC);
+		if (fd < 0) {
+			goto fail;
+		}
+		while (pos < sizeof(buf) - 1) {
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				goto fail;
+			} else if (bytes == 0) {
+				break;
+			}
+			pos += bytes;
+		}
+		close(fd);
+		buf[pos] = '\0';
+
+		regmatch_t match[2];
+		int result = regexec(&mReg, buf, 2, match, 0);
+		if (result != 0) {
+			regerror(result, &mReg, buf, sizeof(buf));
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, buf);
+			handleException();
+		}
+
+		if (match[1].rm_so < 0) {
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed", mPath);
+			handleException();
+		}
+
+		errno = 0;
+		value = strtoll(buf + match[1].rm_so, NULL, 0);
+		if (errno != 0) {
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, strerror(errno));
+			handleException();
+		}
+	} else {
+		if (DriverSource::readInt64Driver(mPath, &value) != 0) {
+			goto fail;
+		}
+	}
+	return value;
+
+ fail:
+	logg->logError(__FILE__, __LINE__, "Unable to read %s", mPath);
+	handleException();
+}
+
+FSDriver::FSDriver() {
+}
+
+FSDriver::~FSDriver() {
+}
+
+void FSDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (counter[0] == '/') {
+			logg->logError(__FILE__, __LINE__, "Old style filesystem counter (%s) detected, please create a new unique counter value and move the filename into the path attribute, see events-Filesystem.xml for examples", counter);
+			handleException();
+		}
+
+		if (strncmp(counter, "filesystem_", 11) != 0) {
+			continue;
+		}
+
+		const char *path = mxmlElementGetAttr(node, "path");
+		if (path == NULL) {
+			logg->logError(__FILE__, __LINE__, "The filesystem counter %s is missing the required path attribute", counter);
+			handleException();
+		}
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		setCounters(new FSCounter(getCounters(), strdup(counter), strdup(path), regex));
+	}
+}
+
+int FSDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (FSCounter *counter = static_cast<FSCounter *>(getCounters()); counter != NULL; counter = static_cast<FSCounter *>(counter->getNext())) {
+		if (access(counter->getPath(), R_OK) == 0) {
+			mxml_node_t *node = mxmlNewElement(root, "counter");
+			mxmlElementSetAttr(node, "name", counter->getName());
+			++count;
+		}
+	}
+
+	return count;
+}
diff --git a/tools/gator/daemon/FSDriver.h b/tools/gator/daemon/FSDriver.h
new file mode 100644
index 000000000000..a7dc8b4df9dd
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.h
@@ -0,0 +1,29 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FSDRIVER_H
+#define FSDRIVER_H
+
+#include "Driver.h"
+
+class FSDriver : public PolledDriver {
+public:
+	FSDriver();
+	~FSDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	int writeCounters(mxml_node_t *root) const;
+
+private:
+	// Intentionally unimplemented
+	FSDriver(const FSDriver &);
+	FSDriver &operator=(const FSDriver &);
+};
+
+#endif // FSDRIVER_H
diff --git a/tools/gator/daemon/Fifo.cpp b/tools/gator/daemon/Fifo.cpp
new file mode 100644
index 000000000000..41275fd287b8
--- /dev/null
+++ b/tools/gator/daemon/Fifo.cpp
@@ -0,0 +1,127 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Fifo.h"
+
+#include <stdlib.h>
+
+#include "Logging.h"
+
+// bufferSize is the amount of data to be filled
+// singleBufferSize is the maximum size that may be filled during a single write
+// (bufferSize + singleBufferSize) will be allocated
+Fifo::Fifo(int singleBufferSize, int bufferSize, sem_t* readerSem) {
+  mWrite = mRead = mReadCommit = mRaggedEnd = 0;
+  mWrapThreshold = bufferSize;
+  mSingleBufferSize = singleBufferSize;
+  mReaderSem = readerSem;
+  mBuffer = (char*)malloc(bufferSize + singleBufferSize);
+  mEnd = false;
+
+  if (mBuffer == NULL) {
+    logg->logError(__FILE__, __LINE__, "failed to allocate %d bytes", bufferSize + singleBufferSize);
+    handleException();
+  }
+
+  if (sem_init(&mWaitForSpaceSem, 0, 0)) {
+    logg->logError(__FILE__, __LINE__, "sem_init() failed");
+    handleException();
+  }
+}
+
+Fifo::~Fifo() {
+  free(mBuffer);
+  sem_destroy(&mWaitForSpaceSem);
+}
+
+int Fifo::numBytesFilled() const {
+  return mWrite - mRead + mRaggedEnd;
+}
+
+char* Fifo::start() const {
+  return mBuffer;
+}
+
+bool Fifo::isEmpty() const {
+  return mRead == mWrite && mRaggedEnd == 0;
+}
+
+bool Fifo::isFull() const {
+  return willFill(0);
+}
+
+// Determines if the buffer will fill assuming 'additional' bytes will be added to the buffer
+// 'full' means there is less than singleBufferSize bytes available contiguously; it does not mean there are zero bytes available
+bool Fifo::willFill(int additional) const {
+  if (mWrite > mRead) {
+    if (numBytesFilled() + additional < mWrapThreshold) {
+      return false;
+    }
+  } else {
+    if (numBytesFilled() + additional < mWrapThreshold - mSingleBufferSize) {
+      return false;
+    }
+  }
+  return true;
+}
+
+// This function will stall until contiguous singleBufferSize bytes are available
+char* Fifo::write(int length) {
+  if (length <= 0) {
+    length = 0;
+    mEnd = true;
+  }
+
+  // update the write pointer
+  mWrite += length;
+
+  // handle the wrap-around
+  if (mWrite >= mWrapThreshold) {
+    mRaggedEnd = mWrite;
+    mWrite = 0;
+  }
+
+  // send a notification that data is ready
+  sem_post(mReaderSem);
+
+  // wait for space
+  while (isFull()) {
+    sem_wait(&mWaitForSpaceSem);
+  }
+
+  return &mBuffer[mWrite];
+}
+
+void Fifo::release() {
+  // update the read pointer now that the data has been handled
+  mRead = mReadCommit;
+
+  // handle the wrap-around
+  if (mRead >= mWrapThreshold) {
+    mRaggedEnd = mRead = mReadCommit = 0;
+  }
+
+  // send a notification that data is free (space is available)
+  sem_post(&mWaitForSpaceSem);
+}
+
+// This function will return null if no data is available
+char* Fifo::read(int *const length) {
+  // wait for data
+  if (isEmpty() && !mEnd) {
+    return NULL;
+  }
+
+  // obtain the length
+  do {
+    mReadCommit = mRaggedEnd ? mRaggedEnd : mWrite;
+    *length = mReadCommit - mRead;
+  } while (*length < 0); // plugs race condition without using semaphores
+
+  return &mBuffer[mRead];
+}
diff --git a/tools/gator/daemon/Fifo.h b/tools/gator/daemon/Fifo.h
new file mode 100644
index 000000000000..21c8d8580391
--- /dev/null
+++ b/tools/gator/daemon/Fifo.h
@@ -0,0 +1,48 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __FIFO_H__
+#define __FIFO_H__
+
+#ifdef WIN32
+#include <windows.h>
+#define sem_t HANDLE
+#define sem_init(sem, pshared, value) ((*(sem) = CreateSemaphore(NULL, value, LONG_MAX, NULL)) == NULL)
+#define sem_wait(sem) WaitForSingleObject(*(sem), INFINITE)
+#define sem_post(sem) ReleaseSemaphore(*(sem), 1, NULL)
+#define sem_destroy(sem) CloseHandle(*(sem))
+#else
+#include <semaphore.h>
+#endif
+
+class Fifo {
+public:
+  Fifo(int singleBufferSize, int totalBufferSize, sem_t* readerSem);
+  ~Fifo();
+  int numBytesFilled() const;
+  bool isEmpty() const;
+  bool isFull() const;
+  bool willFill(int additional) const;
+  char* start() const;
+  char* write(int length);
+  void release();
+  char* read(int *const length);
+
+private:
+  int mSingleBufferSize, mWrite, mRead, mReadCommit, mRaggedEnd, mWrapThreshold;
+  sem_t mWaitForSpaceSem;
+  sem_t* mReaderSem;
+  char* mBuffer;
+  bool mEnd;
+
+  // Intentionally unimplemented
+  Fifo(const Fifo &);
+  Fifo &operator=(const Fifo &);
+};
+
+#endif //__FIFO_H__
diff --git a/tools/gator/daemon/FtraceDriver.cpp b/tools/gator/daemon/FtraceDriver.cpp
new file mode 100644
index 000000000000..b156f1c0b8b4
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.cpp
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceDriver.h"
+
+#include <regex.h>
+
+#include "Logging.h"
+
+class FtraceCounter : public DriverCounter {
+public:
+	FtraceCounter(DriverCounter *next, char *name, const char *regex);
+	~FtraceCounter();
+
+	int read(const char *const line, int64_t *values);
+
+private:
+	regex_t reg;
+
+	// Intentionally unimplemented
+	FtraceCounter(const FtraceCounter &);
+	FtraceCounter &operator=(const FtraceCounter &);
+};
+
+FtraceCounter::FtraceCounter(DriverCounter *next, char *name, const char *regex) : DriverCounter(next, name) {
+	int result = regcomp(&reg, regex, REG_EXTENDED);
+	if (result != 0) {
+		char buf[128];
+		regerror(result, &reg, buf, sizeof(buf));
+		logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf);
+		handleException();
+	}
+}
+
+FtraceCounter::~FtraceCounter() {
+	regfree(&reg);
+}
+
+int FtraceCounter::read(const char *const line, int64_t *values) {
+	regmatch_t match[2];
+	int result = regexec(&reg, line, 2, match, 0);
+	if (result != 0) {
+		// No match
+		return 0;
+	}
+
+	if (match[1].rm_so < 0) {
+		logg->logError(__FILE__, __LINE__, "Parsing %s failed", getName());
+		handleException();
+	}
+
+	errno = 0;
+	int64_t value = strtoll(line + match[1].rm_so, NULL, 0);
+	if (errno != 0) {
+		logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", getName(), strerror(errno));
+		handleException();
+	}
+
+	values[0] = getKey();
+	values[1] = value;
+
+	return 1;
+}
+
+FtraceDriver::FtraceDriver() : mValues(NULL) {
+}
+
+FtraceDriver::~FtraceDriver() {
+	delete [] mValues;
+}
+
+void FtraceDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	int count = 0;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (strncmp(counter, "ftrace_", 7) != 0) {
+			continue;
+		}
+
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		if (regex == NULL) {
+			logg->logError(__FILE__, __LINE__, "The regex counter %s is missing the required regex attribute", counter);
+			handleException();
+		}
+		setCounters(new FtraceCounter(getCounters(), strdup(counter), regex));
+		++count;
+	}
+
+	mValues = new int64_t[2*count];
+}
+
+int FtraceDriver::read(const char *line, int64_t **buf) {
+	int count = 0;
+
+	for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		count += counter->read(line, mValues + 2*count);
+	}
+
+	*buf = mValues;
+	return count;
+}
diff --git a/tools/gator/daemon/FtraceDriver.h b/tools/gator/daemon/FtraceDriver.h
new file mode 100644
index 000000000000..5f958bec672c
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACEDRIVER_H
+#define FTRACEDRIVER_H
+
+#include "Driver.h"
+
+class FtraceDriver : public SimpleDriver {
+public:
+	FtraceDriver();
+	~FtraceDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	int read(const char *line, int64_t **buf);
+
+private:
+	int64_t *mValues;
+
+	// Intentionally unimplemented
+	FtraceDriver(const FtraceDriver &);
+	FtraceDriver &operator=(const FtraceDriver &);
+};
+
+#endif // FTRACEDRIVER_H
diff --git a/tools/gator/daemon/FtraceSource.cpp b/tools/gator/daemon/FtraceSource.cpp
new file mode 100644
index 000000000000..521633357417
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceSource.h"
+
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+static void handler(int signum)
+{
+	(void)signum;
+};
+
+FtraceSource::FtraceSource(sem_t *senderSem) : mFtraceFh(NULL), mBuffer(0, FRAME_BLOCK_COUNTER, 128*1024, senderSem), mTid(-1), mTracingOn(0) {
+}
+
+FtraceSource::~FtraceSource() {
+}
+
+bool FtraceSource::prepare() {
+	{
+		struct sigaction act;
+		act.sa_handler = handler;
+		act.sa_flags = (int)SA_RESETHAND;
+		if (sigaction(SIGUSR1, &act, NULL) != 0) {
+			logg->logError(__FILE__, __LINE__, "sigaction failed: %s\n", strerror(errno));
+			handleException();
+		}
+	}
+
+	if (DriverSource::readIntDriver("/sys/kernel/debug/tracing/tracing_on", &mTracingOn)) {
+		logg->logError(__FILE__, __LINE__, "Unable to read if ftrace is enabled");
+		handleException();
+	}
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "0") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to turn ftrace off before truncating the buffer");
+		handleException();
+	}
+
+	{
+		int fd;
+		fd = open("/sys/kernel/debug/tracing/trace", O_WRONLY | O_TRUNC | O_CLOEXEC, 0666);
+		if (fd < 0) {
+			logg->logError(__FILE__, __LINE__, "Unable truncate ftrace buffer: %s", strerror(errno));
+			handleException();
+		}
+		close(fd);
+	}
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "perf") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to switch ftrace to the perf clock, please ensure you are running Linux 3.10 or later");
+		handleException();
+	}
+
+	mFtraceFh = fopen_cloexec("/sys/kernel/debug/tracing/trace_pipe", "rb");
+	if (mFtraceFh == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to open trace_pipe");
+		handleException();
+	}
+
+	return true;
+}
+
+void FtraceSource::run() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-ftrace", 0, 0, 0);
+	mTid = syscall(__NR_gettid);
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "1") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to turn ftrace on");
+		handleException();
+	}
+
+	while (gSessionData->mSessionIsActive) {
+		char buf[1<<12];
+
+		if (fgets(buf, sizeof(buf), mFtraceFh) == NULL) {
+			if (errno == EINTR) {
+				// Interrupted by interrupt - likely user request to terminate
+				break;
+			}
+			logg->logError(__FILE__, __LINE__, "Unable read trace data: %s", strerror(errno));
+			handleException();
+		}
+
+		const uint64_t currTime = getTime();
+
+		char *const colon = strstr(buf, ": ");
+		if (colon == NULL) {
+			logg->logError(__FILE__, __LINE__, "Unable find colon: %s", buf);
+			handleException();
+		}
+		*colon = '\0';
+
+		char *const space = strrchr(buf, ' ');
+		if (space == NULL) {
+			logg->logError(__FILE__, __LINE__, "Unable find space: %s", buf);
+			handleException();
+		}
+		*colon = ':';
+
+		int64_t *data = NULL;
+		int count = gSessionData->ftraceDriver.read(colon + 2, &data);
+		if (count > 0) {
+			errno = 0;
+			const long long time = strtod(space, NULL) * 1000000000;
+			if (errno != 0) {
+				logg->logError(__FILE__, __LINE__, "Unable to parse time: %s", strerror(errno));
+				handleException();
+			}
+			mBuffer.event64(-1, time);
+
+			for (int i = 0; i < count; ++i) {
+				mBuffer.event64(data[2*i + 0], data[2*i + 1]);
+			}
+
+			mBuffer.check(currTime);
+		}
+
+	}
+
+	mBuffer.setDone();
+
+	DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", mTracingOn);
+	fclose(mFtraceFh);
+	DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "local");
+}
+
+void FtraceSource::interrupt() {
+	// Closing the underlying file handle does not result in the read on the ftrace file handle to return, so send a signal to the thread
+	syscall(__NR_tgkill, getpid(), mTid, SIGUSR1);
+}
+
+bool FtraceSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void FtraceSource::write(Sender *sender) {
+	// Don't send ftrace data until the summary packet is sent so that monotonic delta is available
+	if (!gSessionData->mSentSummary) {
+		return;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+}
diff --git a/tools/gator/daemon/FtraceSource.h b/tools/gator/daemon/FtraceSource.h
new file mode 100644
index 000000000000..2391b881494e
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACESOURCE_H
+#define FTRACESOURCE_H
+
+#include <semaphore.h>
+#include <stdio.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+class FtraceSource : public Source {
+public:
+	FtraceSource(sem_t *senderSem);
+	~FtraceSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	void waitFor(const int bytes);
+
+	FILE *mFtraceFh;
+	Buffer mBuffer;
+	int mTid;
+	int mTracingOn;
+
+	// Intentionally unimplemented
+	FtraceSource(const FtraceSource &);
+	FtraceSource &operator=(const FtraceSource &);
+};
+
+#endif // FTRACESOURCE_H
diff --git a/tools/gator/daemon/HwmonDriver.cpp b/tools/gator/daemon/HwmonDriver.cpp
new file mode 100644
index 000000000000..9d161ae5ac56
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.cpp
@@ -0,0 +1,245 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "HwmonDriver.h"
+
+#include "libsensors/sensors.h"
+
+#include "Logging.h"
+
+// feature->type to input map
+static sensors_subfeature_type getInput(const sensors_feature_type type) {
+	switch (type) {
+	case SENSORS_FEATURE_IN: return SENSORS_SUBFEATURE_IN_INPUT;
+	case SENSORS_FEATURE_FAN: return SENSORS_SUBFEATURE_FAN_INPUT;
+	case SENSORS_FEATURE_TEMP: return SENSORS_SUBFEATURE_TEMP_INPUT;
+	case SENSORS_FEATURE_POWER: return SENSORS_SUBFEATURE_POWER_INPUT;
+	case SENSORS_FEATURE_ENERGY: return SENSORS_SUBFEATURE_ENERGY_INPUT;
+	case SENSORS_FEATURE_CURR: return SENSORS_SUBFEATURE_CURR_INPUT;
+	case SENSORS_FEATURE_HUMIDITY: return SENSORS_SUBFEATURE_HUMIDITY_INPUT;
+	default:
+		logg->logError(__FILE__, __LINE__, "Unsupported hwmon feature %i", type);
+		handleException();
+	}
+};
+
+class HwmonCounter : public DriverCounter {
+public:
+	HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature);
+	~HwmonCounter();
+
+	const char *getLabel() const { return label; }
+	const char *getTitle() const { return title; }
+	bool isDuplicate() const { return duplicate; }
+	const char *getDisplay() const { return display; }
+	const char *getCounterClass() const { return counter_class; }
+	const char *getUnit() const { return unit; }
+	int getModifier() const { return modifier; }
+
+	int64_t read();
+
+private:
+	void init(const sensors_chip_name *chip, const sensors_feature *feature);
+
+	const sensors_chip_name *chip;
+	const sensors_feature *feature;
+	char *label;
+	const char *title;
+	const char *display;
+	const char *counter_class;
+	const char *unit;
+	double previous_value;
+	int modifier;
+	int monotonic: 1,
+		duplicate : 1;
+
+	// Intentionally unimplemented
+	HwmonCounter(const HwmonCounter &);
+	HwmonCounter &operator=(const HwmonCounter &);
+};
+
+HwmonCounter::HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature) : DriverCounter(next, name), chip(chip), feature(feature), duplicate(false) {
+	label = sensors_get_label(chip, feature);
+
+	switch (feature->type) {
+	case SENSORS_FEATURE_IN:
+		title = "Voltage";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "V";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_FAN:
+		title = "Fan";
+		display = "average";
+		counter_class = "absolute";
+		unit = "RPM";
+		modifier = 1;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_TEMP:
+		title = "Temperature";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "°C";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_POWER:
+		title = "Power";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "W";
+		modifier = 1000000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_ENERGY:
+		title = "Energy";
+		display = "accumulate";
+		counter_class = "delta";
+		unit = "J";
+		modifier = 1000000;
+		monotonic = true;
+		break;
+	case SENSORS_FEATURE_CURR:
+		title = "Current";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "A";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_HUMIDITY:
+		title = "Humidity";
+		display = "average";
+		counter_class = "absolute";
+		unit = "%";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	default:
+		logg->logError(__FILE__, __LINE__, "Unsupported hwmon feature %i", feature->type);
+		handleException();
+	}
+
+	for (HwmonCounter * counter = static_cast<HwmonCounter *>(next); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		if (strcmp(label, counter->getLabel()) == 0 && strcmp(title, counter->getTitle()) == 0) {
+			duplicate = true;
+			counter->duplicate = true;
+			break;
+		}
+	}
+}
+
+HwmonCounter::~HwmonCounter() {
+	free((void *)label);
+}
+
+int64_t HwmonCounter::read() {
+	double value;
+	double result;
+	const sensors_subfeature *subfeature;
+
+	// Keep in sync with the read check in HwmonDriver::readEvents
+	subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+	if (!subfeature) {
+		logg->logError(__FILE__, __LINE__, "No input value for hwmon sensor %s", label);
+		handleException();
+	}
+
+	if (sensors_get_value(chip, subfeature->number, &value) != 0) {
+		logg->logError(__FILE__, __LINE__, "Can't get input value for hwmon sensor %s", label);
+		handleException();
+	}
+
+	result = (monotonic ? value - previous_value : value);
+	previous_value = value;
+
+	return result;
+}
+
+HwmonDriver::HwmonDriver() {
+}
+
+HwmonDriver::~HwmonDriver() {
+	sensors_cleanup();
+}
+
+void HwmonDriver::readEvents(mxml_node_t *const) {
+	int err = sensors_init(NULL);
+	if (err) {
+		logg->logMessage("Failed to initialize libsensors! (%d)", err);
+		return;
+	}
+	sensors_sysfs_no_scaling = 1;
+
+	int chip_nr = 0;
+	const sensors_chip_name *chip;
+	while ((chip = sensors_get_detected_chips(NULL, &chip_nr))) {
+		int feature_nr = 0;
+		const sensors_feature *feature;
+		while ((feature = sensors_get_features(chip, &feature_nr))) {
+			// Keep in sync with HwmonCounter::read
+			// Can this counter be read?
+			double value;
+			const sensors_subfeature *const subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+			if ((subfeature == NULL) || (sensors_get_value(chip, subfeature->number, &value) != 0)) {
+				continue;
+			}
+
+			// Get the name of the counter
+			int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1;
+			char *chip_name = new char[len];
+			sensors_snprintf_chip_name(chip_name, len, chip);
+			len = snprintf(NULL, 0, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number) + 1;
+			char *const name = new char[len];
+			snprintf(name, len, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number);
+			delete [] chip_name;
+
+			setCounters(new HwmonCounter(getCounters(), name, chip, feature));
+		}
+	}
+}
+
+void HwmonDriver::writeEvents(mxml_node_t *root) const {
+	root = mxmlNewElement(root, "category");
+	mxmlElementSetAttr(root, "name", "hwmon");
+
+	char buf[1024];
+	for (HwmonCounter *counter = static_cast<HwmonCounter *>(getCounters()); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		mxml_node_t *node = mxmlNewElement(root, "event");
+		mxmlElementSetAttr(node, "counter", counter->getName());
+		mxmlElementSetAttr(node, "title", counter->getTitle());
+		if (counter->isDuplicate()) {
+			mxmlElementSetAttrf(node, "name", "%s (0x%x)", counter->getLabel(), counter->getKey());
+		} else {
+			mxmlElementSetAttr(node, "name", counter->getLabel());
+		}
+		mxmlElementSetAttr(node, "display", counter->getDisplay());
+		mxmlElementSetAttr(node, "class", counter->getCounterClass());
+		mxmlElementSetAttr(node, "units", counter->getUnit());
+		if (counter->getModifier() != 1) {
+			mxmlElementSetAttrf(node, "modifier", "%d", counter->getModifier());
+		}
+		if (strcmp(counter->getDisplay(), "average") == 0 || strcmp(counter->getDisplay(), "maximum") == 0) {
+			mxmlElementSetAttr(node, "average_selection", "yes");
+		}
+		snprintf(buf, sizeof(buf), "libsensors %s sensor %s (%s)", counter->getTitle(), counter->getLabel(), counter->getName());
+		mxmlElementSetAttr(node, "description", buf);
+	}
+}
+
+void HwmonDriver::start() {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
diff --git a/tools/gator/daemon/HwmonDriver.h b/tools/gator/daemon/HwmonDriver.h
new file mode 100644
index 000000000000..f28d825e3b7b
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef HWMONDRIVER_H
+#define HWMONDRIVER_H
+
+#include "Driver.h"
+
+class HwmonDriver : public PolledDriver {
+public:
+	HwmonDriver();
+	~HwmonDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	void writeEvents(mxml_node_t *root) const;
+
+	void start();
+
+private:
+	// Intentionally unimplemented
+	HwmonDriver(const HwmonDriver &);
+	HwmonDriver &operator=(const HwmonDriver &);
+};
+
+#endif // HWMONDRIVER_H
diff --git a/tools/gator/daemon/KMod.cpp b/tools/gator/daemon/KMod.cpp
new file mode 100644
index 000000000000..fe9dc6a7e4f7
--- /dev/null
+++ b/tools/gator/daemon/KMod.cpp
@@ -0,0 +1,119 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "KMod.h"
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <unistd.h>
+
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// Claim all the counters in /dev/gator/events
+bool KMod::claimCounter(const Counter &counter) const {
+	char text[128];
+	snprintf(text, sizeof(text), "/dev/gator/events/%s", counter.getType());
+	return access(text, F_OK) == 0;
+}
+
+void KMod::resetCounters() {
+	char base[128];
+	char text[128];
+
+	// Initialize all perf counters in the driver, i.e. set enabled to zero
+	struct dirent *ent;
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir) {
+		while ((ent = readdir(dir)) != NULL) {
+			// skip hidden files, current dir, and parent dir
+			if (ent->d_name[0] == '.')
+				continue;
+			snprintf(base, sizeof(base), "/dev/gator/events/%s", ent->d_name);
+			snprintf(text, sizeof(text), "%s/enabled", base);
+			DriverSource::writeDriver(text, 0);
+			snprintf(text, sizeof(text), "%s/count", base);
+			DriverSource::writeDriver(text, 0);
+		}
+		closedir(dir);
+	}
+}
+
+static const char ARM_MALI_MIDGARD[] = "ARM_Mali-Midgard_";
+static const char ARM_MALI_T[] = "ARM_Mali-T";
+
+void KMod::setupCounter(Counter &counter) {
+	char base[128];
+	char text[128];
+	snprintf(base, sizeof(base), "/dev/gator/events/%s", counter.getType());
+
+	if ((strncmp(counter.getType(), ARM_MALI_MIDGARD, sizeof(ARM_MALI_MIDGARD) - 1) == 0 ||
+	     strncmp(counter.getType(), ARM_MALI_T, sizeof(ARM_MALI_T) - 1) == 0)) {
+		mIsMaliCapture = true;
+	}
+
+	snprintf(text, sizeof(text), "%s/enabled", base);
+	int enabled = true;
+	if (DriverSource::writeReadDriver(text, &enabled) || !enabled) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	int value = 0;
+	snprintf(text, sizeof(text), "%s/key", base);
+	DriverSource::readIntDriver(text, &value);
+	counter.setKey(value);
+
+	snprintf(text, sizeof(text), "%s/cores", base);
+	if (DriverSource::readIntDriver(text, &value) == 0) {
+		counter.setCores(value);
+	}
+
+	snprintf(text, sizeof(text), "%s/event", base);
+	DriverSource::writeDriver(text, counter.getEvent());
+	snprintf(text, sizeof(text), "%s/count", base);
+	if (access(text, F_OK) == 0) {
+		int count = counter.getCount();
+		if (DriverSource::writeReadDriver(text, &count) && counter.getCount() > 0) {
+			logg->logError(__FILE__, __LINE__, "Cannot enable EBS for %s:%i with a count of %d\n", counter.getType(), counter.getEvent(), counter.getCount());
+			handleException();
+		}
+		counter.setCount(count);
+	} else if (counter.getCount() > 0) {
+		ConfigurationXML::remove();
+		logg->logError(__FILE__, __LINE__, "Event Based Sampling is only supported with kernel versions 3.0.0 and higher with CONFIG_PERF_EVENTS=y, and CONFIG_HW_PERF_EVENTS=y. The invalid configuration.xml has been removed.\n");
+		handleException();
+	}
+}
+
+int KMod::writeCounters(mxml_node_t *root) const {
+	struct dirent *ent;
+	mxml_node_t *counter;
+
+	// counters.xml is simply a file listing of /dev/gator/events
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir == NULL) {
+		return 0;
+	}
+
+	int count = 0;
+	while ((ent = readdir(dir)) != NULL) {
+		// skip hidden files, current dir, and parent dir
+		if (ent->d_name[0] == '.')
+			continue;
+		counter = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(counter, "name", ent->d_name);
+		++count;
+	}
+	closedir(dir);
+
+	return count;
+}
diff --git a/tools/gator/daemon/KMod.h b/tools/gator/daemon/KMod.h
new file mode 100644
index 000000000000..900a60e87d24
--- /dev/null
+++ b/tools/gator/daemon/KMod.h
@@ -0,0 +1,32 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KMOD_H
+#define KMOD_H
+
+#include "Driver.h"
+
+// Driver for the gator kernel module
+class KMod : public Driver {
+public:
+	KMod() : mIsMaliCapture(false) {}
+	~KMod() {}
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	int writeCounters(mxml_node_t *root) const;
+
+	bool isMaliCapture() const { return mIsMaliCapture; }
+
+private:
+	bool mIsMaliCapture;
+};
+
+#endif // KMOD_H
diff --git a/tools/gator/daemon/LocalCapture.cpp b/tools/gator/daemon/LocalCapture.cpp
new file mode 100644
index 000000000000..d2a4b799d7ac
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.cpp
@@ -0,0 +1,131 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "LocalCapture.h"
+
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "EventsXML.h"
+
+LocalCapture::LocalCapture() {}
+
+LocalCapture::~LocalCapture() {}
+
+void LocalCapture::createAPCDirectory(char* target_path) {
+	gSessionData->mAPCDir = createUniqueDirectory(target_path, ".apc");
+	if ((removeDirAndAllContents(gSessionData->mAPCDir) != 0 || mkdir(gSessionData->mAPCDir, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH) != 0)) {
+		logg->logError(__FILE__, __LINE__, "Unable to create directory %s", gSessionData->mAPCDir);
+		handleException();
+	}
+}
+
+void LocalCapture::write(char* string) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/session.xml", gSessionData->mAPCDir);
+
+	// Write the file
+	if (util->writeToDisk(file, string) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	// Write events XML
+	EventsXML eventsXML;
+	eventsXML.write(gSessionData->mAPCDir);
+}
+
+char* LocalCapture::createUniqueDirectory(const char* initialPath, const char* ending) {
+	char* output;
+	char path[PATH_MAX];
+
+	// Ensure the path is an absolute path, i.e. starts with a slash
+	if (initialPath == 0 || strlen(initialPath) == 0) {
+		logg->logError(__FILE__, __LINE__, "Missing -o command line option required for a local capture.");
+		handleException();
+	} else if (initialPath[0] != '/') {
+		if (getcwd(path, PATH_MAX) == 0) {
+			logg->logMessage("Unable to retrieve the current working directory");
+		}
+		strncat(path, "/", PATH_MAX - strlen(path) - 1);
+		strncat(path, initialPath, PATH_MAX - strlen(path) - 1);
+	} else {
+		strncpy(path, initialPath, PATH_MAX);
+		path[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+
+	// Add ending if it is not already there
+	if (strcmp(&path[strlen(path) - strlen(ending)], ending) != 0) {
+		strncat(path, ending, PATH_MAX - strlen(path) - 1);
+	}
+
+	output = strdup(path);
+
+	return output;
+}
+
+int LocalCapture::removeDirAndAllContents(char* path) {
+	int error = 0;
+	struct stat mFileInfo;
+	// Does the path exist?
+	if (stat(path, &mFileInfo) == 0) {
+		// Is it a directory?
+		if (mFileInfo.st_mode & S_IFDIR) {
+			DIR * dir = opendir(path);
+			dirent* entry = readdir(dir);
+			while (entry) {
+				if (strcmp(entry->d_name, ".") != 0 && strcmp(entry->d_name, "..") != 0) {
+					char* newpath = (char*)malloc(strlen(path) + strlen(entry->d_name) + 2);
+					sprintf(newpath, "%s/%s", path, entry->d_name);
+					error = removeDirAndAllContents(newpath);
+					free(newpath);
+					if (error) {
+						break;
+					}
+				}
+				entry = readdir(dir);
+			}
+			closedir(dir);
+			if (error == 0) {
+				error = rmdir(path);
+			}
+		} else {
+			error = remove(path);
+		}
+	}
+	return error;
+}
+
+void LocalCapture::copyImages(ImageLinkList* ptr) {
+	char dstfilename[PATH_MAX];
+
+	while (ptr) {
+		strncpy(dstfilename, gSessionData->mAPCDir, PATH_MAX);
+		dstfilename[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+		if (gSessionData->mAPCDir[strlen(gSessionData->mAPCDir) - 1] != '/') {
+			strncat(dstfilename, "/", PATH_MAX - strlen(dstfilename) - 1);
+		}
+		strncat(dstfilename, util->getFilePart(ptr->path), PATH_MAX - strlen(dstfilename) - 1);
+		if (util->copyFile(ptr->path, dstfilename)) {
+			logg->logMessage("copied file %s to %s", ptr->path, dstfilename);
+		} else {
+			logg->logMessage("copy of file %s to %s failed", ptr->path, dstfilename);
+		}
+
+		ptr = ptr->next;
+	}
+}
diff --git a/tools/gator/daemon/LocalCapture.h b/tools/gator/daemon/LocalCapture.h
new file mode 100644
index 000000000000..25d281f8328b
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOCAL_CAPTURE_H__
+#define __LOCAL_CAPTURE_H__
+
+struct ImageLinkList;
+
+class LocalCapture {
+public:
+	LocalCapture();
+	~LocalCapture();
+	void write(char* string);
+	void copyImages(ImageLinkList* ptr);
+	void createAPCDirectory(char* target_path);
+private:
+	char* createUniqueDirectory(const char* path, const char* ending);
+	int removeDirAndAllContents(char* path);
+};
+
+#endif //__LOCAL_CAPTURE_H__
diff --git a/tools/gator/daemon/Logging.cpp b/tools/gator/daemon/Logging.cpp
new file mode 100644
index 000000000000..41ffa1a45151
--- /dev/null
+++ b/tools/gator/daemon/Logging.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Logging.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+#ifdef WIN32
+#define MUTEX_INIT()    mLoggingMutex = CreateMutex(NULL, false, NULL);
+#define MUTEX_LOCK()    WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF);
+#define MUTEX_UNLOCK()  ReleaseMutex(mLoggingMutex);
+#define snprintf _snprintf
+#else
+#include <pthread.h>
+#define MUTEX_INIT()    pthread_mutex_init(&mLoggingMutex, NULL)
+#define MUTEX_LOCK()    pthread_mutex_lock(&mLoggingMutex)
+#define MUTEX_UNLOCK()  pthread_mutex_unlock(&mLoggingMutex)
+#endif
+
+// Global thread-safe logging
+Logging* logg = NULL;
+
+Logging::Logging(bool debug) {
+	mDebug = debug;
+	MUTEX_INIT();
+
+	strcpy(mErrBuf, "Unknown Error");
+	strcpy(mLogBuf, "Unknown Message");
+}
+
+Logging::~Logging() {
+}
+
+void Logging::logError(const char* file, int line, const char* fmt, ...) {
+	va_list args;
+
+	MUTEX_LOCK();
+	if (mDebug) {
+		snprintf(mErrBuf, sizeof(mErrBuf), "ERROR[%s:%d]: ", file, line);
+	} else {
+		mErrBuf[0] = 0;
+	}
+
+	va_start(args, fmt);
+	vsnprintf(mErrBuf + strlen(mErrBuf), sizeof(mErrBuf) - 2 - strlen(mErrBuf), fmt, args); //  subtract 2 for \n and \0
+	va_end(args);
+
+	if (strlen(mErrBuf) > 0) {
+		strcat(mErrBuf, "\n");
+	}
+	MUTEX_UNLOCK();
+}
+
+void Logging::logMessage(const char* fmt, ...) {
+	if (mDebug) {
+		va_list args;
+
+		MUTEX_LOCK();
+		strcpy(mLogBuf, "INFO: ");
+
+		va_start(args, fmt);
+		vsnprintf(mLogBuf + strlen(mLogBuf), sizeof(mLogBuf) - 2 - strlen(mLogBuf), fmt, args); //  subtract 2 for \n and \0
+		va_end(args);
+		strcat(mLogBuf, "\n");
+
+		fprintf(stdout, "%s", mLogBuf);
+		fflush(stdout);
+		MUTEX_UNLOCK();
+	}
+}
diff --git a/tools/gator/daemon/Logging.h b/tools/gator/daemon/Logging.h
new file mode 100644
index 000000000000..09e93ff13f7a
--- /dev/null
+++ b/tools/gator/daemon/Logging.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOGGING_H__
+#define __LOGGING_H__
+
+#include <pthread.h>
+
+#define DRIVER_ERROR "\n Driver issue:\n  >> gator.ko must be built against the current kernel version & configuration\n  >> gator.ko should be co-located with gatord in the same directory\n  >>   OR insmod gator.ko prior to launching gatord"
+
+class Logging {
+public:
+	Logging(bool debug);
+	~Logging();
+	void logError(const char* file, int line, const char* fmt, ...);
+	void logMessage(const char* fmt, ...);
+	char* getLastError() {return mErrBuf;}
+	char* getLastMessage() {return mLogBuf;}
+
+private:
+	char mErrBuf[4096]; // Arbitrarily large buffer to hold a string
+	char mLogBuf[4096]; // Arbitrarily large buffer to hold a string
+	bool mDebug;
+	pthread_mutex_t mLoggingMutex;
+};
+
+extern Logging* logg;
+
+extern void handleException() __attribute__ ((noreturn));
+
+#endif //__LOGGING_H__
diff --git a/tools/gator/daemon/Makefile b/tools/gator/daemon/Makefile
new file mode 100644
index 000000000000..27531b438b63
--- /dev/null
+++ b/tools/gator/daemon/Makefile
@@ -0,0 +1,22 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/arm-linux-gnueabihf-
+# NOTE: This toolchain uses the hardfloat abi by default. For non-hardfloat
+# targets run 'make SOFTFLOAT=1 SYSROOT=/path/to/sysroot', see
+# README_Streamline.txt for more details
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+ifeq ($(SOFTFLOAT),1)
+	CPPFLAGS += -marm -mthumb-interwork -march=armv4t -mfloat-abi=soft
+	LDFLAGS += -marm -march=armv4t -mfloat-abi=soft
+endif
+ifneq ($(SYSROOT),)
+	LDFLAGS += --sysroot=$(SYSROOT)
+endif
+
+include common.mk
diff --git a/tools/gator/daemon/Makefile_aarch64 b/tools/gator/daemon/Makefile_aarch64
new file mode 100644
index 000000000000..efd1fa002182
--- /dev/null
+++ b/tools/gator/daemon/Makefile_aarch64
@@ -0,0 +1,12 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+# make -f Makefile_aarch64
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/aarch64-linux-gnu-
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+include common.mk
diff --git a/tools/gator/daemon/MaliVideoDriver.cpp b/tools/gator/daemon/MaliVideoDriver.cpp
new file mode 100644
index 000000000000..5eef2643ab15
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.cpp
@@ -0,0 +1,191 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MaliVideoDriver.h"
+
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Counter.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// From instr/src/mve_instr_comm_protocol.h
+typedef enum mve_instr_configuration_type {
+	MVE_INSTR_RAW         = 1 << 0,
+	MVE_INSTR_COUNTERS    = 1 << 1,
+	MVE_INSTR_EVENTS      = 1 << 2,
+	MVE_INSTR_ACTIVITIES  = 1 << 3,
+
+	// Raw always pushed regardless
+	MVE_INSTR_PULL        = 1 << 12,
+	// Raw always unpacked regardless
+	MVE_INSTR_PACKED_COMM = 1 << 13,
+	// Don’t send ACKt response
+	MVE_INSTR_NO_AUTO_ACK   = 1 << 14,
+} mve_instr_configuration_type_t;
+
+static const char COUNTER[] = "ARM_Mali-V500_cnt";
+static const char EVENT[] = "ARM_Mali-V500_evn";
+static const char ACTIVITY[] = "ARM_Mali-V500_act";
+
+class MaliVideoCounter : public DriverCounter {
+public:
+	MaliVideoCounter(DriverCounter *next, const char *name, const MaliVideoCounterType type, const int id) : DriverCounter(next, name), mType(type), mId(id) {
+	}
+
+	~MaliVideoCounter() {
+	}
+
+	MaliVideoCounterType getType() const { return mType; }
+	int getId() const { return mId; }
+
+private:
+	const MaliVideoCounterType mType;
+	// Mali Video id
+	const int mId;
+};
+
+MaliVideoDriver::MaliVideoDriver() {
+}
+
+MaliVideoDriver::~MaliVideoDriver() {
+}
+
+void MaliVideoDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			// Ignore
+		} else if (strncmp(counter, COUNTER, sizeof(COUNTER) - 1) == 0) {
+			const int i = strtol(counter + sizeof(COUNTER) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_COUNTER, i));
+		} else if (strncmp(counter, EVENT, sizeof(EVENT) - 1) == 0) {
+			const int i = strtol(counter + sizeof(EVENT) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_EVENT, i));
+		} else if (strncmp(counter, ACTIVITY, sizeof(ACTIVITY) - 1) == 0) {
+			const int i = strtol(counter + sizeof(ACTIVITY) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_ACTIVITY, i));
+		}
+	}
+}
+
+int MaliVideoDriver::writeCounters(mxml_node_t *root) const {
+	if (access("/dev/mv500", F_OK) != 0) {
+		return 0;
+	}
+
+	return super::writeCounters(root);
+}
+
+void MaliVideoDriver::marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos) {
+	// size
+	int numEnabled = 0;
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			++numEnabled;
+		}
+	}
+	Buffer::packInt(buf, bufsize, pos, numEnabled*sizeof(uint32_t));
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			Buffer::packInt(buf, bufsize, pos, counter->getId());
+		}
+	}
+}
+
+static bool writeAll(const int mveUds, const char *const buf, const int pos) {
+	int written = 0;
+	while (written < pos) {
+		size_t bytes = ::write(mveUds, buf + written, pos - written);
+		if (bytes <= 0) {
+			logg->logMessage("%s(%s:%i): write failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		written += bytes;
+	}
+
+	return true;
+}
+
+bool MaliVideoDriver::start(const int mveUds) {
+	char buf[256];
+	int pos = 0;
+
+	// code - MVE_INSTR_STARTUP
+	buf[pos++] = 'C';
+	buf[pos++] = 'L';
+	buf[pos++] = 'N';
+	buf[pos++] = 'T';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, sizeof(uint32_t));
+	// client_version_number
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+
+	// code - MVE_INSTR_CONFIGURE
+	buf[pos++] = 'C';
+	buf[pos++] = 'N';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, 5*sizeof(uint32_t));
+	// configuration
+	Buffer::packInt(buf, sizeof(buf), pos, MVE_INSTR_COUNTERS | MVE_INSTR_EVENTS | MVE_INSTR_ACTIVITIES | MVE_INSTR_PACKED_COMM);
+	// communication_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// data_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// sample_rate - convert samples/second to ms/sample
+	Buffer::packInt(buf, sizeof(buf), pos, 1000/gSessionData->mSampleRate);
+	// live_rate - convert ns/flush to ms/flush
+	Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mLiveRate/1000000);
+
+	// code - MVE_INSTR_ENABLE_COUNTERS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'c';
+	marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_EVENTS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'e';
+	marshalEnable(MVCT_EVENT, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_ACTIVITIES
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'a';
+	marshalEnable(MVCT_ACTIVITY, buf, sizeof(buf), pos);
+
+	return writeAll(mveUds, buf, pos);
+}
+
+void MaliVideoDriver::stop(const int mveUds) {
+	char buf[8];
+	int pos = 0;
+
+	// code - MVE_INSTR_STOP
+	buf[pos++] = 'S';
+	buf[pos++] = 'T';
+	buf[pos++] = 'O';
+	buf[pos++] = 'P';
+	marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+	writeAll(mveUds, buf, pos);
+
+	close(mveUds);
+}
diff --git a/tools/gator/daemon/MaliVideoDriver.h b/tools/gator/daemon/MaliVideoDriver.h
new file mode 100644
index 000000000000..204a57a447ac
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.h
@@ -0,0 +1,45 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MALIVIDEODRIVER_H
+#define MALIVIDEODRIVER_H
+
+#include "Driver.h"
+
+class MaliVideoCounter;
+
+enum MaliVideoCounterType {
+	MVCT_COUNTER,
+	MVCT_EVENT,
+	MVCT_ACTIVITY,
+};
+
+class MaliVideoDriver : public SimpleDriver {
+private:
+	typedef SimpleDriver super;
+
+public:
+	MaliVideoDriver();
+	~MaliVideoDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	int writeCounters(mxml_node_t *root) const;
+
+	bool start(const int mveUds);
+	void stop(const int mveUds);
+
+private:
+	void marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos);
+
+	// Intentionally unimplemented
+	MaliVideoDriver(const MaliVideoDriver &);
+	MaliVideoDriver &operator=(const MaliVideoDriver &);
+};
+
+#endif // MALIVIDEODRIVER_H
diff --git a/tools/gator/daemon/MemInfoDriver.cpp b/tools/gator/daemon/MemInfoDriver.cpp
new file mode 100644
index 000000000000..cce15c16fcdc
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.cpp
@@ -0,0 +1,93 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MemInfoDriver.h"
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class MemInfoCounter : public DriverCounter {
+public:
+	MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~MemInfoCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+
+	// Intentionally unimplemented
+	MemInfoCounter(const MemInfoCounter &);
+	MemInfoCounter &operator=(const MemInfoCounter &);
+};
+
+MemInfoCounter::MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value) {
+}
+
+MemInfoCounter::~MemInfoCounter() {
+}
+
+int64_t MemInfoCounter::read() {
+	return *mValue;
+}
+
+MemInfoDriver::MemInfoDriver() : mBuf(), mMemUsed(0), mMemFree(0), mBuffers(0) {
+}
+
+MemInfoDriver::~MemInfoDriver() {
+}
+
+void MemInfoDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memused2"), &mMemUsed));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memfree"), &mMemFree));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_bufferram"), &mBuffers));
+}
+
+void MemInfoDriver::read(Buffer *const buffer) {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/meminfo")) {
+		logg->logError(__FILE__, __LINE__, "Failed to read /proc/meminfo");
+		handleException();
+	}
+
+	char *key = mBuf.getBuf();
+	char *colon;
+	int64_t memTotal = 0;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		if (strcmp(key, "MemTotal") == 0) {
+			memTotal = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "MemFree") == 0) {
+			mMemFree = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "Buffers") == 0) {
+			mBuffers = strtoll(colon + 1, NULL, 10) << 10;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	mMemUsed = memTotal - mMemFree;
+
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/MemInfoDriver.h b/tools/gator/daemon/MemInfoDriver.h
new file mode 100644
index 000000000000..eb1b0417f309
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.h
@@ -0,0 +1,37 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MEMINFODRIVER_H
+#define MEMINFODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class MemInfoDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	MemInfoDriver();
+	~MemInfoDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void read(Buffer *const buffer);
+
+private:
+	DynBuf mBuf;
+	int64_t mMemUsed;
+	int64_t mMemFree;
+	int64_t mBuffers;
+
+	// Intentionally unimplemented
+	MemInfoDriver(const MemInfoDriver &);
+	MemInfoDriver &operator=(const MemInfoDriver &);
+};
+
+#endif // MEMINFODRIVER_H
diff --git a/tools/gator/daemon/Monitor.cpp b/tools/gator/daemon/Monitor.cpp
new file mode 100644
index 000000000000..74f22ee29fec
--- /dev/null
+++ b/tools/gator/daemon/Monitor.cpp
@@ -0,0 +1,82 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Monitor.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+Monitor::Monitor() : mFd(-1) {
+}
+
+Monitor::~Monitor() {
+	if (mFd >= 0) {
+		::close(mFd);
+	}
+}
+
+void Monitor::close() {
+	if (mFd >= 0) {
+		::close(mFd);
+		mFd = -1;
+	}
+}
+
+bool Monitor::init() {
+#ifdef EPOLL_CLOEXEC
+	mFd = epoll_create1(EPOLL_CLOEXEC);
+#else
+	mFd = epoll_create(16);
+#endif
+	if (mFd < 0) {
+		logg->logMessage("%s(%s:%i): epoll_create1 failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+#ifndef EPOLL_CLOEXEC
+  int fdf = fcntl(mFd, F_GETFD);
+  if ((fdf == -1) || (fcntl(mFd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		logg->logMessage("%s(%s:%i): fcntl failed", __FUNCTION__, __FILE__, __LINE__);
+    ::close(mFd);
+    return -1;
+  }
+#endif
+
+	return true;
+}
+
+bool Monitor::add(const int fd) {
+	struct epoll_event event;
+	memset(&event, 0, sizeof(event));
+	event.data.fd = fd;
+	event.events = EPOLLIN;
+	if (epoll_ctl(mFd, EPOLL_CTL_ADD, fd, &event) != 0) {
+		logg->logMessage("%s(%s:%i): epoll_ctl failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+int Monitor::wait(struct epoll_event *const events, int maxevents, int timeout) {
+	int result = epoll_wait(mFd, events, maxevents, timeout);
+	if (result < 0) {
+		// Ignore if the call was interrupted as this will happen when SIGINT is received
+		if (errno == EINTR) {
+			result = 0;
+		} else {
+			logg->logMessage("%s(%s:%i): epoll_wait failed", __FUNCTION__, __FILE__, __LINE__);
+		}
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/Monitor.h b/tools/gator/daemon/Monitor.h
new file mode 100644
index 000000000000..7194e0e4ca50
--- /dev/null
+++ b/tools/gator/daemon/Monitor.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MONITOR_H
+#define MONITOR_H
+
+#include <sys/epoll.h>
+
+class Monitor {
+public:
+	Monitor();
+	~Monitor();
+
+	void close();
+	bool init();
+	bool add(const int fd);
+	int wait(struct epoll_event *const events, int maxevents, int timeout);
+
+private:
+
+	int mFd;
+
+	// Intentionally unimplemented
+	Monitor(const Monitor &);
+	Monitor &operator=(const Monitor &);
+};
+
+#endif // MONITOR_H
diff --git a/tools/gator/daemon/NetDriver.cpp b/tools/gator/daemon/NetDriver.cpp
new file mode 100644
index 000000000000..e75c0695779a
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "NetDriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class NetCounter : public DriverCounter {
+public:
+	NetCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~NetCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	NetCounter(const NetCounter &);
+	NetCounter &operator=(const NetCounter &);
+};
+
+NetCounter::NetCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+NetCounter::~NetCounter() {
+}
+
+int64_t NetCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	return result;
+}
+
+NetDriver::NetDriver() : mBuf(), mReceiveBytes(0), mTransmitBytes(0) {
+}
+
+NetDriver::~NetDriver() {
+}
+
+void NetDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_rx"), &mReceiveBytes));
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_tx"), &mTransmitBytes));
+}
+
+bool NetDriver::doRead() {
+	if (!countersEnabled()) {
+		return true;
+	}
+
+	if (!mBuf.read("/proc/net/dev")) {
+		return false;
+	}
+
+	// Skip the header
+	char *key;
+	if (((key = strchr(mBuf.getBuf(), '\n')) == NULL) ||
+			((key = strchr(key + 1, '\n')) == NULL)) {
+		return false;
+	}
+	key = key + 1;
+
+	mReceiveBytes = 0;
+	mTransmitBytes = 0;
+
+	char *colon;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		int64_t receiveBytes;
+		int64_t transmitBytes;
+		const int count = sscanf(colon + 1, " %" SCNu64 " %*u %*u %*u %*u %*u %*u %*u %" SCNu64, &receiveBytes, &transmitBytes);
+		if (count != 2) {
+			return false;
+		}
+		mReceiveBytes += receiveBytes;
+		mTransmitBytes += transmitBytes;
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	return true;
+}
+
+void NetDriver::start() {
+	if (!doRead()) {
+		logg->logError(__FILE__, __LINE__, "Unable to read network stats");
+		handleException();
+	}
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void NetDriver::read(Buffer *const buffer) {
+	if (!doRead()) {
+		logg->logError(__FILE__, __LINE__, "Unable to read network stats");
+		handleException();
+	}
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/NetDriver.h b/tools/gator/daemon/NetDriver.h
new file mode 100644
index 000000000000..50ff850bfc6d
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef NETDRIVER_H
+#define NETDRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class NetDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	NetDriver();
+	~NetDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	bool doRead();
+
+	DynBuf mBuf;
+	int64_t mReceiveBytes;
+	int64_t mTransmitBytes;
+
+	// Intentionally unimplemented
+	NetDriver(const NetDriver &);
+	NetDriver &operator=(const NetDriver &);
+};
+
+#endif // NETDRIVER_H
diff --git a/tools/gator/daemon/OlySocket.cpp b/tools/gator/daemon/OlySocket.cpp
new file mode 100644
index 000000000000..aa0ce4929916
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.cpp
@@ -0,0 +1,324 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlySocket.h"
+
+#include <stdio.h>
+#include <string.h>
+#ifdef WIN32
+#include <Winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <netinet/in.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <fcntl.h>
+#endif
+
+#include "Logging.h"
+
+#ifdef WIN32
+#define CLOSE_SOCKET(x) closesocket(x)
+#define SHUTDOWN_RX_TX SD_BOTH
+#define snprintf       _snprintf
+#else
+#define CLOSE_SOCKET(x) close(x)
+#define SHUTDOWN_RX_TX SHUT_RDWR
+#endif
+
+int socket_cloexec(int domain, int type, int protocol) {
+#ifdef SOCK_CLOEXEC
+  return socket(domain, type | SOCK_CLOEXEC, protocol);
+#else
+  int sock = socket(domain, type, protocol);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+#endif
+}
+
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen) {
+  int sock;
+#ifdef SOCK_CLOEXEC
+  sock = accept4(sockfd, addr, addrlen, SOCK_CLOEXEC);
+  if (sock >= 0) {
+    return sock;
+  }
+  // accept4 with SOCK_CLOEXEC may not work on all kernels, so fallback
+#endif
+  sock = accept(sockfd, addr, addrlen);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+}
+
+OlyServerSocket::OlyServerSocket(int port) {
+#ifdef WIN32
+  WSADATA wsaData;
+  if (WSAStartup(0x0202, &wsaData) != 0) {
+    logg->logError(__FILE__, __LINE__, "Windows socket initialization failed");
+    handleException();
+  }
+#endif
+
+  createServerSocket(port);
+}
+
+OlySocket::OlySocket(int socketID) : mSocketID(socketID) {
+}
+
+#ifndef WIN32
+
+#define MIN(A, B) ({ \
+  const __typeof__(A) __a = A; \
+  const __typeof__(B) __b = B; \
+  __a > __b ? __b : __a; \
+})
+
+OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize) {
+  // Create socket
+  mFDServer = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (mFDServer < 0) {
+    logg->logError(__FILE__, __LINE__, "Error creating server socket");
+    handleException();
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    logg->logError(__FILE__, __LINE__, "Binding of server socket failed.");
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError(__FILE__, __LINE__, "Listening of server socket failed");
+    handleException();
+  }
+}
+
+int OlySocket::connect(const char* path, const size_t pathSize) {
+  int fd = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (fd < 0) {
+    return -1;
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  if (::connect(fd, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    close(fd);
+    return -1;
+  }
+
+  return fd;
+}
+
+#endif
+
+OlySocket::~OlySocket() {
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+  }
+}
+
+OlyServerSocket::~OlyServerSocket() {
+  if (mFDServer > 0) {
+    CLOSE_SOCKET(mFDServer);
+  }
+}
+
+void OlySocket::shutdownConnection() {
+  // Shutdown is primarily used to unblock other threads that are blocking on send/receive functions
+  shutdown(mSocketID, SHUTDOWN_RX_TX);
+}
+
+void OlySocket::closeSocket() {
+  // Used for closing an accepted socket but keeping the server socket active
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+    mSocketID = -1;
+  }
+}
+
+void OlyServerSocket::closeServerSocket() {
+  if (CLOSE_SOCKET(mFDServer) != 0) {
+    logg->logError(__FILE__, __LINE__, "Failed to close server socket.");
+    handleException();
+  }
+  mFDServer = 0;
+}
+
+void OlyServerSocket::createServerSocket(int port) {
+  int family = AF_INET6;
+
+  // Create socket
+  mFDServer = socket_cloexec(PF_INET6, SOCK_STREAM, IPPROTO_TCP);
+  if (mFDServer < 0) {
+    family = AF_INET;
+    mFDServer = socket_cloexec(PF_INET, SOCK_STREAM, IPPROTO_TCP);
+    if (mFDServer < 0) {
+      logg->logError(__FILE__, __LINE__, "Error creating server socket");
+      handleException();
+    }
+  }
+
+  // Enable address reuse, another solution would be to create the server socket once and only close it when the object exits
+  int on = 1;
+  if (setsockopt(mFDServer, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+    logg->logError(__FILE__, __LINE__, "Setting server socket options failed");
+    handleException();
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_in6 sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sin6_family = family;
+  sockaddr.sin6_port = htons(port);
+  sockaddr.sin6_addr = in6addr_any;
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    logg->logError(__FILE__, __LINE__, "Binding of server socket failed.\nIs an instance already running?");
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError(__FILE__, __LINE__, "Listening of server socket failed");
+    handleException();
+  }
+}
+
+// mSocketID is always set to the most recently accepted connection
+// The user of this class should maintain the different socket connections, e.g. by forking the process
+int OlyServerSocket::acceptConnection() {
+  int socketID;
+  if (mFDServer <= 0) {
+    logg->logError(__FILE__, __LINE__, "Attempting multiple connections on a single connection server socket or attempting to accept on a client socket");
+    handleException();
+  }
+
+  // Accept a connection, note that this call blocks until a client connects
+  socketID = accept_cloexec(mFDServer, NULL, NULL);
+  if (socketID < 0) {
+    logg->logError(__FILE__, __LINE__, "Socket acceptance failed");
+    handleException();
+  }
+  return socketID;
+}
+
+void OlySocket::send(const char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return;
+  }
+
+  while (size > 0) {
+    int n = ::send(mSocketID, buffer, size, 0);
+    if (n < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket send error");
+      handleException();
+    }
+    size -= n;
+    buffer += n;
+  }
+}
+
+// Returns the number of bytes received
+int OlySocket::receive(char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return 0;
+  }
+
+  int bytes = recv(mSocketID, buffer, size, 0);
+  if (bytes < 0) {
+    logg->logError(__FILE__, __LINE__, "Socket receive error");
+    handleException();
+  } else if (bytes == 0) {
+    logg->logMessage("Socket disconnected");
+    return -1;
+  }
+  return bytes;
+}
+
+// Receive exactly size bytes of data. Note, this function will block until all bytes are received
+int OlySocket::receiveNBytes(char* buffer, int size) {
+  int bytes = 0;
+  while (size > 0 && buffer != NULL) {
+    bytes = recv(mSocketID, buffer, size, 0);
+    if (bytes < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+    buffer += bytes;
+    size -= bytes;
+  }
+  return bytes;
+}
+
+// Receive data until a carriage return, line feed, or null is encountered, or the buffer fills
+int OlySocket::receiveString(char* buffer, int size) {
+  int bytes_received = 0;
+  bool found = false;
+
+  if (buffer == 0) {
+    return 0;
+  }
+
+  while (!found && bytes_received < size) {
+    // Receive a single character
+    int bytes = recv(mSocketID, &buffer[bytes_received], 1, 0);
+    if (bytes < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+
+    // Replace carriage returns and line feeds with zero
+    if (buffer[bytes_received] == '\n' || buffer[bytes_received] == '\r' || buffer[bytes_received] == '\0') {
+      buffer[bytes_received] = '\0';
+      found = true;
+    }
+
+    bytes_received++;
+  }
+
+  return bytes_received;
+}
diff --git a/tools/gator/daemon/OlySocket.h b/tools/gator/daemon/OlySocket.h
new file mode 100644
index 000000000000..6b53b01fc3ee
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.h
@@ -0,0 +1,64 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __OLY_SOCKET_H__
+#define __OLY_SOCKET_H__
+
+#include <stddef.h>
+
+#ifdef WIN32
+typedef socklen_t int;
+#else
+#include <sys/socket.h>
+#endif
+
+class OlySocket {
+public:
+#ifndef WIN32
+  static int connect(const char* path, const size_t pathSize);
+#endif
+
+  OlySocket(int socketID);
+  ~OlySocket();
+
+  void closeSocket();
+  void shutdownConnection();
+  void send(const char* buffer, int size);
+  int receive(char* buffer, int size);
+  int receiveNBytes(char* buffer, int size);
+  int receiveString(char* buffer, int size);
+
+  bool isValid() const { return mSocketID >= 0; }
+
+private:
+  int mSocketID;
+};
+
+class OlyServerSocket {
+public:
+  OlyServerSocket(int port);
+#ifndef WIN32
+  OlyServerSocket(const char* path, const size_t pathSize);
+#endif
+  ~OlyServerSocket();
+
+  int acceptConnection();
+  void closeServerSocket();
+
+  int getFd() { return mFDServer; }
+
+private:
+  int mFDServer;
+
+  void createServerSocket(int port);
+};
+
+int socket_cloexec(int domain, int type, int protocol);
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen);
+
+#endif //__OLY_SOCKET_H__
diff --git a/tools/gator/daemon/OlyUtility.cpp b/tools/gator/daemon/OlyUtility.cpp
new file mode 100644
index 000000000000..45340a27d9fa
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.cpp
@@ -0,0 +1,227 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlyUtility.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+#if defined(WIN32)
+#include <windows.h>
+#elif defined(__linux__)
+#include <unistd.h>
+#elif defined(DARWIN)
+#include <mach-o/dyld.h>
+#endif
+
+OlyUtility* util = NULL;
+
+bool OlyUtility::stringToBool(const char* string, bool defValue) {
+  char value[32];
+
+  if (string == NULL) {
+    return defValue;
+  }
+
+  strncpy(value, string, sizeof(value));
+  if (value[0] == 0) {
+    return defValue;
+  }
+  value[sizeof(value) - 1] = 0; // strncpy does not guarantee a null-terminated string
+
+  // Convert to lowercase
+  int i = 0;
+  while (value[i]) {
+    value[i] = tolower(value[i]);
+    i++;
+  }
+
+  if (strcmp(value, "true") == 0 || strcmp(value, "yes") == 0 || strcmp(value, "1") == 0 || strcmp(value, "on") == 0) {
+    return true;
+  } else if (strcmp(value, "false") == 0 || strcmp(value, "no") == 0 || strcmp(value, "0") == 0 || strcmp(value, "off") == 0) {
+    return false;
+  } else {
+    return defValue;
+  }
+}
+
+void OlyUtility::stringToLower(char* string) {
+  if (string == NULL) {
+    return;
+  }
+
+  while (*string) {
+    *string = tolower(*string);
+    string++;
+  }
+}
+
+// Modifies fullpath with the path part including the trailing path separator
+int OlyUtility::getApplicationFullPath(char* fullpath, int sizeOfPath) {
+  memset(fullpath, 0, sizeOfPath);
+#if defined(WIN32)
+  int length = GetModuleFileName(NULL, fullpath, sizeOfPath);
+#elif defined(__linux__)
+  int length = readlink("/proc/self/exe", fullpath, sizeOfPath);
+#elif defined(DARWIN)
+  uint32_t length_u = (uint32_t)sizeOfPath;
+  int length = sizeOfPath;
+  if (_NSGetExecutablePath(fullpath, &length_u) == 0) {
+    length = strlen(fullpath);
+  }
+#endif
+
+  if (length == sizeOfPath) {
+    return -1;
+  }
+
+  fullpath[length] = 0;
+  getPathPart(fullpath);
+
+  return 0;
+}
+
+char* OlyUtility::readFromDisk(const char* file, unsigned int *size, bool appendNull) {
+  // Open the file
+  FILE* pFile = fopen(file, "rb");
+  if (pFile==NULL) {
+    return NULL;
+  }
+
+  // Obtain file size
+  fseek(pFile , 0 , SEEK_END);
+  unsigned int lSize = ftell(pFile);
+  rewind(pFile);
+
+  // Allocate memory to contain the whole file
+  char* buffer = (char*)malloc(lSize + (int)appendNull);
+  if (buffer == NULL) {
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Copy the file into the buffer
+  if (fread(buffer, 1, lSize, pFile) != lSize) {
+    free(buffer);
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Terminate
+  fclose(pFile);
+
+  if (appendNull) {
+    buffer[lSize] = 0;
+  }
+
+  if (size) {
+    *size = lSize;
+  }
+
+  return buffer;
+}
+
+int OlyUtility::writeToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "wb");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+int OlyUtility::appendToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "a");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+/**
+ * Copies the srcFile into dstFile in 1kB chunks.
+ * The dstFile will be overwritten if it exists.
+ * 0 is returned on an error; otherwise 1.
+ */
+#define TRANSFER_SIZE 1024
+int OlyUtility::copyFile(const char* srcFile, const char* dstFile) {
+  char buffer[TRANSFER_SIZE];
+  FILE * f_src = fopen(srcFile,"rb");
+  if (!f_src) {
+    return 0;
+  }
+  FILE * f_dst = fopen(dstFile,"wb");
+  if (!f_dst) {
+    fclose(f_src);
+    return 0;
+  }
+  while (!feof(f_src)) {
+    int num_bytes_read = fread(buffer, 1, TRANSFER_SIZE, f_src);
+    if (num_bytes_read < TRANSFER_SIZE && !feof(f_src)) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+    int num_bytes_written = fwrite(buffer, 1, num_bytes_read, f_dst);
+    if (num_bytes_written != num_bytes_read) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+  }
+  fclose(f_src);
+  fclose(f_dst);
+  return 1;
+}
+
+const char* OlyUtility::getFilePart(const char* path) {
+  const char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return path;
+  }
+
+  return last_sep++;
+}
+
+// getPathPart may modify the contents of path
+// returns the path including the trailing path separator
+char* OlyUtility::getPathPart(char* path) {
+  char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return 0;
+  }
+  last_sep++;
+  *last_sep = 0;
+
+  return (path);
+}
diff --git a/tools/gator/daemon/OlyUtility.h b/tools/gator/daemon/OlyUtility.h
new file mode 100644
index 000000000000..1d26beb596fa
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef OLY_UTILITY_H
+#define OLY_UTILITY_H
+
+#include <stddef.h>
+
+#ifdef WIN32
+#define PATH_SEPARATOR '\\'
+#define CAIMAN_PATH_MAX MAX_PATH
+#define snprintf _snprintf
+#else
+#include <limits.h>
+#define PATH_SEPARATOR '/'
+#define CAIMAN_PATH_MAX PATH_MAX
+#endif
+
+class OlyUtility {
+public:
+  OlyUtility() {};
+  ~OlyUtility() {};
+  bool stringToBool(const char* string, bool defValue);
+  void stringToLower(char* string);
+  int getApplicationFullPath(char* path, int sizeOfPath);
+  char* readFromDisk(const char* file, unsigned int *size = NULL, bool appendNull = true);
+  int writeToDisk(const char* path, const char* file);
+  int appendToDisk(const char* path, const char* file);
+  int copyFile(const char* srcFile, const char* dstFile);
+  const char* getFilePart(const char* path);
+  char* getPathPart(char* path);
+private:
+};
+
+extern OlyUtility* util;
+
+#endif // OLY_UTILITY_H
diff --git a/tools/gator/daemon/PerfBuffer.cpp b/tools/gator/daemon/PerfBuffer.cpp
new file mode 100644
index 000000000000..f127c996d43b
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfBuffer.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+PerfBuffer::PerfBuffer() {
+	for (int cpu = 0; cpu < ARRAY_LENGTH(mBuf); ++cpu) {
+		mBuf[cpu] = MAP_FAILED;
+		mDiscard[cpu] = false;
+		mFds[cpu] = -1;
+	}
+}
+
+PerfBuffer::~PerfBuffer() {
+	for (int cpu = ARRAY_LENGTH(mBuf) - 1; cpu >= 0; --cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+		}
+	}
+}
+
+bool PerfBuffer::useFd(const int cpu, const int fd) {
+	if (mFds[cpu] < 0) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): cpu %i already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__, cpu);
+			return false;
+		}
+
+		// The buffer isn't mapped yet
+		mBuf[cpu] = mmap(NULL, gSessionData->mPageSize + BUF_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): mmap failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		mFds[cpu] = fd;
+
+		// Check the version
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		if (pemp->compat_version != 0) {
+			logg->logMessage("%s(%s:%i): Incompatible perf_event_mmap_page compat_version", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	} else {
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): cpu already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, mFds[cpu]) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+void PerfBuffer::discard(const int cpu) {
+	if (mBuf[cpu] != MAP_FAILED) {
+		mDiscard[cpu] = true;
+	}
+}
+
+bool PerfBuffer::isEmpty() {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			// Take a snapshot of the positions
+			struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+			const __u64 head = pemp->data_head;
+			const __u64 tail = pemp->data_tail;
+
+			if (head != tail) {
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+static void compressAndSend(const int cpu, const __u64 head, __u64 tail, const uint8_t *const b, Sender *const sender) {
+	// Pick a big size but something smaller than the chunkSize in Sender::writeData which is 100k
+	char buf[1<<16];
+	int writePos = 0;
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+
+	while (head > tail) {
+		writePos = 0;
+		if (!gSessionData->mLocalCapture) {
+			buf[writePos++] = RESPONSE_APC_DATA;
+		}
+		// Reserve space for size
+		writePos += sizeof(uint32_t);
+		Buffer::packInt(buf, sizeof(buf), writePos, FRAME_PERF);
+		Buffer::packInt(buf, sizeof(buf), writePos, cpu);
+
+		while (head > tail) {
+			const int count = reinterpret_cast<const struct perf_event_header *>(b + (tail & BUF_MASK))->size/sizeof(uint64_t);
+			// Can this whole message be written as Streamline assumes events are not split between frames
+			if (sizeof(buf) <= writePos + count*Buffer::MAXSIZE_PACK64) {
+				break;
+			}
+			for (int i = 0; i < count; ++i) {
+				// Must account for message size
+				Buffer::packInt64(buf, sizeof(buf), writePos, *reinterpret_cast<const uint64_t *>(b + (tail & BUF_MASK)));
+				tail += sizeof(uint64_t);
+			}
+		}
+
+		// Write size
+		Buffer::writeLEInt(reinterpret_cast<unsigned char *>(buf + typeLength), writePos - typeLength - sizeof(uint32_t));
+		sender->writeData(buf, writePos, RESPONSE_APC_DATA);
+	}
+}
+
+bool PerfBuffer::send(Sender *const sender) {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] == MAP_FAILED) {
+			continue;
+		}
+
+		// Take a snapshot of the positions
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		const __u64 head = pemp->data_head;
+		const __u64 tail = pemp->data_tail;
+
+		if (head > tail) {
+			const uint8_t *const b = static_cast<uint8_t *>(mBuf[cpu]) + gSessionData->mPageSize;
+			compressAndSend(cpu, head, tail, b, sender);
+
+			// Update tail with the data read
+			pemp->data_tail = head;
+		}
+
+		if (mDiscard[cpu]) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+			mBuf[cpu] = MAP_FAILED;
+			mDiscard[cpu] = false;
+			mFds[cpu] = -1;
+			logg->logMessage("%s(%s:%i): Unmaped cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+		}
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/PerfBuffer.h b/tools/gator/daemon/PerfBuffer.h
new file mode 100644
index 000000000000..25a10625a9e8
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.h
@@ -0,0 +1,41 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_BUFFER
+#define PERF_BUFFER
+
+#include "Config.h"
+
+#define BUF_SIZE (gSessionData->mTotalBufferSize * 1024 * 1024)
+#define BUF_MASK (BUF_SIZE - 1)
+
+class Sender;
+
+class PerfBuffer {
+public:
+	PerfBuffer();
+	~PerfBuffer();
+
+	bool useFd(const int cpu, const int fd);
+	void discard(const int cpu);
+	bool isEmpty();
+	bool send(Sender *const sender);
+
+private:
+	void *mBuf[NR_CPUS];
+	// After the buffer is flushed it should be unmaped
+	bool mDiscard[NR_CPUS];
+	// fd that corresponds to the mBuf
+	int mFds[NR_CPUS];
+
+	// Intentionally undefined
+	PerfBuffer(const PerfBuffer &);
+	PerfBuffer &operator=(const PerfBuffer &);
+};
+
+#endif // PERF_BUFFER
diff --git a/tools/gator/daemon/PerfDriver.cpp b/tools/gator/daemon/PerfDriver.cpp
new file mode 100644
index 000000000000..ee90284cee41
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.cpp
@@ -0,0 +1,351 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfDriver.h"
+
+#include <dirent.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Config.h"
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfGroup.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+#define PERF_DEVICES "/sys/bus/event_source/devices"
+
+#define TYPE_DERIVED ~0U
+
+// From gator.h
+struct gator_cpu {
+	const int cpuid;
+	// Human readable name
+	const char *const core_name;
+	// gatorfs event and Perf PMU name
+	const char *const pmnc_name;
+	const int pmnc_counters;
+};
+
+// From gator_main.c
+static const struct gator_cpu gator_cpus[] = {
+	{ 0xb36, "ARM1136",      "ARM_ARM11",        3 },
+	{ 0xb56, "ARM1156",      "ARM_ARM11",        3 },
+	{ 0xb76, "ARM1176",      "ARM_ARM11",        3 },
+	{ 0xb02, "ARM11MPCore",  "ARM_ARM11MPCore",  3 },
+	{ 0xc05, "Cortex-A5",    "ARMv7_Cortex_A5",  2 },
+	{ 0xc07, "Cortex-A7",    "ARMv7_Cortex_A7",  4 },
+	{ 0xc08, "Cortex-A8",    "ARMv7_Cortex_A8",  4 },
+	{ 0xc09, "Cortex-A9",    "ARMv7_Cortex_A9",  6 },
+	{ 0xc0f, "Cortex-A15",   "ARMv7_Cortex_A15", 6 },
+	{ 0xc0e, "Cortex-A17",   "ARMv7_Cortex_A17", 6 },
+	{ 0x00f, "Scorpion",     "Scorpion",         4 },
+	{ 0x02d, "ScorpionMP",   "ScorpionMP",       4 },
+	{ 0x049, "KraitSIM",     "Krait",            4 },
+	{ 0x04d, "Krait",        "Krait",            4 },
+	{ 0x06f, "Krait S4 Pro", "Krait",            4 },
+	{ 0xd03, "Cortex-A53",   "ARM_Cortex-A53",   6 },
+	{ 0xd07, "Cortex-A57",   "ARM_Cortex-A57",   6 },
+	{ 0xd0f, "AArch64",      "ARM_AArch64",      6 },
+};
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+struct uncore_counter {
+	// Perf PMU name
+	const char *const perfName;
+	// gatorfs event name
+	const char *const gatorName;
+	const int count;
+};
+
+static const struct uncore_counter uncore_counters[] = {
+	{ "CCI_400", "CCI_400", 4 },
+	{ "CCI_400-r1", "CCI_400-r1", 4 },
+	{ "ccn", "ARM_CCN_5XX", 8 },
+};
+
+class PerfCounter : public DriverCounter {
+public:
+	PerfCounter(DriverCounter *next, const char *name, uint32_t type, uint64_t config, bool perCpu) : DriverCounter(next, name), mType(type), mCount(0), mConfig(config), mPerCpu(perCpu) {}
+
+	~PerfCounter() {
+	}
+
+	uint32_t getType() const { return mType; }
+	int getCount() const { return mCount; }
+	void setCount(const int count) { mCount = count; }
+	uint64_t getConfig() const { return mConfig; }
+	void setConfig(const uint64_t config) { mConfig = config; }
+	bool isPerCpu() const { return mPerCpu; }
+
+private:
+	const uint32_t mType;
+	int mCount;
+	uint64_t mConfig;
+	bool mPerCpu;
+};
+
+PerfDriver::PerfDriver() : mIsSetup(false), mLegacySupport(false) {
+}
+
+PerfDriver::~PerfDriver() {
+}
+
+void PerfDriver::addCpuCounters(const char *const counterName, const int type, const int numCounters) {
+	int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+	char *name = new char[len];
+	snprintf(name, len, "%s_ccnt", counterName);
+	setCounters(new PerfCounter(getCounters(), name, type, -1, true));
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, true));
+	}
+}
+
+void PerfDriver::addUncoreCounters(const char *const counterName, const int type, const int numCounters) {
+	int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+	char *name = new char[len];
+	snprintf(name, len, "%s_ccnt", counterName);
+	setCounters(new PerfCounter(getCounters(), name, type, -1, false));
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, false));
+	}
+}
+
+bool PerfDriver::setup() {
+	// Check the kernel version
+	int release[3];
+	if (!getLinuxVersion(release)) {
+		logg->logMessage("%s(%s:%i): getLinuxVersion failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logMessage("%s(%s:%i): Unsupported kernel version", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	mLegacySupport = KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 12, 0);
+
+	if (access(EVENTS_PATH, R_OK) != 0) {
+		logg->logMessage("%s(%s:%i): " EVENTS_PATH " does not exist, is CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER enabled?", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	// Add supported PMUs
+	bool foundCpu = false;
+	DIR *dir = opendir(PERF_DEVICES);
+	if (dir == NULL) {
+		logg->logMessage("%s(%s:%i): opendif failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+			// Do the names match exactly?
+			if (strcasecmp(gator_cpu->pmnc_name, dirent->d_name) != 0 &&
+			    // Do these names match but have the old vs new prefix?
+			    ((strncasecmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 ||
+			      strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 ||
+			      strcasecmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0))) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters for %s", gator_cpu->pmnc_name);
+			addCpuCounters(gator_cpu->pmnc_name, type, gator_cpu->pmnc_counters);
+		}
+
+		for (int i = 0; i < ARRAY_LENGTH(uncore_counters); ++i) {
+			if (strcmp(dirent->d_name, uncore_counters[i].perfName) != 0) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			logg->logMessage("Adding uncore counters for %s", uncore_counters[i].gatorName);
+			addUncoreCounters(uncore_counters[i].gatorName, type, uncore_counters[i].count);
+		}
+	}
+	closedir(dir);
+
+	if (!foundCpu) {
+		// If no cpu was found based on pmu names, try by cpuid
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			if (gSessionData->mMaxCpuId != gator_cpus[i].cpuid) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters (based on cpuid) for %s", gator_cpus[i].pmnc_name);
+			addCpuCounters(gator_cpus[i].pmnc_name, PERF_TYPE_RAW, gator_cpus[i].pmnc_counters);
+		}
+	}
+
+	/*
+	if (!foundCpu) {
+		// If all else fails, use the perf architected counters
+		// 9 because that's how many are in events-Perf-Hardware.xml - assume they can all be enabled at once
+		addCpuCounters("Perf_Hardware", PERF_TYPE_HARDWARE, 9);
+	}
+	*/
+
+	// Add supported software counters
+	long long id;
+	DynBuf printb;
+
+	id = getTracepointId("irq/softirq_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	id = getTracepointId("irq/irq_handler_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	id = getTracepointId(SCHED_SWITCH, &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	setCounters(new PerfCounter(getCounters(), "Linux_cpu_wait_contention", TYPE_DERIVED, -1, false));
+
+	//Linux_cpu_wait_io
+
+	mIsSetup = true;
+	return true;
+}
+
+bool PerfDriver::summary(Buffer *const buffer) {
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	char buf[512];
+	snprintf(buf, sizeof(buf), "%s %s %s %s %s GNU/Linux", utsname.sysname, utsname.nodename, utsname.release, utsname.version, utsname.machine);
+
+	struct timespec ts;
+	if (clock_gettime(CLOCK_REALTIME, &ts) != 0) {
+		logg->logMessage("%s(%s:%i): clock_gettime failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	const int64_t timestamp = (int64_t)ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+	const uint64_t monotonicStarted = getTime();
+	gSessionData->mMonotonicStarted = monotonicStarted;
+
+	buffer->summary(monotonicStarted, timestamp, monotonicStarted, monotonicStarted, buf);
+
+	for (int i = 0; i < gSessionData->mCores; ++i) {
+		coreName(monotonicStarted, buffer, i);
+	}
+	buffer->commit(monotonicStarted);
+
+	return true;
+}
+
+void PerfDriver::coreName(const uint32_t startTime, Buffer *const buffer, const int cpu) {
+	// Don't send information on a cpu we know nothing about
+	if (gSessionData->mCpuIds[cpu] == -1) {
+		return;
+	}
+
+	int j;
+	for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) {
+		if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+			break;
+		}
+	}
+	if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+		buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], gator_cpus[j].core_name);
+	} else {
+		char buf[32];
+		if (gSessionData->mCpuIds[cpu] == -1) {
+			snprintf(buf, sizeof(buf), "Unknown");
+		} else {
+			snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", gSessionData->mCpuIds[cpu]);
+		}
+		buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], buf);
+	}
+}
+
+void PerfDriver::setupCounter(Counter &counter) {
+	PerfCounter *const perfCounter = static_cast<PerfCounter *>(findCounter(counter));
+	if (perfCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	// Don't use the config from counters XML if it's not set, ex: software counters
+	if (counter.getEvent() != -1) {
+		perfCounter->setConfig(counter.getEvent());
+	}
+	perfCounter->setCount(counter.getCount());
+	perfCounter->setEnabled(true);
+	counter.setKey(perfCounter->getKey());
+}
+
+bool PerfDriver::enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const {
+	for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() != TYPE_DERIVED)) {
+			if (!group->add(currTime, buffer, counter->getKey(), counter->getType(), counter->getConfig(), counter->getCount(), counter->getCount() > 0 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP : 0, counter->isPerCpu() ? PERF_GROUP_PER_CPU : 0)) {
+				logg->logMessage("%s(%s:%i): PerfGroup::add failed", __FUNCTION__, __FILE__, __LINE__);
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+long long PerfDriver::getTracepointId(const char *const name, DynBuf *const printb) {
+	if (!printb->printf(EVENTS_PATH "/%s/id", name)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return -1;
+	}
+
+	int64_t result;
+	if (DriverSource::readInt64Driver(printb->getBuf(), &result) != 0) {
+		logg->logMessage("%s(%s:%i): DriverSource::readInt64Driver failed", __FUNCTION__, __FILE__, __LINE__);
+		return -1;
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/PerfDriver.h b/tools/gator/daemon/PerfDriver.h
new file mode 100644
index 000000000000..846203a9e18b
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFDRIVER_H
+#define PERFDRIVER_H
+
+#include <stdint.h>
+
+#include "Driver.h"
+
+// If debugfs is not mounted at /sys/kernel/debug, update DEBUGFS_PATH
+#define DEBUGFS_PATH "/sys/kernel/debug"
+#define EVENTS_PATH DEBUGFS_PATH "/tracing/events"
+
+#define SCHED_SWITCH "sched/sched_switch"
+#define CPU_IDLE "power/cpu_idle"
+
+class Buffer;
+class DynBuf;
+class PerfGroup;
+
+class PerfDriver : public SimpleDriver {
+public:
+	PerfDriver();
+	~PerfDriver();
+
+	bool getLegacySupport() const { return mLegacySupport; }
+
+	bool setup();
+	bool summary(Buffer *const buffer);
+	void coreName(const uint32_t startTime, Buffer *const buffer, const int cpu);
+	bool isSetup() const { return mIsSetup; }
+
+	void setupCounter(Counter &counter);
+
+	bool enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const;
+
+	static long long getTracepointId(const char *const name, DynBuf *const printb);
+
+private:
+	void addCpuCounters(const char *const counterName, const int type, const int numCounters);
+	void addUncoreCounters(const char *const counterName, const int type, const int numCounters);
+
+	bool mIsSetup;
+	bool mLegacySupport;
+
+	// Intentionally undefined
+	PerfDriver(const PerfDriver &);
+	PerfDriver &operator=(const PerfDriver &);
+};
+
+#endif // PERFDRIVER_H
diff --git a/tools/gator/daemon/PerfGroup.cpp b/tools/gator/daemon/PerfGroup.cpp
new file mode 100644
index 000000000000..4fd960a9058c
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.cpp
@@ -0,0 +1,244 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfGroup.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "SessionData.h"
+
+#define DEFAULT_PEA_ARGS(pea, additionalSampleType) \
+	pea.size = sizeof(pea); \
+	/* Emit time, read_format below, group leader id, and raw tracepoint info */ \
+	pea.sample_type = (gSessionData->perf.getLegacySupport() \
+										 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_TIME | PERF_SAMPLE_READ | PERF_SAMPLE_ID \
+										 : PERF_SAMPLE_TIME | PERF_SAMPLE_READ | PERF_SAMPLE_IDENTIFIER ) | additionalSampleType; \
+	/* Emit emit value in group format */ \
+	pea.read_format = PERF_FORMAT_ID | PERF_FORMAT_GROUP; \
+	/* start out disabled */ \
+	pea.disabled = 1; \
+	/* have a sampling interrupt happen when we cross the wakeup_watermark boundary */ \
+	pea.watermark = 1; \
+	/* Be conservative in flush size as only one buffer set is monitored */ \
+	pea.wakeup_watermark = BUF_SIZE / 2
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	int fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	if (fd < 0) {
+		return -1;
+	}
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(fd);
+		return -1;
+	}
+	return fd;
+}
+
+PerfGroup::PerfGroup(PerfBuffer *const pb) : mPb(pb) {
+	memset(&mAttrs, 0, sizeof(mAttrs));
+	memset(&mPerCpu, 0, sizeof(mPerCpu));
+	memset(&mKeys, -1, sizeof(mKeys));
+	memset(&mFds, -1, sizeof(mFds));
+}
+
+PerfGroup::~PerfGroup() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			close(mFds[pos]);
+		}
+	}
+}
+
+bool PerfGroup::add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+	int i;
+	for (i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			break;
+		}
+	}
+
+	if (i >= ARRAY_LENGTH(mKeys)) {
+		logg->logMessage("%s(%s:%i): Too many counters", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	DEFAULT_PEA_ARGS(mAttrs[i], sampleType);
+	mAttrs[i].type = type;
+	mAttrs[i].config = config;
+	mAttrs[i].sample_period = sample;
+	// always be on the CPU but only a group leader can be pinned
+	mAttrs[i].pinned = (i == 0 ? 1 : 0);
+	mAttrs[i].mmap = (flags & PERF_GROUP_MMAP ? 1 : 0);
+	mAttrs[i].comm = (flags & PERF_GROUP_COMM ? 1 : 0);
+	mAttrs[i].freq = (flags & PERF_GROUP_FREQ ? 1 : 0);
+	mAttrs[i].task = (flags & PERF_GROUP_TASK ? 1 : 0);
+	mAttrs[i].sample_id_all = (flags & PERF_GROUP_SAMPLE_ID_ALL ? 1 : 0);
+	mPerCpu[i] = (flags & PERF_GROUP_PER_CPU);
+
+	mKeys[i] = key;
+
+	buffer->pea(currTime, &mAttrs[i], key);
+
+	return true;
+}
+
+int PerfGroup::prepareCPU(const int cpu, Monitor *const monitor) {
+	logg->logMessage("%s(%s:%i): Onlining cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		if ((cpu != 0) && !mPerCpu[i]) {
+			continue;
+		}
+
+		const int offset = i * gSessionData->mCores;
+		if (mFds[cpu + offset] >= 0) {
+			logg->logMessage("%s(%s:%i): cpu already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__);
+			return PG_FAILURE;
+		}
+
+		logg->logMessage("%s(%s:%i): perf_event_open cpu: %i type: %lli config: %lli sample: %lli sample_type: 0x%llx pinned: %i mmap: %i comm: %i freq: %i task: %i sample_id_all: %i", __FUNCTION__, __FILE__, __LINE__, cpu, (long long)mAttrs[i].type, (long long)mAttrs[i].config, (long long)mAttrs[i].sample_period, (long long)mAttrs[i].sample_type, mAttrs[i].pinned, mAttrs[i].mmap, mAttrs[i].comm, mAttrs[i].freq, mAttrs[i].task, mAttrs[i].sample_id_all);
+		mFds[cpu + offset] = sys_perf_event_open(&mAttrs[i], -1, cpu, i == 0 ? -1 : mFds[cpu], i == 0 ? 0 : PERF_FLAG_FD_OUTPUT);
+		if (mFds[cpu + offset] < 0) {
+			logg->logMessage("%s(%s:%i): failed %s", __FUNCTION__, __FILE__, __LINE__, strerror(errno));
+			if (errno == ENODEV) {
+				return PG_CPU_OFFLINE;
+			}
+			continue;
+		}
+
+		if (!mPb->useFd(cpu, mFds[cpu + offset])) {
+			logg->logMessage("%s(%s:%i): PerfBuffer::useFd failed", __FUNCTION__, __FILE__, __LINE__);
+			return PG_FAILURE;
+		}
+
+
+		if (!monitor->add(mFds[cpu + offset])) {
+		  logg->logMessage("%s(%s:%i): Monitor::add failed", __FUNCTION__, __FILE__, __LINE__);
+		  return PG_FAILURE;
+		}
+	}
+
+	return PG_SUCCESS;
+}
+
+int PerfGroup::onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer) {
+	__u64 ids[ARRAY_LENGTH(mKeys)];
+	int coreKeys[ARRAY_LENGTH(mKeys)];
+	int idCount = 0;
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		const int fd = mFds[cpu + i * gSessionData->mCores];
+		if (fd < 0) {
+			continue;
+		}
+
+		coreKeys[idCount] = mKeys[i];
+		if (!gSessionData->perf.getLegacySupport() && ioctl(fd, PERF_EVENT_IOC_ID, &ids[idCount]) != 0 &&
+				// Workaround for running 32-bit gatord on 64-bit systems, kernel patch in the works
+				ioctl(fd, (PERF_EVENT_IOC_ID & ~IOCSIZE_MASK) | (8 << _IOC_SIZESHIFT), &ids[idCount]) != 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return 0;
+		}
+		++idCount;
+	}
+
+	if (!gSessionData->perf.getLegacySupport()) {
+		buffer->keys(currTime, idCount, ids, coreKeys);
+	} else {
+		char buf[1024];
+		ssize_t bytes = read(mFds[cpu], buf, sizeof(buf));
+		if (bytes < 0) {
+			logg->logMessage("read failed");
+			return 0;
+		}
+		buffer->keysOld(currTime, idCount, coreKeys, bytes, buf);
+	}
+
+	if (start) {
+		for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+			int offset = i * gSessionData->mCores + cpu;
+			if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+				logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+				return 0;
+			}
+		}
+	}
+
+	if (idCount == 0) {
+		logg->logMessage("%s(%s:%i): no events came online", __FUNCTION__, __FILE__, __LINE__);
+	}
+
+	return idCount;
+}
+
+bool PerfGroup::offlineCPU(const int cpu) {
+	logg->logMessage("%s(%s:%i): Offlining cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE, 0) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	// Mark the buffer so that it will be released next time it's read
+	mPb->discard(cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0) {
+			close(mFds[offset]);
+			mFds[offset] = -1;
+		}
+	}
+
+	return true;
+}
+
+bool PerfGroup::start() {
+	for (int pos = 0; pos < ARRAY_LENGTH(mFds); ++pos) {
+		if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+	}
+
+	return true;
+
+ fail:
+	stop();
+
+	return false;
+}
+
+void PerfGroup::stop() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE, 0);
+		}
+	}
+}
diff --git a/tools/gator/daemon/PerfGroup.h b/tools/gator/daemon/PerfGroup.h
new file mode 100644
index 000000000000..f7b3d725bac7
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.h
@@ -0,0 +1,65 @@
+ /**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_GROUP
+#define PERF_GROUP
+
+#include <stdint.h>
+
+// Use a snapshot of perf_event.h as it may be more recent than what is on the target and if not newer features won't be supported anyways
+#include "k/perf_event.h"
+
+#include "Config.h"
+
+class Buffer;
+class Monitor;
+class PerfBuffer;
+
+enum PerfGroupFlags {
+	PERF_GROUP_MMAP          = 1 << 0,
+	PERF_GROUP_COMM          = 1 << 1,
+	PERF_GROUP_FREQ          = 1 << 2,
+	PERF_GROUP_TASK          = 1 << 3,
+	PERF_GROUP_SAMPLE_ID_ALL = 1 << 4,
+	PERF_GROUP_PER_CPU       = 1 << 5,
+};
+
+enum {
+	PG_SUCCESS = 0,
+	PG_FAILURE,
+	PG_CPU_OFFLINE,
+};
+
+class PerfGroup {
+public:
+	PerfGroup(PerfBuffer *const pb);
+	~PerfGroup();
+
+	bool add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+	// Safe to call concurrently
+	int prepareCPU(const int cpu, Monitor *const monitor);
+	// Not safe to call concurrently. Returns the number of events enabled
+	int onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer);
+	bool offlineCPU(int cpu);
+	bool start();
+	void stop();
+
+private:
+	// +1 for the group leader
+	struct perf_event_attr mAttrs[MAX_PERFORMANCE_COUNTERS + 1];
+	bool mPerCpu[MAX_PERFORMANCE_COUNTERS + 1];
+	int mKeys[MAX_PERFORMANCE_COUNTERS + 1];
+	int mFds[NR_CPUS * (MAX_PERFORMANCE_COUNTERS + 1)];
+	PerfBuffer *const mPb;
+
+	// Intentionally undefined
+	PerfGroup(const PerfGroup &);
+	PerfGroup &operator=(const PerfGroup &);
+};
+
+#endif // PERF_GROUP
diff --git a/tools/gator/daemon/PerfSource.cpp b/tools/gator/daemon/PerfSource.cpp
new file mode 100644
index 000000000000..193b7789a290
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.cpp
@@ -0,0 +1,449 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfSource.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfDriver.h"
+#include "Proc.h"
+#include "SessionData.h"
+
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
+
+extern Child *child;
+
+static bool sendTracepointFormat(const uint64_t currTime, Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) {
+	if (!printb->printf(EVENTS_PATH "/%s/format", name)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	buffer->format(currTime, b->getLength(), b->getBuf());
+
+	return true;
+}
+
+static void *syncFunc(void *arg)
+{
+	struct timespec ts;
+	int64_t nextTime = gSessionData->mMonotonicStarted;
+	int err;
+	(void)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sync", 0, 0, 0);
+
+	// Mask all signals so that this thread will not be woken up
+	{
+		sigset_t set;
+		if (sigfillset(&set) != 0) {
+			logg->logError(__FILE__, __LINE__, "sigfillset failed");
+			handleException();
+		}
+		if ((err = pthread_sigmask(SIG_SETMASK, &set, NULL)) != 0) {
+			logg->logError(__FILE__, __LINE__, "pthread_sigmask failed");
+			handleException();
+		}
+	}
+
+	for (;;) {
+		if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+			logg->logError(__FILE__, __LINE__, "clock_gettime failed");
+			handleException();
+		}
+		const int64_t currTime = ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+		// Wake up once a second
+		nextTime += NS_PER_S;
+
+		// Always sleep more than 1 ms, hopefully things will line up better next time
+		const int64_t sleepTime = max(nextTime - currTime, (int64_t)(NS_PER_MS + 1));
+		ts.tv_sec = sleepTime/NS_PER_S;
+		ts.tv_nsec = sleepTime % NS_PER_S;
+
+		err = nanosleep(&ts, NULL);
+		if (err != 0) {
+			fprintf(stderr, "clock_nanosleep failed: %s\n", strerror(err));
+			return NULL;
+		}
+	}
+
+	return NULL;
+}
+
+static long getMaxCoreNum() {
+	DIR *dir = opendir("/sys/devices/system/cpu");
+	if (dir == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, opendir failed");
+		handleException();
+	}
+
+	long maxCoreNum = -1;
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		if (strncmp(dirent->d_name, "cpu", 3) == 0) {
+			char *endptr;
+			errno = 0;
+			long coreNum = strtol(dirent->d_name + 3, &endptr, 10);
+			if ((errno == 0) && (*endptr == '\0') && (coreNum >= maxCoreNum)) {
+				maxCoreNum = coreNum + 1;
+			}
+		}
+	}
+	closedir(dir);
+
+	if (maxCoreNum < 1) {
+		logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, no cpu# directories found");
+		handleException();
+	}
+
+	if (maxCoreNum >= NR_CPUS) {
+		logg->logError(__FILE__, __LINE__, "Too many cores on the target, please increase NR_CPUS in Config.h");
+		handleException();
+	}
+
+	return maxCoreNum;
+}
+
+PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(0, FRAME_PERF_ATTRS, 1024*1024, senderSem), mCountersBuf(), mCountersGroup(&mCountersBuf), mIdleGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) {
+	long l = sysconf(_SC_PAGE_SIZE);
+	if (l < 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to obtain the page size");
+		handleException();
+	}
+	gSessionData->mPageSize = static_cast<int>(l);
+	gSessionData->mCores = static_cast<int>(getMaxCoreNum());
+}
+
+PerfSource::~PerfSource() {
+}
+
+bool PerfSource::prepare() {
+	DynBuf printb;
+	DynBuf b1;
+	long long schedSwitchId;
+	long long cpuIdleId;
+
+	const uint64_t currTime = getTime();
+
+	// Reread cpuinfo since cores may have changed since startup
+	gSessionData->readCpuInfo();
+
+	if (0
+			|| !mMonitor.init()
+			|| !mUEvent.init()
+			|| !mMonitor.add(mUEvent.getFd())
+
+			|| (schedSwitchId = PerfDriver::getTracepointId(SCHED_SWITCH, &printb)) < 0
+			|| !sendTracepointFormat(currTime, &mBuffer, SCHED_SWITCH, &printb, &b1)
+
+			|| (cpuIdleId = PerfDriver::getTracepointId(CPU_IDLE, &printb)) < 0
+			|| !sendTracepointFormat(currTime, &mBuffer, CPU_IDLE, &printb, &b1)
+
+			// Only want RAW but not IP on sched_switch and don't want TID on SAMPLE_ID
+			|| !mCountersGroup.add(currTime, &mBuffer, 100/**/, PERF_TYPE_TRACEPOINT, schedSwitchId, 1, PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU)
+			|| !mIdleGroup.add(currTime, &mBuffer, 101/**/, PERF_TYPE_TRACEPOINT, cpuIdleId, 1, PERF_SAMPLE_RAW, PERF_GROUP_PER_CPU)
+
+			// Only want TID and IP but not RAW on timer
+			|| (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && !mCountersGroup.add(currTime, &mBuffer, 102/**/, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP, PERF_GROUP_PER_CPU))
+
+			|| !gSessionData->perf.enable(currTime, &mCountersGroup, &mBuffer)
+			|| 0) {
+		logg->logMessage("%s(%s:%i): perf setup failed, are you running Linux 3.4 or later?", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		const int result = mCountersGroup.prepareCPU(cpu, &mMonitor);
+		if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mCountersGroup failed");
+			handleException();
+		}
+	}
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		const int result = mIdleGroup.prepareCPU(cpu, &mMonitor);
+		if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mIdleGroup failed");
+			handleException();
+		}
+	}
+
+	int numEvents = 0;
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		numEvents += mCountersGroup.onlineCPU(currTime, cpu, false, &mBuffer);
+	}
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		numEvents += mIdleGroup.onlineCPU(currTime, cpu, false, &mBuffer);
+	}
+	if (numEvents <= 0) {
+		logg->logMessage("%s(%s:%i): PerfGroup::onlineCPU failed on all cores", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	// Send the summary right before the start so that the monotonic delta is close to the start time
+	if (!gSessionData->perf.summary(&mSummary)) {
+	  logg->logError(__FILE__, __LINE__, "PerfDriver::summary failed", __FUNCTION__, __FILE__, __LINE__);
+	  handleException();
+	}
+
+	// Start the timer thread to used to sync perf and monotonic raw times
+	pthread_t syncThread;
+	if (pthread_create(&syncThread, NULL, syncFunc, NULL)) {
+	  logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__);
+	  handleException();
+	}
+	struct sched_param param;
+	param.sched_priority = sched_get_priority_max(SCHED_FIFO);
+	if (pthread_setschedparam(syncThread, SCHED_FIFO | SCHED_RESET_ON_FORK, &param) != 0) {
+	  logg->logError(__FILE__, __LINE__, "pthread_setschedparam failed");
+	  handleException();
+	}
+
+	mBuffer.commit(currTime);
+
+	return true;
+}
+
+struct ProcThreadArgs {
+	Buffer *mBuffer;
+	uint64_t mCurrTime;
+	bool mIsDone;
+};
+
+void *procFunc(void *arg) {
+	DynBuf printb;
+	DynBuf b;
+	const ProcThreadArgs *const args = (ProcThreadArgs *)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	// Gator runs at a high priority, reset the priority to the default
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+		logg->logError(__FILE__, __LINE__, "setpriority failed");
+		handleException();
+	}
+
+	if (!readProcMaps(args->mCurrTime, args->mBuffer, &printb, &b)) {
+		logg->logError(__FILE__, __LINE__, "readProcMaps failed");
+		handleException();
+	}
+	args->mBuffer->commit(args->mCurrTime);
+
+	if (!readKallsyms(args->mCurrTime, args->mBuffer, &args->mIsDone)) {
+		logg->logError(__FILE__, __LINE__, "readKallsyms failed");
+		handleException();
+	}
+	args->mBuffer->commit(args->mCurrTime);
+
+	return NULL;
+}
+
+static const char CPU_DEVPATH[] = "/devices/system/cpu/cpu";
+
+void PerfSource::run() {
+	int pipefd[2];
+	pthread_t procThread;
+	ProcThreadArgs procThreadArgs;
+
+	{
+		DynBuf printb;
+		DynBuf b1;
+		DynBuf b2;
+
+		const uint64_t currTime = getTime();
+
+		// Start events before reading proc to avoid race conditions
+		if (!mCountersGroup.start() || !mIdleGroup.start()) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::start failed", __FUNCTION__, __FILE__, __LINE__);
+			handleException();
+		}
+
+		if (!readProcComms(currTime, &mBuffer, &printb, &b1, &b2)) {
+			logg->logError(__FILE__, __LINE__, "readProcComms failed");
+			handleException();
+		}
+		mBuffer.commit(currTime);
+
+		// Postpone reading kallsyms as on android adb gets too backed up and data is lost
+		procThreadArgs.mBuffer = &mBuffer;
+		procThreadArgs.mCurrTime = currTime;
+		procThreadArgs.mIsDone = false;
+		if (pthread_create(&procThread, NULL, procFunc, &procThreadArgs)) {
+			logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__);
+			handleException();
+		}
+	}
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError(__FILE__, __LINE__, "Monitor::add failed");
+		handleException();
+	}
+
+	int timeout = -1;
+	if (gSessionData->mLiveRate > 0) {
+		timeout = gSessionData->mLiveRate/NS_PER_MS;
+	}
+
+	sem_post(mStartProfile);
+
+	while (gSessionData->mSessionIsActive) {
+		// +1 for uevents, +1 for pipe
+		struct epoll_event events[NR_CPUS + 2];
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), timeout);
+		if (ready < 0) {
+			logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+			handleException();
+		}
+		const uint64_t currTime = getTime();
+
+		for (int i = 0; i < ready; ++i) {
+			if (events[i].data.fd == mUEvent.getFd()) {
+				if (!handleUEvent(currTime)) {
+					logg->logError(__FILE__, __LINE__, "PerfSource::handleUEvent failed");
+					handleException();
+				}
+				break;
+			}
+		}
+
+		// send a notification that data is ready
+		sem_post(mSenderSem);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		// Assume timeout == 0 in this case
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			logg->logMessage("%s(%s:%i): One shot", __FUNCTION__, __FILE__, __LINE__);
+			child->endSession();
+		}
+	}
+
+	procThreadArgs.mIsDone = true;
+	pthread_join(procThread, NULL);
+	mIdleGroup.stop();
+	mCountersGroup.stop();
+	mBuffer.setDone();
+	mIsDone = true;
+
+	// send a notification that data is ready
+	sem_post(mSenderSem);
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+bool PerfSource::handleUEvent(const uint64_t currTime) {
+	UEventResult result;
+	if (!mUEvent.read(&result)) {
+		logg->logMessage("%s(%s:%i): UEvent::Read failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (strcmp(result.mSubsystem, "cpu") == 0) {
+		if (strncmp(result.mDevPath, CPU_DEVPATH, sizeof(CPU_DEVPATH) - 1) != 0) {
+			logg->logMessage("%s(%s:%i): Unexpected cpu DEVPATH format", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		char *endptr;
+		errno = 0;
+		int cpu = strtol(result.mDevPath + sizeof(CPU_DEVPATH) - 1, &endptr, 10);
+		if (errno != 0 || *endptr != '\0') {
+			logg->logMessage("%s(%s:%i): strtol failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		if (cpu >= gSessionData->mCores) {
+			logg->logError(__FILE__, __LINE__, "Only %i cores are expected but core %i reports %s", gSessionData->mCores, cpu, result.mAction);
+			handleException();
+		}
+
+		if (strcmp(result.mAction, "online") == 0) {
+			mBuffer.onlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu);
+			// Only call onlineCPU if prepareCPU succeeded
+			bool result = false;
+			int err = mCountersGroup.prepareCPU(cpu, &mMonitor);
+			if (err == PG_CPU_OFFLINE) {
+				result = true;
+			} else if (err == PG_SUCCESS) {
+				if (mCountersGroup.onlineCPU(currTime, cpu, true, &mBuffer)) {
+					err = mIdleGroup.prepareCPU(cpu, &mMonitor);
+					if (err == PG_CPU_OFFLINE) {
+						result = true;
+					} else if (err == PG_SUCCESS) {
+						if (mIdleGroup.onlineCPU(currTime, cpu, true, &mBuffer)) {
+							result = true;
+						}
+					}
+				}
+			}
+			mBuffer.commit(currTime);
+
+			gSessionData->readCpuInfo();
+			gSessionData->perf.coreName(currTime, &mSummary, cpu);
+			mSummary.commit(currTime);
+			return result;
+		} else if (strcmp(result.mAction, "offline") == 0) {
+			const bool result = mCountersGroup.offlineCPU(cpu) && mIdleGroup.offlineCPU(cpu);
+			mBuffer.offlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu);
+			return result;
+		}
+	}
+
+	return true;
+}
+
+void PerfSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError(__FILE__, __LINE__, "write failed");
+			handleException();
+		}
+	}
+}
+
+bool PerfSource::isDone () {
+	return mBuffer.isDone() && mIsDone && mCountersBuf.isEmpty();
+}
+
+void PerfSource::write (Sender *sender) {
+	if (!mSummary.isDone()) {
+		mSummary.write(sender);
+		gSessionData->mSentSummary = true;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+	if (!mCountersBuf.send(sender)) {
+		logg->logError(__FILE__, __LINE__, "PerfBuffer::send failed");
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/PerfSource.h b/tools/gator/daemon/PerfSource.h
new file mode 100644
index 000000000000..ce1eafe8e953
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.h
@@ -0,0 +1,55 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFSOURCE_H
+#define PERFSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "PerfGroup.h"
+#include "Source.h"
+#include "UEvent.h"
+
+class Sender;
+
+class PerfSource : public Source {
+public:
+	PerfSource(sem_t *senderSem, sem_t *startProfile);
+	~PerfSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	bool handleUEvent(const uint64_t currTime);
+
+	Buffer mSummary;
+	Buffer mBuffer;
+	PerfBuffer mCountersBuf;
+	PerfGroup mCountersGroup;
+	PerfGroup mIdleGroup;
+	Monitor mMonitor;
+	UEvent mUEvent;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mInterruptFd;
+	bool mIsDone;
+
+	// Intentionally undefined
+	PerfSource(const PerfSource &);
+	PerfSource &operator=(const PerfSource &);
+};
+
+#endif // PERFSOURCE_H
diff --git a/tools/gator/daemon/Proc.cpp b/tools/gator/daemon/Proc.cpp
new file mode 100644
index 000000000000..e6b26b1199fa
--- /dev/null
+++ b/tools/gator/daemon/Proc.cpp
@@ -0,0 +1,312 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Proc.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+struct ProcStat {
+	// From linux-dev/include/linux/sched.h
+#define TASK_COMM_LEN 16
+	// TASK_COMM_LEN may grow, so be ready for it to get larger
+	char comm[2*TASK_COMM_LEN];
+	long numThreads;
+};
+
+static bool readProcStat(ProcStat *const ps, const char *const pathname, DynBuf *const b) {
+	if (!b->read(pathname)) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the thread exited", __FUNCTION__, __FILE__, __LINE__);
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	char *comm = strchr(b->getBuf(), '(');
+	if (comm == NULL) {
+		logg->logMessage("%s(%s:%i): parsing stat failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	++comm;
+	char *const str = strrchr(comm, ')');
+	if (str == NULL) {
+		logg->logMessage("%s(%s:%i): parsing stat failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	*str = '\0';
+	strncpy(ps->comm, comm, sizeof(ps->comm) - 1);
+	ps->comm[sizeof(ps->comm) - 1] = '\0';
+
+	const int count = sscanf(str + 2, " %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %ld", &ps->numThreads);
+	if (count != 1) {
+		logg->logMessage("%s(%s:%i): sscanf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static const char *readProcExe(DynBuf *const printb, const int pid, const int tid, DynBuf *const b) {
+	if (tid == -1 ? !printb->printf("/proc/%i/exe", pid)
+			: !printb->printf("/proc/%i/task/%i/exe", pid, tid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	const int err = b->readlink(printb->getBuf());
+	const char *image;
+	if (err == 0) {
+		image = strrchr(b->getBuf(), '/');
+		if (image == NULL) {
+			image = b->getBuf();
+		} else {
+			++image;
+		}
+	} else if (err == -ENOENT) {
+		// readlink /proc/[pid]/exe returns ENOENT for kernel threads
+		image = "\0";
+	} else {
+		logg->logMessage("%s(%s:%i): DynBuf::readlink failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	// Android apps are run by app_process but the cmdline is changed to reference the actual app name
+	// On 64-bit android app_process can be app_process32 or app_process64
+	if (strncmp(image, APP_PROCESS, sizeof(APP_PROCESS) - 1) != 0) {
+		return image;
+	}
+
+	if (tid == -1 ? !printb->printf("/proc/%i/cmdline", pid)
+			: !printb->printf("/proc/%i/task/%i/cmdline", pid, tid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the thread exited", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	return b->getBuf();
+}
+
+static bool readProcTask(const uint64_t currTime, Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	if (!b1->printf("/proc/%i/task", pid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+	DIR *task = opendir(b1->getBuf());
+	if (task == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(task)) != NULL) {
+		char *endptr;
+		const int tid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore task items that are not integers like ., etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/task/%i/stat", pid, tid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("%s(%s:%i): readProcStat failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		const char *const image = readProcExe(printb, pid, tid, b2);
+		if (image == NULL) {
+			logg->logMessage("%s(%s:%i): readImage failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		buffer->comm(currTime, pid, tid, image, ps.comm);
+	}
+
+	result = true;
+
+ fail:
+	closedir(task);
+
+	return result;
+}
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("%s(%s:%i): readProcStat failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		if (ps.numThreads <= 1) {
+			const char *const image = readProcExe(printb, pid, -1, b1);
+			if (image == NULL) {
+				logg->logMessage("%s(%s:%i): readImage failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+
+			buffer->comm(currTime, pid, pid, image, ps.comm);
+		} else {
+			if (!readProcTask(currTime, buffer, pid, printb, b1, b2)) {
+				logg->logMessage("%s(%s:%i): readProcTask failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+		}
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/maps", pid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		if (!b->read(printb->getBuf())) {
+			logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the process exited", __FUNCTION__, __FILE__, __LINE__);
+			// This is not a fatal error - the process just doesn't exist any more
+			continue;
+		}
+
+		buffer->maps(currTime, pid, pid, b->getBuf());
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone) {
+	int fd = ::open("/proc/kallsyms", O_RDONLY | O_CLOEXEC);
+
+	if (fd < 0) {
+		logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__);
+		return true;
+	};
+
+	char buf[1<<12];
+	ssize_t pos = 0;
+	while (gSessionData->mSessionIsActive && !ACCESS_ONCE(*isDone)) {
+		// Assert there is still space in the buffer
+		if (sizeof(buf) - pos - 1 == 0) {
+			logg->logError(__FILE__, __LINE__, "no space left in buffer");
+			handleException();
+		}
+
+		{
+			// -1 to reserve space for \0
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				logg->logError(__FILE__, __LINE__, "read failed", __FUNCTION__, __FILE__, __LINE__);
+				handleException();
+			}
+			if (bytes == 0) {
+				// Assert the buffer is empty
+				if (pos != 0) {
+					logg->logError(__FILE__, __LINE__, "buffer not empty on eof");
+					handleException();
+				}
+				break;
+			}
+			pos += bytes;
+		}
+
+		ssize_t newline;
+		// Find the last '\n'
+		for (newline = pos - 1; newline >= 0; --newline) {
+			if (buf[newline] == '\n') {
+				const char was = buf[newline + 1];
+				buf[newline + 1] = '\0';
+				buffer->kallsyms(currTime, buf);
+				// Sleep 3 ms to avoid sending out too much data too quickly
+				usleep(3000);
+				buf[0] = was;
+				// Assert the memory regions do not overlap
+				if (pos - newline >= newline + 1) {
+					logg->logError(__FILE__, __LINE__, "memcpy src and dst overlap");
+					handleException();
+				}
+				if (pos - newline - 2 > 0) {
+					memcpy(buf + 1, buf + newline + 2, pos - newline - 2);
+				}
+				pos -= newline + 1;
+				break;
+			}
+		}
+	}
+
+	close(fd);
+
+	return true;
+}
diff --git a/tools/gator/daemon/Proc.h b/tools/gator/daemon/Proc.h
new file mode 100644
index 000000000000..2a1a7cbc1e99
--- /dev/null
+++ b/tools/gator/daemon/Proc.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PROC_H
+#define PROC_H
+
+#include <stdint.h>
+
+class Buffer;
+class DynBuf;
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2);
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b);
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone);
+
+#endif // PROC_H
diff --git a/tools/gator/daemon/Sender.cpp b/tools/gator/daemon/Sender.cpp
new file mode 100644
index 000000000000..8a54a6678974
--- /dev/null
+++ b/tools/gator/daemon/Sender.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Sender.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+Sender::Sender(OlySocket* socket) {
+	mDataFile = NULL;
+	mDataSocket = NULL;
+
+	// Set up the socket connection
+	if (socket) {
+		char streamline[64] = {0};
+		mDataSocket = socket;
+
+		// Receive magic sequence - can wait forever
+		// Streamline will send data prior to the magic sequence for legacy support, which should be ignored for v4+
+		while (strcmp("STREAMLINE", streamline) != 0) {
+			if (mDataSocket->receiveString(streamline, sizeof(streamline)) == -1) {
+				logg->logError(__FILE__, __LINE__, "Socket disconnected");
+				handleException();
+			}
+		}
+
+		// Send magic sequence - must be done first, after which error messages can be sent
+		char magic[32];
+		snprintf(magic, 32, "GATOR %i\n", PROTOCOL_VERSION);
+		mDataSocket->send(magic, strlen(magic));
+
+		gSessionData->mWaitingOnCommand = true;
+		logg->logMessage("Completed magic sequence");
+	}
+
+	pthread_mutex_init(&mSendMutex, NULL);
+}
+
+Sender::~Sender() {
+	// Just close it as the client socket is on the stack
+	if (mDataSocket != NULL) {
+		mDataSocket->closeSocket();
+		mDataSocket = NULL;
+	}
+	if (mDataFile != NULL) {
+		fclose(mDataFile);
+	}
+}
+
+void Sender::createDataFile(char* apcDir) {
+	if (apcDir == NULL) {
+		return;
+	}
+
+	mDataFileName = (char*)malloc(strlen(apcDir) + 12);
+	sprintf(mDataFileName, "%s/0000000000", apcDir);
+	mDataFile = fopen_cloexec(mDataFileName, "wb");
+	if (!mDataFile) {
+		logg->logError(__FILE__, __LINE__, "Failed to open binary file: %s", mDataFileName);
+		handleException();
+	}
+}
+
+void Sender::writeData(const char* data, int length, int type) {
+	if (length < 0 || (data == NULL && length > 0)) {
+		return;
+	}
+
+	// Multiple threads call writeData()
+	pthread_mutex_lock(&mSendMutex);
+
+	// Send data over the socket connection
+	if (mDataSocket) {
+		// Start alarm
+		const int alarmDuration = 8;
+		alarm(alarmDuration);
+
+		// Send data over the socket, sending the type and size first
+		logg->logMessage("Sending data with length %d", length);
+		if (type != RESPONSE_APC_DATA) {
+			// type and length already added by the Collector for apc data
+			unsigned char header[5];
+			header[0] = type;
+			Buffer::writeLEInt(header + 1, length);
+			mDataSocket->send((char*)&header, sizeof(header));
+		}
+
+		// 100Kbits/sec * alarmDuration sec / 8 bits/byte
+		const int chunkSize = 100*1000 * alarmDuration / 8;
+		int pos = 0;
+		while (true) {
+			mDataSocket->send((const char*)data + pos, min(length - pos, chunkSize));
+			pos += chunkSize;
+			if (pos >= length) {
+				break;
+			}
+
+			// Reset the alarm
+			alarm(alarmDuration);
+			logg->logMessage("Resetting the alarm");
+		}
+
+		// Stop alarm
+		alarm(0);
+	}
+
+	// Write data to disk as long as it is not meta data
+	if (mDataFile && type == RESPONSE_APC_DATA) {
+		logg->logMessage("Writing data with length %d", length);
+		// Send data to the data file
+		if (fwrite(data, 1, length, mDataFile) != (unsigned int)length) {
+			logg->logError(__FILE__, __LINE__, "Failed writing binary file %s", mDataFileName);
+			handleException();
+		}
+	}
+
+	pthread_mutex_unlock(&mSendMutex);
+}
diff --git a/tools/gator/daemon/Sender.h b/tools/gator/daemon/Sender.h
new file mode 100644
index 000000000000..5aa911713820
--- /dev/null
+++ b/tools/gator/daemon/Sender.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SENDER_H__
+#define __SENDER_H__
+
+#include <stdio.h>
+#include <pthread.h>
+
+class OlySocket;
+
+enum {
+	RESPONSE_XML = 1,
+	RESPONSE_APC_DATA = 3,
+	RESPONSE_ACK = 4,
+	RESPONSE_NAK = 5,
+	RESPONSE_ERROR = 0xFF
+};
+
+class Sender {
+public:
+	Sender(OlySocket* socket);
+	~Sender();
+	void writeData(const char* data, int length, int type);
+	void createDataFile(char* apcDir);
+private:
+	OlySocket* mDataSocket;
+	FILE* mDataFile;
+	char* mDataFileName;
+	pthread_mutex_t mSendMutex;
+
+	// Intentionally unimplemented
+	Sender(const Sender &);
+	Sender &operator=(const Sender &);
+};
+
+#endif //__SENDER_H__
diff --git a/tools/gator/daemon/SessionData.cpp b/tools/gator/daemon/SessionData.cpp
new file mode 100644
index 000000000000..0e65d7842647
--- /dev/null
+++ b/tools/gator/daemon/SessionData.cpp
@@ -0,0 +1,261 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionData.h"
+
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "CPUFreqDriver.h"
+#include "DiskIODriver.h"
+#include "FSDriver.h"
+#include "HwmonDriver.h"
+#include "Logging.h"
+#include "MemInfoDriver.h"
+#include "NetDriver.h"
+#include "SessionXML.h"
+
+#define CORE_NAME_UNKNOWN "unknown"
+
+SessionData* gSessionData = NULL;
+
+SessionData::SessionData() {
+	usDrivers[0] = new HwmonDriver();
+	usDrivers[1] = new FSDriver();
+	usDrivers[2] = new MemInfoDriver();
+	usDrivers[3] = new NetDriver();
+	usDrivers[4] = new CPUFreqDriver();
+	usDrivers[5] = new DiskIODriver();
+	initialize();
+}
+
+SessionData::~SessionData() {
+}
+
+void SessionData::initialize() {
+	mWaitingOnCommand = false;
+	mSessionIsActive = false;
+	mLocalCapture = false;
+	mOneShot = false;
+	mSentSummary = false;
+	mAllowCommands = false;
+	const size_t cpuIdSize = sizeof(int)*NR_CPUS;
+	// Share mCpuIds across all instances of gatord
+	mCpuIds = (int *)mmap(NULL, cpuIdSize, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (mCpuIds == MAP_FAILED) {
+		logg->logError(__FILE__, __LINE__, "Unable to mmap shared memory for cpuids");
+		handleException();
+	}
+	memset(mCpuIds, -1, cpuIdSize);
+	strcpy(mCoreName, CORE_NAME_UNKNOWN);
+	readModel();
+	readCpuInfo();
+	mImages = NULL;
+	mConfigurationXMLPath = NULL;
+	mSessionXMLPath = NULL;
+	mEventsXMLPath = NULL;
+	mTargetPath = NULL;
+	mAPCDir = NULL;
+	mCaptureWorkingDir = NULL;
+	mCaptureCommand = NULL;
+	mCaptureUser = NULL;
+	mSampleRate = 0;
+	mLiveRate = 0;
+	mDuration = 0;
+	mMonotonicStarted = -1;
+	mBacktraceDepth = 0;
+	mTotalBufferSize = 0;
+	// sysconf(_SC_NPROCESSORS_CONF) is unreliable on 2.6 Android, get the value from the kernel module
+	mCores = 1;
+	mPageSize = 0;
+}
+
+void SessionData::parseSessionXML(char* xmlString) {
+	SessionXML session(xmlString);
+	session.parse();
+
+	// Set session data values - use prime numbers just below the desired value to reduce the chance of events firing at the same time
+	if (strcmp(session.parameters.sample_rate, "high") == 0) {
+		mSampleRate = 9973; // 10000
+	} else if (strcmp(session.parameters.sample_rate, "normal") == 0) {
+		mSampleRate = 997; // 1000
+	} else if (strcmp(session.parameters.sample_rate, "low") == 0) {
+		mSampleRate = 97; // 100
+	} else if (strcmp(session.parameters.sample_rate, "none") == 0) {
+		mSampleRate = 0;
+	} else {
+		logg->logError(__FILE__, __LINE__, "Invalid sample rate (%s) in session xml.", session.parameters.sample_rate);
+		handleException();
+	}
+	mBacktraceDepth = session.parameters.call_stack_unwinding == true ? 128 : 0;
+
+	// Determine buffer size (in MB) based on buffer mode
+	mOneShot = true;
+	if (strcmp(session.parameters.buffer_mode, "streaming") == 0) {
+		mOneShot = false;
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "small") == 0) {
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "normal") == 0) {
+		mTotalBufferSize = 4;
+	} else if (strcmp(session.parameters.buffer_mode, "large") == 0) {
+		mTotalBufferSize = 16;
+	} else {
+		logg->logError(__FILE__, __LINE__, "Invalid value for buffer mode in session xml.");
+		handleException();
+	}
+
+	// Convert milli- to nanoseconds
+	mLiveRate = session.parameters.live_rate * (int64_t)1000000;
+	if (mLiveRate > 0 && mLocalCapture) {
+		logg->logMessage("Local capture is not compatable with live, disabling live");
+		mLiveRate = 0;
+	}
+
+	if (!mAllowCommands && (mCaptureCommand != NULL)) {
+		logg->logError(__FILE__, __LINE__, "Running a command during a capture is not currently allowed. Please restart gatord with the -a flag.");
+		handleException();
+	}
+}
+
+void SessionData::readModel() {
+	FILE *fh = fopen("/proc/device-tree/model", "rb");
+	if (fh == NULL) {
+		return;
+	}
+
+	char buf[256];
+	if (fgets(buf, sizeof(buf), fh) != NULL) {
+		strcpy(mCoreName, buf);
+	}
+
+	fclose(fh);
+}
+
+void SessionData::readCpuInfo() {
+	char temp[256]; // arbitrarily large amount
+	mMaxCpuId = -1;
+
+	FILE *f = fopen("/proc/cpuinfo", "r");
+	if (f == NULL) {
+		logg->logMessage("Error opening /proc/cpuinfo\n"
+			"The core name in the captured xml file will be 'unknown'.");
+		return;
+	}
+
+	bool foundCoreName = false;
+	int processor = -1;
+	while (fgets(temp, sizeof(temp), f)) {
+		const size_t len = strlen(temp);
+
+		if (len == 1) {
+			// New section, clear the processor. Streamline will not know the cpus if the pre Linux 3.8 format of cpuinfo is encountered but also that no incorrect information will be transmitted.
+			processor = -1;
+			continue;
+		}
+
+		if (len > 0) {
+			// Replace the line feed with a null
+			temp[len - 1] = '\0';
+		}
+
+		const bool foundHardware = strstr(temp, "Hardware") != 0;
+		const bool foundCPUPart = strstr(temp, "CPU part") != 0;
+		const bool foundProcessor = strstr(temp, "processor") != 0;
+		if (foundHardware || foundCPUPart || foundProcessor) {
+			char* position = strchr(temp, ':');
+			if (position == NULL || (unsigned int)(position - temp) + 2 >= strlen(temp)) {
+				logg->logMessage("Unknown format of /proc/cpuinfo\n"
+					"The core name in the captured xml file will be 'unknown'.");
+				return;
+			}
+			position += 2;
+
+			if (foundHardware && (strcmp(mCoreName, CORE_NAME_UNKNOWN) == 0)) {
+				strncpy(mCoreName, position, sizeof(mCoreName));
+				mCoreName[sizeof(mCoreName) - 1] = 0; // strncpy does not guarantee a null-terminated string
+				foundCoreName = true;
+			}
+
+			if (foundCPUPart) {
+				const int cpuId = strtol(position, NULL, 0);
+				// If this does not have the full topology in /proc/cpuinfo, mCpuIds[0] may not have the 1 CPU part emitted - this guarantees it's in mMaxCpuId
+				if (cpuId > mMaxCpuId) {
+					mMaxCpuId = cpuId;
+				}
+				if (processor >= NR_CPUS) {
+					logg->logMessage("Too many processors, please increase NR_CPUS");
+				} else if (processor >= 0) {
+					mCpuIds[processor] = cpuId;
+				}
+			}
+
+			if (foundProcessor) {
+				processor = strtol(position, NULL, 0);
+			}
+		}
+	}
+
+	if (!foundCoreName) {
+		logg->logMessage("Could not determine core name from /proc/cpuinfo\n"
+				 "The core name in the captured xml file will be 'unknown'.");
+	}
+	fclose(f);
+}
+
+uint64_t getTime() {
+	struct timespec ts;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+		logg->logError(__FILE__, __LINE__, "Failed to get uptime");
+		handleException();
+	}
+	return (NS_PER_S*ts.tv_sec + ts.tv_nsec);
+}
+
+int getEventKey() {
+	// key 0 is reserved as a timestamp
+	// key 1 is reserved as the marker for thread specific counters
+	// key 2 is reserved as the marker for core
+	// Odd keys are assigned by the driver, even keys by the daemon
+	static int key = 4;
+
+	const int ret = key;
+	key += 2;
+	return ret;
+}
+
+int pipe_cloexec(int pipefd[2]) {
+	if (pipe(pipefd) != 0) {
+		return -1;
+	}
+
+	int fdf;
+	if (((fdf = fcntl(pipefd[0], F_GETFD)) == -1) || (fcntl(pipefd[0], F_SETFD, fdf | FD_CLOEXEC) != 0) ||
+			((fdf = fcntl(pipefd[1], F_GETFD)) == -1) || (fcntl(pipefd[1], F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(pipefd[0]);
+		close(pipefd[1]);
+		return -1;
+	}
+	return 0;
+}
+
+FILE *fopen_cloexec(const char *path, const char *mode) {
+	FILE *fh = fopen(path, mode);
+	if (fh == NULL) {
+		return NULL;
+	}
+	int fd = fileno(fh);
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		fclose(fh);
+		return NULL;
+	}
+	return fh;
+}
diff --git a/tools/gator/daemon/SessionData.h b/tools/gator/daemon/SessionData.h
new file mode 100644
index 000000000000..ed282af4a869
--- /dev/null
+++ b/tools/gator/daemon/SessionData.h
@@ -0,0 +1,102 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_DATA_H
+#define SESSION_DATA_H
+
+#include <stdint.h>
+
+#include "AnnotateListener.h"
+#include "Config.h"
+#include "Counter.h"
+#include "FtraceDriver.h"
+#include "KMod.h"
+#include "MaliVideoDriver.h"
+#include "PerfDriver.h"
+
+#define PROTOCOL_VERSION 20
+// Differentiates development versions (timestamp) from release versions
+#define PROTOCOL_DEV 1000
+
+#define NS_PER_S 1000000000LL
+#define NS_PER_MS 1000000LL
+#define NS_PER_US 1000LL
+
+struct ImageLinkList {
+	char* path;
+	struct ImageLinkList *next;
+};
+
+class SessionData {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+
+	SessionData();
+	~SessionData();
+	void initialize();
+	void parseSessionXML(char* xmlString);
+	void readModel();
+	void readCpuInfo();
+
+	PolledDriver *usDrivers[6];
+	KMod kmod;
+	PerfDriver perf;
+	MaliVideoDriver maliVideo;
+	FtraceDriver ftraceDriver;
+	AnnotateListener annotateListener;
+
+	char mCoreName[MAX_STRING_LEN];
+	struct ImageLinkList *mImages;
+	char *mConfigurationXMLPath;
+	char *mSessionXMLPath;
+	char *mEventsXMLPath;
+	char *mTargetPath;
+	char *mAPCDir;
+	char *mCaptureWorkingDir;
+	char *mCaptureCommand;
+	char *mCaptureUser;
+
+	bool mWaitingOnCommand;
+	bool mSessionIsActive;
+	bool mLocalCapture;
+	// halt processing of the driver data until profiling is complete or the buffer is filled
+	bool mOneShot;
+	bool mIsEBS;
+	bool mSentSummary;
+	bool mAllowCommands;
+
+	int64_t mMonotonicStarted;
+	int mBacktraceDepth;
+	// number of MB to use for the entire collection buffer
+	int mTotalBufferSize;
+	int mSampleRate;
+	int64_t mLiveRate;
+	int mDuration;
+	int mCores;
+	int mPageSize;
+	int *mCpuIds;
+	int mMaxCpuId;
+
+	// PMU Counters
+	int mCounterOverflow;
+	Counter mCounters[MAX_PERFORMANCE_COUNTERS];
+
+private:
+	// Intentionally unimplemented
+	SessionData(const SessionData &);
+	SessionData &operator=(const SessionData &);
+};
+
+extern SessionData* gSessionData;
+
+uint64_t getTime();
+int getEventKey();
+int pipe_cloexec(int pipefd[2]);
+FILE *fopen_cloexec(const char *path, const char *mode);
+
+#endif // SESSION_DATA_H
diff --git a/tools/gator/daemon/SessionXML.cpp b/tools/gator/daemon/SessionXML.cpp
new file mode 100644
index 000000000000..dea4c8f299ec
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.cpp
@@ -0,0 +1,111 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char *TAG_SESSION = "session";
+static const char *TAG_IMAGE   = "image";
+
+static const char *ATTR_VERSION              = "version";
+static const char *ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding";
+static const char *ATTR_BUFFER_MODE          = "buffer_mode";
+static const char *ATTR_SAMPLE_RATE          = "sample_rate";
+static const char *ATTR_DURATION             = "duration";
+static const char *ATTR_PATH                 = "path";
+static const char *ATTR_LIVE_RATE            = "live_rate";
+static const char *ATTR_CAPTURE_WORKING_DIR  = "capture_working_dir";
+static const char *ATTR_CAPTURE_COMMAND      = "capture_command";
+static const char *ATTR_CAPTURE_USER         = "capture_user";
+
+SessionXML::SessionXML(const char *str) {
+	parameters.buffer_mode[0] = 0;
+	parameters.sample_rate[0] = 0;
+	parameters.call_stack_unwinding = false;
+	parameters.live_rate = 0;
+	mSessionXML = str;
+	logg->logMessage(mSessionXML);
+}
+
+SessionXML::~SessionXML() {
+}
+
+void SessionXML::parse() {
+	mxml_node_t *tree;
+	mxml_node_t *node;
+
+	tree = mxmlLoadString(NULL, mSessionXML, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND);
+
+	if (node) {
+		sessionTag(tree, node);
+		mxmlDelete(tree);
+		return;
+	}
+
+	logg->logError(__FILE__, __LINE__, "No session tag found in the session.xml file");
+	handleException();
+}
+
+void SessionXML::sessionTag(mxml_node_t *tree, mxml_node_t *node) {
+	int version = 0;
+	if (mxmlElementGetAttr(node, ATTR_VERSION)) version = strtol(mxmlElementGetAttr(node, ATTR_VERSION), NULL, 10);
+	if (version != 1) {
+		logg->logError(__FILE__, __LINE__, "Invalid session.xml version: %d", version);
+		handleException();
+	}
+
+	// copy to pre-allocated strings
+	if (mxmlElementGetAttr(node, ATTR_BUFFER_MODE)) {
+		strncpy(parameters.buffer_mode, mxmlElementGetAttr(node, ATTR_BUFFER_MODE), sizeof(parameters.buffer_mode));
+		parameters.buffer_mode[sizeof(parameters.buffer_mode) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_SAMPLE_RATE)) {
+		strncpy(parameters.sample_rate, mxmlElementGetAttr(node, ATTR_SAMPLE_RATE), sizeof(parameters.sample_rate));
+		parameters.sample_rate[sizeof(parameters.sample_rate) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)) gSessionData->mCaptureWorkingDir = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)) gSessionData->mCaptureCommand = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_USER)) gSessionData->mCaptureUser = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_USER));
+
+	// integers/bools
+	parameters.call_stack_unwinding = util->stringToBool(mxmlElementGetAttr(node, ATTR_CALL_STACK_UNWINDING), false);
+	if (mxmlElementGetAttr(node, ATTR_DURATION)) gSessionData->mDuration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10);
+	if (mxmlElementGetAttr(node, ATTR_LIVE_RATE)) parameters.live_rate = strtol(mxmlElementGetAttr(node, ATTR_LIVE_RATE), NULL, 10);
+
+	// parse subtags
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		if (strcmp(TAG_IMAGE, mxmlGetElement(node)) == 0) {
+			sessionImage(node);
+		}
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+}
+
+void SessionXML::sessionImage(mxml_node_t *node) {
+	int length = strlen(mxmlElementGetAttr(node, ATTR_PATH));
+	struct ImageLinkList *image;
+
+	image = (struct ImageLinkList *)malloc(sizeof(struct ImageLinkList));
+	image->path = (char*)malloc(length + 1);
+	image->path = strdup(mxmlElementGetAttr(node, ATTR_PATH));
+	image->next = gSessionData->mImages;
+	gSessionData->mImages = image;
+}
diff --git a/tools/gator/daemon/SessionXML.h b/tools/gator/daemon/SessionXML.h
new file mode 100644
index 000000000000..53965749c74b
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_XML_H
+#define SESSION_XML_H
+
+#include "mxml/mxml.h"
+
+struct ImageLinkList;
+
+struct ConfigParameters {
+	// buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size
+	char buffer_mode[64];
+	// capture mode, "high", "normal", or "low"
+	char sample_rate[64];
+	// whether stack unwinding is performed
+	bool call_stack_unwinding;
+	int live_rate;
+};
+
+class SessionXML {
+public:
+	SessionXML(const char *str);
+	~SessionXML();
+	void parse();
+	ConfigParameters parameters;
+private:
+	const char *mSessionXML;
+	void sessionTag(mxml_node_t *tree, mxml_node_t *node);
+	void sessionImage(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	SessionXML(const SessionXML &);
+	SessionXML &operator=(const SessionXML &);
+};
+
+#endif // SESSION_XML_H
diff --git a/tools/gator/daemon/Setup.cpp b/tools/gator/daemon/Setup.cpp
new file mode 100644
index 000000000000..d4ce0328c633
--- /dev/null
+++ b/tools/gator/daemon/Setup.cpp
@@ -0,0 +1,232 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Setup.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Config.h"
+#include "DynBuf.h"
+#include "Logging.h"
+
+bool getLinuxVersion(int version[3]) {
+	// Check the kernel version
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	version[0] = 0;
+	version[1] = 0;
+	version[2] = 0;
+
+	int part = 0;
+	char *ch = utsname.release;
+	while (*ch >= '0' && *ch <= '9' && part < 3) {
+		version[part] = 10*version[part] + *ch - '0';
+
+		++ch;
+		if (*ch == '.') {
+			++part;
+			++ch;
+		}
+	}
+
+	return true;
+}
+
+static int pgrep_gator(DynBuf *const printb) {
+	DynBuf b;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logError(__FILE__, __LINE__, "gator: error: opendir failed");
+		handleException();
+	}
+
+	int self = getpid();
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0' || (pid == self)) {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logError(__FILE__, __LINE__, "gator: error: DynBuf::printf failed");
+			handleException();
+		}
+
+		if (!b.read(printb->getBuf())) {
+			// This is not a fatal error - the thread just doesn't exist any more
+			continue;
+		}
+
+		char *comm = strchr(b.getBuf(), '(');
+		if (comm == NULL) {
+			logg->logError(__FILE__, __LINE__, "gator: error: parsing stat begin failed");
+			handleException();
+		}
+		++comm;
+		char *const str = strrchr(comm, ')');
+		if (str == NULL) {
+			logg->logError(__FILE__, __LINE__, "gator: error: parsing stat end failed");
+			handleException();
+		}
+		*str = '\0';
+
+		if (strncmp(comm, "gator", 5) == 0) {
+			// Assume there is only one gator process
+			return pid;
+		}
+	}
+
+	closedir(proc);
+
+	return -1;
+}
+
+int update(const char *const gatorPath) {
+	printf("gator: starting\n");
+
+	int version[3];
+	if (!getLinuxVersion(version)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: getLinuxVersion failed");
+		handleException();
+	}
+
+	if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(2, 6, 32)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as this kernel version is not supported. Please upgrade the kernel on your device.");
+		handleException();
+	}
+
+	if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as gator.ko is required for this version of Linux. Please build gator.ko and gatord and install them on your device.");
+		handleException();
+	}
+
+	if (access("/sys/module/gator", F_OK) == 0) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline has detected that the gator kernel module is loaded on your device. Please build an updated version of gator.ko and gatord and install them on your device.");
+		handleException();
+	}
+
+	if (geteuid() != 0) {
+		printf("gator: trying sudo\n");
+		execlp("sudo", "sudo", gatorPath, "-u", NULL);
+		// Streamline will provide the password if needed
+
+		printf("gator: trying su\n");
+		char buf[1<<10];
+		snprintf(buf, sizeof(buf), "%s -u", gatorPath);
+		execlp("su", "su", "-", "-c", buf, NULL);
+		// Streamline will provide the password if needed
+
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline was unable to sudo to root on your device. Please double check passwords, ensure sudo or su work with this user or try a different username.");
+		handleException();
+	}
+	printf("gator: now root\n");
+
+	// setenforce 0 not needed for userspace gator
+
+	// Kill existing gator
+	DynBuf gatorStatPath;
+	int gator_main = pgrep_gator(&gatorStatPath);
+	if (gator_main > 0) {
+		if (kill(gator_main, SIGTERM) != 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: kill SIGTERM failed");
+			handleException();
+		}
+		for (int i = 0; ; ++i) {
+			if (access(gatorStatPath.getBuf(), F_OK) != 0) {
+				break;
+			}
+			if (i == 5) {
+				if (kill(gator_main, SIGKILL) != 0) {
+					logg->logError(__FILE__, __LINE__, "gator: error: kill SIGKILL failed");
+					handleException();
+				}
+			} else if (i >= 10) {
+				logg->logError(__FILE__, __LINE__, "gator: error: unable to kill running gator");
+				handleException();
+			}
+			sleep(1);
+		}
+	}
+	printf("gator: no gatord running\n");
+
+	rename("gatord", "gatord.old");
+	rename("gator.ko", "gator.ko.old");
+
+	// Rename gatord.YYYYMMDDHHMMSSMMMM to gatord
+	char *newGatorPath = strdup(gatorPath);
+	char *dot = strrchr(newGatorPath, '.');
+	if (dot != NULL) {
+		*dot = '\0';
+		if (rename(gatorPath, newGatorPath) != 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: rename failed");
+			handleException();
+		}
+	}
+
+	// Fork and start gatord (redirect stdout and stderr)
+	int child = fork();
+	if (child < 0) {
+		logg->logError(__FILE__, __LINE__, "gator: error: fork failed");
+		handleException();
+	} else if (child == 0) {
+		int inFd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		if (inFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of /dev/null failed");
+			handleException();
+		}
+		int outFd = open("gatord.out", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600);
+		if (outFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.out failed");
+			handleException();
+		}
+		int errFd = open("gatord.err", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600);
+		if (errFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.err failed");
+			handleException();
+		}
+		if (dup2(inFd, STDIN_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdin failed");
+			handleException();
+		}
+		if (dup2(outFd, STDOUT_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdout failed");
+			handleException();
+		}
+		if (dup2(errFd, STDERR_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stderr failed");
+			handleException();
+		}
+		execlp(newGatorPath, newGatorPath, "-a", NULL);
+		logg->logError(__FILE__, __LINE__, "gator: error: execlp failed");
+		handleException();
+	}
+
+	printf("gator: done\n");
+
+	return 0;
+}
diff --git a/tools/gator/daemon/Setup.h b/tools/gator/daemon/Setup.h
new file mode 100644
index 000000000000..280d61139784
--- /dev/null
+++ b/tools/gator/daemon/Setup.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SETUP_H
+#define SETUP_H
+
+// From include/generated/uapi/linux/version.h
+#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))
+
+bool getLinuxVersion(int version[3]);
+int update(const char *const gatorPath);
+
+#endif // SETUP_H
diff --git a/tools/gator/daemon/Source.cpp b/tools/gator/daemon/Source.cpp
new file mode 100644
index 000000000000..60cf704e599b
--- /dev/null
+++ b/tools/gator/daemon/Source.cpp
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Source.h"
+
+#include "Logging.h"
+
+Source::Source() : mThreadID() {
+}
+
+Source::~Source() {
+}
+
+void Source::start() {
+	if (pthread_create(&mThreadID, NULL, runStatic, this)) {
+		logg->logError(__FILE__, __LINE__, "Failed to create source thread");
+		handleException();
+	}
+}
+
+void Source::join() {
+	pthread_join(mThreadID, NULL);
+}
+
+void *Source::runStatic(void *arg) {
+	static_cast<Source *>(arg)->run();
+	return NULL;
+}
diff --git a/tools/gator/daemon/Source.h b/tools/gator/daemon/Source.h
new file mode 100644
index 000000000000..56ac3d6e94f3
--- /dev/null
+++ b/tools/gator/daemon/Source.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SOURCE_H
+#define SOURCE_H
+
+#include <pthread.h>
+
+class Sender;
+
+class Source {
+public:
+	Source();
+	virtual ~Source();
+
+	virtual bool prepare() = 0;
+	void start();
+	virtual void run() = 0;
+	virtual void interrupt() = 0;
+	void join();
+
+	virtual bool isDone() = 0;
+	virtual void write(Sender *sender) = 0;
+
+private:
+	static void *runStatic(void *arg);
+
+	pthread_t mThreadID;
+
+	// Intentionally undefined
+	Source(const Source &);
+	Source &operator=(const Source &);
+};
+
+#endif // SOURCE_H
diff --git a/tools/gator/daemon/StreamlineSetup.cpp b/tools/gator/daemon/StreamlineSetup.cpp
new file mode 100644
index 000000000000..2b61eaeb290d
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.cpp
@@ -0,0 +1,272 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "StreamlineSetup.h"
+
+#include "Buffer.h"
+#include "CapturedXML.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+static const char* TAG_SESSION = "session";
+static const char* TAG_REQUEST = "request";
+static const char* TAG_CONFIGURATIONS = "configurations";
+
+static const char* ATTR_TYPE           = "type";
+static const char* VALUE_EVENTS        = "events";
+static const char* VALUE_CONFIGURATION = "configuration";
+static const char* VALUE_COUNTERS      = "counters";
+static const char* VALUE_CAPTURED      = "captured";
+static const char* VALUE_DEFAULTS      = "defaults";
+
+StreamlineSetup::StreamlineSetup(OlySocket* s) {
+	bool ready = false;
+	char* data = NULL;
+	int type;
+
+	mSocket = s;
+
+	// Receive commands from Streamline (master)
+	while (!ready) {
+		// receive command over socket
+		gSessionData->mWaitingOnCommand = true;
+		data = readCommand(&type);
+
+		// parse and handle data
+		switch (type) {
+			case COMMAND_REQUEST_XML:
+				handleRequest(data);
+				break;
+			case COMMAND_DELIVER_XML:
+				handleDeliver(data);
+				break;
+			case COMMAND_APC_START:
+				logg->logMessage("Received apc start request");
+				ready = true;
+				break;
+			case COMMAND_APC_STOP:
+				logg->logMessage("Received apc stop request before apc start request");
+				exit(0);
+				break;
+			case COMMAND_DISCONNECT:
+				logg->logMessage("Received disconnect command");
+				exit(0);
+				break;
+			case COMMAND_PING:
+				logg->logMessage("Received ping command");
+				sendData(NULL, 0, RESPONSE_ACK);
+				break;
+			default:
+				logg->logError(__FILE__, __LINE__, "Target error: Unknown command type, %d", type);
+				handleException();
+		}
+
+		free(data);
+	}
+
+	if (gSessionData->mCounterOverflow > 0) {
+		logg->logError(__FILE__, __LINE__, "Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+		handleException();
+	}
+}
+
+StreamlineSetup::~StreamlineSetup() {
+}
+
+char* StreamlineSetup::readCommand(int* command) {
+	unsigned char header[5];
+	char* data;
+	int response;
+
+	// receive type and length
+	response = mSocket->receiveNBytes((char*)&header, sizeof(header));
+
+	// After receiving a single byte, we are no longer waiting on a command
+	gSessionData->mWaitingOnCommand = false;
+
+	if (response < 0) {
+		logg->logError(__FILE__, __LINE__, "Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	const char type = header[0];
+	const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+
+	// add artificial limit
+	if ((length < 0) || length > 1024 * 1024) {
+		logg->logError(__FILE__, __LINE__, "Target error: Invalid length received, %d", length);
+		handleException();
+	}
+
+	// allocate memory to contain the xml file, size of zero returns a zero size object
+	data = (char*)calloc(length + 1, 1);
+	if (data == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to allocate memory for xml");
+		handleException();
+	}
+
+	// receive data
+	response = mSocket->receiveNBytes(data, length);
+	if (response < 0) {
+		logg->logError(__FILE__, __LINE__, "Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	// null terminate the data for string parsing
+	if (length > 0) {
+		data[length] = 0;
+	}
+
+	*command = type;
+	return data;
+}
+
+void StreamlineSetup::handleRequest(char* xml) {
+	mxml_node_t *tree, *node;
+	const char * attr = NULL;
+
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_REQUEST, ATTR_TYPE, NULL, MXML_DESCEND_FIRST);
+	if (node) {
+		attr = mxmlElementGetAttr(node, ATTR_TYPE);
+	}
+	if (attr && strcmp(attr, VALUE_EVENTS) == 0) {
+		sendEvents();
+		logg->logMessage("Sent events xml response");
+	} else if (attr && strcmp(attr, VALUE_CONFIGURATION) == 0) {
+		sendConfiguration();
+		logg->logMessage("Sent configuration xml response");
+	} else if (attr && strcmp(attr, VALUE_COUNTERS) == 0) {
+		sendCounters();
+		logg->logMessage("Sent counters xml response");
+	} else if (attr && strcmp(attr, VALUE_CAPTURED) == 0) {
+		CapturedXML capturedXML;
+		char* capturedText = capturedXML.getXML(false);
+		sendData(capturedText, strlen(capturedText), RESPONSE_XML);
+		free(capturedText);
+		logg->logMessage("Sent captured xml response");
+	} else if (attr && strcmp(attr, VALUE_DEFAULTS) == 0) {
+		sendDefaults();
+		logg->logMessage("Sent default configuration xml response");
+	} else {
+		char error[] = "Unknown request";
+		sendData(error, strlen(error), RESPONSE_NAK);
+		logg->logMessage("Received unknown request:\n%s", xml);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::handleDeliver(char* xml) {
+	mxml_node_t *tree;
+
+	// Determine xml type
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	if (mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Session XML
+		gSessionData->parseSessionXML(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received session xml");
+	} else if (mxmlFindElement(tree, tree, TAG_CONFIGURATIONS, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Configuration XML
+		writeConfiguration(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received configuration xml");
+	} else {
+		// Unknown XML
+		logg->logMessage("Received unknown XML delivery type");
+		sendData(NULL, 0, RESPONSE_NAK);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::sendData(const char* data, uint32_t length, char type) {
+	unsigned char header[5];
+	header[0] = type;
+	Buffer::writeLEInt(header + 1, length);
+	mSocket->send((char*)&header, sizeof(header));
+	mSocket->send((const char*)data, length);
+}
+
+void StreamlineSetup::sendEvents() {
+	EventsXML eventsXML;
+	char* string = eventsXML.getXML();
+	sendString(string, RESPONSE_XML);
+	free(string);
+}
+
+void StreamlineSetup::sendConfiguration() {
+	ConfigurationXML xml;
+
+	const char* string = xml.getConfigurationXML();
+	sendData(string, strlen(string), RESPONSE_XML);
+}
+
+void StreamlineSetup::sendDefaults() {
+	// Send the config built into the binary
+	const char* xml;
+	unsigned int size;
+	ConfigurationXML::getDefaultConfigurationXml(xml, size);
+
+	// Artificial size restriction
+	if (size > 1024*1024) {
+		logg->logError(__FILE__, __LINE__, "Corrupt default configuration file");
+		handleException();
+	}
+
+	sendData(xml, size, RESPONSE_XML);
+}
+
+void StreamlineSetup::sendCounters() {
+	mxml_node_t *xml;
+	mxml_node_t *counters;
+
+	xml = mxmlNewXML("1.0");
+	counters = mxmlNewElement(xml, "counters");
+	int count = 0;
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		count += driver->writeCounters(counters);
+	}
+
+	if (count == 0) {
+		logg->logError(__FILE__, __LINE__, "No counters found, this could be because /dev/gator/events can not be read or because perf is not working correctly");
+		handleException();
+	}
+
+	char* string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	sendString(string, RESPONSE_XML);
+
+	free(string);
+	mxmlDelete(xml);
+}
+
+void StreamlineSetup::writeConfiguration(char* xml) {
+	char path[PATH_MAX];
+
+	ConfigurationXML::getPath(path);
+
+	if (util->writeToDisk(path, xml) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify write permissions to this path.", path);
+		handleException();
+	}
+
+	// Re-populate gSessionData with the configuration, as it has now changed
+	{ ConfigurationXML configuration; }
+
+	if (gSessionData->mCounterOverflow > 0) {
+		logg->logError(__FILE__, __LINE__, "Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/StreamlineSetup.h b/tools/gator/daemon/StreamlineSetup.h
new file mode 100644
index 000000000000..623e14f2b64a
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.h
@@ -0,0 +1,50 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __STREAMLINE_SETUP_H__
+#define __STREAMLINE_SETUP_H__
+
+#include <stdint.h>
+#include <string.h>
+
+class OlySocket;
+
+// Commands from Streamline
+enum {
+	COMMAND_REQUEST_XML = 0,
+	COMMAND_DELIVER_XML = 1,
+	COMMAND_APC_START   = 2,
+	COMMAND_APC_STOP    = 3,
+	COMMAND_DISCONNECT  = 4,
+	COMMAND_PING        = 5
+};
+
+class StreamlineSetup {
+public:
+	StreamlineSetup(OlySocket *socket);
+	~StreamlineSetup();
+private:
+	OlySocket* mSocket;
+
+	char* readCommand(int*);
+	void handleRequest(char* xml);
+	void handleDeliver(char* xml);
+	void sendData(const char* data, uint32_t length, char type);
+	void sendString(const char* string, int type) {sendData(string, strlen(string), type);}
+	void sendEvents();
+	void sendConfiguration();
+	void sendDefaults();
+	void sendCounters();
+	void writeConfiguration(char* xml);
+
+	// Intentionally unimplemented
+	StreamlineSetup(const StreamlineSetup &);
+	StreamlineSetup &operator=(const StreamlineSetup &);
+};
+
+#endif //__STREAMLINE_SETUP_H__
diff --git a/tools/gator/daemon/UEvent.cpp b/tools/gator/daemon/UEvent.cpp
new file mode 100644
index 000000000000..f94a995393e8
--- /dev/null
+++ b/tools/gator/daemon/UEvent.cpp
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UEvent.h"
+
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#include <linux/netlink.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+
+static const char EMPTY[] = "";
+static const char ACTION[] = "ACTION=";
+static const char DEVPATH[] = "DEVPATH=";
+static const char SUBSYSTEM[] = "SUBSYSTEM=";
+
+UEvent::UEvent() : mFd(-1) {
+}
+
+UEvent::~UEvent() {
+	if (mFd >= 0) {
+		close(mFd);
+	}
+}
+
+bool UEvent::init() {
+	mFd = socket_cloexec(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT);
+	if (mFd < 0) {
+		logg->logMessage("%s(%s:%i): socket failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	struct sockaddr_nl sockaddr;
+	memset(&sockaddr, 0, sizeof(sockaddr));
+	sockaddr.nl_family = AF_NETLINK;
+	sockaddr.nl_groups = 1; // bitmask: (1 << 0) == kernel events, (1 << 1) == udev events
+	sockaddr.nl_pid = 0;
+	if (bind(mFd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) != 0) {
+		logg->logMessage("%s(%s:%i): bind failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+bool UEvent::read(UEventResult *const result) {
+	ssize_t bytes = recv(mFd, result->mBuf, sizeof(result->mBuf), 0);
+	if (bytes <= 0) {
+		logg->logMessage("%s(%s:%i): recv failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	result->mAction = EMPTY;
+	result->mDevPath = EMPTY;
+	result->mSubsystem = EMPTY;
+
+	for (int pos = 0; pos < bytes; pos += strlen(result->mBuf + pos) + 1) {
+		char *const str = result->mBuf + pos;
+		if (strncmp(str, ACTION, sizeof(ACTION) - 1) == 0) {
+			result->mAction = str + sizeof(ACTION) - 1;
+		} else if (strncmp(str, DEVPATH, sizeof(DEVPATH) - 1) == 0) {
+			result->mDevPath = str + sizeof(DEVPATH) - 1;
+		} else if (strncmp(str, SUBSYSTEM, sizeof(SUBSYSTEM) - 1) == 0) {
+			result->mSubsystem = str + sizeof(SUBSYSTEM) - 1;
+		}
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/UEvent.h b/tools/gator/daemon/UEvent.h
new file mode 100644
index 000000000000..2f7ef2c93f5d
--- /dev/null
+++ b/tools/gator/daemon/UEvent.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef UEVENT_H
+#define UEVENT_H
+
+struct UEventResult {
+	const char *mAction;
+	const char *mDevPath;
+	const char *mSubsystem;
+	char mBuf[1<<13];
+};
+
+class UEvent {
+public:
+	UEvent();
+	~UEvent();
+
+	bool init();
+	bool read(UEventResult *const result);
+	int getFd() const { return mFd; }
+
+private:
+	int mFd;
+
+	// Intentionally undefined
+	UEvent(const UEvent &);
+	UEvent &operator=(const UEvent &);
+};
+
+#endif // UEVENT_H
diff --git a/tools/gator/daemon/UserSpaceSource.cpp b/tools/gator/daemon/UserSpaceSource.cpp
new file mode 100644
index 000000000000..4a9b22f4b555
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.cpp
@@ -0,0 +1,94 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UserSpaceSource.h"
+
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+UserSpaceSource::UserSpaceSource(sem_t *senderSem) : mBuffer(0, FRAME_BLOCK_COUNTER, gSessionData->mTotalBufferSize*1024*1024, senderSem) {
+}
+
+UserSpaceSource::~UserSpaceSource() {
+}
+
+bool UserSpaceSource::prepare() {
+	return true;
+}
+
+void UserSpaceSource::run() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-counters", 0, 0, 0);
+
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+		gSessionData->usDrivers[i]->start();
+	}
+
+	int64_t monotonic_started = 0;
+	while (monotonic_started <= 0) {
+		usleep(10);
+
+		if (gSessionData->perf.isSetup()) {
+			monotonic_started = gSessionData->mMonotonicStarted;
+		} else {
+			if (DriverSource::readInt64Driver("/dev/gator/started", &monotonic_started) == -1) {
+				logg->logError(__FILE__, __LINE__, "Error reading gator driver start time");
+				handleException();
+			}
+			gSessionData->mMonotonicStarted = monotonic_started;
+		}
+	}
+
+	uint64_t next_time = 0;
+	while (gSessionData->mSessionIsActive) {
+		const uint64_t curr_time = getTime() - monotonic_started;
+		// Sample ten times a second ignoring gSessionData->mSampleRate
+		next_time += NS_PER_S/10;//gSessionData->mSampleRate;
+		if (next_time < curr_time) {
+			logg->logMessage("Too slow, curr_time: %lli next_time: %lli", curr_time, next_time);
+			next_time = curr_time;
+		}
+
+		if (mBuffer.eventHeader(curr_time)) {
+			for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+				gSessionData->usDrivers[i]->read(&mBuffer);
+			}
+			// Only check after writing all counters so that time and corresponding counters appear in the same frame
+			mBuffer.check(curr_time);
+		}
+
+		if (mBuffer.bytesAvailable() <= 0) {
+			logg->logMessage("One shot (counters)");
+			child->endSession();
+		}
+
+		usleep((next_time - curr_time)/NS_PER_US);
+	}
+
+	mBuffer.setDone();
+}
+
+void UserSpaceSource::interrupt() {
+	// Do nothing
+}
+
+bool UserSpaceSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void UserSpaceSource::write(Sender *sender) {
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+}
diff --git a/tools/gator/daemon/UserSpaceSource.h b/tools/gator/daemon/UserSpaceSource.h
new file mode 100644
index 000000000000..9b3666016dc5
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef USERSPACESOURCE_H
+#define USERSPACESOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+// User space counters
+class UserSpaceSource : public Source {
+public:
+	UserSpaceSource(sem_t *senderSem);
+	~UserSpaceSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	Buffer mBuffer;
+
+	// Intentionally unimplemented
+	UserSpaceSource(const UserSpaceSource &);
+	UserSpaceSource &operator=(const UserSpaceSource &);
+};
+
+#endif // USERSPACESOURCE_H
diff --git a/tools/gator/daemon/c++.cpp b/tools/gator/daemon/c++.cpp
new file mode 100644
index 000000000000..6041e5e96469
--- /dev/null
+++ b/tools/gator/daemon/c++.cpp
@@ -0,0 +1,40 @@
+/**
+ * Minimal set of C++ functions so that libstdc++ is not required
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+void operator delete(void *ptr) {
+  if (ptr != NULL) {
+    free(ptr);
+  }
+}
+
+void operator delete[](void *ptr) {
+  operator delete(ptr);
+}
+
+void *operator new(size_t size) {
+  void *ptr = malloc(size == 0 ? 1 : size);
+  if (ptr == NULL) {
+    abort();
+  }
+  return ptr;
+}
+
+void *operator new[](size_t size) {
+  return operator new(size);
+}
+
+extern "C"
+void __cxa_pure_virtual() {
+  printf("pure virtual method called\n");
+  abort();
+}
diff --git a/tools/gator/daemon/common.mk b/tools/gator/daemon/common.mk
new file mode 100644
index 000000000000..769a92e51a35
--- /dev/null
+++ b/tools/gator/daemon/common.mk
@@ -0,0 +1,52 @@
+# -g produces debugging information
+# -O3 maximum optimization
+# -O0 no optimization, used for debugging
+# -Wall enables most warnings
+# -Werror treats warnings as errors
+# -std=c++0x is the planned new c++ standard
+# -std=c++98 is the 1998 c++ standard
+CPPFLAGS += -O3 -Wall -fno-exceptions -pthread -MMD -DETCDIR=\"/etc\" -Ilibsensors
+CXXFLAGS += -fno-rtti -Wextra # -Weffc++
+ifeq ($(WERROR),1)
+	CPPFLAGS += -Werror
+endif
+# -s strips the binary of debug info
+LDFLAGS += -s
+LDLIBS += -lrt -lm -pthread
+TARGET = gatord
+C_SRC = $(wildcard mxml/*.c) $(wildcard libsensors/*.c)
+CXX_SRC = $(wildcard *.cpp)
+
+all: $(TARGET)
+
+events.xml: events_header.xml $(wildcard events-*.xml) events_footer.xml
+	cat $^ > $@
+
+include $(wildcard *.d)
+include $(wildcard mxml/*.d)
+
+EventsXML.cpp: events_xml.h
+ConfigurationXML.cpp: defaults_xml.h
+
+# Don't regenerate conf-lex.c or conf-parse.c
+libsensors/conf-lex.c: ;
+libsensors/conf-parse.c: ;
+
+%_xml.h: %.xml escape
+	./escape $< > $@
+
+%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+%.o: %.cpp
+	$(CXX) $(CXXFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+$(TARGET): $(CXX_SRC:%.cpp=%.o) $(C_SRC:%.c=%.o)
+	$(CC) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
+# Intentionally ignore CC as a native binary is required
+escape: escape.c
+	gcc $^ -o $@
+
+clean:
+	rm -f *.d *.o mxml/*.d mxml/*.o libsensors/*.d libsensors/*.o $(TARGET) escape events.xml events_xml.h defaults_xml.h
diff --git a/tools/gator/daemon/defaults.xml b/tools/gator/daemon/defaults.xml
new file mode 100644
index 000000000000..086eca1e804e
--- /dev/null
+++ b/tools/gator/daemon/defaults.xml
@@ -0,0 +1,84 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configurations revision="3">
+  <configuration counter="ARM_ARM11_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11_cnt0" event="0x7"/>
+  <configuration counter="ARM_ARM11_cnt1" event="0xb"/>
+  <configuration counter="ARM_ARM11MPCore_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11MPCore_cnt0" event="0x08"/>
+  <configuration counter="ARM_ARM11MPCore_cnt1" event="0x0b"/>
+  <configuration counter="ARMv7_Cortex_A5_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt1" event="0x1"/>
+  <configuration counter="ARMv7_Cortex_A7_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt1" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt2" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A8_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt1" event="0x44"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt2" event="0x43"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt3" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A9_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt0" event="0x68"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt1" event="0x06"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt2" event="0x07"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt3" event="0x03"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt4" event="0x04"/>
+  <configuration counter="ARMv7_Cortex_A15_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt3" event="0x19"/>
+  <configuration counter="ARMv7_Cortex_A17_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt3" event="0x19"/>
+  <configuration counter="ARM_Cortex-A53_ccnt" event="0x11"/>
+  <configuration counter="ARM_Cortex-A53_cnt0" event="0x8"/>
+  <configuration counter="ARM_Cortex-A53_cnt1" event="0x16"/>
+  <configuration counter="ARM_Cortex-A53_cnt2" event="0x10"/>
+  <configuration counter="ARM_Cortex-A53_cnt3" event="0x19"/>
+  <configuration counter="ARM_Cortex-A57_ccnt" event="0x11"/>
+  <configuration counter="ARM_Cortex-A57_cnt0" event="0x8"/>
+  <configuration counter="ARM_Cortex-A57_cnt1" event="0x16"/>
+  <configuration counter="ARM_Cortex-A57_cnt2" event="0x10"/>
+  <configuration counter="ARM_Cortex-A57_cnt3" event="0x19"/>
+  <configuration counter="Scorpion_ccnt" event="0xff"/>
+  <configuration counter="Scorpion_cnt0" event="0x08"/>
+  <configuration counter="Scorpion_cnt1" event="0x10"/>
+  <configuration counter="ScorpionMP_ccnt" event="0xff"/>
+  <configuration counter="ScorpionMP_cnt0" event="0x08"/>
+  <configuration counter="ScorpionMP_cnt1" event="0x10"/>
+  <configuration counter="Krait_ccnt" event="0xff"/>
+  <configuration counter="Krait_cnt0" event="0x08"/>
+  <configuration counter="Krait_cnt1" event="0x10"/>
+  <configuration counter="Linux_block_rq_wr"/>
+  <configuration counter="Linux_block_rq_rd"/>
+  <configuration counter="Linux_meminfo_memused"/>
+  <configuration counter="Linux_meminfo_memused2"/>
+  <configuration counter="Linux_meminfo_memfree"/>
+  <configuration counter="Linux_power_cpu_freq"/>
+  <configuration counter="ARM_Mali-4xx_fragment"/>
+  <configuration counter="ARM_Mali-4xx_vertex"/>
+  <configuration counter="ARM_Mali-Midgard_fragment" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_vertex" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_opencl" cores="1"/>
+  <configuration counter="ARM_Mali-T60x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS2_ACTIVE"/>
+  <configuration counter="L2C-310_cnt0" event="0x1"/>
+</configurations>
diff --git a/tools/gator/daemon/escape.c b/tools/gator/daemon/escape.c
new file mode 100644
index 000000000000..2b0863aaf425
--- /dev/null
+++ b/tools/gator/daemon/escape.c
@@ -0,0 +1,75 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * The Makefile in the daemon folder builds and executes 'escape'
+ * 'escape' creates configuration_xml.h from configuration.xml and events_xml.h from events-*.xml
+ * these genereated xml files are then #included and built as part of the gatord binary
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+static void print_escaped_path(char *path) {
+  if (isdigit(*path)) {
+    printf("__");
+  }
+  for (; *path != '\0'; ++path) {
+    printf("%c", isalnum(*path) ? *path : '_');
+  }
+}
+
+int main(int argc, char *argv[]) {
+  int i;
+  char *path;
+  FILE *in = NULL;
+  int ch;
+  unsigned int len = 0;
+
+  for (i = 1; i < argc && argv[i][0] == '-'; ++i) ;
+  if (i == argc) {
+    fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
+    return EXIT_FAILURE;
+  }
+  path = argv[i];
+
+  errno = 0;
+  if ((in = fopen(path, "r")) == NULL) {
+    fprintf(stderr, "Unable to open '%s': %s\n", path, strerror(errno));
+    return EXIT_FAILURE;
+  }
+
+  printf("static const unsigned char ");
+  print_escaped_path(path);
+  printf("[] = {");
+  for (;;) {
+    ch = fgetc(in);
+    if (len != 0) {
+      printf(",");
+    }
+    if (len % 12 == 0) {
+      printf("\n ");
+    }
+    // Write out a null character after the contents of the file but do not increment len
+    printf(" 0x%.2x", (ch == EOF ? 0 : ch));
+    if (ch == EOF) {
+      break;
+    }
+    ++len;
+  }
+  printf("\n};\nstatic const unsigned int ");
+  print_escaped_path(path);
+  printf("_len = %i;\n", len);
+
+  fclose(in);
+
+  return EXIT_SUCCESS;
+}
diff --git a/tools/gator/daemon/events-ARM11.xml b/tools/gator/daemon/events-ARM11.xml
new file mode 100644
index 000000000000..57e323546314
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11.xml
@@ -0,0 +1,39 @@
+  <counter_set name="ARM_ARM11_cnt" count="3"/>
+  <category name="ARM11" counter_set="ARM_ARM11_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instruction executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Mispredicted" description="Branch mis-predicted"/>
+    <event event="0x07" title="Instruction" name="Executed" description="Instructions executed"/>
+    <event event="0x09" title="Cache" name="Data access" description="Data cache access, not including Cache operations"/>
+    <event event="0x0a" title="Cache" name="Data all access" description="Data cache access, not including Cache Operations regardless of whether or not the location is cacheable"/>
+    <event event="0x0b" title="Cache" name="Data miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Write-back" description="Data cache write-back"/>
+    <event event="0x0d" title="Program Counter" name="SW change" description="Software changed the PC"/>
+    <event event="0x0f" title="Cache " name="TLB miss" description="Main TLB miss (unused on ARM1156)"/>
+    <event event="0x10" title="External" name="Access" description="Explicit external data or peripheral access"/>
+    <event event="0x11" title="Cache" name="Data miss" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x12" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of a Data Synchronization Barrier command or Strongly Ordered operation"/>
+    <event event="0x13" title="Disable Interrupts" name="FIQ" description="The number of cycles which FIQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x14" title="Disable Interrupts" name="IRQ" description="The number of cycles which IRQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x20" title="ETM" name="ETMEXTOUT[0]" description="ETMEXTOUT[0] signal was asserted for a cycle"/>
+    <event event="0x21" title="ETM" name="ETMEXTOUT[1]" description="ETMEXTOUT[1] signal was asserted for a cycle"/>
+    <event event="0x22" title="ETM" name="ETMEXTOUT[0,1]" description="ETMEXTOUT[0] or ETMEXTOUT[1] was asserted"/>
+    <event event="0x23" title="Procedure" name="Calls" description="Procedure call instruction executed"/>
+    <event event="0x24" title="Procedure" name="Returns" description="Procedure return instruction executed"/>
+    <event event="0x25" title="Procedure" name="Return and predicted" description="Procedure return instruction executed and return address predicted"/>
+    <event event="0x26" title="Procedure" name="Return and mispredicted" description="Procedure return instruction executed and return address predicted incorrectly"/>
+    <event event="0x30" title="Cache" name="Inst tag or parity error" description="Instruction cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x31" title="Cache" name="Inst parity error" description="Instruction cache RAM parity error (ARM1156 only)"/>
+    <event event="0x32" title="Cache" name="Data tag or parity error" description="Data cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x33" title="Cache" name="Data parity error" description="Data cache RAM parity error (ARM1156 only)"/>
+    <event event="0x34" title="ITCM" name="Error" description="ITCM error (ARM1156 only)"/>
+    <event event="0x35" title="DTCM" name="Error" description="DTCM error (ARM1156 only)"/>
+    <event event="0x36" title="Procedure" name="Return address pop" description="Procedure return address popped off the return stack (ARM1156 only)"/>
+    <event event="0x37" title="Procedure" name="Return address misprediction" description="Procedure return address popped off the return stack has been incorrectly predicted by the PFU (ARM1156 only)"/>
+    <event event="0x38" title="Cache" name="Data dirty parity error" description="Data cache Dirty RAM parity error (ARM1156 only)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ARM11MPCore.xml b/tools/gator/daemon/events-ARM11MPCore.xml
new file mode 100644
index 000000000000..2d5c5e199e66
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11MPCore.xml
@@ -0,0 +1,26 @@
+  <counter_set name="ARM_ARM11MPCore_cnt" count="3"/>
+  <category name="ARM11MPCore" counter_set="ARM_ARM11MPCore_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11MPCore_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instructions executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Not predicted" description="Branch not predicted"/>
+    <event event="0x07" title="Branch" name="Mispredicted" description="Branch mispredicted"/>
+    <event event="0x08" title="Core" name="Instructions" description="Instructions executed"/>
+    <event event="0x09" title="Core" name="Folded Instructions" description="Folded instructions executed"/>
+    <event event="0x0a" title="Cache" name="Data read access" description="Data cache read access, not including cache operations"/>
+    <event event="0x0b" title="Cache" name="Data read miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Data write access" description="Data cache write access"/>
+    <event event="0x0d" title="Cache" name="Data write miss" description="Data cache write miss"/>
+    <event event="0x0e" title="Cache" name="Data line eviction" description="Data cache line eviction, not including cache operations"/>
+    <event event="0x0f" title="Branch" name="PC change w/o mode change" description="Software changed the PC and there is not a mode change"/>
+    <event event="0x10" title="Cache " name="TLB miss" description="Main TLB miss"/>
+    <event event="0x11" title="External" name="External Memory request" description="External memory request (cache refill, noncachable, write-back)"/>
+    <event event="0x12" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x13" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of LSU ordering constraints or CP15 operations (Data Synchronization Barrier command) or Strongly Ordered operation"/>
+    <event event="0x14" title="Write Buffer" name="Write Merges" description="Buffered write merged in a store buffer slot"/>
+    <event event="0xFF" title="Core" name="Cycle counter" description="An increment each cycle"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCI-400.xml b/tools/gator/daemon/events-CCI-400.xml
new file mode 100644
index 000000000000..20002efd1543
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-400.xml
@@ -0,0 +1,98 @@
+  <counter_set name="CCI_400_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400_cnt" per_cpu="no" supports_event_based_sampling="yes">
+    <event counter="CCI_400_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation, CleanInvalid, CleanShared, MakeInvalid"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x14" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x15" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Read request stall cycle because of an address hazard"/>
+    <event event="0x16" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of an ID hazard"/>
+    <event event="0x17" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="Read request stall cycle because the transaction tracker is full. Increase MIx_R_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+    <event event="0x18" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x19" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x1a" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase MIx_W_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+  </category>
+  <counter_set name="CCI_400-r1_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400-r1_cnt" per_cpu="no" supports_event_based_sampling="yes">
+    <event counter="CCI_400-r1_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <event event="0x14" option_set="Slave" title="CCI-400" name="Read stall: slave hazard" description="Read request stall cycle because of a slave interface ID hazard"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x00" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x01" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Stall cycle because of an address hazard. A read or write invalidation is stalled because of an outstanding transaction to an overlapping address"/>
+    <event event="0x02" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of a master interface ID hazard"/>
+    <event event="0x03" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="A read request with a QoS value in the high priority group is stalled for a cycle because the read transaction queue is full. Increase MIx_R_MAX to avoid this stall"/>
+    <event event="0x04" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x05" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x06" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="A write request is stalled for a cycle because the write transaction tracker is full. Increase MIx_W_MAX to avoid this stall"/>
+    <event event="0x07" option_set="Master" title="CCI-400" name="Read Stall: Low Priority" description="A read request with a QoS value in the low priority group is stalled for a cycle because there are no slots available in the read queue for the low priority group"/>
+    <event event="0x08" option_set="Master" title="CCI-400" name="Read Stall: Medium Priority" description="A read request with a QoS value in the medium priority group is stalled for a cycle because there are no slots available in the read queue for the medium priority group"/>
+    <event event="0x09" option_set="Master" title="CCI-400" name="Read Stall: VN0" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0a" option_set="Master" title="CCI-400" name="Read Stall: VN1" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0b" option_set="Master" title="CCI-400" name="Read Stall: VN2" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x0c" option_set="Master" title="CCI-400" name="Read Stall: VN3" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN3"/>
+    <event event="0x0d" option_set="Master" title="CCI-400" name="Write Stall: VN0" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0e" option_set="Master" title="CCI-400" name="Write Stall: VN1" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0f" option_set="Master" title="CCI-400" name="Write Stall: VN2" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x10" option_set="Master" title="CCI-400" name="Write Stall: VN" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN"/>
+    <event event="0x11" option_set="Master" title="CCI-400" name="WriteUnique or WriteLineUnique Stall" description="A WriteUnique or WriteLineUnique request is stalled for a cycle because of an address hazard"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCN-504.xml b/tools/gator/daemon/events-CCN-504.xml
new file mode 100644
index 000000000000..6ef3e6483717
--- /dev/null
+++ b/tools/gator/daemon/events-CCN-504.xml
@@ -0,0 +1,113 @@
+  <counter_set name="CCN-504_cnt" count="4"/>
+  <category name="CCN-504" counter_set="CCN-504_cnt">
+    <event counter="CCN-504_ccnt" title="CCN-504 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="XP_Region">
+      <option event_delta="0x400000" name="XP 0" description="Crosspoint 0"/>
+      <option event_delta="0x410000" name="XP 1" description="Crosspoint 1"/>
+      <option event_delta="0x420000" name="XP 2" description="Crosspoint 2"/>
+      <option event_delta="0x430000" name="XP 3" description="Crosspoint 3"/>
+      <option event_delta="0x440000" name="XP 4" description="Crosspoint 4"/>
+      <option event_delta="0x450000" name="XP 5" description="Crosspoint 5"/>
+      <option event_delta="0x460000" name="XP 6" description="Crosspoint 6"/>
+      <option event_delta="0x470000" name="XP 7" description="Crosspoint 7"/>
+      <option event_delta="0x480000" name="XP 8" description="Crosspoint 8"/>
+      <option event_delta="0x490000" name="XP 9" description="Crosspoint 9"/>
+      <option event_delta="0x4A0000" name="XP 10" description="Crosspoint 10"/>
+    </option_set>
+    <event event="0x0801" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: H-bit" description="Bus 0: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0802" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: S-bit" description="Bus 0: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0803" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: P-Cnt" description="Bus 0: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0804" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: TknV" description="Bus 0: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0809" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: H-bit" description="Bus 1: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x080A" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: S-bit" description="Bus 1: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x080B" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: P-Cnt" description="Bus 1: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x080C" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: TknV" description="Bus 1: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0811" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: H-bit" description="Bus 0: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0812" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: S-bit" description="Bus 0: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0813" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: P-Cnt" description="Bus 0: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0814" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: TknV" description="Bus 0: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0819" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: H-bit" description="Bus 1: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x081A" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: S-bit" description="Bus 1: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x081B" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: P-Cnt" description="Bus 1: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x081C" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: TknV" description="Bus 1: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0821" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: H-bit" description="Bus 0: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0822" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: S-bit" description="Bus 0: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0823" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: P-Cnt" description="Bus 0: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0824" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: TknV" description="Bus 0: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0829" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: H-bit" description="Bus 1: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x082A" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: S-bit" description="Bus 1: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x082B" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: P-Cnt" description="Bus 1: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x082C" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: TknV" description="Bus 1: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0831" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: H-bit" description="Bus 0: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0832" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: S-bit" description="Bus 0: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0833" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: P-Cnt" description="Bus 0: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0834" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: TknV" description="Bus 0: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0839" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: H-bit" description="Bus 1: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x083A" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: S-bit" description="Bus 1: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x083B" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: P-Cnt" description="Bus 1: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x083C" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: TknV" description="Bus 1: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0871" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: H-bit" description="Bus 0: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0872" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: S-bit" description="Bus 0: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0873" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: P-Cnt" description="Bus 0: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0874" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: TknV" description="Bus 0: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0879" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: H-bit" description="Bus 1: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x087A" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: S-bit" description="Bus 1: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x087B" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: P-Cnt" description="Bus 1: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x087C" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: TknV" description="Bus 1: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <option_set name="HN-F_Region">
+      <option event_delta="0x200000" name="HN-F 3" description="Fully-coherent Home Node 3"/>
+      <option event_delta="0x210000" name="HN-F 5" description="Fully-coherent Home Node 5"/>
+      <option event_delta="0x220000" name="HN-F 7" description="Fully-coherent Home Node 7"/>
+      <option event_delta="0x230000" name="HN-F 8" description="Fully-coherent Home Node 8"/>
+      <option event_delta="0x240000" name="HN-F 13" description="Fully-coherent Home Node 13"/>
+      <option event_delta="0x250000" name="HN-F 15" description="Fully-coherent Home Node 15"/>
+      <option event_delta="0x260000" name="HN-F 17" description="Fully-coherent Home Node 17"/>
+      <option event_delta="0x270000" name="HN-F 18" description="Fully-coherent Home Node 18"/>
+    </option_set>
+    <event event="0x0401" option_set="HN-F_Region" title="CCN-504" name="Cache Miss" description="Counts the total cache misses. This is the first time lookup result, and is high priority."/>
+    <event event="0x0402" option_set="HN-F_Region" title="CCN-504" name="L3 SF Cache Access" description="Counts the number of cache accesses. This is the first time access, and is high priority."/>
+    <event event="0x0403" option_set="HN-F_Region" title="CCN-504" name="Cache Fill" description="Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache."/>
+    <event event="0x0404" option_set="HN-F_Region" title="CCN-504" name="POCQ Retry" description="Counts the number of requests that have been retried."/>
+    <event event="0x0405" option_set="HN-F_Region" title="CCN-504" name="POCQ Reqs Recvd" description="Counts the number of requests received by HN."/>
+    <event event="0x0406" option_set="HN-F_Region" title="CCN-504" name="SF Hit" description="Counts the number of snoop filter hits."/>
+    <event event="0x0407" option_set="HN-F_Region" title="CCN-504" name="SF Evictions" description="Counts the number of snoop filter evictions. Cache invalidations are initiated."/>
+    <event event="0x0408" option_set="HN-F_Region" title="CCN-504" name="Snoops Sent" description="Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops."/>
+    <event event="0x0409" option_set="HN-F_Region" title="CCN-504" name="Snoops Broadcast" description="Counts the number of snoop broadcasts sent."/>
+    <event event="0x040A" option_set="HN-F_Region" title="CCN-504" name="L3 Eviction" description="Counts the number of L3 evictions."/>
+    <event event="0x040B" option_set="HN-F_Region" title="CCN-504" name="L3 Fill Invalid Way" description="Counts the number of L3 fills to an invalid way."/>
+    <event event="0x040C" option_set="HN-F_Region" title="CCN-504" name="MC Retries" description="Counts the number of transactions retried by the memory controller."/>
+    <event event="0x040D" option_set="HN-F_Region" title="CCN-504" name="MC Reqs" description="Counts the number of requests to the memory controller."/>
+    <event event="0x040E" option_set="HN-F_Region" title="CCN-504" name="QOS HH Retry" description="Counts the number of times a highest-priority QoS class was retried at the HN-F."/>
+    <option_set name="RN-I_Region">
+      <option event_delta="0x800000" name="RN-I 0" description="I/O-coherent Requesting Node 0"/>
+      <option event_delta="0x820000" name="RN-I 2" description="I/O-coherent Requesting Node 2"/>
+      <option event_delta="0x860000" name="RN-I 6" description="I/O-coherent Requesting Node 6"/>
+      <option event_delta="0x8C0000" name="RN-I 12" description="I/O-coherent Requesting Node 12"/>
+      <option event_delta="0x900000" name="RN-I 16" description="I/O-coherent Requesting Node 16"/>
+      <option event_delta="0x940000" name="RN-I 20" description="I/O-coherent Requesting Node 20"/>
+    </option_set>
+    <event event="0x1601" option_set="RN-I_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1602" option_set="RN-I_Region" title="CCN-504" name="S1 RDataBeats" description="S1 RDataBeats."/>
+    <event event="0x1603" option_set="RN-I_Region" title="CCN-504" name="S2 RDataBeats" description="S2 RDataBeats."/>
+    <event event="0x1604" option_set="RN-I_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1605" option_set="RN-I_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1606" option_set="RN-I_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1607" option_set="RN-I_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1608" option_set="RN-I_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1609" option_set="RN-I_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x160A" option_set="RN-I_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+    <option_set name="SBAS_Region">
+      <option event_delta="0x810000" name="SBAS 1" description="ACE master to CHI protocol bridge 1"/>
+      <option event_delta="0x890000" name="SBAS 9" description="ACE master to CHI protocol bridge 9"/>
+      <option event_delta="0x8B0000" name="SBAS 11" description="ACE master to CHI protocol bridge 11"/>
+      <option event_delta="0x930000" name="SBAS 19" description="ACE master to CHI protocol bridge 19"/>
+    </option_set>
+    <event event="0x1001" option_set="SBAS_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1004" option_set="SBAS_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1005" option_set="SBAS_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1006" option_set="SBAS_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1007" option_set="SBAS_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1008" option_set="SBAS_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1009" option_set="SBAS_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x100A" option_set="SBAS_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A15.xml b/tools/gator/daemon/events-Cortex-A15.xml
new file mode 100644
index 000000000000..f50e55d66195
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A15.xml
@@ -0,0 +1,68 @@
+  <counter_set name="ARMv7_Cortex_A15_cnt" count="6"/>
+  <category name="Cortex-A15" counter_set="ARMv7_Cortex_A15_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A15_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment architecturally executed"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table base architecturally executed"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-Back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4c" title="TLB" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4d" title="TLB" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-Back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+    <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A17.xml b/tools/gator/daemon/events-Cortex-A17.xml
new file mode 100644
index 000000000000..4dd08c1f203d
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A17.xml
@@ -0,0 +1,86 @@
+  <counter_set name="ARMv7_Cortex_A17_cnt" count="6"/>
+  <category name="Cortex-A17" counter_set="ARMv7_Cortex_A17_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A17_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table base architecturally executed"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-Back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+    <event event="0x6f" title="Intrinsic" name="STREX" description="Exclusive instruction speculatively executed - STREX"/>
+    <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0xc0" title="Instruction" name="Stalled Linefill" description="Instruction side stalled due to a Linefill"/>
+    <event event="0xc1" title="Instruction" name="Stalled Page Table Walk" description="Instruction Side stalled due to a Page Table Walk"/>
+    <event event="0xc2" title="Cache" name="4 Ways Read" description="Number of set of 4 ways read in the instruction cache - Tag RAM"/>
+    <event event="0xc3" title="Cache" name="Ways Read" description="Number of ways read in the instruction cache - Data RAM"/>
+    <event event="0xc4" title="Cache" name="BATC Read" description="Number of ways read in the instruction BTAC RAM"/>
+    <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A17 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data"/>
+    <event event="0xd3" title="Slots" name="Load-Store Unit" description="Duration during which all slots in the Load-Store Unit are busy"/>
+    <event event="0xd8" title="Slots" name="Load-Store Issue Queue" description="Duration during which all slots in the Load-Store Issue queue are busy"/>
+    <event event="0xd9" title="Slots" name="Data Processing Issue Queue" description="Duration during which all slots in the Data Processing issue queue are busy"/>
+    <event event="0xda" title="Slots" name="Data Engine Issue Queue" description="Duration during which all slots in the Data Engine issue queue are busy"/>
+    <event event="0xdb" title="NEON" name="Flush" description="Number of NEON instruction which fail their condition code and lead to a flush of the DE pipe"/>
+    <event event="0xdc" title="Hypervisor" name="Traps" description="Number of Trap to hypervisor"/>
+    <event event="0xde" title="PTM" name="EXTOUT 0" description="PTM EXTOUT 0"/>
+    <event event="0xdf" title="PTM" name="EXTOUT 1" description="PTM EXTOUT 1"/>
+    <event event="0xe0" title="MMU" name="Table Walk" description="Duration during which the MMU handle a Page table walk"/>
+    <event event="0xe1" title="MMU" name="Stage1 Table Walk" description="Duration during which the MMU handle a Stage1 Page table walk"/>
+    <event event="0xe2" title="MMU" name="Stage2 Table Walk" description="Duration during which the MMU handle a Stage2 Page table walk"/>
+    <event event="0xe3" title="MMU" name="LSU Table Walk" description="Duration during which the MMU handle a Page table walk requested by the Load Store Unit"/>
+    <event event="0xe4" title="MMU" name="Instruction Table Walk" description="Duration during which the MMU handle a Page table walk requested by the Instruction side"/>
+    <event event="0xe5" title="MMU" name="Preload Table Walk" description="Duration during which the MMU handle a Page table walk requested by a Preload instruction or Prefetch request"/>
+    <event event="0xe6" title="MMU" name="cp15 Table Walk" description="Duration during which the MMU handle a Page table walk requested by a cp15 operation (maintenance by MVA and VA-to-PA operation)"/>
+    <event event="0xe7" title="Cache" name="L1 PLD TLB refill" description="Level 1 PLD TLB refill"/>
+    <event event="0xe8" title="Cache" name="L1 CP15 TLB refill" description="Level 1 CP15 TLB refill"/>
+    <event event="0xe9" title="Cache" name="L1 TLB flush" description="Level 1 TLB flush"/>
+    <event event="0xea" title="Cache" name="L2 TLB access" description="Level 2 TLB access"/>
+    <event event="0xeb" title="Cache" name="L2 TLB miss" description="Level 2 TLB miss"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A5.xml b/tools/gator/daemon/events-Cortex-A5.xml
new file mode 100644
index 000000000000..d67581d77c08
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A5.xml
@@ -0,0 +1,36 @@
+  <counter_set name="ARMv7_Cortex_A5_cnt" count="2"/>
+  <category name="Cortex-A5" counter_set="ARMv7_Cortex_A5_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A5_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception return, architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="Instruction access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="Data eviction" description="Data cache eviction"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xC0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xC1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xC2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xC3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xC4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xC5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xC7" title="ETM" name="ETM Ext Out[0]" description="ETM - ETM Ext Out[0]"/>
+    <event event="0xC8" title="ETM" name="ETM Ext Out[1]" description="ETM - ETM Ext Out[1]"/>
+    <event event="0xC9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A53.xml b/tools/gator/daemon/events-Cortex-A53.xml
new file mode 100644
index 000000000000..5ba17907d5ab
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A53.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARM_Cortex-A53_cnt" count="6"/>
+  <category name="Cortex-A53" counter_set="ARM_Cortex-A53_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARM_Cortex-A53_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4C" title="Cache" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4D" title="Cache" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7A" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+    <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A57.xml b/tools/gator/daemon/events-Cortex-A57.xml
new file mode 100644
index 000000000000..fbe96c2d4eb2
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A57.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARM_Cortex-A57_cnt" count="6"/>
+  <category name="Cortex-A57" counter_set="ARM_Cortex-A57_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARM_Cortex-A57_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4C" title="Cache" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4D" title="Cache" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7A" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+    <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A7.xml b/tools/gator/daemon/events-Cortex-A7.xml
new file mode 100644
index 000000000000..6e078b3cffa3
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A7.xml
@@ -0,0 +1,43 @@
+  <counter_set name="ARMv7_Cortex_A7_cnt" count="4"/>
+  <category name="Cortex-A7" counter_set="ARMv7_Cortex_A7_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A7_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment architecturally executed"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Memory" name="Data Read" description="Data read architecturally executed"/>
+    <event event="0x07" title="Memory" name="Data Write" description="Data write architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data eviction" description="Level 1 data cache eviction"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x86" title="Exception" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Exception" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xC0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xC1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xC2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xC3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xC4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xC5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xC7" title="ETM" name="ETM Ext Out[0]" description="ETM - ETM Ext Out[0]"/>
+    <event event="0xC8" title="ETM" name="ETM Ext Out[1]" description="ETM - ETM Ext Out[1]"/>
+    <event event="0xC9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+    <event event="0xCA" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local cluster, rather than accessing the L2 cache or issuing an external read."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A8.xml b/tools/gator/daemon/events-Cortex-A8.xml
new file mode 100644
index 000000000000..a69e25ab2c34
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A8.xml
@@ -0,0 +1,52 @@
+  <counter_set name="ARMv7_Cortex_A8_cnt" count="4"/>
+  <category name="Cortex-A8" counter_set="ARMv7_Cortex_A8_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A8_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception return, architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Cache" name="Write buffer full" description="Any write buffer full cycle"/>
+    <event event="0x41" title="Cache" name="L2 store" description="Any store that is merged in the L2 memory system"/>
+    <event event="0x42" title="Cache" name="Bufferable transaction" description="Any bufferable store transaction from load/store to L2 cache, excluding eviction or cast out data"/>
+    <event event="0x43" title="Cache" name="L2 access" description="Any accesses to the L2 cache"/>
+    <event event="0x44" title="Cache" name="L2 miss" description="Any cacheable miss in the L2 cache"/>
+    <event event="0x45" title="AXI" name="Read" description="The number of AXI read data transfers"/>
+    <event event="0x46" title="AXI" name="Write" description="The number of AXI write data transfers"/>
+    <event event="0x47" title="Memory" name="Replay event" description="Any replay event in the memory system"/>
+    <event event="0x48" title="Memory" name="Unaligned access replay" description="Any unaligned memory access that results in a replay"/>
+    <event event="0x49" title="Cache" name="L1 data hash miss" description="Any L1 data memory access that misses in the cache as a result of the hashing algorithm"/>
+    <event event="0x4a" title="Cache" name="L1 inst hash miss" description="Any L1 instruction memory access that misses in the cache as a result of the hashing algorithm"/>
+    <event event="0x4b" title="Cache" name="L1 page coloring" description="Any L1 data memory access in which a page coloring alias occurs"/>
+    <event event="0x4c" title="NEON" name="L1 cache hit" description="Any NEON access that hits in the L1 data cache"/>
+    <event event="0x4d" title="NEON" name="L1 cache access" description="Any NEON cacheable data accesses for L1 data cache"/>
+    <event event="0x4e" title="NEON" name="L2 cache access" description="Any L2 cache accesses as a result of a NEON memory access"/>
+    <event event="0x4f" title="NEON" name="L2 cache hit" description="Any NEON hit in the L2 cache"/>
+    <event event="0x50" title="Cache" name="L1 inst access" description="Any L1 instruction cache access, excluding CP15 cache accesses"/>
+    <event event="0x51" title="Branch" name="Return stack misprediction" description="Any return stack misprediction because of incorrect target address for a taken return stack pop"/>
+    <event event="0x52" title="Branch" name="Direction misprediction" description="Branch direction misprediction"/>
+    <event event="0x53" title="Branch" name="Taken prediction" description="Any predictable branch that is predicted to be taken"/>
+    <event event="0x54" title="Branch" name="Executed and taken prediction" description="Any predictable branch that is executed and taken"/>
+    <event event="0x55" title="Core" name="Operations issued" description="Number of operations issued, where an operation is either: an instruction or one operation in a sequence of operations that make up a multi-cycle instruction"/>
+    <event event="0x56" title="Core" name="No issue cycles" description="Increment for every cycle that no instructions are available for issue"/>
+    <event event="0x57" title="Core" name="Issue cycles" description="For every cycle, this event counts the number of instructions issued in that cycle. Multi-cycle instructions are only counted once"/>
+    <event event="0x58" title="NEON" name="MRC data wait" description="Number of cycles the processor stalls waiting on MRC data from NEON"/>
+    <event event="0x59" title="NEON" name="Full queue" description="Number of cycles that the processor stalls as a result of a full NEON instruction queue or NEON load queue"/>
+    <event event="0x5a" title="NEON" name="Idle" description="Number of cycles that NEON and integer processors are both not idle"/>
+    <event event="0x70" title="External" name="PMUEXTIN[0]" description="Counts any event from external input source PMUEXTIN[0]"/>
+    <event event="0x71" title="External" name="PMUEXTIN[1]" description="Counts any event from external input source PMUEXTIN[1]"/>
+    <event event="0x72" title="External" name="PMUEXTIN[0,1]" description="Counts any event from both external input sources PMUEXTIN[0] and PMUEXTIN[1]"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A9.xml b/tools/gator/daemon/events-Cortex-A9.xml
new file mode 100644
index 000000000000..3e7f8289062e
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A9.xml
@@ -0,0 +1,65 @@
+  <counter_set name="ARMv7_Cortex_A9_cnt" count="6"/>
+  <category name="Cortex-A9" counter_set="ARMv7_Cortex_A9_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A9_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Java" name="Bytecode execute" description="Counts the number of Java bytecodes being decoded, including speculative ones"/>
+    <event event="0x41" title="Java" name="SW bytecode execute" description="Counts the number of software java bytecodes being decoded, including speculative ones"/>
+    <event event="0x42" title="Jazelle" name="Backward branch execute" description="Counts the number of Jazelle taken branches being executed"/>
+    <event event="0x50" title="Cache" name="Coherency miss" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor which also miss in all the other Cortex-A9 processors, meaning that the request is sent to the external memory"/>
+    <event event="0x51" title="Cache" name="Coherency hit" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor which hit in another Cortex-A9 processor, meaning that the linefill data is fetched directly from the relevant Cortex-A9 cache"/>
+    <event event="0x60" title="Cache" name="Inst dependent stall" description="Counts the number of cycles where the processor is ready to accept new instructions, but does not receive any because of the instruction side not being able to provide any and the instruction cache is currently performing at least one linefill"/>
+    <event event="0x61" title="Cache" name="Data dependent stall" description="Counts the number of cycles where the core has some instructions that it cannot issue to any pipeline, and the Load Store unit has at least one pending linefill request, and no pending TLB requests"/>
+    <event event="0x62" title="Cache" name="TLB stall" description="Counts the number of cycles where the processor is stalled waiting for the completion of translation table walks from the main TLB"/>
+    <event event="0x63" title="Intrinsic" name="STREX pass" description="Counts the number of STREX instructions architecturally executed and passed"/>
+    <event event="0x64" title="Intrinsic" name="STREX fail" description="Counts the number of STREX instructions architecturally executed and failed"/>
+    <event event="0x65" title="Cache" name="Data eviction" description="Counts the number of eviction requests because of a linefill in the data cache"/>
+    <event event="0x66" title="Pipeline" name="Issue stage no dispatch" description="Counts the number of cycles where the issue stage does not dispatch any instruction because it is empty or cannot dispatch any instructions"/>
+    <event event="0x67" title="Pipeline" name="Issue stage empty" description="Counts the number of cycles where the issue stage is empty"/>
+    <event event="0x68" title="Instruction" name="Executed" description="Counts the number of instructions going through the Register Renaming stage. This number is an approximate number of the total number of instructions speculatively executed, and even more approximate of the total number of instructions architecturally executed"/>
+    <event event="0x69" title="Cache" name="Data linefills" description="Counts the number of linefills performed on the external AXI bus"/>
+    <event event="0x6A" title="Cache" name="Prefetch linefills" description="Counts the number of data linefills caused by prefetcher requests"/>
+    <event event="0x6B" title="Cache" name="Prefetch hits" description="Counts the number of cache hits in a line that belongs to a stream followed by the prefetcher"/>
+    <event event="0x6E" title="Core" name="Functions" description="Counts the number of procedure returns whose condition codes do not fail, excluding all returns from exception"/>
+    <event event="0x70" title="Instruction" name="Main execution unit" description="Counts the number of instructions being executed in the main execution pipeline of the processor, the multiply pipeline and arithmetic logic unit pipeline"/>
+    <event event="0x71" title="Instruction" name="Second execution unit" description="Counts the number of instructions being executed in the processor second execution pipeline (ALU)"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Counts the number of instructions being executed in the Load/Store unit"/>
+    <event event="0x73" title="Instruction" name="Floating point" description="Counts the number of Floating-point instructions going through the Register Rename stage"/>
+    <event event="0x74" title="Instruction" name="NEON" description="Counts the number of NEON instructions going through the Register Rename stage"/>
+    <event event="0x80" title="Stalls" name="PLD" description="Counts the number of cycles where the processor is stalled because PLD slots are all full"/>
+    <event event="0x81" title="Stalls" name="Memory write" description="Counts the number of cycles when the processor is stalled and the data side is stalled too because it is full and executing writes to the external memory"/>
+    <event event="0x82" title="Stalls" name="Inst main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the instruction side"/>
+    <event event="0x83" title="Stalls" name="Data main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the data side"/>
+    <event event="0x84" title="Stalls" name="Inst micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the instruction side"/>
+    <event event="0x85" title="Stalls" name="Data micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the data side"/>
+    <event event="0x86" title="Stalls" name="DMB" description="Counts the number of stall cycles because of the execution of a DMB memory barrier"/>
+    <event event="0x8A" title="Clock" name="Integer core" description="Counts the number of cycles during which the integer core clock is enabled"/>
+    <event event="0x8B" title="Clock" name="Data engine" description="Counts the number of cycles during which the Data Engine clock is enabled"/>
+    <event event="0x8C" title="Clock" name="NEON" description="Counts the number of cycles when the NEON SIMD clock is enabled"/>
+    <event event="0x8D" title="Memory" name="TLB inst allocations" description="Counts the number of TLB allocations because of Instruction requests"/>
+    <event event="0x8E" title="Memory" name="TLB data allocations" description="Counts the number of TLB allocations because of Data requests"/>
+    <event event="0x90" title="Instruction" name="ISB" description="Counts the number of ISB instructions architecturally executed"/>
+    <event event="0x91" title="Instruction" name="DSB" description="Counts the number of DSB instructions architecturally executed"/>
+    <event event="0x92" title="Instruction" name="DMB" description="Counts the number of DMB instructions speculatively executed"/>
+    <event event="0x93" title="External" name="Interrupts" description="Counts the number of external interrupts executed by the processor"/>
+    <event event="0xA0" title="PLE" name="Cache line rq completed" description="Counts the number of PLE cache line requests completed"/>
+    <event event="0xA1" title="PLE" name="Cache line rq skipped" description="Counts the number of PLE cache line requests skipped"/>
+    <event event="0xA2" title="PLE" name="FIFO flush" description="Counts the number of PLE FIFO flush requests"/>
+    <event event="0xA3" title="PLE" name="Request completed" description="Counts the number of PLE FIFO flush completed"/>
+    <event event="0xA4" title="PLE" name="FIFO overflow" description="Counts the number of PLE FIFO flush overflowed"/>
+    <event event="0xA5" title="PLE" name="Request programmed" description="Counts the number of PLE FIFO flush program requests"/>
+  </category>
diff --git a/tools/gator/daemon/events-Filesystem.xml b/tools/gator/daemon/events-Filesystem.xml
new file mode 100644
index 000000000000..9ef61ddac811
--- /dev/null
+++ b/tools/gator/daemon/events-Filesystem.xml
@@ -0,0 +1,11 @@
+  <category name="Filesystem">
+    <!-- counter attribute must start with filesystem_ and be unique -->
+    <!-- regex item in () is the value shown -->
+    <!--
+    <event counter="filesystem_cpu1_online" path="/sys/devices/system/cpu/cpu1/online" title="online" name="cpu 1" class="absolute" description="If cpu 1 is online"/>
+    <event counter="filesystem_loginuid" path="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/>
+    <event counter="filesystem_gatord_rss" path="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/>
+    <event counter="filesystem_processes" path="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/>
+    <event counter="filesystem_context_switches" path="/proc/stat" title="proc-stat" name="context switches" class="absolute" regex="ctxt ([0-9]+)" description="Number of processes and threads created"/>
+    -->
+  </category>
diff --git a/tools/gator/daemon/events-Krait-architected.xml b/tools/gator/daemon/events-Krait-architected.xml
new file mode 100644
index 000000000000..b8d3bcb48de7
--- /dev/null
+++ b/tools/gator/daemon/events-Krait-architected.xml
@@ -0,0 +1,22 @@
+  <counter_set name="Krait_cnt" count="4"/>
+  <category name="Krait" counter_set="Krait_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Krait_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+  </category>
diff --git a/tools/gator/daemon/events-L2C-310.xml b/tools/gator/daemon/events-L2C-310.xml
new file mode 100644
index 000000000000..923fb90334d0
--- /dev/null
+++ b/tools/gator/daemon/events-L2C-310.xml
@@ -0,0 +1,18 @@
+  <counter_set name="L2C-310_cnt" count="2"/>
+  <category name="L2C-310" counter_set="L2C-310_cnt" per_cpu="no">
+    <event event="0x1" title="L2 Cache" name="CastOUT" description="Eviction, CastOUT, of a line from the L2 cache"/>
+    <event event="0x2" title="L2 Cache" name="Data Read Hit" description="Data read hit in the L2 cache"/>
+    <event event="0x3" title="L2 Cache" name="Data Read Request" description="Data read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x4" title="L2 Cache" name="Data Write Hit" description="Data write hit in the L2 cache"/>
+    <event event="0x5" title="L2 Cache" name="Data Write Request" description="Data write lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x6" title="L2 Cache" name="Data Write-Through Request" description="Data write lookup to the L2 cache with Write-Through attribute. Subsequently results in a hit or miss"/>
+    <event event="0x7" title="L2 Cache" name="Instruction Read Hit" description="Instruction read hit in the L2 cache"/>
+    <event event="0x8" title="L2 Cache" name="Instruction Read Request" description="Instruction read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x9" title="L2 Cache" name="Write Allocate Miss" description="Allocation into the L2 cache caused by a write, with Write-Allocate attribute, miss"/>
+    <event event="0xa" title="L2 Cache" name="Internal Prefetch Allocate" description="Allocation of a prefetch generated by L2C-310 into the L2 cache"/>
+    <event event="0xb" title="L2 Cache" name="Prefitch Hit" description="Prefetch hint hits in the L2 cache"/>
+    <event event="0xc" title="L2 Cache" name="Prefitch Allocate" description="Prefetch hint allocated into the L2 cache"/>
+    <event event="0xd" title="L2 Cache" name="Speculative Read Received" description="Speculative read received"/>
+    <event event="0xe" title="L2 Cache" name="Speculative Read Confirmed" description="Speculative read confirmed"/>
+    <event event="0xf" title="L2 Cache" name="Prefetch Hint Received" description="Prefetch hint received"/>
+  </category>
diff --git a/tools/gator/daemon/events-Linux.xml b/tools/gator/daemon/events-Linux.xml
new file mode 100644
index 000000000000..62a7018d038f
--- /dev/null
+++ b/tools/gator/daemon/events-Linux.xml
@@ -0,0 +1,17 @@
+  <category name="Linux">
+    <event counter="Linux_irq_softirq" title="Interrupts" name="SoftIRQ" per_cpu="yes" description="Linux SoftIRQ taken"/>
+    <event counter="Linux_irq_irq" title="Interrupts" name="IRQ" per_cpu="yes" description="Linux IRQ taken"/>
+    <event counter="Linux_block_rq_wr" title="Disk I/O" name="Write" units="B" description="Disk I/O Bytes Written"/>
+    <event counter="Linux_block_rq_rd" title="Disk I/O" name="Read" units="B" description="Disk I/O Bytes Read"/>
+    <event counter="Linux_net_rx" title="Network" name="Receive" units="B" description="Receive network traffic, including effect from Streamline"/>
+    <event counter="Linux_net_tx" title="Network" name="Transmit" units="B" description="Transmit network traffic, including effect from Streamline"/>
+    <event counter="Linux_sched_switch" title="Scheduler" name="Switch" per_cpu="yes" description="Context switch events"/>
+    <event counter="Linux_meminfo_memused" title="Memory" name="Used" class="absolute" units="B" proc="yes" description="Total used memory size. Note: a process' used memory includes shared memory that may be counted more than once (equivalent to RES from top). Kernel threads are not filterable."/>
+    <event counter="Linux_meminfo_memused2" title="Memory" name="Used" class="absolute" units="B" description="Total used memory size"/>
+    <event counter="Linux_meminfo_memfree" title="Memory" name="Free" class="absolute" display="minimum" units="B" description="Available memory size"/>
+    <event counter="Linux_meminfo_bufferram" title="Memory" name="Buffer" class="absolute" units="B" description="Memory used by OS disk buffers"/>
+    <event counter="Linux_power_cpu_freq" title="Clock" name="Frequency" per_cpu="yes" class="absolute" units="Hz" series_composition="overlay" average_cores="yes" description="Frequency setting of the CPU"/>
+    <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x003c96fb" description="One or more threads are runnable but waiting due to CPU contention"/>
+    <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x00b30000" description="One or more threads are blocked on an I/O resource"/>
+    <event counter="Linux_power_cpu" title="CPU Status" name="Activity" class="activity" activity1="Off" activity_color1="0x0000ff00" activity2="WFI" activity_color2="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="CPU Status"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-4xx.xml b/tools/gator/daemon/events-Mali-4xx.xml
new file mode 100644
index 000000000000..0a95dfeb6485
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-4xx.xml
@@ -0,0 +1,245 @@
+  <counter_set name="ARM_Mali-4xx_VP_0_cnt" count="2"/>
+  <counter_set name="ARM_Mali-4xx_SW_cnt" count="0"/>
+  <category name="Mali Vertex Processor" counter_set="ARM_Mali-4xx_VP_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali-4xx VP" name="Active cycles" description="Number of cycles per frame the MaliGP2 was active."/>
+    <event event="0x02" title="Mali-4xx VP" name="Active cycles, vertex shader" description="Number of cycles per frame the vertex shader unit was active."/>
+    <event event="0x03" title="Mali-4xx VP" name="Active cycles, vertex storer" description="Number of cycles per frame the vertex storer unit was active."/>
+    <event event="0x04" title="Mali-4xx VP" name="Active cycles, vertex loader" description="Number of cycles per frame the vertex loader unit was active."/>
+    <event event="0x05" title="Mali-4xx VP" name="Cycles vertex loader waiting for vertex shader" description="Number of cycles per frame the vertex loader was idle while waiting on the vertex shader."/>
+    <event event="0x06" title="Mali-4xx VP" name="Words read, system bus" description="Total number of 64 bit words read by the GP2 from the system bus per frame."/>
+    <event event="0x07" title="Mali-4xx VP" name="Words written, system bus" description="Total number of 64 bit words written by the GP2 to the system bus per frame."/>
+    <event event="0x08" title="Mali-4xx VP" name="Read bursts, system bus" description="Number of read bursts by the GP2 from the system bus per frame."/>
+    <event event="0x09" title="Mali-4xx VP" name="Write bursts, system bus" description="Number of write bursts from the MaliGP2 to the system bus per frame."/>
+    <event event="0x0a" title="Mali-4xx VP" name="Vertices processed" description="Number of vertices processed by the MaliGP2 per frame."/>
+    <event event="0x0b" title="Mali-4xx VP" name="Vertices fetched" description="Number of vertices fetched by the MaliGP2 per frame."/>
+    <event event="0x0c" title="Mali-4xx VP" name="Primitives fetched" description="Number of graphics primitives fetched by the MaliGP2 per frame."/>
+    <event event="0x0e" title="Mali-4xx VP" name="Primitives culled" description="Number of graphics primitives discarded per frame, because they were seen from the back or were offscreen."/>
+    <event event="0x0f" title="Mali-4xx VP" name="Commands written to tiles" description="Number of commands (8 Bytes, mainly primitives) written by GP2 to the PP input data structure per frame."/>
+    <event event="0x10" title="Mali-4xx VP" name="Memory blocks allocated" description="Number of overflow data blocks needed for outputting the PP input data structure per frame ."/>
+    <event event="0x13" title="Mali-4xx VP" name="Vertex loader cache misses" description="Number of cache misses for the vertex shader's vertex input unit per frame."/>
+    <event event="0x16" title="Mali-4xx VP" name="Active cycles, vertex shader command processor" description="Number of cycles per frame the GP2 vertex shader command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x17" title="Mali-4xx VP" name="Active cycles, PLBU command processor" description="Number of cycles per frame the MaliGP2 PLBU command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x18" title="Mali-4xx VP" name="Active Cycles, PLBU list writer" description="Number of cycles per frame the MaliGP2 PLBU output unit was active. This includes time spent waiting on the bus."/>
+    <event event="0x19" title="Mali-4xx VP" name="Active cycles, PLBU geometry processing" description="Number of cycles per frame the MaliGP2 PLBU was active, excepting final data output. In other words: active cycles through the prepare list commands. This includes time spent waiting on the bus."/>
+    <event event="0x1b" title="Mali-4xx VP" name="Active cycles, PLBU primitive assembly" description="Number of active cycles per frame spent by the MaliGP2 PLBU doing primitive assembly. This does not include scissoring or final output. This includes time spent waiting on the bus."/>
+    <event event="0x1c" title="Mali-4xx VP" name="Active cycles, PLBU vertex fetcher" description="Number of active cycles per frame spent by the MaliGP2 PLBU fetching vertex data. This includes time spent waiting on the bus."/>
+    <event event="0x1e" title="Mali-4xx VP" name="Active cycles, Bounding-box and command generator" description="Number of active cycles per frame spent by the MaliGP2 PLBU setting up bounding boxes and commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+    <event event="0x20" title="Mali-4xx VP" name="Active cycles, Scissor tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over tiles to perform scissoring. This includes time spent waiting on the bus."/>
+    <event event="0x21" title="Mali-4xx VP" name="Active cycles, PLBU tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over the tiles in the bounding box generating commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+  </category>
+  <category name="Mali Fragment Processor" per_cpu="no">
+    <counter_set name="ARM_Mali-4xx_FP_0_cnt" title="Mali-4xx FP0" description="Mali GPU Fragment Processor 0" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_1_cnt" title="Mali-4xx FP1" description="Mali GPU Fragment Processor 1" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_2_cnt" title="Mali-4xx FP2" description="Mali GPU Fragment Processor 2" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_3_cnt" title="Mali-4xx FP3" description="Mali GPU Fragment Processor 3" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_4_cnt" title="Mali-4xx FP4" description="Mali GPU Fragment Processor 4" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_5_cnt" title="Mali-4xx FP5" description="Mali GPU Fragment Processor 5" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_6_cnt" title="Mali-4xx FP6" description="Mali GPU Fragment Processor 6" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_7_cnt" title="Mali-4xx FP7" description="Mali GPU Fragment Processor 7" count="2"/>
+    <event event="0x00" title="Mali-4xx FP" name="Active clock cycles" description="Active clock cycles, between polygon start and IRQ."/>
+    <event event="0x02" title="Mali-4xx FP" name="Total bus reads" description="Total number of 64-bit words read from the bus."/>
+    <event event="0x03" title="Mali-4xx FP" name="Total bus writes" description="Total number of 64-bit words written to the bus."/>
+    <event event="0x04" title="Mali-4xx FP" name="Bus read request cycles" description="Number of cycles during which the bus read request signal was HIGH."/>
+    <event event="0x05" title="Mali-4xx FP" name="Bus write request cycles" description="Number of cycles during which the bus write request signal was HIGH."/>
+    <event event="0x06" title="Mali-4xx FP" name="Bus read transactions count" description="Number of read requests accepted by the bus."/>
+    <event event="0x07" title="Mali-4xx FP" name="Bus write transactions" description="Number of write requests accepted by the bus."/>
+    <event event="0x09" title="Mali-4xx FP" name="Tile writeback writes" description="64-bit words written to the bus by the writeback unit."/>
+    <event event="0x0a" title="Mali-4xx FP" name="Store unit writes" description="64-bit words written to the bus by the store unit."/>
+    <event event="0x0d" title="Mali-4xx FP" name="Texture cache uncompressed reads" description="Number of 64-bit words read from the bus into the uncompressed textures cache."/>
+    <event event="0x0e" title="Mali-4xx FP" name="Polygon list reads" description="Number of 64-bit words read from the bus by the polygon list reader."/>
+    <event event="0x0f" title="Mali-4xx FP" name="RSW reads" description="Number of 64-bit words read from the bus into the Render State Word register."/>
+    <event event="0x10" title="Mali-4xx FP" name="Vertex cache reads" description="Number of 64-bit words read from the bus into the vertex cache."/>
+    <event event="0x11" title="Mali-4xx FP" name="Uniform remapping reads" description="Number of 64-bit words read from the bus when reading from the uniform remapping table."/>
+    <event event="0x12" title="Mali-4xx FP" name="Program cache reads" description="Number of 64-bit words read from the bus into the fragment shader program cache."/>
+    <event event="0x13" title="Mali-4xx FP" name="Varying reads" description="Number of 64-bit words containing varyings generated by the vertex processing read from the bus."/>
+    <event event="0x14" title="Mali-4xx FP" name="Texture descriptors reads" description="Number of 64-bit words containing texture descriptors read from the bus."/>
+    <event event="0x15" title="Mali-4xx FP" name="Texture descriptor remapping reads" description="Number of 64-bit words read from the bus when reading from the texture descriptor remapping table."/>
+    <event event="0x17" title="Mali-4xx FP" name="Load unit reads" description="Number of 64-bit words read from the bus by the LOAD sub-instruction."/>
+    <event event="0x18" title="Mali-4xx FP" name="Polygon count" description="Number of triangles read from the polygon list."/>
+    <event event="0x19" title="Mali-4xx FP" name="Pixel rectangle count" description="Number of pixel rectangles read from the polygon list."/>
+    <event event="0x1a" title="Mali-4xx FP" name="Lines count" description="Number of lines read from the polygon list."/>
+    <event event="0x1b" title="Mali-4xx FP" name="Points count" description="Number of points read from the polygon list."/>
+    <event event="0x1c" title="Mali-4xx FP" name="Stall cycles PolygonListReader" description="Number of clock cycles the Polygon List Reader waited for output being collected."/>
+    <event event="0x1d" title="Mali-4xx FP" name="Stall cycles triangle setup" description="Number of clock cycles the TSC waited for input."/>
+    <event event="0x1e" title="Mali-4xx FP" name="Quad rasterized count" description="Number of 2x?2 quads output from rasterizer."/>
+    <event event="0x1f" title="Mali-4xx FP" name="Fragment rasterized count" description="Number of fragment rasterized. Fragments/(Quads*4) gives average actual fragments per quad."/>
+    <event event="0x20" title="Mali-4xx FP" name="Fragment rejected fragment-kill count" description="Number of fragments exiting the fragment shader as killed."/>
+    <event event="0x21" title="Mali-4xx FP" name="Fragment rejected fwd-fragment-kill count" description="Number of fragments killed by forward fragment kill."/>
+    <event event="0x22" title="Mali-4xx FP" name="Fragment passed z/stencil count" description="Number of fragments passing Z and stencil test."/>
+    <event event="0x23" title="Mali-4xx FP" name="Patches rejected early z/stencil count" description="Number of patches rejected by EarlyZ. A patch can be 8x8, 4x4 or 2x2 pixels."/>
+    <event event="0x24" title="Mali-4xx FP" name="Patches evaluated" description="Number of patches evaluated for EarlyZ rejection."/>
+    <event event="0x25" title="Mali-4xx FP" name="Instruction completed count" description="Number of fragment shader instruction words completed. It is a function of pixels processed and the length of the shader programs."/>
+    <event event="0x26" title="Mali-4xx FP" name="Instruction failed rendezvous count" description="Number of fragment shader instructions not completed because of failed Rendezvous."/>
+    <event event="0x27" title="Mali-4xx FP" name="Instruction failed varying-miss count" description="Number of fragment shader instructions not completed because of failed varying operation."/>
+    <event event="0x28" title="Mali-4xx FP" name="Instruction failed texture-miss count" description="Number of fragment shader instructions not completed because of failed texture operation."/>
+    <event event="0x29" title="Mali-4xx FP" name="Instruction failed load-miss count" description="Number of fragment shader instructions not completed because of failed load operation."/>
+    <event event="0x2a" title="Mali-4xx FP" name="Instruction failed tile read-miss count" description="Number of fragment shader instructions not completed because of failed read from the tilebuffer."/>
+    <event event="0x2b" title="Mali-4xx FP" name="Instruction failed store-miss count" description="Number of fragment shader instructions not completed because of failed store operation."/>
+    <event event="0x2c" title="Mali-4xx FP" name="Rendezvous breakage count" description="Number of Rendezvous breakages reported."/>
+    <event event="0x2d" title="Mali-4xx FP" name="Pipeline bubbles cycle count" description="Number of unused cycles in the fragment shader while rendering is active."/>
+    <event event="0x2e" title="Mali-4xx FP" name="Texture mapper multipass count" description="Number of texture operations looped because of more texture passes needed."/>
+    <event event="0x2f" title="Mali-4xx FP" name="Texture mapper cycle count" description="Number of texture operation cycles."/>
+    <event event="0x30" title="Mali-4xx FP" name="Vertex cache hit count" description="Number of times a requested vertex was found in the cache (Number of vertex cache hits)."/>
+    <event event="0x31" title="Mali-4xx FP" name="Vertex cache miss count" description="Number of times a requested vertex was not found in the cache (Number of vertex cache misses)."/>
+    <event event="0x32" title="Mali-4xx FP" name="Varying cache hit count" description="Number of times a requested varying was found in the cache (Number of varying cache hits)."/>
+    <event event="0x33" title="Mali-4xx FP" name="Varying cache miss count" description="Number of times a requested varying was not found in the cache (Number of varying cache misses)."/>
+    <event event="0x34" title="Mali-4xx FP" name="Varying cache conflict miss count" description="Number of times a requested varying was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x35" title="Mali-4xx FP" name="Texture cache hit count" description="Number of times a requested texel was found in the texture cache (Number of texture cache hits)."/>
+    <event event="0x36" title="Mali-4xx FP" name="Texture cache miss count" description="Number of times a requested texel was not found in the texture cache (Number of texture cache misses)."/>
+    <event event="0x37" title="Mali-4xx FP" name="Texture cache conflict miss count" description="Number of times a requested texel was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x38" title="Mali-4xx FP" name="Compressed texture cache hit count" description="Number of times a requested item was found in the cache."/>
+    <event event="0x39" title="Mali-4xx FP" name="Compressed texture cache miss count" description="Number of times a requested item was not found in the cache."/>
+    <event event="0x3a" title="Mali-4xx FP" name="Load/Store cache hit count" description="Number of hits in the load/store cache."/>
+    <event event="0x3b" title="Mali-4xx FP" name="Load/Store cache miss count" description="Number of misses in the load/store cache."/>
+    <event event="0x3c" title="Mali-4xx FP" name="Program cache hit count" description="Number of hits in the program cache."/>
+    <event event="0x3d" title="Mali-4xx FP" name="Program cache miss count" description="Number of misses in the program cache."/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_0_cnt" title="Mali-4xx L2" description="Mali GPU L2 Cache Core 0" count="2"/>
+  <category name="Mali-4xx L2" counter_set="ARM_Mali-4xx_L2_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_1_cnt" title="Mali-4xx L2 1" description="Mali GPU L2 Cache Core 1" count="2"/>
+  <category name="Mali-4xx L2_1" counter_set="ARM_Mali-4xx_L2_1_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 1" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 1" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 1" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 1" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 1" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 1" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 1" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 1" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 1" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 1" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 1" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_2_cnt" title="Mali-4xx L2 2" description="Mali GPU L2 Cache Core 2" count="2"/>
+  <category name="Mali-4xx L2_2" counter_set="ARM_Mali-4xx_L2_2_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 2" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 2" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 2" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 2" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 2" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 2" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 2" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 2" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 2" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 2" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 2" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_Filmstrip_cnt" count="1"/>
+  <category name="Mali-4xx Filmstrip" counter_set="ARM_Mali-4xx_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-4xx" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="ARM_Mali-4xx_Voltage" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Voltage" title="Mali GPU Voltage" name="Voltage" class="absolute" display="average" average_selection="yes" units="mV" description="GPU core voltage."/>
+  </category>
+  <category name="ARM_Mali-4xx_Frequency" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Frequency" title="Mali GPU Frequency" name="Frequency" display="average" average_selection="yes" units="MHz" description="GPU core frequency."/>
+  </category>
+  <category name="Mali-4xx Activity" counter_set="ARM_Mali-4xx_Activity_cnt">
+    <event counter="ARM_Mali-4xx_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="GPU Fragment Activity"/>
+    <event counter="ARM_Mali-4xx_vertex" title="GPU Vertex" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" description="GPU Vertex Activity"/>
+  </category>
+  <category name="Mali-4xx Software Counters" counter_set="ARM_Mali-4xx_SW_cnt" per_cpu="no">
+    <!-- EGL Counters -->
+    <event counter="ARM_Mali-4xx_SW_0" title="Mali EGL Software Counters" name="Blit Time" description="Time spent blitting the framebuffer from video memory to framebuffer."/>
+    <!-- glDrawElements Counters -->
+    <event counter="ARM_Mali-4xx_SW_1" title="glDrawElements Statistics" name="Calls to glDrawElements" description="Number of calls to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_2" title="glDrawElements Statistics" name="Indices to glDrawElements" description="Number of indices to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_3" title="glDrawElements Statistics" name="Transformed by glDrawElements" description="Number of vertices transformed by glDrawElements."/>
+    <!-- glDrawArrays Counters -->
+    <event counter="ARM_Mali-4xx_SW_4" title="glDrawArrays Statistics" name="Calls to glDrawArrays" description="Number of calls to glDrawArrays."/>
+    <event counter="ARM_Mali-4xx_SW_5" title="glDrawArrays Statistics" name="Transformed by glDrawArrays" description="Number of vertices transformed by glDrawArrays."/>
+    <!-- Draw Call Counters -->
+    <event counter="ARM_Mali-4xx_SW_6" title="Drawcall Statistics" name="Points" description="Number of calls to glDraw* with parameter GL_POINTS."/>
+    <event counter="ARM_Mali-4xx_SW_7" title="Drawcall Statistics" name="Lines" description="Number of calls to glDraw* with parameter GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_8" title="Drawcall Statistics" name="Lineloop" description="Number of calls to glDraw* with parameter GL_LINE_LOOP."/>
+    <event counter="ARM_Mali-4xx_SW_9" title="Drawcall Statistics" name="Linestrip" description="Number of calls to glDraw* with parameter GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_10" title="Drawcall Statistics" name="Triangles" description="Number of calls to glDraw* with parameter GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_11" title="Drawcall Statistics" name="Trianglestrip" description="Number of calls to glDraw* with parameter GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_12" title="Drawcall Statistics" name="Trianglefan" description="Number of calls to glDraw* with parameter GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_13" title="Drawcall Statistics" name="Vertex Upload Time (us)" description="Time spent uploading vertex attributes and faceindex data not present in a VBO."/>
+    <event counter="ARM_Mali-4xx_SW_14" title="Drawcall Statistics" name="Uniform Bytes Copied (bytes)" description="Number of bytes copied to Mali memory as a result of uniforms update."/>
+    <!-- Buffer Profiling Counters -->
+    <event counter="ARM_Mali-4xx_SW_15" title="Buffer Profiling" name="Texture Upload Time (ms)" description="Time spent uploading textures."/>
+    <event counter="ARM_Mali-4xx_SW_16" title="Buffer Profiling" name="VBO Upload Time (ms)" description="Time spent uploading vertex buffer objects."/>
+    <event counter="ARM_Mali-4xx_SW_17" title="Buffer Profiling" name="FBO Flushes" description="Number of flushed on framebuffer attachment."/>
+    <!-- OpenGL ES 1.1 Emulation -->
+    <event counter="ARM_Mali-4xx_SW_18" title="Fixed-function Emulation" name="# Vertex Shaders Generated" description="Number of vertex shaders generated."/>
+    <event counter="ARM_Mali-4xx_SW_19" title="Fixed-function Emulation" name="# Fragment Shaders Generated" description="Number of fragment shaders generated."/>
+    <!-- Geometry Statistics -->
+    <event counter="ARM_Mali-4xx_SW_33" title="Geometry Statistics" name="Triangles" description="The total number of triangles passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_34" title="Geometry Statistics" name="Independent Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_35" title="Geometry Statistics" name="Strip Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_36" title="Geometry Statistics" name="Fan Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_37" title="Geometry Statistics" name="Lines" description="Number of lines passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_38" title="Geometry Statistics" name="Independent Lines" description="Number of lines passed to GLES using the mode GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_39" title="Geometry Statistics" name="Strip Lines" description="Number of lines passed to GLES using the mode GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_40" title="Geometry Statistics" name="Loop Lines" description="Number of lines passed to GLES using the mode GL_LINE_LOOP."/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard.xml b/tools/gator/daemon/events-Mali-Midgard.xml
new file mode 100644
index 000000000000..b6ab4b88cd2e
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard.xml
@@ -0,0 +1,46 @@
+  <category name="Mali-Midgard Software Counters" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/>
+  </category>
+  <category name="Mali-Midgard PM Shader" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/>
+  </category>
+  <category name="Mali-Midgard PM Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_TILER_0" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/>
+  </category>
+  <category name="Mali-Midgard PM L2" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_L2_0" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_L2_1" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/>
+  </category>
+  <category name="Mali-Midgard MMU Address Space" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_AS_0" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_1" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_2" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_3" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/>
+  </category>
+  <category name="Mali-Midgard MMU Page Fault" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/>
+  </category>
+  <counter_set name="ARM_Mali-Midgard_Filmstrip_cnt" count="1"/>
+  <category name="Mali-Midgard Filmstrip" counter_set="ARM_Mali-Midgard_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-Midgard" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="Mali-Midgard Activity" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/>
+    <event counter="ARM_Mali-Midgard_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/>
+    <event counter="ARM_Mali-Midgard_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard_hw.xml b/tools/gator/daemon/events-Mali-Midgard_hw.xml
new file mode 100644
index 000000000000..4f3323f197d7
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard_hw.xml
@@ -0,0 +1,91 @@
+  <category name="Mali-Midgard Job Manager" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/>
+    <event counter="ARM_Mali-Midgard_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/>
+    <event counter="ARM_Mali-Midgard_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/>
+    <event counter="ARM_Mali-Midgard_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/>
+    <event counter="ARM_Mali-Midgard_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/>
+    <event counter="ARM_Mali-Midgard_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-Midgard_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+  </category>
+  <category name="Mali-Midgard Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-Midgard_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-Midgard_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-Midgard_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-Midgard_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+    <event counter="ARM_Mali-Midgard_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-Midgard_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+    <event counter="ARM_Mali-Midgard_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-Midgard_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-Midgard_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-Midgard_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-Midgard_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-Midgard_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-Midgard_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-Midgard_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_1" title="Mali Tiler Commands" name="Prims in 1 command" description="Number of primitives producing 1 command"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_2" title="Mali Tiler Commands" name="Prims in 2 command" description="Number of primitives producing 2 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_3" title="Mali Tiler Commands" name="Prims in 3 command" description="Number of primitives producing 3 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_4" title="Mali Tiler Commands" name="Prims in 4 command" description="Number of primitives producing 4 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_4_7" title="Mali Tiler Commands" name="Prims in 4-7 commands" description="Number of primitives producing 4-7 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_5_7" title="Mali Tiler Commands" name="Prims in 5-7 commands" description="Number of primitives producing 5-7 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_8_15" title="Mali Tiler Commands" name="Prims in 8-15 commands" description="Number of primitives producing 8-15 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_16_63" title="Mali Tiler Commands" name="Prims in 16-63 commands" description="Number of primitives producing 16-63 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_64" title="Mali Tiler Commands" name="Prims in &gt;= 64 commands" description="Number of primitives producing &gt;= 64 commands"/>
+  </category>
+  <category name="Mali-Midgard Shader Core" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-Midgard_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+    <event counter="ARM_Mali-Midgard_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+    <event counter="ARM_Mali-Midgard_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-Midgard_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+    <event counter="ARM_Mali-Midgard_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-Midgard_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/>
+    <event counter="ARM_Mali-Midgard_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+    <event counter="ARM_Mali-Midgard_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+  </category>
+  <category name="Mali-Midgard L2 and MMU" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_L2_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T60x_hw.xml b/tools/gator/daemon/events-Mali-T60x_hw.xml
new file mode 100644
index 000000000000..50797e6492ad
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T60x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T60x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T60x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T60x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T60x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T60x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T60x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T60x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T60x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T60x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T60x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T60x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T60x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T60x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T60x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T60x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T60x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T60x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T60x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T60x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T60x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T60x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T60x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T60x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T60x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T62x_hw.xml b/tools/gator/daemon/events-Mali-T62x_hw.xml
new file mode 100644
index 000000000000..6ecc53c2ada1
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T62x_hw.xml
@@ -0,0 +1,109 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T62x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T62x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T62x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T62x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T62x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T62x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T62x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T62x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T62x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T62x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T62x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T62x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T62x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T62x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T62x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T62x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T62x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T62x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T62x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T62x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T62x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T62x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T62x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T62x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T72x_hw.xml b/tools/gator/daemon/events-Mali-T72x_hw.xml
new file mode 100644
index 000000000000..5587534770c8
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T72x_hw.xml
@@ -0,0 +1,95 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T72x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T72x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T72x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T72x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T72x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T72x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T72x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T72x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T72x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T72x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T72x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T72x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T72x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T72x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T72x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe"/>
+
+    <event counter="ARM_Mali-T72x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T72x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T72x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T72x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+
+    <event counter="ARM_Mali-T72x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T72x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T72x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T76x_hw.xml b/tools/gator/daemon/events-Mali-T76x_hw.xml
new file mode 100644
index 000000000000..be74c5a42624
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T76x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T76x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T76x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T76x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T76x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T76x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T76x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T76x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T76x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T76x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T76x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T76x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T76x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T76x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T76x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T76x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T76x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T76x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T76x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T76x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T76x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T76x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T76x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T76x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T76x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-V500.xml b/tools/gator/daemon/events-Mali-V500.xml
new file mode 100644
index 000000000000..89bc7f4734df
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-V500.xml
@@ -0,0 +1,30 @@
+  <category name="Mali-V500">
+    <event counter="ARM_Mali-V500_cnt0" title="MVE-V500 Stats" name="Samples" class="absolute" description="The number of times we have taken a sample"/>
+    <event counter="ARM_Mali-V500_cnt1" title="MVE-V500 Input Totals" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt2" title="MVE-V500 Input Totals" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt3" title="MVE-V500 Output Totals" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt4" title="MVE-V500 Output Totals" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt5" title="MVE-V500 Stats" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/>
+    <event counter="ARM_Mali-V500_cnt6" title="MVE-V500 Sessions" name="Active Sessions" description="The number of currently existing sessions"/>
+    <event counter="ARM_Mali-V500_cnt7" title="MVE-V500 Stats" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/>
+    <event counter="ARM_Mali-V500_cnt8" title="MVE-V500 Input Totals" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt9" title="MVE-V500 Input Totals" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt10" title="MVE-V500 Output Totals" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt11" title="MVE-V500 Output Totals" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt12" title="MVE-V500 Output" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt13" title="MVE-V500 Input" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt14" title="MVE-V500 Output" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/>
+    <event counter="ARM_Mali-V500_cnt15" title="MVE-V500 Input" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/>
+    <event counter="ARM_Mali-V500_cnt16" title="MVE-V500 Stats" name="Errors encountered" class="absolute" description="The number of errors encountered"/>
+    <event counter="ARM_Mali-V500_cnt17" title="MVE-V500 Bandwidth" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/>
+    <event counter="ARM_Mali-V500_cnt18" title="MVE-V500 Bandwidth" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/>
+    <event counter="ARM_Mali-V500_cnt19" title="MVE-V500 Bandwidth" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/>
+    <event counter="ARM_Mali-V500_cnt20" title="MVE-V500 Bandwidth" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/>
+    <event counter="ARM_Mali-V500_evn0" title="MVE-V500 Sessions" name="Session created" description="Generated when a session has been created"/>
+    <event counter="ARM_Mali-V500_evn1" title="MVE-V500 Sessions" name="Session destroyed" description="Generated when a session has been destroyed"/>
+    <event counter="ARM_Mali-V500_evn2" title="MVE-V500 Frames" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/>
+    <event counter="ARM_Mali-V500_evn3" title="MVE-V500 Output" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_evn4" title="MVE-V500 Input" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_act0" title="MVE-V500 Parsed" name="Activity" class="activity" activity1="activity" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+    <event counter="ARM_Mali-V500_act1" title="MVE-V500 Piped" name="Activity" class="activity" activity1="activity" activity_color1="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Perf-Hardware.xml b/tools/gator/daemon/events-Perf-Hardware.xml
new file mode 100644
index 000000000000..423696f82420
--- /dev/null
+++ b/tools/gator/daemon/events-Perf-Hardware.xml
@@ -0,0 +1,12 @@
+  <counter_set name="Perf_Hardware_cnt" count="6"/>
+  <category name="Perf Hardware" counter_set="Perf_Hardware_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Perf_Hardware_ccnt" event="0" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="1" title="Instruction" name="Executed" description="Instruction executed"/>
+    <event event="2" title="Cache" name="References" description="Cache References"/>
+    <event event="3" title="Cache" name="Misses" description="Cache Misses"/>
+    <event event="4" title="Branch" name="Instructions" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="5" title="Branch" name="Misses" description="Branch mispredicted or not predicted"/>
+    <event event="6" title="Bus" name="Cycles" description="Bus Cycles"/>
+    <event event="7" title="Instruction" name="Stalled Frontend" description="Stalled Frontend Cycles"/>
+    <event event="8" title="Instruction" name="Stalled Backend" description="Stalled Backend Cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-Scorpion.xml b/tools/gator/daemon/events-Scorpion.xml
new file mode 100644
index 000000000000..fa716fdc4840
--- /dev/null
+++ b/tools/gator/daemon/events-Scorpion.xml
@@ -0,0 +1,107 @@
+  <counter_set name="Scorpion_cnt" count="4"/>
+  <category name="Scorpion" counter_set="Scorpion_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Scorpion_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="Scorpion" name="BANK_AB_HIT" description="L2 hit rates bank A/B hits"/>
+    <event event="0x8f" title="Scorpion" name="BANK_AB_ACCESS" description="L2 hit rates bank A/B accesses"/>
+    <event event="0x90" title="Scorpion" name="BANK_CD_HIT" description="L2 hit rates bank C/D hits"/>
+    <event event="0x91" title="Scorpion" name="BANK_CD_ACCESS" description="L2 hit rates bank C/D accesses"/>
+    <event event="0x92" title="Scorpion" name="BANK_AB_DSIDE_HIT" description="L2 hit rates bank A/B d-side hits"/>
+    <event event="0x93" title="Scorpion" name="BANK_AB_DSIDE_ACCESS" description="L2 hit rates bank A/B d-side accesses"/>
+    <event event="0x94" title="Scorpion" name="BANK_CD_DSIDE_HIT" description="L2 hit rates bank C/D d-side hits"/>
+    <event event="0x95" title="Scorpion" name="BANK_CD_DSIDE_ACCESS" description="L2 hit rates bank C/D d-side accesses"/>
+    <event event="0x96" title="Scorpion" name="BANK_AB_ISIDE_HIT" description="L2 hit rates bank A/B i-side hits"/>
+    <event event="0x97" title="Scorpion" name="BANK_AB_ISIDE_ACCESS" description="L2 hit rates bank A/B i-side accesses"/>
+    <event event="0x98" title="Scorpion" name="BANK_CD_ISIDE_HIT" description="L2 hit rates bank C/D i-side hits"/>
+    <event event="0x99" title="Scorpion" name="BANK_CD_ISIDE_ACCESS" description="L2 hit rates bank C/D i-side accesses"/>
+    <event event="0x9a" title="Scorpion" name="ISIDE_RD_WAIT" description="fills and castouts cycles that i-side RD requests wait on data from bus"/>
+    <event event="0x9b" title="Scorpion" name="DSIDE_RD_WAIT" description="fills and castouts cycles that d-side RD requests wait on data from bus"/>
+    <event event="0x9c" title="Scorpion" name="BANK_BYPASS_WRITE" description="fills and castouts bank bypass writes"/>
+    <event event="0x9d" title="Scorpion" name="BANK_AB_NON_CASTOUT" description="fills and castouts bank A/B non-castout writes to bus"/>
+    <event event="0x9e" title="Scorpion" name="BANK_AB_L2_CASTOUT" description="fills and castouts bank A/B L2 castouts (granules)"/>
+    <event event="0x9f" title="Scorpion" name="BANK_CD_NON_CASTOUT" description="fills and castouts bank C/D non-castout writes to bus"/>
+    <event event="0xa0" title="Scorpion" name="BANK_CD_L2_CASTOUT" description="fills and castouts bank C/D L2 castouts (granules)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ScorpionMP.xml b/tools/gator/daemon/events-ScorpionMP.xml
new file mode 100644
index 000000000000..c648ccefb287
--- /dev/null
+++ b/tools/gator/daemon/events-ScorpionMP.xml
@@ -0,0 +1,90 @@
+  <counter_set name="ScorpionMP_cnt" count="4"/>
+  <category name="ScorpionMP" counter_set="ScorpionMP_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ScorpionMP_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="ScorpionMP" name="NUM_BARRIERS" description="Barriers"/>
+    <event event="0x8f" title="ScorpionMP" name="BARRIER_CYCLES" description="Barrier cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-ftrace.xml b/tools/gator/daemon/events-ftrace.xml
new file mode 100644
index 000000000000..33ab7aab2196
--- /dev/null
+++ b/tools/gator/daemon/events-ftrace.xml
@@ -0,0 +1,7 @@
+  <category name="Ftrace">
+    <!-- counter attribute must start with ftrace_ and be unique -->
+    <!-- regex item in () is the value shown -->
+    <!--
+    <event counter="ftrace_trace_marker_numbers" title="ftrace" name="trace_marker" class="absolute" regex="([0-9]+)" description="Numbers written to /sys/kernel/debug/tracing/trace_marker, ex: echo 42 > /sys/kernel/debug/tracing/trace_marker"/>
+    -->
+  </category>
diff --git a/tools/gator/daemon/events_footer.xml b/tools/gator/daemon/events_footer.xml
new file mode 100644
index 000000000000..cd2b44665bab
--- /dev/null
+++ b/tools/gator/daemon/events_footer.xml
@@ -0,0 +1 @@
+</events>
diff --git a/tools/gator/daemon/events_header.xml b/tools/gator/daemon/events_header.xml
new file mode 100644
index 000000000000..38ec4c03246e
--- /dev/null
+++ b/tools/gator/daemon/events_header.xml
@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<events>
diff --git a/tools/gator/daemon/k/perf_event.3.12.h b/tools/gator/daemon/k/perf_event.3.12.h
new file mode 100644
index 000000000000..e886c48cadf6
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.3.12.h
@@ -0,0 +1,792 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_EVENT_H
+#define _LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+
+				__reserved_1   : 40;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	/* Align to u64. */
+	__u32	__reserved_2;
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, idx, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     idx = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_usr_rdpmc && idx) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(idx - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_usr_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & ((1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if idx), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (idx)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & ((1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
+#define PERF_FLAG_FD_OUTPUT		(1U << 1)
+#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
+
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ */
+struct perf_branch_entry {
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		reserved:60;
+};
+
+#endif /* _LINUX_PERF_EVENT_H */
diff --git a/tools/gator/daemon/k/perf_event.h b/tools/gator/daemon/k/perf_event.h
new file mode 120000
index 000000000000..e5dff8c21ef4
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.h
@@ -0,0 +1 @@
+perf_event.3.12.h
\ No newline at end of file
diff --git a/tools/gator/daemon/libsensors/COPYING.LGPL b/tools/gator/daemon/libsensors/COPYING.LGPL
new file mode 100644
index 000000000000..4362b49151d7
--- /dev/null
+++ b/tools/gator/daemon/libsensors/COPYING.LGPL
@@ -0,0 +1,502 @@
+                  GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL.  It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it.  You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+  When we speak of free software, we are referring to freedom of use,
+not price.  Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+  To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights.  These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  To protect each distributor, we want to make it very clear that
+there is no warranty for the free library.  Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+  Finally, software patents pose a constant threat to the existence of
+any free program.  We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder.  Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+  Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License.  This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License.  We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+  When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library.  The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom.  The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+  We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License.  It also provides other free software developers Less
+of an advantage over competing non-free programs.  These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries.  However, the Lesser license provides advantages in certain
+special circumstances.
+
+  For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard.  To achieve this, non-free programs must be
+allowed to use the library.  A more frequent case is that a free
+library does the same job as widely used non-free libraries.  In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+  In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software.  For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+  Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+                  GNU LESSER GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Use a suitable shared library mechanism for linking with the
+    Library.  A suitable mechanism is one that (1) uses at run time a
+    copy of the library already present on the user's computer system,
+    rather than copying library functions into the executable, and (2)
+    will operate properly with a modified version of the library, if
+    the user installs one, as long as the modified version is
+    interface-compatible with the version that the work was made with.
+
+    c) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    d) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    e) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+                            NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+           How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public
+    License along with this library; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/libsensors/access.c b/tools/gator/daemon/libsensors/access.c
new file mode 100644
index 000000000000..8e227e2550db
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.c
@@ -0,0 +1,561 @@
+/*
+    access.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include "access.h"
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "sysfs.h"
+
+/* We watch the recursion depth for variables only, as an easy way to
+   detect cycles. */
+#define DEPTH_MAX	8
+
+static int sensors_eval_expr(const sensors_chip_features *chip_features,
+			     const sensors_expr *expr,
+			     double val, int depth, double *result);
+
+/* Compare two chips name descriptions, to see whether they could match.
+   Return 0 if it does not match, return 1 if it does match. */
+static int sensors_match_chip(const sensors_chip_name *chip1,
+		       const sensors_chip_name *chip2)
+{
+	if ((chip1->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    (chip2->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    strcmp(chip1->prefix, chip2->prefix))
+		return 0;
+
+	if ((chip1->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip2->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip1->bus.type != chip2->bus.type))
+		return 0;
+
+	if ((chip1->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip2->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip1->bus.nr != chip2->bus.nr))
+		return 0;
+
+	if ((chip1->addr != chip2->addr) &&
+	    (chip1->addr != SENSORS_CHIP_NAME_ADDR_ANY) &&
+	    (chip2->addr != SENSORS_CHIP_NAME_ADDR_ANY))
+		return 0;
+
+	return 1;
+}
+
+/* Returns, one by one, a pointer to all sensor_chip structs of the
+   config file which match with the given chip name. Last should be
+   the value returned by the last call, or NULL if this is the first
+   call. Returns NULL if no more matches are found. Do not modify
+   the struct the return value points to! 
+   Note that this visits the list of chips from last to first. Usually,
+   you want the match that was latest in the config file. */
+static sensors_chip *
+sensors_for_all_config_chips(const sensors_chip_name *name,
+			     const sensors_chip *last)
+{
+	int nr, i;
+	sensors_chip_name_list chips;
+
+	for (nr = last ? last - sensors_config_chips - 1 :
+			 sensors_config_chips_count - 1; nr >= 0; nr--) {
+
+		chips = sensors_config_chips[nr].chips;
+		for (i = 0; i < chips.fits_count; i++) {
+			if (sensors_match_chip(&chips.fits[i], name))
+				return sensors_config_chips + nr;
+		}
+	}
+	return NULL;
+}
+
+/* Look up a chip in the intern chip list, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_chip_features *
+sensors_lookup_chip(const sensors_chip_name *name)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++)
+		if (sensors_match_chip(&sensors_proc_chips[i].chip, name))
+			return &sensors_proc_chips[i];
+
+	return NULL;
+}
+
+/* Look up a subfeature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_nr(const sensors_chip_features *chip,
+			     int subfeat_nr)
+{
+	if (subfeat_nr < 0 ||
+	    subfeat_nr >= chip->subfeature_count)
+		return NULL;
+	return chip->subfeature + subfeat_nr;
+}
+
+/* Look up a feature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_feature *
+sensors_lookup_feature_nr(const sensors_chip_features *chip, int feat_nr)
+{
+	if (feat_nr < 0 ||
+	    feat_nr >= chip->feature_count)
+		return NULL;
+	return chip->feature + feat_nr;
+}
+
+/* Look up a subfeature by name, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if 
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_name(const sensors_chip_features *chip,
+			       const char *name)
+{
+	int j;
+
+	for (j = 0; j < chip->subfeature_count; j++)
+		if (!strcmp(chip->subfeature[j].name, name))
+			return chip->subfeature + j;
+	return NULL;
+}
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip)
+{
+	if ((chip->prefix == SENSORS_CHIP_NAME_PREFIX_ANY) ||
+	    (chip->bus.type == SENSORS_BUS_TYPE_ANY) ||
+	    (chip->bus.nr == SENSORS_BUS_NR_ANY) ||
+	    (chip->addr == SENSORS_CHIP_NAME_ADDR_ANY))
+		return 1;
+	else
+		return 0;
+}
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature)
+{
+	char *label;
+	const sensors_chip *chip;
+	char buf[PATH_MAX];
+	FILE *f;
+	int i;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return NULL;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->labels_count; i++)
+			if (!strcmp(feature->name, chip->labels[i].name)) {
+				label = chip->labels[i].value;
+				goto sensors_get_label_exit;
+			}
+
+	/* No user specified label, check for a _label sysfs file */
+	snprintf(buf, PATH_MAX, "%s/%s_label", name->path, feature->name);
+	
+	if ((f = fopen(buf, "r"))) {
+		i = fread(buf, 1, sizeof(buf), f);
+		fclose(f);
+		if (i > 0) {
+			/* i - 1 to strip the '\n' at the end */
+			buf[i - 1] = 0;
+			label = buf;
+			goto sensors_get_label_exit;
+		}
+	}
+
+	/* No label, return the feature name instead */
+	label = feature->name;
+	
+sensors_get_label_exit:
+	label = strdup(label);
+	if (!label)
+		sensors_fatal_error(__func__, "Allocating label text");
+	return label;
+}
+
+/* Looks up whether a feature should be ignored. Returns
+   1 if it should be ignored, 0 if not. */
+static int sensors_get_ignored(const sensors_chip_name *name,
+			       const sensors_feature *feature)
+{
+	const sensors_chip *chip;
+	int i;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->ignores_count; i++)
+			if (!strcmp(feature->name, chip->ignores[i].name))
+				return 1;
+	return 0;
+}
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+static int __sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+			       int depth, double *result)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	double val;
+	int res, i;
+
+	if (depth >= DEPTH_MAX)
+		return -SENSORS_ERR_RECURSION;
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_R))
+		return -SENSORS_ERR_ACCESS_R;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].from_proc;
+					break;
+				}
+			}
+	}
+
+	res = sensors_read_sysfs_attr(name, subfeature, &val);
+	if (res)
+		return res;
+	if (!expr)
+		*result = val;
+	else if ((res = sensors_eval_expr(chip_features, expr, val, depth,
+					  result)))
+		return res;
+	return 0;
+}
+
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *result)
+{
+	return __sensors_get_value(name, subfeat_nr, 0, result);
+}
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	int i, res;
+	double to_write;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_W))
+		return -SENSORS_ERR_ACCESS_W;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].to_proc;
+					break;
+				}
+			}
+	}
+
+	to_write = value;
+	if (expr)
+		if ((res = sensors_eval_expr(chip_features, expr,
+					     value, 0, &to_write)))
+			return res;
+	return sensors_write_sysfs_attr(name, subfeature, to_write);
+}
+
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr)
+{
+	const sensors_chip_name *res;
+
+	while (*nr < sensors_proc_chips_count) {
+		res = &sensors_proc_chips[(*nr)++].chip;
+		if (!match || sensors_match_chip(res, match))
+			return res;
+	}
+	return NULL;
+}
+
+const char *sensors_get_adapter_name(const sensors_bus_id *bus)
+{
+	int i;
+
+	/* bus types with a single instance */
+	switch (bus->type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return "ISA adapter";
+	case SENSORS_BUS_TYPE_PCI:
+		return "PCI adapter";
+	/* SPI should not be here, but for now SPI adapters have no name
+	   so we don't have any custom string to return. */
+	case SENSORS_BUS_TYPE_SPI:
+		return "SPI adapter";
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return "Virtual device";
+	case SENSORS_BUS_TYPE_ACPI:
+		return "ACPI interface";
+	/* HID should probably not be there either, but I don't know if
+	   HID buses have a name nor where to find it. */
+	case SENSORS_BUS_TYPE_HID:
+		return "HID adapter";
+	}
+
+	/* bus types with several instances */
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		if (sensors_proc_bus[i].bus.type == bus->type &&
+		    sensors_proc_bus[i].bus.nr == bus->nr)
+			return sensors_proc_bus[i].adapter;
+	return NULL;
+}
+
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr)
+{
+	const sensors_chip_features *chip;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	while (*nr < chip->feature_count
+	    && sensors_get_ignored(name, &chip->feature[*nr]))
+		(*nr)++;
+	if (*nr >= chip->feature_count)
+		return NULL;
+	return &chip->feature[(*nr)++];
+}
+
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			const sensors_feature *feature, int *nr)
+{
+	const sensors_chip_features *chip;
+	const sensors_subfeature *subfeature;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	/* Seek directly to the first subfeature */
+	if (*nr < feature->first_subfeature)
+		*nr = feature->first_subfeature;
+
+	if (*nr >= chip->subfeature_count)
+		return NULL;	/* end of list */
+	subfeature = &chip->subfeature[(*nr)++];
+	if (subfeature->mapping == feature->number)
+		return subfeature;
+	return NULL;	/* end of subfeature list */
+}
+
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type)
+{
+	const sensors_chip_features *chip;
+	int i;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	for (i = feature->first_subfeature; i < chip->subfeature_count &&
+	     chip->subfeature[i].mapping == feature->number; i++) {
+		if (chip->subfeature[i].type == type)
+			return &chip->subfeature[i];
+	}
+	return NULL;	/* No such subfeature */
+}
+
+/* Evaluate an expression */
+int sensors_eval_expr(const sensors_chip_features *chip_features,
+		      const sensors_expr *expr,
+		      double val, int depth, double *result)
+{
+	double res1, res2;
+	int res;
+	const sensors_subfeature *subfeature;
+
+	if (expr->kind == sensors_kind_val) {
+		*result = expr->data.val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_source) {
+		*result = val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_var) {
+		if (!(subfeature = sensors_lookup_subfeature_name(chip_features,
+							    expr->data.var)))
+			return -SENSORS_ERR_NO_ENTRY;
+		return __sensors_get_value(&chip_features->chip,
+					   subfeature->number, depth + 1,
+					   result);
+	}
+	if ((res = sensors_eval_expr(chip_features, expr->data.subexpr.sub1,
+				     val, depth, &res1)))
+		return res;
+	if (expr->data.subexpr.sub2 &&
+	    (res = sensors_eval_expr(chip_features, expr->data.subexpr.sub2,
+				     val, depth, &res2)))
+		return res;
+	switch (expr->data.subexpr.op) {
+	case sensors_add:
+		*result = res1 + res2;
+		return 0;
+	case sensors_sub:
+		*result = res1 - res2;
+		return 0;
+	case sensors_multiply:
+		*result = res1 * res2;
+		return 0;
+	case sensors_divide:
+		if (res2 == 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = res1 / res2;
+		return 0;
+	case sensors_negate:
+		*result = -res1;
+		return 0;
+	case sensors_exp:
+		*result = exp(res1);
+		return 0;
+	case sensors_log:
+		if (res1 < 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = log(res1);
+		return 0;
+	}
+	return 0;
+}
+
+/* Execute all set statements for this particular chip. The chip may not 
+   contain wildcards!  This function will return 0 on success, and <0 on 
+   failure. */
+static int sensors_do_this_chip_sets(const sensors_chip_name *name)
+{
+	const sensors_chip_features *chip_features;
+	sensors_chip *chip;
+	double value;
+	int i;
+	int err = 0, res;
+	const sensors_subfeature *subfeature;
+
+	chip_features = sensors_lookup_chip(name);	/* Can't fail */
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->sets_count; i++) {
+			subfeature = sensors_lookup_subfeature_name(chip_features,
+							chip->sets[i].name);
+			if (!subfeature) {
+				sensors_parse_error_wfn("Unknown feature name",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = -SENSORS_ERR_NO_ENTRY;
+				continue;
+			}
+
+			res = sensors_eval_expr(chip_features,
+						chip->sets[i].value, 0,
+						0, &value);
+			if (res) {
+				sensors_parse_error_wfn("Error parsing expression",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+			if ((res = sensors_set_value(name, subfeature->number,
+						     value))) {
+				sensors_parse_error_wfn("Failed to set value",
+						chip->sets[i].line.filename,
+						chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+		}
+	return err;
+}
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name)
+{
+	int nr, this_res;
+	const sensors_chip_name *found_name;
+	int res = 0;
+
+	for (nr = 0; (found_name = sensors_get_detected_chips(name, &nr));) {
+		this_res = sensors_do_this_chip_sets(found_name);
+		if (this_res)
+			res = this_res;
+	}
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/access.h b/tools/gator/daemon/libsensors/access.h
new file mode 100644
index 000000000000..1d3784340757
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.h
@@ -0,0 +1,33 @@
+/*
+    access.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ACCESS_H
+#define LIB_SENSORS_ACCESS_H
+
+#include "sensors.h"
+#include "data.h"
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip);
+
+#endif /* def LIB_SENSORS_ACCESS_H */
diff --git a/tools/gator/daemon/libsensors/conf-lex.c b/tools/gator/daemon/libsensors/conf-lex.c
new file mode 100644
index 000000000000..a54664b3d77b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.c
@@ -0,0 +1,2881 @@
+
+#line 3 "<stdout>"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer sensors_yy_create_buffer
+#define yy_delete_buffer sensors_yy_delete_buffer
+#define yy_flex_debug sensors_yy_flex_debug
+#define yy_init_buffer sensors_yy_init_buffer
+#define yy_flush_buffer sensors_yy_flush_buffer
+#define yy_load_buffer_state sensors_yy_load_buffer_state
+#define yy_switch_to_buffer sensors_yy_switch_to_buffer
+#define yyin sensors_yyin
+#define yyleng sensors_yyleng
+#define yylex sensors_yylex
+#define yylineno sensors_yylineno
+#define yyout sensors_yyout
+#define yyrestart sensors_yyrestart
+#define yytext sensors_yytext
+#define yywrap sensors_yywrap
+#define yyalloc sensors_yyalloc
+#define yyrealloc sensors_yyrealloc
+#define yyfree sensors_yyfree
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! C99 */
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE sensors_yyrestart(sensors_yyin  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k.
+ * Moreover, YY_BUF_SIZE is 2*YY_READ_BUF_SIZE in the general case.
+ * Ditto for the __ia64__ case accordingly.
+ */
+#define YY_BUF_SIZE 32768
+#else
+#define YY_BUF_SIZE 16384
+#endif /* __ia64__ */
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE   ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int sensors_yyleng;
+
+extern FILE *sensors_yyin, *sensors_yyout;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    #define YY_LESS_LINENO(n)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up sensors_yytext again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via sensors_yyrestart()), so that the user can continue scanning by
+	 * just pointing sensors_yyin at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when sensors_yytext is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int sensors_yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow sensors_yywrap()'s to do buffer switches
+ * instead of setting up a fresh sensors_yyin.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void sensors_yyrestart (FILE *input_file  );
+void sensors_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE sensors_yy_create_buffer (FILE *file,int size  );
+void sensors_yy_delete_buffer (YY_BUFFER_STATE b  );
+void sensors_yy_flush_buffer (YY_BUFFER_STATE b  );
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer  );
+void sensors_yypop_buffer_state (void );
+
+static void sensors_yyensure_buffer_stack (void );
+static void sensors_yy_load_buffer_state (void );
+static void sensors_yy_init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER sensors_yy_flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE sensors_yy_scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE sensors_yy_scan_bytes (yyconst char *bytes,int len  );
+
+void *sensors_yyalloc (yy_size_t  );
+void *sensors_yyrealloc (void *,yy_size_t  );
+void sensors_yyfree (void *  );
+
+#define yy_new_buffer sensors_yy_create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+#define sensors_yywrap(n) 1
+#define YY_SKIP_YYWRAP
+
+typedef unsigned char YY_CHAR;
+
+FILE *sensors_yyin = (FILE *) 0, *sensors_yyout = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int sensors_yylineno;
+
+int sensors_yylineno = 1;
+
+extern char *sensors_yytext;
+#define yytext_ptr sensors_yytext
+static yyconst flex_int16_t yy_nxt[][39] =
+    {
+    {
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9
+
+    },
+
+    {
+        9,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10
+    },
+
+    {
+        9,  -11,   45,   46,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11
+    },
+
+    {
+        9,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+      -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+      -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   50,   49
+    },
+
+    {
+        9,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+      -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+       49,   49,   49,   49,   49,   49,   49,   51,   49,   49,
+       49,   49,   52,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+      -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+
+       49,   49,   49,   49,   49,   49,   53,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+      -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+       54,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+      -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+       49,   49,   49,   49,   55,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20
+    },
+
+    {
+        9,  -21,   56,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21
+    },
+
+    {
+        9,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22
+    },
+
+    {
+        9,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+
+    },
+
+    {
+        9,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25
+    },
+
+    {
+        9,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26
+    },
+
+    {
+        9,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27
+    },
+
+    {
+        9,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28
+    },
+
+    {
+        9,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29
+
+    },
+
+    {
+        9,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30
+    },
+
+    {
+        9,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,   59,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31
+    },
+
+    {
+        9,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32
+    },
+
+    {
+        9,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,
+      -33,  -33,   60,  -33,   61,  -33,   62,  -33,  -33,  -33,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34
+
+    },
+
+    {
+        9,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,
+      -35,  -35,  -35,  -35,   62,  -35,   62,  -35,  -35,  -35,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -36,   63,   64,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36
+    },
+
+    {
+        9,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37
+    },
+
+    {
+        9,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38
+    },
+
+    {
+        9,   65,   65,  -39,  -39,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -39,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+
+    },
+
+    {
+        9,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40
+    },
+
+    {
+        9,  -41,  -41,  -41,   66,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41
+    },
+
+    {
+        9,   67,   67,   68,   67,   67,   67,   67,   67,   67,
+       67,   67,   67,   67,   67,   67,   67,   67,   67,   67,
+
+       69,   70,   67,   67,   67,   71,   67,   67,   67,   67,
+       67,   72,   67,   67,   73,   67,   74,   67,   75
+    },
+
+    {
+        9,   76,   76,  -43,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44
+
+    },
+
+    {
+        9,  -45,   45,   46,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45
+    },
+
+    {
+        9,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48
+    },
+
+    {
+        9,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+      -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+      -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   77,   49,   49,   49
+    },
+
+    {
+        9,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+      -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+       49,   49,   49,   49,   49,   49,   49,   49,   78,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+      -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       79,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+      -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   80,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+      -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+       49,   81,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+      -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   82,   49,   49
+    },
+
+    {
+        9,  -56,   56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+    },
+
+    {
+        9,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58
+    },
+
+    {
+        9,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,   59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59
+
+    },
+
+    {
+        9,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,   59,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60
+    },
+
+    {
+        9,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,
+      -61,  -61,   60,  -61,   61,  -61,   62,  -61,  -61,  -61,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,
+      -62,  -62,  -62,  -62,   62,  -62,   62,  -62,  -62,  -62,
+
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -63,   63,   64,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63
+    },
+
+    {
+        9,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64
+
+    },
+
+    {
+        9,   65,   65,  -65,  -65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+    },
+
+    {
+        9,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66
+    },
+
+    {
+        9,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67
+    },
+
+    {
+        9,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68
+    },
+
+    {
+        9,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69
+
+    },
+
+    {
+        9,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70
+    },
+
+    {
+        9,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71
+    },
+
+    {
+        9,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72
+    },
+
+    {
+        9,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73
+    },
+
+    {
+        9,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74
+
+    },
+
+    {
+        9,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75
+    },
+
+    {
+        9,   76,   76,  -76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -77,   83,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+      -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+      -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   84,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+      -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   85,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+      -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   86,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+      -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+       49,   49,   49,   49,   87,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -82,   88,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+      -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -83,   83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83
+    },
+
+    {
+        9,  -84,   89,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+      -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+      -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   90,   49
+    },
+
+    {
+        9,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+      -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   91,   49,   49,   49,   49
+    },
+
+    {
+        9,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+      -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   92,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -88,   88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88
+    },
+
+    {
+        9,  -89,   89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89
+
+    },
+
+    {
+        9,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+      -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   93,   49,   49
+    },
+
+    {
+        9,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+      -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+       49,   49,   49,   49,   94,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -92,   95,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+      -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+      -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+       49,   49,   49,   49,   96,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -94,   97,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+      -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -95,   95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95
+    },
+
+    {
+        9,  -96,   98,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+      -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -97,   97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97
+    },
+
+    {
+        9,  -98,   98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98
+    },
+
+    } ;
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up sensors_yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	sensors_yyleng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 50
+#define YY_END_OF_BUFFER 51
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[99] =
+    {   0,
+        0,    0,    0,    0,    0,    0,   13,   13,   51,   12,
+        1,    2,    3,   11,   11,   11,   11,   11,   11,   33,
+       15,   16,   31,   18,   25,   26,   23,   21,   27,   22,
+       33,   24,   20,   28,   32,   33,   29,   30,   49,   36,
+       39,   48,   13,   14,    1,    2,    3,    4,   11,   11,
+       11,   11,   11,   11,   11,   15,   18,   19,   20,   34,
+       20,   32,   35,   17,   49,   38,   47,   37,   40,   41,
+       42,   43,   44,   45,   46,   13,    8,   11,   11,   11,
+       11,    6,    8,    9,   11,   11,   11,    6,    9,   11,
+       11,    5,   11,   10,    5,    7,   10,    7
+
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    2,    3,
+        2,    2,    2,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    1,    4,    5,    1,    1,    1,    1,    6,
+        7,    8,    9,   10,   11,   12,   13,   14,   14,   14,
+       14,   14,   14,   14,   14,   14,   14,    1,    1,    1,
+        1,    1,    1,   15,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+        1,   17,    1,   18,   16,   19,   20,   21,   22,   23,
+
+       24,   25,   26,   27,   28,   23,   23,   29,   30,   31,
+       32,   33,   23,   34,   35,   36,   37,   38,   23,   23,
+       23,   23,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1
+    } ;
+
+extern int sensors_yy_flex_debug;
+int sensors_yy_flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *sensors_yytext;
+#line 1 "lib/conf-lex.l"
+#line 2 "lib/conf-lex.l"
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+/* Scanner for configuration files */
+/* All states are exclusive */
+
+
+
+/* Any whitespace-like character */
+/* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+/* Only positive whole numbers are recognized here */
+#line 1255 "<stdout>"
+
+#define INITIAL 0
+#define MIDDLE 1
+#define STRING 2
+#define ERR 3
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int sensors_yylex_destroy (void );
+
+int sensors_yyget_debug (void );
+
+void sensors_yyset_debug (int debug_flag  );
+
+YY_EXTRA_TYPE sensors_yyget_extra (void );
+
+void sensors_yyset_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *sensors_yyget_in (void );
+
+void sensors_yyset_in  (FILE * in_str  );
+
+FILE *sensors_yyget_out (void );
+
+void sensors_yyset_out  (FILE * out_str  );
+
+int sensors_yyget_leng (void );
+
+char *sensors_yyget_text (void );
+
+int sensors_yyget_lineno (void );
+
+void sensors_yyset_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int sensors_yywrap (void );
+#else
+extern int sensors_yywrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k */
+#define YY_READ_BUF_SIZE 16384
+#else
+#define YY_READ_BUF_SIZE 8192
+#endif /* __ia64__ */
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( sensors_yytext, sensors_yyleng, 1, sensors_yyout )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		size_t n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( sensors_yyin )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( sensors_yyin ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, sensors_yyin))==0 && ferror(sensors_yyin)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(sensors_yyin); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int sensors_yylex (void);
+
+#define YY_DECL int sensors_yylex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after sensors_yytext and sensors_yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 80 "lib/conf-lex.l"
+
+
+ /*
+  * STATE: INITIAL
+  */
+
+#line 1450 "<stdout>"
+
+	if ( !(yy_init) )
+		{
+		(yy_init) = 1;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! sensors_yyin )
+			sensors_yyin = stdin;
+
+		if ( ! sensors_yyout )
+			sensors_yyout = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			sensors_yyensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+		}
+
+		sensors_yy_load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of sensors_yytext. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+yy_match:
+		while ( (yy_current_state = yy_nxt[yy_current_state][ yy_ec[YY_SC_TO_UI(*yy_cp)]  ]) > 0 )
+			++yy_cp;
+
+		yy_current_state = -yy_current_state;
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+
+		YY_DO_BEFORE_ACTION;
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+
+case YY_STATE_EOF(INITIAL):
+#line 88 "lib/conf-lex.l"
+{ /* EOF from this state terminates */
+		  return 0;
+		}
+	YY_BREAK
+case 1:
+YY_RULE_SETUP
+#line 92 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 2:
+/* rule 2 can match eol */
+YY_RULE_SETUP
+#line 94 "lib/conf-lex.l"
+{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 3:
+YY_RULE_SETUP
+#line 100 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 4:
+/* rule 4 can match eol */
+YY_RULE_SETUP
+#line 102 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+case 5:
+YY_RULE_SETUP
+#line 113 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 120 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 127 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 134 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+	YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 141 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 148 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+	YY_BREAK
+/* Anything else at the beginning of a line is an error */
+case 11:
+#line 158 "lib/conf-lex.l"
+case 12:
+YY_RULE_SETUP
+#line 158 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: ERROR
+  */
+
+case 13:
+YY_RULE_SETUP
+#line 171 "lib/conf-lex.l"
+; /* eat whatever is left on this line */
+	YY_BREAK
+case 14:
+/* rule 14 can match eol */
+YY_RULE_SETUP
+#line 173 "lib/conf-lex.l"
+{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+
+/*
+  * STATE: MIDDLE
+  */
+
+case 15:
+YY_RULE_SETUP
+#line 186 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 16:
+/* rule 16 can match eol */
+YY_RULE_SETUP
+#line 188 "lib/conf-lex.l"
+{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+case YY_STATE_EOF(MIDDLE):
+#line 194 "lib/conf-lex.l"
+{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+	YY_BREAK
+case 17:
+/* rule 17 can match eol */
+YY_RULE_SETUP
+#line 199 "lib/conf-lex.l"
+{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 18:
+YY_RULE_SETUP
+#line 205 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 19:
+/* rule 19 can match eol */
+YY_RULE_SETUP
+#line 207 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+/* A number */
+case 20:
+YY_RULE_SETUP
+#line 215 "lib/conf-lex.l"
+{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+	YY_BREAK
+/* Some operators */
+case 21:
+YY_RULE_SETUP
+#line 222 "lib/conf-lex.l"
+return '+';
+	YY_BREAK
+case 22:
+YY_RULE_SETUP
+#line 223 "lib/conf-lex.l"
+return '-';
+	YY_BREAK
+case 23:
+YY_RULE_SETUP
+#line 224 "lib/conf-lex.l"
+return '*';
+	YY_BREAK
+case 24:
+YY_RULE_SETUP
+#line 225 "lib/conf-lex.l"
+return '/';
+	YY_BREAK
+case 25:
+YY_RULE_SETUP
+#line 226 "lib/conf-lex.l"
+return '(';
+	YY_BREAK
+case 26:
+YY_RULE_SETUP
+#line 227 "lib/conf-lex.l"
+return ')';
+	YY_BREAK
+case 27:
+YY_RULE_SETUP
+#line 228 "lib/conf-lex.l"
+return ',';
+	YY_BREAK
+case 28:
+YY_RULE_SETUP
+#line 229 "lib/conf-lex.l"
+return '@';
+	YY_BREAK
+case 29:
+YY_RULE_SETUP
+#line 230 "lib/conf-lex.l"
+return '^';
+	YY_BREAK
+case 30:
+YY_RULE_SETUP
+#line 231 "lib/conf-lex.l"
+return '`';
+	YY_BREAK
+/* Quoted string */
+case 31:
+YY_RULE_SETUP
+#line 235 "lib/conf-lex.l"
+{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+	YY_BREAK
+/* A normal, unquoted identifier */
+case 32:
+YY_RULE_SETUP
+#line 242 "lib/conf-lex.l"
+{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+	YY_BREAK
+/* anything else is bogus */
+case 33:
+#line 254 "lib/conf-lex.l"
+case 34:
+#line 255 "lib/conf-lex.l"
+case 35:
+YY_RULE_SETUP
+#line 255 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: STRING
+  */
+
+/* Oops, newline or EOF while in a string is not good */
+case 36:
+/* rule 36 can match eol */
+#line 270 "lib/conf-lex.l"
+case 37:
+/* rule 37 can match eol */
+YY_RULE_SETUP
+#line 270 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case YY_STATE_EOF(STRING):
+#line 280 "lib/conf-lex.l"
+{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+	YY_BREAK
+/* At the end */
+case 38:
+YY_RULE_SETUP
+#line 290 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case 39:
+YY_RULE_SETUP
+#line 299 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+	YY_BREAK
+case 40:
+YY_RULE_SETUP
+#line 310 "lib/conf-lex.l"
+buffer_add_char("\a");
+	YY_BREAK
+case 41:
+YY_RULE_SETUP
+#line 311 "lib/conf-lex.l"
+buffer_add_char("\b");
+	YY_BREAK
+case 42:
+YY_RULE_SETUP
+#line 312 "lib/conf-lex.l"
+buffer_add_char("\f");
+	YY_BREAK
+case 43:
+YY_RULE_SETUP
+#line 313 "lib/conf-lex.l"
+buffer_add_char("\n");
+	YY_BREAK
+case 44:
+YY_RULE_SETUP
+#line 314 "lib/conf-lex.l"
+buffer_add_char("\r");
+	YY_BREAK
+case 45:
+YY_RULE_SETUP
+#line 315 "lib/conf-lex.l"
+buffer_add_char("\t");
+	YY_BREAK
+case 46:
+YY_RULE_SETUP
+#line 316 "lib/conf-lex.l"
+buffer_add_char("\v");
+	YY_BREAK
+/* Other escapes: just copy the character behind the slash */
+case 47:
+YY_RULE_SETUP
+#line 320 "lib/conf-lex.l"
+{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+	YY_BREAK
+/* Anything else (including a bare '\' which may be followed by EOF) */
+case 48:
+#line 327 "lib/conf-lex.l"
+case 49:
+YY_RULE_SETUP
+#line 327 "lib/conf-lex.l"
+{
+		  buffer_add_string(sensors_yytext);
+		}
+	YY_BREAK
+
+case 50:
+YY_RULE_SETUP
+#line 332 "lib/conf-lex.l"
+YY_FATAL_ERROR( "flex scanner jammed" );
+	YY_BREAK
+#line 1903 "<stdout>"
+			case YY_STATE_EOF(ERR):
+				yyterminate();
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed sensors_yyin at a new source and called
+			 * sensors_yylex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = sensors_yyin;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( sensors_yywrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * sensors_yytext, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of sensors_yylex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			int num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					sensors_yyrealloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), (size_t) num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			sensors_yyrestart(sensors_yyin  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+		/* Extend the array by 50%, plus the number we really need. */
+		yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+		YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) sensors_yyrealloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size  );
+		if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+	}
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		yy_current_state = yy_nxt[yy_current_state][(*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1)];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    
+	yy_current_state = yy_nxt[yy_current_state][1];
+	yy_is_jam = (yy_current_state <= 0);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					sensors_yyrestart(sensors_yyin );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( sensors_yywrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve sensors_yytext */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void sensors_yyrestart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        sensors_yyensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+	}
+
+	sensors_yy_init_buffer(YY_CURRENT_BUFFER,input_file );
+	sensors_yy_load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void sensors_yy_switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		sensors_yypop_buffer_state();
+	 *		sensors_yypush_buffer_state(new_buffer);
+     */
+	sensors_yyensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	sensors_yy_load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (sensors_yywrap()) processing, but the only time this flag
+	 * is looked at is after sensors_yywrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void sensors_yy_load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	sensors_yyin = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE sensors_yy_create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) sensors_yyalloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	sensors_yy_init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with sensors_yy_create_buffer()
+ * 
+ */
+    void sensors_yy_delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		sensors_yyfree((void *) b->yy_ch_buf  );
+
+	sensors_yyfree((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a sensors_yyrestart() or at EOF.
+ */
+    static void sensors_yy_init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	sensors_yy_flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then sensors_yy_init_buffer was _probably_
+     * called from sensors_yyrestart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void sensors_yy_flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		sensors_yy_load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	sensors_yyensure_buffer_stack();
+
+	/* This block is copied from sensors_yy_switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from sensors_yy_switch_to_buffer. */
+	sensors_yy_load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void sensors_yypop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	sensors_yy_delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		sensors_yy_load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void sensors_yyensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyalloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+								  
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyrealloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE sensors_yy_scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	sensors_yy_switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to sensors_yylex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       sensors_yy_scan_bytes() instead.
+ */
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char * yystr )
+{
+    
+	return sensors_yy_scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to sensors_yylex() will
+ * scan from a @e copy of @a bytes.
+ * @param yybytes the byte buffer to scan
+ * @param _yybytes_len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE sensors_yy_scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = _yybytes_len + 2;
+	buf = (char *) sensors_yyalloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_bytes()" );
+
+	for ( i = 0; i < _yybytes_len; ++i )
+		buf[i] = yybytes[i];
+
+	buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = sensors_yy_scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in sensors_yy_scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		sensors_yytext[sensors_yyleng] = (yy_hold_char); \
+		(yy_c_buf_p) = sensors_yytext + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		sensors_yyleng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int sensors_yyget_lineno  (void)
+{
+        
+    return sensors_yylineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *sensors_yyget_in  (void)
+{
+        return sensors_yyin;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *sensors_yyget_out  (void)
+{
+        return sensors_yyout;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int sensors_yyget_leng  (void)
+{
+        return sensors_yyleng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *sensors_yyget_text  (void)
+{
+        return sensors_yytext;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void sensors_yyset_lineno (int  line_number )
+{
+    
+    sensors_yylineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see sensors_yy_switch_to_buffer
+ */
+void sensors_yyset_in (FILE *  in_str )
+{
+        sensors_yyin = in_str ;
+}
+
+void sensors_yyset_out (FILE *  out_str )
+{
+        sensors_yyout = out_str ;
+}
+
+int sensors_yyget_debug  (void)
+{
+        return sensors_yy_flex_debug;
+}
+
+void sensors_yyset_debug (int  bdebug )
+{
+        sensors_yy_flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+        /* Initialization is the same as for the non-reentrant scanner.
+     * This function is called from sensors_yylex_destroy(), so don't allocate here.
+     */
+
+    (yy_buffer_stack) = 0;
+    (yy_buffer_stack_top) = 0;
+    (yy_buffer_stack_max) = 0;
+    (yy_c_buf_p) = (char *) 0;
+    (yy_init) = 0;
+    (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+    sensors_yyin = stdin;
+    sensors_yyout = stdout;
+#else
+    sensors_yyin = (FILE *) 0;
+    sensors_yyout = (FILE *) 0;
+#endif
+
+    /* For future reference: Set errno on error, since we are called by
+     * sensors_yylex_init()
+     */
+    return 0;
+}
+
+/* sensors_yylex_destroy is for both reentrant and non-reentrant scanners. */
+int sensors_yylex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		sensors_yy_delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		sensors_yypop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	sensors_yyfree((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    /* Reset the globals. This is important in a non-reentrant scanner so the next time
+     * sensors_yylex() is called, initialization will occur. */
+    yy_init_globals( );
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *sensors_yyalloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *sensors_yyrealloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void sensors_yyfree (void * ptr )
+{
+	free( (char *) ptr );	/* see sensors_yyrealloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 332 "lib/conf-lex.l"
+
+
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, sensors_yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
+
diff --git a/tools/gator/daemon/libsensors/conf-lex.l b/tools/gator/daemon/libsensors/conf-lex.l
new file mode 100644
index 000000000000..43ddbd8f5bd5
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.l
@@ -0,0 +1,372 @@
+%{
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+%}
+
+ /* Scanner for configuration files */
+
+%option nodefault
+%option noyywrap
+%option nounput
+
+ /* All states are exclusive */
+
+%x MIDDLE
+%x STRING
+%x ERR
+
+ /* Any whitespace-like character */
+
+BLANK		[ \f\r\t\v]
+
+IDCHAR		[[:alnum:]_]
+
+ /* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+
+FLOAT   [[:digit:]]*\.?[[:digit:]]+
+
+ /* Only positive whole numbers are recognized here */
+
+NUM	0|([1-9][[:digit:]]*)
+
+
+%%
+
+ /*
+  * STATE: INITIAL
+  */
+
+<INITIAL>{
+
+<<EOF>>		{ /* EOF from this state terminates */
+		  return 0;
+		}
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+{BLANK}*\n	{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+
+ /*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+
+label{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+
+set{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+
+compute{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+
+bus{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+
+chip{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+
+ignore{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+
+ /* Anything else at the beginning of a line is an error */
+
+[a-z]+		|
+.		{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: ERROR
+  */
+
+<ERR>{
+
+.*		; /* eat whatever is left on this line */
+
+\n		{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+}
+
+ /*
+  * STATE: MIDDLE
+  */
+
+<MIDDLE>{
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+\n		{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+<<EOF>>		{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+
+\\{BLANK}*\n	{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+ /* A number */
+
+{FLOAT}		{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+
+ /* Some operators */
+
+"+"		return '+';
+"-"		return '-';
+"*"		return '*';
+"/"		return '/';
+"("		return '(';
+")"		return ')';
+","		return ',';
+"@"		return '@';
+"^"		return '^';
+"`"		return '`';
+
+ /* Quoted string */
+
+\"		{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+
+ /* A normal, unquoted identifier */
+
+{IDCHAR}+	{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+
+ /* anything else is bogus */
+
+.		|
+[[:digit:]]*\.	|
+\\{BLANK}*	{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: STRING
+  */
+
+<STRING>{
+
+ /* Oops, newline or EOF while in a string is not good */
+
+\n		|
+\\\n		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+
+<<EOF>>		{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+
+ /* At the end */
+
+\"\"		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+		
+\"		{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+
+\\a		buffer_add_char("\a");
+\\b		buffer_add_char("\b");
+\\f		buffer_add_char("\f");
+\\n		buffer_add_char("\n");
+\\r		buffer_add_char("\r");
+\\t		buffer_add_char("\t");
+\\v		buffer_add_char("\v");
+
+ /* Other escapes: just copy the character behind the slash */
+
+\\.		{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+
+ /* Anything else (including a bare '\' which may be followed by EOF) */
+
+\\		|
+[^\\\n\"]+	{
+		  buffer_add_string(sensors_yytext);
+		}
+}
+
+%%
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.c b/tools/gator/daemon/libsensors/conf-parse.c
new file mode 100644
index 000000000000..fb775460a1c3
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.c
@@ -0,0 +1,2042 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison implementation for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+   simplifying the original so-called "semantic" parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Bison version.  */
+#define YYBISON_VERSION "2.5"
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Push parsers.  */
+#define YYPUSH 0
+
+/* Pull parsers.  */
+#define YYPULL 1
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names.  */
+#define yyparse         sensors_yyparse
+#define yylex           sensors_yylex
+#define yyerror         sensors_yyerror
+#define yylval          sensors_yylval
+#define yychar          sensors_yychar
+#define yydebug         sensors_yydebug
+#define yynerrs         sensors_yynerrs
+
+
+/* Copy the first part of user declarations.  */
+
+/* Line 268 of yacc.c  */
+#line 1 "lib/conf-parse.y"
+
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+
+
+/* Line 268 of yacc.c  */
+#line 158 "lib/conf-parse.c"
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table.  */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 293 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 293 of yacc.c  */
+#line 220 "lib/conf-parse.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 343 of yacc.c  */
+#line 232 "lib/conf-parse.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+#  define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+#  define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# else
+#  define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+#  if ENABLE_NLS
+#   include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+#   define YY_(msgid) dgettext ("bison-runtime", msgid)
+#  endif
+# endif
+# ifndef YY_
+#  define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E.  */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions.  */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+    int yyi;
+#endif
+{
+  return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   elif defined __BUILTIN_VA_ARG_INCR
+#    include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+#   elif defined _AIX
+#    define YYSTACK_ALLOC __alloca
+#   elif defined _MSC_VER
+#    include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+#    define alloca _alloca
+#   else
+#    define YYSTACK_ALLOC alloca
+#    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#     ifndef EXIT_SUCCESS
+#      define EXIT_SUCCESS 0
+#     endif
+#    endif
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+    /* The OS might guarantee only one guard page at the bottom of the stack,
+       and a page size can be as small as 4096 bytes.  So we cannot safely
+       invoke alloca (N) if N exceeds 4096.  Use a slightly smaller number
+       to allow for a few compiler-allocated temporary stack slots.  */
+#   define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+#  endif
+# else
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+#   define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+#  endif
+#  if (defined __cplusplus && ! defined EXIT_SUCCESS \
+       && ! ((defined YYMALLOC || defined malloc) \
+	     && (defined YYFREE || defined free)))
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   ifndef EXIT_SUCCESS
+#    define EXIT_SUCCESS 0
+#   endif
+#  endif
+#  ifndef YYMALLOC
+#   define YYMALLOC malloc
+#   if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+#  ifndef YYFREE
+#   define YYFREE free
+#   if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+     && (! defined __cplusplus \
+	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  yytype_int16 yyss_alloc;
+  YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+      + YYSTACK_GAP_MAXIMUM)
+
+# define YYCOPY_NEEDED 1
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
+	Stack = &yyptr->Stack_alloc;					\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (YYID (0))
+
+#endif
+
+#if defined YYCOPY_NEEDED && YYCOPY_NEEDED
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined __GNUC__ && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  YYSIZE_T yyi;				\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (YYID (0))
+#  endif
+# endif
+#endif /* !YYCOPY_NEEDED */
+
+/* YYFINAL -- State number of the termination state.  */
+#define YYFINAL  2
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   58
+
+/* YYNTOKENS -- Number of terminals.  */
+#define YYNTOKENS  24
+/* YYNNTS -- Number of nonterminals.  */
+#define YYNNTS  16
+/* YYNRULES -- Number of rules.  */
+#define YYNRULES  34
+/* YYNRULES -- Number of states.  */
+#define YYNSTATES  63
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   268
+
+#define YYTRANSLATE(YYX)						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const yytype_uint8 yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+      22,    23,     5,     4,    10,     3,     2,     6,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,    21,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     8,     2,     9,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     7,    11,
+      12,    13,    14,    15,    16,    17,    18,    19,    20
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const yytype_uint8 yyprhs[] =
+{
+       0,     0,     3,     4,     7,    10,    13,    16,    19,    22,
+      25,    28,    32,    36,    40,    46,    49,    52,    54,    57,
+      59,    61,    63,    67,    71,    75,    79,    82,    86,    89,
+      92,    94,    96,    98,   100
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
+static const yytype_int8 yyrhs[] =
+{
+      25,     0,    -1,    -1,    25,    26,    -1,    27,    11,    -1,
+      28,    11,    -1,    29,    11,    -1,    32,    11,    -1,    30,
+      11,    -1,    31,    11,    -1,     1,    11,    -1,    12,    35,
+      36,    -1,    13,    37,    38,    -1,    14,    37,    34,    -1,
+      16,    37,    34,    10,    34,    -1,    17,    37,    -1,    15,
+      33,    -1,    39,    -1,    33,    39,    -1,    18,    -1,    19,
+      -1,    21,    -1,    34,     4,    34,    -1,    34,     3,    34,
+      -1,    34,     5,    34,    -1,    34,     6,    34,    -1,     3,
+      34,    -1,    22,    34,    23,    -1,     8,    34,    -1,     9,
+      34,    -1,    19,    -1,    19,    -1,    19,    -1,    19,    -1,
+      19,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const yytype_uint16 yyrline[] =
+{
+       0,   119,   119,   120,   123,   124,   125,   126,   127,   128,
+     129,   132,   141,   156,   171,   188,   201,   219,   225,   231,
+     236,   241,   245,   252,   259,   266,   273,   280,   282,   289,
+     298,   308,   312,   316,   320
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals.  */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "'-'", "'+'", "'*'", "'/'", "NEG", "'^'",
+  "'`'", "','", "EOL", "BUS", "LABEL", "SET", "CHIP", "COMPUTE", "IGNORE",
+  "FLOAT", "NAME", "ERROR", "'@'", "'('", "')'", "$accept", "input",
+  "line", "bus_statement", "label_statement", "set_statement",
+  "compute_statement", "ignore_statement", "chip_statement",
+  "chip_name_list", "expression", "bus_id", "adapter_name",
+  "function_name", "string", "chip_name", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const yytype_uint16 yytoknum[] =
+{
+       0,   256,   257,    45,    43,    42,    47,   258,    94,    96,
+      44,   259,   260,   261,   262,   263,   264,   265,   266,   267,
+     268,    64,    40,    41
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    24,    25,    25,    26,    26,    26,    26,    26,    26,
+      26,    27,    28,    29,    30,    31,    32,    33,    33,    34,
+      34,    34,    34,    34,    34,    34,    34,    34,    34,    34,
+      35,    36,    37,    38,    39
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     0,     2,     2,     2,     2,     2,     2,     2,
+       2,     3,     3,     3,     5,     2,     2,     1,     2,     1,
+       1,     1,     3,     3,     3,     3,     2,     3,     2,     2,
+       1,     1,     1,     1,     1
+};
+
+/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
+   Performed when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       2,     0,     1,     0,     0,     0,     0,     0,     0,     0,
+       3,     0,     0,     0,     0,     0,     0,    10,    30,     0,
+      32,     0,     0,    34,    16,    17,     0,    15,     4,     5,
+       6,     8,     9,     7,    31,    11,    33,    12,     0,     0,
+       0,    19,    20,    21,     0,    13,    18,     0,    26,    28,
+      29,     0,     0,     0,     0,     0,     0,    27,    23,    22,
+      24,    25,    14
+};
+
+/* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int8 yydefgoto[] =
+{
+      -1,     1,    10,    11,    12,    13,    14,    15,    16,    24,
+      45,    19,    35,    21,    37,    25
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -27
+static const yytype_int8 yypact[] =
+{
+     -27,    37,   -27,    -4,    -3,     1,     1,     6,     1,     1,
+     -27,     8,    13,    20,    23,    32,    34,   -27,   -27,    29,
+     -27,    39,    14,   -27,     6,   -27,    14,   -27,   -27,   -27,
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,    14,    14,
+      14,   -27,   -27,   -27,    14,    36,   -27,     5,   -27,   -27,
+     -27,    -2,    14,    14,    14,    14,    14,   -27,     0,     0,
+     -27,   -27,    36
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,
+     -26,   -27,   -27,    38,   -27,    31
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+      47,    52,    53,    54,    55,    54,    55,    17,    52,    53,
+      54,    55,    48,    49,    50,    56,    18,    38,    51,    28,
+      20,    57,    39,    40,    29,    23,    58,    59,    60,    61,
+      62,    30,    41,    42,    31,    43,    44,     2,     3,    52,
+      53,    54,    55,    32,    22,    33,    26,    27,    34,     4,
+       5,     6,     7,     8,     9,    46,     0,     0,    36
+};
+
+#define yypact_value_is_default(yystate) \
+  ((yystate) == (-27))
+
+#define yytable_value_is_error(yytable_value) \
+  YYID (0)
+
+static const yytype_int8 yycheck[] =
+{
+      26,     3,     4,     5,     6,     5,     6,    11,     3,     4,
+       5,     6,    38,    39,    40,    10,    19,     3,    44,    11,
+      19,    23,     8,     9,    11,    19,    52,    53,    54,    55,
+      56,    11,    18,    19,    11,    21,    22,     0,     1,     3,
+       4,     5,     6,    11,     6,    11,     8,     9,    19,    12,
+      13,    14,    15,    16,    17,    24,    -1,    -1,    19
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const yytype_uint8 yystos[] =
+{
+       0,    25,     0,     1,    12,    13,    14,    15,    16,    17,
+      26,    27,    28,    29,    30,    31,    32,    11,    19,    35,
+      19,    37,    37,    19,    33,    39,    37,    37,    11,    11,
+      11,    11,    11,    11,    19,    36,    19,    38,     3,     8,
+       9,    18,    19,    21,    22,    34,    39,    34,    34,    34,
+      34,    34,     3,     4,     5,     6,    10,    23,    34,    34,
+      34,    34,    34
+};
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  However,
+   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
+   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+   discussed.  */
+
+#define YYFAIL		goto yyerrlab
+#if defined YYFAIL
+  /* This is here to suppress warnings from the GCC cpp's
+     -Wunused-macros.  Normally we don't worry about that warning, but
+     some users do, and we want to make it easy for users to remove
+     YYFAIL uses, which will produce warnings from Bison 2.5.  */
+#endif
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      YYPOPSTACK (1);						\
+      goto yybackup;						\
+    }								\
+  else								\
+    {								\
+      yyerror (YY_("syntax error: cannot back up")); \
+      YYERROR;							\
+    }								\
+while (YYID (0))
+
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)				\
+    do									\
+      if (YYID (N))                                                    \
+	{								\
+	  (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;	\
+	  (Current).first_column = YYRHSLOC (Rhs, 1).first_column;	\
+	  (Current).last_line    = YYRHSLOC (Rhs, N).last_line;		\
+	  (Current).last_column  = YYRHSLOC (Rhs, N).last_column;	\
+	}								\
+      else								\
+	{								\
+	  (Current).first_line   = (Current).last_line   =		\
+	    YYRHSLOC (Rhs, 0).last_line;				\
+	  (Current).first_column = (Current).last_column =		\
+	    YYRHSLOC (Rhs, 0).last_column;				\
+	}								\
+    while (YYID (0))
+#endif
+
+
+/* This macro is provided for backward compatibility. */
+
+#ifndef YY_LOCATION_PRINT
+# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
+do {									  \
+  if (yydebug)								  \
+    {									  \
+      YYFPRINTF (stderr, "%s ", Title);					  \
+      yy_symbol_print (stderr,						  \
+		  Type, Value); \
+      YYFPRINTF (stderr, "\n");						  \
+    }									  \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (!yyvaluep)
+    return;
+# ifdef YYPRINT
+  if (yytype < YYNTOKENS)
+    YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+  YYUSE (yyoutput);
+# endif
+  switch (yytype)
+    {
+      default:
+	break;
+    }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (yytype < YYNTOKENS)
+    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep);
+  YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+    yytype_int16 *yybottom;
+    yytype_int16 *yytop;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (; yybottom <= yytop; yybottom++)
+    {
+      int yybot = *yybottom;
+      YYFPRINTF (stderr, " %d", yybot);
+    }
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule)
+    YYSTYPE *yyvsp;
+    int yyrule;
+#endif
+{
+  int yynrhs = yyr2[yyrule];
+  int yyi;
+  unsigned long int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+	     yyrule - 1, yylno);
+  /* The symbols being reduced.  */
+  for (yyi = 0; yyi < yynrhs; yyi++)
+    {
+      YYFPRINTF (stderr, "   $%d = ", yyi + 1);
+      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+		       &(yyvsp[(yyi + 1) - (yynrhs)])
+		       		       );
+      YYFPRINTF (stderr, "\n");
+    }
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (yyvsp, Rule); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined __GLIBC__ && defined _STRING_H
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+    const char *yystr;
+#endif
+{
+  YYSIZE_T yylen;
+  for (yylen = 0; yystr[yylen]; yylen++)
+    continue;
+  return yylen;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+    char *yydest;
+    const char *yysrc;
+#endif
+{
+  char *yyd = yydest;
+  const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+   quotes and backslashes, so that it's suitable for yyerror.  The
+   heuristic is that double-quoting is unnecessary unless the string
+   contains an apostrophe, a comma, or backslash (other than
+   backslash-backslash).  YYSTR is taken from yytname.  If YYRES is
+   null, do not copy; instead, return the length of what the result
+   would have been.  */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+  if (*yystr == '"')
+    {
+      YYSIZE_T yyn = 0;
+      char const *yyp = yystr;
+
+      for (;;)
+	switch (*++yyp)
+	  {
+	  case '\'':
+	  case ',':
+	    goto do_not_strip_quotes;
+
+	  case '\\':
+	    if (*++yyp != '\\')
+	      goto do_not_strip_quotes;
+	    /* Fall through.  */
+	  default:
+	    if (yyres)
+	      yyres[yyn] = *yyp;
+	    yyn++;
+	    break;
+
+	  case '"':
+	    if (yyres)
+	      yyres[yyn] = '\0';
+	    return yyn;
+	  }
+    do_not_strip_quotes: ;
+    }
+
+  if (! yyres)
+    return yystrlen (yystr);
+
+  return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message
+   about the unexpected token YYTOKEN for the state stack whose top is
+   YYSSP.
+
+   Return 0 if *YYMSG was successfully written.  Return 1 if *YYMSG is
+   not large enough to hold the message.  In that case, also set
+   *YYMSG_ALLOC to the required number of bytes.  Return 2 if the
+   required number of bytes is too large to store.  */
+static int
+yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
+                yytype_int16 *yyssp, int yytoken)
+{
+  YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+  YYSIZE_T yysize = yysize0;
+  YYSIZE_T yysize1;
+  enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+  /* Internationalized format string. */
+  const char *yyformat = 0;
+  /* Arguments of yyformat. */
+  char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+  /* Number of reported tokens (one for the "unexpected", one per
+     "expected"). */
+  int yycount = 0;
+
+  /* There are many possibilities here to consider:
+     - Assume YYFAIL is not used.  It's too flawed to consider.  See
+       <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
+       for details.  YYERROR is fine as it does not invoke this
+       function.
+     - If this state is a consistent state with a default action, then
+       the only way this function was invoked is if the default action
+       is an error action.  In that case, don't check for expected
+       tokens because there are none.
+     - The only way there can be no lookahead present (in yychar) is if
+       this state is a consistent state with a default action.  Thus,
+       detecting the absence of a lookahead is sufficient to determine
+       that there is no unexpected or expected token to report.  In that
+       case, just report a simple "syntax error".
+     - Don't assume there isn't a lookahead just because this state is a
+       consistent state with a default action.  There might have been a
+       previous inconsistent state, consistent state with a non-default
+       action, or user semantic action that manipulated yychar.
+     - Of course, the expected token list depends on states to have
+       correct lookahead information, and it depends on the parser not
+       to perform extra reductions after fetching a lookahead from the
+       scanner and before detecting a syntax error.  Thus, state merging
+       (from LALR or IELR) and default reductions corrupt the expected
+       token list.  However, the list is correct for canonical LR with
+       one exception: it will still contain any token that will not be
+       accepted due to an error action in a later state.
+  */
+  if (yytoken != YYEMPTY)
+    {
+      int yyn = yypact[*yyssp];
+      yyarg[yycount++] = yytname[yytoken];
+      if (!yypact_value_is_default (yyn))
+        {
+          /* Start YYX at -YYN if negative to avoid negative indexes in
+             YYCHECK.  In other words, skip the first -YYN actions for
+             this state because they are default actions.  */
+          int yyxbegin = yyn < 0 ? -yyn : 0;
+          /* Stay within bounds of both yycheck and yytname.  */
+          int yychecklim = YYLAST - yyn + 1;
+          int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+          int yyx;
+
+          for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+            if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR
+                && !yytable_value_is_error (yytable[yyx + yyn]))
+              {
+                if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+                  {
+                    yycount = 1;
+                    yysize = yysize0;
+                    break;
+                  }
+                yyarg[yycount++] = yytname[yyx];
+                yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+                if (! (yysize <= yysize1
+                       && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+                  return 2;
+                yysize = yysize1;
+              }
+        }
+    }
+
+  switch (yycount)
+    {
+# define YYCASE_(N, S)                      \
+      case N:                               \
+        yyformat = S;                       \
+      break
+      YYCASE_(0, YY_("syntax error"));
+      YYCASE_(1, YY_("syntax error, unexpected %s"));
+      YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s"));
+      YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s"));
+      YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s"));
+      YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s"));
+# undef YYCASE_
+    }
+
+  yysize1 = yysize + yystrlen (yyformat);
+  if (! (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+    return 2;
+  yysize = yysize1;
+
+  if (*yymsg_alloc < yysize)
+    {
+      *yymsg_alloc = 2 * yysize;
+      if (! (yysize <= *yymsg_alloc
+             && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM))
+        *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM;
+      return 1;
+    }
+
+  /* Avoid sprintf, as that infringes on the user's name space.
+     Don't have undefined behavior even if the translation
+     produced a string with the wrong number of "%s"s.  */
+  {
+    char *yyp = *yymsg;
+    int yyi = 0;
+    while ((*yyp = *yyformat) != '\0')
+      if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount)
+        {
+          yyp += yytnamerr (yyp, yyarg[yyi++]);
+          yyformat += 2;
+        }
+      else
+        {
+          yyp++;
+          yyformat++;
+        }
+  }
+  return 0;
+}
+#endif /* YYERROR_VERBOSE */
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep)
+    const char *yymsg;
+    int yytype;
+    YYSTYPE *yyvaluep;
+#endif
+{
+  YYUSE (yyvaluep);
+
+  if (!yymsg)
+    yymsg = "Deleting";
+  YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+  switch (yytype)
+    {
+
+      default:
+	break;
+    }
+}
+
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+/*----------.
+| yyparse.  |
+`----------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+    void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void)
+#else
+int
+yyparse ()
+
+#endif
+#endif
+{
+    int yystate;
+    /* Number of tokens to shift before error messages enabled.  */
+    int yyerrstatus;
+
+    /* The stacks and their tools:
+       `yyss': related to states.
+       `yyvs': related to semantic values.
+
+       Refer to the stacks thru separate pointers, to allow yyoverflow
+       to reallocate them elsewhere.  */
+
+    /* The state stack.  */
+    yytype_int16 yyssa[YYINITDEPTH];
+    yytype_int16 *yyss;
+    yytype_int16 *yyssp;
+
+    /* The semantic value stack.  */
+    YYSTYPE yyvsa[YYINITDEPTH];
+    YYSTYPE *yyvs;
+    YYSTYPE *yyvsp;
+
+    YYSIZE_T yystacksize;
+
+  int yyn;
+  int yyresult;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken;
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+  /* Buffer for error messages, and its allocated size.  */
+  char yymsgbuf[128];
+  char *yymsg = yymsgbuf;
+  YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+
+  /* The number of symbols on the RHS of the reduced rule.
+     Keep to zero when no symbol should be popped.  */
+  int yylen = 0;
+
+  yytoken = 0;
+  yyss = yyssa;
+  yyvs = yyvsa;
+  yystacksize = YYINITDEPTH;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY; /* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed.  So pushing a state here evens the stacks.  */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack.  Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	yytype_int16 *yyss1 = yyss;
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow (YY_("memory exhausted"),
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyexhaustedlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyexhaustedlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	yytype_int16 *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyexhaustedlab;
+	YYSTACK_RELOCATE (yyss_alloc, yyss);
+	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  if (yystate == YYFINAL)
+    YYACCEPT;
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+  /* Do appropriate processing given the current state.  Read a
+     lookahead token if we need one and don't already have one.  */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+  yyn = yypact[yystate];
+  if (yypact_value_is_default (yyn))
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yytable_value_is_error (yyn))
+        goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  /* Shift the lookahead token.  */
+  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;
+
+  yystate = yyn;
+  *++yyvsp = yylval;
+
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 11:
+
+/* Line 1806 of yacc.c  */
+#line 133 "lib/conf-parse.y"
+    { sensors_bus new_el;
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.bus = (yyvsp[(2) - (3)].bus);
+                    new_el.adapter = (yyvsp[(3) - (3)].name);
+		    bus_add_el(&new_el);
+		  }
+    break;
+
+  case 12:
+
+/* Line 1806 of yacc.c  */
+#line 142 "lib/conf-parse.y"
+    { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free((yyvsp[(2) - (3)].name));
+			      free((yyvsp[(3) - (3)].name));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (3)].line);
+			    new_el.name = (yyvsp[(2) - (3)].name);
+			    new_el.value = (yyvsp[(3) - (3)].name);
+			    label_add_el(&new_el);
+			  }
+    break;
+
+  case 13:
+
+/* Line 1806 of yacc.c  */
+#line 157 "lib/conf-parse.y"
+    { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free((yyvsp[(2) - (3)].name));
+		      sensors_free_expr((yyvsp[(3) - (3)].expr));
+		      YYERROR;
+		    }
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.name = (yyvsp[(2) - (3)].name);
+		    new_el.value = (yyvsp[(3) - (3)].expr);
+		    set_add_el(&new_el);
+		  }
+    break;
+
+  case 14:
+
+/* Line 1806 of yacc.c  */
+#line 172 "lib/conf-parse.y"
+    { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free((yyvsp[(2) - (5)].name));
+			      sensors_free_expr((yyvsp[(3) - (5)].expr));
+			      sensors_free_expr((yyvsp[(5) - (5)].expr));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (5)].line);
+			    new_el.name = (yyvsp[(2) - (5)].name);
+			    new_el.from_proc = (yyvsp[(3) - (5)].expr);
+			    new_el.to_proc = (yyvsp[(5) - (5)].expr);
+			    compute_add_el(&new_el);
+			  }
+    break;
+
+  case 15:
+
+/* Line 1806 of yacc.c  */
+#line 189 "lib/conf-parse.y"
+    { sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free((yyvsp[(2) - (2)].name));
+			    YYERROR;
+			  }
+			  new_el.line = (yyvsp[(1) - (2)].line);
+			  new_el.name = (yyvsp[(2) - (2)].name);
+			  ignore_add_el(&new_el);
+			}
+    break;
+
+  case 16:
+
+/* Line 1806 of yacc.c  */
+#line 202 "lib/conf-parse.y"
+    { sensors_chip new_el;
+		    new_el.line = (yyvsp[(1) - (2)].line);
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = (yyvsp[(2) - (2)].chips);
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+    break;
+
+  case 17:
+
+/* Line 1806 of yacc.c  */
+#line 220 "lib/conf-parse.y"
+    { 
+		    (yyval.chips).fits = NULL;
+		    (yyval.chips).fits_count = (yyval.chips).fits_max = 0;
+		    fits_add_el(&(yyvsp[(1) - (1)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 18:
+
+/* Line 1806 of yacc.c  */
+#line 226 "lib/conf-parse.y"
+    { (yyval.chips) = (yyvsp[(1) - (2)].chips);
+		    fits_add_el(&(yyvsp[(2) - (2)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 19:
+
+/* Line 1806 of yacc.c  */
+#line 232 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.val = (yyvsp[(1) - (1)].value); 
+		    (yyval.expr)->kind = sensors_kind_val;
+		  }
+    break;
+
+  case 20:
+
+/* Line 1806 of yacc.c  */
+#line 237 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.var = (yyvsp[(1) - (1)].name);
+		    (yyval.expr)->kind = sensors_kind_var;
+		  }
+    break;
+
+  case 21:
+
+/* Line 1806 of yacc.c  */
+#line 242 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr();
+		    (yyval.expr)->kind = sensors_kind_source;
+		  }
+    break;
+
+  case 22:
+
+/* Line 1806 of yacc.c  */
+#line 246 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_add;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 23:
+
+/* Line 1806 of yacc.c  */
+#line 253 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_sub;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 24:
+
+/* Line 1806 of yacc.c  */
+#line 260 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_multiply;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 25:
+
+/* Line 1806 of yacc.c  */
+#line 267 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_divide;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 26:
+
+/* Line 1806 of yacc.c  */
+#line 274 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_negate;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 27:
+
+/* Line 1806 of yacc.c  */
+#line 281 "lib/conf-parse.y"
+    { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
+    break;
+
+  case 28:
+
+/* Line 1806 of yacc.c  */
+#line 283 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_exp;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 29:
+
+/* Line 1806 of yacc.c  */
+#line 290 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_log;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 30:
+
+/* Line 1806 of yacc.c  */
+#line 299 "lib/conf-parse.y"
+    { int res = sensors_parse_bus_id((yyvsp[(1) - (1)].name),&(yyval.bus));
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+    break;
+
+  case 31:
+
+/* Line 1806 of yacc.c  */
+#line 309 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 32:
+
+/* Line 1806 of yacc.c  */
+#line 313 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 33:
+
+/* Line 1806 of yacc.c  */
+#line 317 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 34:
+
+/* Line 1806 of yacc.c  */
+#line 321 "lib/conf-parse.y"
+    { int res = sensors_parse_chip_name((yyvsp[(1) - (1)].name),&(yyval.chip)); 
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+    break;
+
+
+
+/* Line 1806 of yacc.c  */
+#line 1793 "lib/conf-parse.c"
+      default: break;
+    }
+  /* User semantic actions sometimes alter yychar, and that requires
+     that yytoken be updated with the new translation.  We take the
+     approach of translating immediately before every use of yytoken.
+     One alternative is translating here after every semantic action,
+     but that translation would be missed if the semantic action invokes
+     YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or
+     if it invokes YYBACKUP.  In the case of YYABORT or YYACCEPT, an
+     incorrect destructor might then be invoked immediately.  In the
+     case of YYERROR or YYBACKUP, subsequent parser actions might lead
+     to an incorrect destructor call or verbose syntax error message
+     before the lookahead is translated.  */
+  YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* Make sure we have latest lookahead translation.  See comments at
+     user semantic actions for why this is necessary.  */
+  yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar);
+
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if ! YYERROR_VERBOSE
+      yyerror (YY_("syntax error"));
+#else
+# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \
+                                        yyssp, yytoken)
+      {
+        char const *yymsgp = YY_("syntax error");
+        int yysyntax_error_status;
+        yysyntax_error_status = YYSYNTAX_ERROR;
+        if (yysyntax_error_status == 0)
+          yymsgp = yymsg;
+        else if (yysyntax_error_status == 1)
+          {
+            if (yymsg != yymsgbuf)
+              YYSTACK_FREE (yymsg);
+            yymsg = (char *) YYSTACK_ALLOC (yymsg_alloc);
+            if (!yymsg)
+              {
+                yymsg = yymsgbuf;
+                yymsg_alloc = sizeof yymsgbuf;
+                yysyntax_error_status = 2;
+              }
+            else
+              {
+                yysyntax_error_status = YYSYNTAX_ERROR;
+                yymsgp = yymsg;
+              }
+          }
+        yyerror (yymsgp);
+        if (yysyntax_error_status == 2)
+          goto yyexhaustedlab;
+      }
+# undef YYSYNTAX_ERROR
+#endif
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+	{
+	  /* Return failure if at end of input.  */
+	  if (yychar == YYEOF)
+	    YYABORT;
+	}
+      else
+	{
+	  yydestruct ("Error: discarding",
+		      yytoken, &yylval);
+	  yychar = YYEMPTY;
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+  /* Pacify compilers like GCC when the user code never invokes
+     YYERROR and the label yyerrorlab therefore never appears in user
+     code.  */
+  if (/*CONSTCOND*/ 0)
+     goto yyerrorlab;
+
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYERROR.  */
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (!yypact_value_is_default (yyn))
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+
+      yydestruct ("Error: popping",
+		  yystos[yystate], yyvsp);
+      YYPOPSTACK (1);
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  *++yyvsp = yylval;
+
+
+  /* Shift the error token.  */
+  YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here.  |
+`-------------------------------------------------*/
+yyexhaustedlab:
+  yyerror (YY_("memory exhausted"));
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+  if (yychar != YYEMPTY)
+    {
+      /* Make sure we have latest lookahead translation.  See comments at
+         user semantic actions for why this is necessary.  */
+      yytoken = YYTRANSLATE (yychar);
+      yydestruct ("Cleanup: discarding lookahead",
+                  yytoken, &yylval);
+    }
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYABORT or YYACCEPT.  */
+  YYPOPSTACK (yylen);
+  YY_STACK_PRINT (yyss, yyssp);
+  while (yyssp != yyss)
+    {
+      yydestruct ("Cleanup: popping",
+		  yystos[*yyssp], yyvsp);
+      YYPOPSTACK (1);
+    }
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+  if (yymsg != yymsgbuf)
+    YYSTACK_FREE (yymsg);
+#endif
+  /* Make sure YYID is used.  */
+  return YYID (yyresult);
+}
+
+
+
+/* Line 2067 of yacc.c  */
+#line 330 "lib/conf-parse.y"
+
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.h b/tools/gator/daemon/libsensors/conf-parse.h
new file mode 100644
index 000000000000..89c9c1a0d59f
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.h
@@ -0,0 +1,84 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison interface for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 2068 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 2068 of yacc.c  */
+#line 76 "lib/conf-parse.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE sensors_yylval;
+
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.y b/tools/gator/daemon/libsensors/conf-parse.y
new file mode 100644
index 000000000000..1937f544dc66
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.y
@@ -0,0 +1,347 @@
+%{
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+%}
+
+%union {
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+}  
+
+%left <nothing> '-' '+'
+%left <nothing> '*' '/'
+%left <nothing> NEG
+%right <nothing> '^' '`'
+
+%token <nothing> ','
+%token <nothing> EOL
+%token <line> BUS
+%token <line> LABEL
+%token <line> SET
+%token <line> CHIP
+%token <line> COMPUTE
+%token <line> IGNORE
+%token <value> FLOAT
+%token <name> NAME
+%token <nothing> ERROR
+
+%type <chips> chip_name_list
+%type <expr> expression
+%type <bus> bus_id
+%type <name> adapter_name
+%type <name> function_name
+%type <name> string
+%type <chip> chip_name
+
+%start input
+
+%%
+
+input:	  /* empty */
+	| input line
+;
+
+line:	  bus_statement EOL
+	| label_statement EOL
+	| set_statement EOL
+	| chip_statement EOL
+	| compute_statement EOL
+	| ignore_statement EOL
+	| error	EOL
+;
+
+bus_statement:	  BUS bus_id adapter_name
+		  { sensors_bus new_el;
+		    new_el.line = $1;
+		    new_el.bus = $2;
+                    new_el.adapter = $3;
+		    bus_add_el(&new_el);
+		  }
+;
+
+label_statement:	  LABEL function_name string
+			  { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free($2);
+			      free($3);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.value = $3;
+			    label_add_el(&new_el);
+			  }
+;
+
+set_statement:	  SET function_name expression
+		  { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free($2);
+		      sensors_free_expr($3);
+		      YYERROR;
+		    }
+		    new_el.line = $1;
+		    new_el.name = $2;
+		    new_el.value = $3;
+		    set_add_el(&new_el);
+		  }
+;
+
+compute_statement:	  COMPUTE function_name expression ',' expression
+			  { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free($2);
+			      sensors_free_expr($3);
+			      sensors_free_expr($5);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.from_proc = $3;
+			    new_el.to_proc = $5;
+			    compute_add_el(&new_el);
+			  }
+;
+
+ignore_statement:	IGNORE function_name
+			{ sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free($2);
+			    YYERROR;
+			  }
+			  new_el.line = $1;
+			  new_el.name = $2;
+			  ignore_add_el(&new_el);
+			}
+;
+
+chip_statement:	  CHIP chip_name_list
+		  { sensors_chip new_el;
+		    new_el.line = $1;
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = $2;
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+;
+
+chip_name_list:	  chip_name
+		  { 
+		    $$.fits = NULL;
+		    $$.fits_count = $$.fits_max = 0;
+		    fits_add_el(&$1,$$);
+		  }
+		| chip_name_list chip_name
+		  { $$ = $1;
+		    fits_add_el(&$2,$$);
+		  }
+;
+	
+expression:	  FLOAT	
+		  { $$ = malloc_expr(); 
+		    $$->data.val = $1; 
+		    $$->kind = sensors_kind_val;
+		  }
+		| NAME
+		  { $$ = malloc_expr(); 
+		    $$->data.var = $1;
+		    $$->kind = sensors_kind_var;
+		  }
+		| '@'
+		  { $$ = malloc_expr();
+		    $$->kind = sensors_kind_source;
+		  }
+		| expression '+' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_add;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '-' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_sub;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '*' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_multiply;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '/' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_divide;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| '-' expression  %prec NEG
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_negate;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '(' expression ')'
+		  { $$ = $2; }
+		| '^' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_exp;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '`' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_log;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+;
+
+bus_id:		  NAME
+		  { int res = sensors_parse_bus_id($1,&$$);
+		    free($1);
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+;
+
+adapter_name:	  NAME
+		  { $$ = $1; }
+;
+
+function_name:	  NAME
+		  { $$ = $1; }
+;
+
+string:	  NAME
+	  { $$ = $1; }
+;
+
+chip_name:	  NAME
+		  { int res = sensors_parse_chip_name($1,&$$); 
+		    free($1);
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+;
+
+%%
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
diff --git a/tools/gator/daemon/libsensors/conf.h b/tools/gator/daemon/libsensors/conf.h
new file mode 100644
index 000000000000..b7ce4f7ca833
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf.h
@@ -0,0 +1,34 @@
+/*
+    conf.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_CONF_H
+#define LIB_SENSORS_CONF_H
+
+/* This is defined in conf-lex.l */
+int sensors_yylex(void);
+extern char sensors_lex_error[];
+extern const char *sensors_yyfilename;
+extern int sensors_yylineno;
+extern FILE *sensors_yyin;
+
+/* This is defined in conf-parse.y */
+int sensors_yyparse(void);
+
+#endif /* LIB_SENSORS_CONF_H */
diff --git a/tools/gator/daemon/libsensors/data.c b/tools/gator/daemon/libsensors/data.c
new file mode 100644
index 000000000000..cac9c8dc6eb1
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.c
@@ -0,0 +1,278 @@
+/*
+    data.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to move version.h to the current directory. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "access.h"
+#include "error.h"
+#include "data.h"
+#include "sensors.h"
+#include "version.h"
+
+const char *libsensors_version = LM_VERSION;
+
+char **sensors_config_files = NULL;
+int sensors_config_files_count = 0;
+int sensors_config_files_max = 0;
+
+sensors_chip *sensors_config_chips = NULL;
+int sensors_config_chips_count = 0;
+int sensors_config_chips_subst = 0;
+int sensors_config_chips_max = 0;
+
+sensors_bus *sensors_config_busses = NULL;
+int sensors_config_busses_count = 0;
+int sensors_config_busses_max = 0;
+
+sensors_chip_features *sensors_proc_chips = NULL;
+int sensors_proc_chips_count = 0;
+int sensors_proc_chips_max = 0;
+
+sensors_bus *sensors_proc_bus = NULL;
+int sensors_proc_bus_count = 0;
+int sensors_proc_bus_max = 0;
+
+void sensors_free_chip_name(sensors_chip_name *chip)
+{
+	free(chip->prefix);
+}
+
+/*
+   Parse a chip name to the internal representation. These are valid names:
+
+     lm78-i2c-10-5e		*-i2c-10-5e
+     lm78-i2c-10-*		*-i2c-10-*
+     lm78-i2c-*-5e		*-i2c-*-5e
+     lm78-i2c-*-*		*-i2c-*-*
+     lm78-isa-10dd		*-isa-10dd
+     lm78-isa-*			*-isa-*
+     lm78-*			*-*
+
+   Here 'lm78' can be any prefix. 'i2c' and 'isa' are
+   literal strings, just like all dashes '-' and wildcards '*'. '10' can
+   be any decimal i2c bus number. '5e' can be any hexadecimal i2c device
+   address, and '10dd' any hexadecimal isa address.
+
+   The 'prefix' part in the result is freshly allocated. All old contents
+   of res is overwritten. res itself is not allocated. In case of an error
+   return (ie. != 0), res is undefined, but all allocations are undone.
+*/
+
+int sensors_parse_chip_name(const char *name, sensors_chip_name *res)
+{
+	char *dash;
+
+	/* First, the prefix. It's either "*" or a real chip name. */
+	if (!strncmp(name, "*-", 2)) {
+		res->prefix = SENSORS_CHIP_NAME_PREFIX_ANY;
+		name += 2;
+	} else {
+		if (!(dash = strchr(name, '-')))
+			return -SENSORS_ERR_CHIP_NAME;
+		res->prefix = strndup(name, dash - name);
+		if (!res->prefix)
+			sensors_fatal_error(__func__,
+					    "Allocating name prefix");
+		name = dash + 1;
+	}
+
+	/* Then we have either a sole "*" (all chips with this name) or a bus
+	   type and an address. */
+	if (!strcmp(name, "*")) {
+		res->bus.type = SENSORS_BUS_TYPE_ANY;
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+		return 0;
+	}
+
+	if (!(dash = strchr(name, '-')))
+		goto ERROR;
+	if (!strncmp(name, "i2c", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_I2C;
+	else if (!strncmp(name, "isa", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ISA;
+	else if (!strncmp(name, "pci", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_PCI;
+	else if (!strncmp(name, "spi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_SPI;
+	else if (!strncmp(name, "virtual", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+	else if (!strncmp(name, "acpi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ACPI;
+	else if (!strncmp(name, "hid", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_HID;
+	else
+		goto ERROR;
+	name = dash + 1;
+
+	/* Some bus types (i2c, spi) have an additional bus number.
+	   For these, the next part is either a "*" (any bus of that type)
+	   or a decimal number. */
+	switch (res->bus.type) {
+	case SENSORS_BUS_TYPE_I2C:
+	case SENSORS_BUS_TYPE_SPI:
+	case SENSORS_BUS_TYPE_HID:
+		if (!strncmp(name, "*-", 2)) {
+			res->bus.nr = SENSORS_BUS_NR_ANY;
+			name += 2;
+			break;
+		}
+
+		res->bus.nr = strtoul(name, &dash, 10);
+		if (*name == '\0' || *dash != '-' || res->bus.nr < 0)
+			goto ERROR;
+		name = dash + 1;
+		break;
+	default:
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+	}
+
+	/* Last part is the chip address, or "*" for any address. */
+	if (!strcmp(name, "*")) {
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+	} else {
+		res->addr = strtoul(name, &dash, 16);
+		if (*name == '\0' || *dash != '\0' || res->addr < 0)
+			goto ERROR;
+	}
+
+	return 0;
+
+ERROR:
+	free(res->prefix);
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip)
+{
+	if (sensors_chip_name_has_wildcards(chip))
+		return -SENSORS_ERR_WILDCARDS;
+
+	switch (chip->bus.type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return snprintf(str, size, "%s-isa-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_PCI:
+		return snprintf(str, size, "%s-pci-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_I2C:
+		return snprintf(str, size, "%s-i2c-%hd-%02x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_SPI:
+		return snprintf(str, size, "%s-spi-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return snprintf(str, size, "%s-virtual-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_ACPI:
+		return snprintf(str, size, "%s-acpi-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_HID:
+		return snprintf(str, size, "%s-hid-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	}
+
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus)
+{
+	char *endptr;
+
+	if (strncmp(name, "i2c-", 4)) {
+		return -SENSORS_ERR_BUS_NAME;
+	}
+	name += 4;
+	bus->type = SENSORS_BUS_TYPE_I2C;
+	bus->nr = strtoul(name, &endptr, 10);
+	if (*name == '\0' || *endptr != '\0' || bus->nr < 0)
+		return -SENSORS_ERR_BUS_NAME;
+	return 0;
+}
+
+static int sensors_substitute_chip(sensors_chip_name *name,
+				   const char *filename, int lineno)
+{
+	int i, j;
+	for (i = 0; i < sensors_config_busses_count; i++)
+		if (sensors_config_busses[i].bus.type == name->bus.type &&
+		    sensors_config_busses[i].bus.nr == name->bus.nr)
+			break;
+
+	if (i == sensors_config_busses_count) {
+		sensors_parse_error_wfn("Undeclared bus id referenced",
+					filename, lineno);
+		name->bus.nr = SENSORS_BUS_NR_IGNORE;
+		return -SENSORS_ERR_BUS_NAME;
+	}
+
+	/* Compare the adapter names */
+	for (j = 0; j < sensors_proc_bus_count; j++) {
+		if (!strcmp(sensors_config_busses[i].adapter,
+			    sensors_proc_bus[j].adapter)) {
+			name->bus.nr = sensors_proc_bus[j].bus.nr;
+			return 0;
+		}
+	}
+
+	/* We did not find a matching bus name, simply ignore this chip
+	   config entry. */
+	name->bus.nr = SENSORS_BUS_NR_IGNORE;
+	return 0;
+}
+
+/* Bus substitution is on a per-configuration file basis, so we keep
+   memory (in sensors_config_chips_subst) of which chip entries have been
+   already substituted. */
+int sensors_substitute_busses(void)
+{
+	int err, i, j, lineno;
+	sensors_chip_name_list *chips;
+	const char *filename;
+	int res = 0;
+
+	for (i = sensors_config_chips_subst;
+	     i < sensors_config_chips_count; i++) {
+		filename = sensors_config_chips[i].line.filename;
+		lineno = sensors_config_chips[i].line.lineno;
+		chips = &sensors_config_chips[i].chips;
+		for (j = 0; j < chips->fits_count; j++) {
+			/* We can only substitute if a specific bus number
+			   is given. */
+			if (chips->fits[j].bus.nr == SENSORS_BUS_NR_ANY)
+				continue;
+
+			err = sensors_substitute_chip(&chips->fits[j],
+						      filename, lineno);
+			if (err)
+				res = err;
+		}
+	}
+	sensors_config_chips_subst = sensors_config_chips_count;
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/data.h b/tools/gator/daemon/libsensors/data.h
new file mode 100644
index 000000000000..4a23eabe1414
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.h
@@ -0,0 +1,184 @@
+/*
+    data.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_DATA_H
+#define LIB_SENSORS_DATA_H
+
+#include "sensors.h"
+#include "general.h"
+
+/* This header file contains all kinds of data structures which are used
+   for the representation of the config file data and the sensors
+   data. */
+
+/* Kinds of expression operators recognized */
+typedef enum sensors_operation {
+	sensors_add, sensors_sub, sensors_multiply, sensors_divide,
+	sensors_negate, sensors_exp, sensors_log,
+} sensors_operation;
+
+/* An expression can have several forms */
+typedef enum sensors_expr_kind {
+	sensors_kind_val, sensors_kind_source, sensors_kind_var,
+	sensors_kind_sub
+} sensors_expr_kind;
+
+/* An expression. It is either a floating point value, a variable name,
+   an operation on subexpressions, or the special value 'sub' } */
+struct sensors_expr;
+
+typedef struct sensors_subexpr {
+	sensors_operation op;
+	struct sensors_expr *sub1;
+	struct sensors_expr *sub2;
+} sensors_subexpr;
+
+typedef struct sensors_expr {
+	sensors_expr_kind kind;
+	union {
+		double val;
+		char *var;
+		sensors_subexpr subexpr;
+	} data;
+} sensors_expr;
+
+/* Config file line reference */
+typedef struct sensors_config_line {
+	const char *filename;
+	int lineno;
+} sensors_config_line;
+
+/* Config file label declaration: a feature name, combined with the label
+   value */
+typedef struct sensors_label {
+	char *name;
+	char *value;
+	sensors_config_line line;
+} sensors_label;
+
+/* Config file set declaration: a subfeature name, combined with an
+   expression */
+typedef struct sensors_set {
+	char *name;
+	sensors_expr *value;
+	sensors_config_line line;
+} sensors_set;
+
+/* Config file compute declaration: a feature name, combined with two
+   expressions */
+typedef struct sensors_compute {
+	char *name;
+	sensors_expr *from_proc;
+	sensors_expr *to_proc;
+	sensors_config_line line;
+} sensors_compute;
+
+/* Config file ignore declaration: a feature name */
+typedef struct sensors_ignore {
+	char *name;
+	sensors_config_line line;
+} sensors_ignore;
+
+/* A list of chip names, used to represent a config file chips declaration */
+typedef struct sensors_chip_name_list {
+	sensors_chip_name *fits;
+	int fits_count;
+	int fits_max;
+} sensors_chip_name_list;
+
+/* A config file chip block */
+typedef struct sensors_chip {
+	sensors_chip_name_list chips;
+	sensors_label *labels;
+	int labels_count;
+	int labels_max;
+	sensors_set *sets;
+	int sets_count;
+	int sets_max;
+	sensors_compute *computes;
+	int computes_count;
+	int computes_max;
+	sensors_ignore *ignores;
+	int ignores_count;
+	int ignores_max;
+	sensors_config_line line;
+} sensors_chip;
+
+/* Config file bus declaration: the bus type and number, combined with adapter
+   name */
+typedef struct sensors_bus {
+	char *adapter;
+	sensors_bus_id bus;
+	sensors_config_line line;
+} sensors_bus;
+
+/* Internal data about all features and subfeatures of a chip */
+typedef struct sensors_chip_features {
+	struct sensors_chip_name chip;
+	struct sensors_feature *feature;
+	struct sensors_subfeature *subfeature;
+	int feature_count;
+	int subfeature_count;
+} sensors_chip_features;
+
+extern char **sensors_config_files;
+extern int sensors_config_files_count;
+extern int sensors_config_files_max;
+
+#define sensors_add_config_files(el) sensors_add_array_el( \
+	(el), &sensors_config_files, &sensors_config_files_count, \
+	&sensors_config_files_max, sizeof(char *))
+
+extern sensors_chip *sensors_config_chips;
+extern int sensors_config_chips_count;
+extern int sensors_config_chips_subst;
+extern int sensors_config_chips_max;
+
+extern sensors_bus *sensors_config_busses;
+extern int sensors_config_busses_count;
+extern int sensors_config_busses_max;
+
+extern sensors_chip_features *sensors_proc_chips;
+extern int sensors_proc_chips_count;
+extern int sensors_proc_chips_max;
+
+#define sensors_add_proc_chips(el) sensors_add_array_el( \
+	(el), &sensors_proc_chips, &sensors_proc_chips_count,\
+	&sensors_proc_chips_max, sizeof(struct sensors_chip_features))
+
+extern sensors_bus *sensors_proc_bus;
+extern int sensors_proc_bus_count;
+extern int sensors_proc_bus_max;
+
+#define sensors_add_proc_bus(el) sensors_add_array_el( \
+	(el), &sensors_proc_bus, &sensors_proc_bus_count,\
+	&sensors_proc_bus_max, sizeof(struct sensors_bus))
+
+/* Substitute configuration bus numbers with real-world bus numbers
+   in the chips lists */
+int sensors_substitute_busses(void);
+
+
+/* Parse a bus id into its components. Returns 0 on success, a value from
+   error.h on failure. */
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus);
+
+#endif /* def LIB_SENSORS_DATA_H */
diff --git a/tools/gator/daemon/libsensors/error.c b/tools/gator/daemon/libsensors/error.c
new file mode 100644
index 000000000000..55bde81295fb
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.c
@@ -0,0 +1,92 @@
+/*
+    error.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <stdio.h>
+#include "error.h"
+#include "general.h"
+
+static void sensors_default_parse_error(const char *err, int lineno);
+static void sensors_default_parse_error_wfn(const char *err,
+					    const char *filename, int lineno);
+static void sensors_default_fatal_error(const char *proc, const char *err);
+
+void (*sensors_parse_error) (const char *err, int lineno) =
+						sensors_default_parse_error;
+void (*sensors_parse_error_wfn) (const char *err, const char *filename,
+				 int lineno) = sensors_default_parse_error_wfn;
+void (*sensors_fatal_error) (const char *proc, const char *err) =
+						sensors_default_fatal_error;
+
+static const char *errorlist[] = {
+	/* Invalid error code    */ "Unknown error",
+	/* SENSORS_ERR_WILDCARDS */ "Wildcard found in chip name",
+	/* SENSORS_ERR_NO_ENTRY  */ "No such subfeature known",
+	/* SENSORS_ERR_ACCESS_R  */ "Can't read",
+	/* SENSORS_ERR_KERNEL    */ "Kernel interface error",
+	/* SENSORS_ERR_DIV_ZERO  */ "Divide by zero",
+	/* SENSORS_ERR_CHIP_NAME */ "Can't parse chip name",
+	/* SENSORS_ERR_BUS_NAME  */ "Can't parse bus name",
+	/* SENSORS_ERR_PARSE     */ "General parse error",
+	/* SENSORS_ERR_ACCESS_W  */ "Can't write",
+	/* SENSORS_ERR_IO        */ "I/O error",
+	/* SENSORS_ERR_RECURSION */ "Evaluation recurses too deep",
+};
+
+const char *sensors_strerror(int errnum)
+{
+	if (errnum < 0)
+		errnum = -errnum;
+	if (errnum >= ARRAY_SIZE(errorlist))
+		errnum = 0;
+	return errorlist[errnum];
+}
+
+void sensors_default_parse_error(const char *err, int lineno)
+{
+	if (lineno)
+		fprintf(stderr, "Error: Line %d: %s\n", lineno, err);
+	else
+		fprintf(stderr, "Error: %s\n", err);
+}
+
+void sensors_default_parse_error_wfn(const char *err,
+				     const char *filename, int lineno)
+{
+	/* If application provided a custom parse error reporting function
+	   but not the variant with the filename, fall back to the original
+	   variant without the filename, for backwards compatibility. */
+	if (sensors_parse_error != sensors_default_parse_error ||
+	    !filename)
+		return sensors_parse_error(err, lineno);
+
+	if (lineno)
+		fprintf(stderr, "Error: File %s, line %d: %s\n", filename,
+			lineno, err);
+	else
+		fprintf(stderr, "Error: File %s: %s\n", filename, err);
+}
+
+void sensors_default_fatal_error(const char *proc, const char *err)
+{
+	fprintf(stderr, "Fatal error in `%s': %s\n", proc, err);
+	exit(1);
+}
diff --git a/tools/gator/daemon/libsensors/error.h b/tools/gator/daemon/libsensors/error.h
new file mode 100644
index 000000000000..37cdc956151d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.h
@@ -0,0 +1,74 @@
+/*
+    error.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ERROR_H
+#define LIB_SENSORS_ERROR_H
+
+#define SENSORS_ERR_WILDCARDS	1 /* Wildcard found in chip name */
+#define SENSORS_ERR_NO_ENTRY	2 /* No such subfeature known */
+#define SENSORS_ERR_ACCESS_R	3 /* Can't read */
+#define SENSORS_ERR_KERNEL	4 /* Kernel interface error */
+#define SENSORS_ERR_DIV_ZERO	5 /* Divide by zero */
+#define SENSORS_ERR_CHIP_NAME	6 /* Can't parse chip name */
+#define SENSORS_ERR_BUS_NAME	7 /* Can't parse bus name */
+#define SENSORS_ERR_PARSE	8 /* General parse error */
+#define SENSORS_ERR_ACCESS_W	9 /* Can't write */
+#define SENSORS_ERR_IO		10 /* I/O error */
+#define SENSORS_ERR_RECURSION	11 /* Evaluation recurses too deep */
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+
+/* This function returns a pointer to a string which describes the error.
+   errnum may be negative (the corresponding positive error is returned).
+   You may not modify the result! */
+const char *sensors_strerror(int errnum);
+
+/* These functions are called when a parse error is detected. Give them new
+   values, and your own functions are called instead of the default (which
+   print to stderr). These functions may terminate the program, but they
+   usually output an error and return. The first function is the original
+   one, the second one was added later when support for multiple
+   configuration files was added.
+   The library code now only calls the second function. However, for
+   backwards compatibility, if an application provides a custom handling
+   function for the first function but not the second, then all parse
+   errors will be reported using the first function (that is, the filename
+   is never reported.)
+   Note that filename can be NULL (if filename isn't known) and lineno
+   can be 0 (if the error occurs before the actual parsing starts.) */
+extern void (*sensors_parse_error) (const char *err, int lineno);
+extern void (*sensors_parse_error_wfn) (const char *err,
+					const char *filename, int lineno);
+
+/* This function is called when an immediately fatal error (like no
+   memory left) is detected. Give it a new value, and your own function
+   is called instead of the default (which prints to stderr and ends
+   the program). Never let it return! */
+extern void (*sensors_fatal_error) (const char *proc, const char *err);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/general.c b/tools/gator/daemon/libsensors/general.c
new file mode 100644
index 000000000000..f237e3b59c22
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.c
@@ -0,0 +1,85 @@
+/*
+    general.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include "error.h"
+#include "general.h"
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+
+#define A_BUNCH 16
+
+void sensors_malloc_array(void *list, int *num_el, int *max_el, int el_size)
+{
+	void **my_list = (void **)list;
+
+	*my_list = malloc(el_size*A_BUNCH);
+	if (! *my_list)
+		sensors_fatal_error(__func__, "Allocating new elements");
+	*max_el = A_BUNCH;
+	*num_el = 0;
+}
+
+void sensors_free_array(void *list, int *num_el, int *max_el)
+{
+	void **my_list = (void **)list;
+
+	free(*my_list);
+	*my_list = NULL;
+	*num_el = 0;
+	*max_el = 0;
+}
+
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + 1 > *max_el) {
+		new_max_el = *max_el + A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *) *my_list) + *num_el * el_size, el, el_size);
+	(*num_el) ++;
+}
+
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + nr_els > *max_el) {
+		new_max_el = (*max_el + nr_els + A_BUNCH);
+		new_max_el -= new_max_el % A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *)*my_list) + *num_el * el_size, els, el_size * nr_els);
+	*num_el += nr_els;
+}
diff --git a/tools/gator/daemon/libsensors/general.h b/tools/gator/daemon/libsensors/general.h
new file mode 100644
index 000000000000..a3971e02e1b7
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.h
@@ -0,0 +1,39 @@
+/*
+    general.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_GENERAL
+#define LIB_SENSORS_GENERAL
+
+/* These are general purpose functions. They allow you to use variable-
+   length arrays, which are extended automatically. A distinction is
+   made between the current number of elements and the maximum number.
+   You can only add elements at the end. Primitive, but very useful
+   for internal use. */
+void sensors_malloc_array(void *list, int *num_el, int *max_el,
+			  int el_size);
+void sensors_free_array(void *list, int *num_el, int *max_el);
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size);
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size);
+
+#define ARRAY_SIZE(arr)	(int)(sizeof(arr) / sizeof((arr)[0]))
+
+#endif /* LIB_SENSORS_GENERAL */
diff --git a/tools/gator/daemon/libsensors/init.c b/tools/gator/daemon/libsensors/init.c
new file mode 100644
index 000000000000..558046e76c24
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.c
@@ -0,0 +1,341 @@
+/*
+    init.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to cast alphasort to supress a warning as it's prototype is different on android. ***/
+
+/* Needed for scandir() and alphasort() */
+#define _BSD_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <locale.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <dirent.h>
+#include <unistd.h>
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "conf.h"
+#include "sysfs.h"
+#include "scanner.h"
+#include "init.h"
+
+#define DEFAULT_CONFIG_FILE	ETCDIR "/sensors3.conf"
+#define ALT_CONFIG_FILE		ETCDIR "/sensors.conf"
+#define DEFAULT_CONFIG_DIR	ETCDIR "/sensors.d"
+
+/* Wrapper around sensors_yyparse(), which clears the locale so that
+   the decimal numbers are always parsed properly. */
+static int sensors_parse(void)
+{
+	int res;
+	char *locale;
+
+	/* Remember the current locale and clear it */
+	locale = setlocale(LC_ALL, NULL);
+	if (locale) {
+		locale = strdup(locale);
+		if (!locale)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		setlocale(LC_ALL, "C");
+	}
+
+	res = sensors_yyparse();
+
+	/* Restore the old locale */
+	if (locale) {
+		setlocale(LC_ALL, locale);
+		free(locale);
+	}
+
+	return res;
+}
+
+static void free_bus(sensors_bus *bus)
+{
+	free(bus->adapter);
+}
+
+static void free_config_busses(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_config_busses_count; i++)
+		free_bus(&sensors_config_busses[i]);
+	free(sensors_config_busses);
+	sensors_config_busses = NULL;
+	sensors_config_busses_count = sensors_config_busses_max = 0;
+}
+
+static int parse_config(FILE *input, const char *name)
+{
+	int err;
+	char *name_copy;
+
+	if (name) {
+		/* Record configuration file name for error reporting */
+		name_copy = strdup(name);
+		if (!name_copy)
+			sensors_fatal_error(__func__, "Out of memory");
+		sensors_add_config_files(&name_copy);
+	} else
+		name_copy = NULL;
+
+	if (sensors_scanner_init(input, name_copy)) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+	err = sensors_parse();
+	sensors_scanner_exit();
+	if (err) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+
+	err = sensors_substitute_busses();
+
+exit_cleanup:
+	free_config_busses();
+	return err;
+}
+
+static int config_file_filter(const struct dirent *entry)
+{
+	return entry->d_name[0] != '.';		/* Skip hidden files */
+}
+
+static int add_config_from_dir(const char *dir)
+{
+	int count, res, i;
+	struct dirent **namelist;
+
+	count = scandir(dir, &namelist, config_file_filter, (int (*)(const struct dirent **, const struct dirent **))alphasort);
+	if (count < 0) {
+		/* Do not return an error if directory does not exist */
+		if (errno == ENOENT)
+			return 0;
+		
+		sensors_parse_error_wfn(strerror(errno), NULL, 0);
+		return -SENSORS_ERR_PARSE;
+	}
+
+	for (res = 0, i = 0; !res && i < count; i++) {
+		int len;
+		char path[PATH_MAX];
+		FILE *input;
+		struct stat st;
+
+		len = snprintf(path, sizeof(path), "%s/%s", dir,
+			       namelist[i]->d_name);
+		if (len < 0 || len >= (int)sizeof(path)) {
+			res = -SENSORS_ERR_PARSE;
+			continue;
+		}
+
+		/* Only accept regular files */
+		if (stat(path, &st) < 0 || !S_ISREG(st.st_mode))
+			continue;
+
+		input = fopen(path, "r");
+		if (input) {
+			res = parse_config(input, path);
+			fclose(input);
+		} else {
+			res = -SENSORS_ERR_PARSE;
+			sensors_parse_error_wfn(strerror(errno), path, 0);
+		}
+	}
+
+	/* Free memory allocated by scandir() */
+	for (i = 0; i < count; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return res;
+}
+
+int sensors_init(FILE *input)
+{
+	int res;
+
+	if (!sensors_init_sysfs())
+		return -SENSORS_ERR_KERNEL;
+	if ((res = sensors_read_sysfs_bus()) ||
+	    (res = sensors_read_sysfs_chips()))
+		goto exit_cleanup;
+
+	if (input) {
+		res = parse_config(input, NULL);
+		if (res)
+			goto exit_cleanup;
+	} else {
+		const char* name;
+
+		/* No configuration provided, use default */
+		input = fopen(name = DEFAULT_CONFIG_FILE, "r");
+		if (!input && errno == ENOENT)
+			input = fopen(name = ALT_CONFIG_FILE, "r");
+		if (input) {
+			res = parse_config(input, name);
+			fclose(input);
+			if (res)
+				goto exit_cleanup;
+
+		} else if (errno != ENOENT) {
+			sensors_parse_error_wfn(strerror(errno), name, 0);
+			res = -SENSORS_ERR_PARSE;
+			goto exit_cleanup;
+		}
+
+		/* Also check for files in default directory */
+		res = add_config_from_dir(DEFAULT_CONFIG_DIR);
+		if (res)
+			goto exit_cleanup;
+	}
+
+	return 0;
+
+exit_cleanup:
+	sensors_cleanup();
+	return res;
+}
+
+static void free_chip_name(sensors_chip_name *name)
+{
+	free(name->prefix);
+	free(name->path);
+}
+
+static void free_chip_features(sensors_chip_features *features)
+{
+	int i;
+
+	for (i = 0; i < features->subfeature_count; i++)
+		free(features->subfeature[i].name);
+	free(features->subfeature);
+	for (i = 0; i < features->feature_count; i++)
+		free(features->feature[i].name);
+	free(features->feature);
+}
+
+static void free_label(sensors_label *label)
+{
+	free(label->name);
+	free(label->value);
+}
+
+void sensors_free_expr(sensors_expr *expr)
+{
+	if (expr->kind == sensors_kind_var)
+		free(expr->data.var);
+	else if (expr->kind == sensors_kind_sub) {
+		if (expr->data.subexpr.sub1)
+			sensors_free_expr(expr->data.subexpr.sub1);
+		if (expr->data.subexpr.sub2)
+			sensors_free_expr(expr->data.subexpr.sub2);
+	}
+	free(expr);
+}
+
+static void free_set(sensors_set *set)
+{
+	free(set->name);
+	sensors_free_expr(set->value);
+}
+
+static void free_compute(sensors_compute *compute)
+{
+	free(compute->name);
+	sensors_free_expr(compute->from_proc);
+	sensors_free_expr(compute->to_proc);
+}
+
+static void free_ignore(sensors_ignore *ignore)
+{
+	free(ignore->name);
+}
+
+static void free_chip(sensors_chip *chip)
+{
+	int i;
+
+	for (i = 0; i < chip->chips.fits_count; i++)
+		free_chip_name(&chip->chips.fits[i]);
+	free(chip->chips.fits);
+	chip->chips.fits_count = chip->chips.fits_max = 0;
+
+	for (i = 0; i < chip->labels_count; i++)
+		free_label(&chip->labels[i]);
+	free(chip->labels);
+	chip->labels_count = chip->labels_max = 0;
+
+	for (i = 0; i < chip->sets_count; i++)
+		free_set(&chip->sets[i]);
+	free(chip->sets);
+	chip->sets_count = chip->sets_max = 0;
+
+	for (i = 0; i < chip->computes_count; i++)
+		free_compute(&chip->computes[i]);
+	free(chip->computes);
+	chip->computes_count = chip->computes_max = 0;
+
+	for (i = 0; i < chip->ignores_count; i++)
+		free_ignore(&chip->ignores[i]);
+	free(chip->ignores);
+	chip->ignores_count = chip->ignores_max = 0;
+}
+
+void sensors_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++) {
+		free_chip_name(&sensors_proc_chips[i].chip);
+		free_chip_features(&sensors_proc_chips[i]);
+	}
+	free(sensors_proc_chips);
+	sensors_proc_chips = NULL;
+	sensors_proc_chips_count = sensors_proc_chips_max = 0;
+
+	for (i = 0; i < sensors_config_chips_count; i++)
+		free_chip(&sensors_config_chips[i]);
+	free(sensors_config_chips);
+	sensors_config_chips = NULL;
+	sensors_config_chips_count = sensors_config_chips_max = 0;
+	sensors_config_chips_subst = 0;
+
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		free_bus(&sensors_proc_bus[i]);
+	free(sensors_proc_bus);
+	sensors_proc_bus = NULL;
+	sensors_proc_bus_count = sensors_proc_bus_max = 0;
+
+	for (i = 0; i < sensors_config_files_count; i++)
+		free(sensors_config_files[i]);
+	free(sensors_config_files);
+	sensors_config_files = NULL;
+	sensors_config_files_count = sensors_config_files_max = 0;
+}
diff --git a/tools/gator/daemon/libsensors/init.h b/tools/gator/daemon/libsensors/init.h
new file mode 100644
index 000000000000..47006a62db63
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.h
@@ -0,0 +1,28 @@
+/*
+    init.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (C) 2007  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_INIT_H
+#define LIB_SENSORS_INIT_H
+
+#include "data.h"
+
+void sensors_free_expr(sensors_expr *expr);
+
+#endif /* def LIB_SENSORS_INIT_H */
diff --git a/tools/gator/daemon/libsensors/scanner.h b/tools/gator/daemon/libsensors/scanner.h
new file mode 100644
index 000000000000..4c415167de5c
--- /dev/null
+++ b/tools/gator/daemon/libsensors/scanner.h
@@ -0,0 +1,32 @@
+/*
+    scanner.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 2006 Mark M. Hoffman <mhoffman@lightlink.com>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to fix input defined but not used warning from conf-lex.c. ***/
+
+#ifndef LIB_SENSORS_SCANNER_H
+#define LIB_SENSORS_SCANNER_H
+
+int sensors_scanner_init(FILE *input, const char *filename);
+void sensors_scanner_exit(void);
+
+#define YY_NO_INPUT
+
+#endif
+
diff --git a/tools/gator/daemon/libsensors/sensors.h b/tools/gator/daemon/libsensors/sensors.h
new file mode 100644
index 000000000000..7874d028dc82
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sensors.h
@@ -0,0 +1,311 @@
+/*
+    sensors.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2010  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to read non-scaled values. ***/
+
+#ifndef LIB_SENSORS_SENSORS_H
+#define LIB_SENSORS_SENSORS_H
+
+#include <stdio.h>
+#include <limits.h>
+
+/* Publicly accessible library functions */
+
+/* libsensors API version define, first digit is the major version (changed
+   when the API + ABI breaks), the third digit is incremented to track small
+   API additions like new flags / enum values. The second digit is for tracking
+   larger additions like new methods. */
+#define SENSORS_API_VERSION		0x432
+
+#define SENSORS_CHIP_NAME_PREFIX_ANY	NULL
+#define SENSORS_CHIP_NAME_ADDR_ANY	(-1)
+
+#define SENSORS_BUS_TYPE_ANY		(-1)
+#define SENSORS_BUS_TYPE_I2C		0
+#define SENSORS_BUS_TYPE_ISA		1
+#define SENSORS_BUS_TYPE_PCI		2
+#define SENSORS_BUS_TYPE_SPI		3
+#define SENSORS_BUS_TYPE_VIRTUAL	4
+#define SENSORS_BUS_TYPE_ACPI		5
+#define SENSORS_BUS_TYPE_HID		6
+#define SENSORS_BUS_NR_ANY		(-1)
+#define SENSORS_BUS_NR_IGNORE		(-2)
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+extern const char *libsensors_version;
+
+extern int sensors_sysfs_no_scaling;
+
+typedef struct sensors_bus_id {
+	short type;
+	short nr;
+} sensors_bus_id;
+
+/* A chip name is encoded in this structure */
+typedef struct sensors_chip_name {
+	char *prefix;
+	sensors_bus_id bus;
+	int addr;
+	char *path;
+} sensors_chip_name;
+
+/* Load the configuration file and the detected chips list. If this
+   returns a value unequal to zero, you are in trouble; you can not
+   assume anything will be initialized properly. If you want to
+   reload the configuration file, call sensors_cleanup() below before
+   calling sensors_init() again. */
+int sensors_init(FILE *input);
+
+/* Clean-up function: You can't access anything after
+   this, until the next sensors_init() call! */
+void sensors_cleanup(void);
+
+/* Parse a chip name to the internal representation. Return 0 on success, <0
+   on error. */
+int sensors_parse_chip_name(const char *orig_name, sensors_chip_name *res);
+
+/* Free memory allocated for the internal representation of a chip name. */
+void sensors_free_chip_name(sensors_chip_name *chip);
+
+/* Print a chip name from its internal representation. Note that chip should
+   not contain wildcard values! Return the number of characters printed on
+   success (same as snprintf), <0 on error. */
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip);
+
+/* This function returns the adapter name of a bus,
+   as used within the sensors_chip_name structure. If it could not be found,
+   it returns NULL */
+const char *sensors_get_adapter_name(const sensors_bus_id *bus);
+
+typedef struct sensors_feature sensors_feature;
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature);
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure.  */
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *value);
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value);
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name);
+
+/* This function returns all detected chips that match a given chip name,
+   one by one. If no chip name is provided, all detected chips are returned.
+   To start at the beginning of the list, use 0 for nr; NULL is returned if
+   we are at the end of the list. Do not try to change these chip names, as
+   they point to internal structures! */
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr);
+
+/* These defines are used in the flags field of sensors_subfeature */
+#define SENSORS_MODE_R			1
+#define SENSORS_MODE_W			2
+#define SENSORS_COMPUTE_MAPPING		4
+
+typedef enum sensors_feature_type {
+	SENSORS_FEATURE_IN		= 0x00,
+	SENSORS_FEATURE_FAN		= 0x01,
+	SENSORS_FEATURE_TEMP		= 0x02,
+	SENSORS_FEATURE_POWER		= 0x03,
+	SENSORS_FEATURE_ENERGY		= 0x04,
+	SENSORS_FEATURE_CURR		= 0x05,
+	SENSORS_FEATURE_HUMIDITY	= 0x06,
+	SENSORS_FEATURE_MAX_MAIN,
+	SENSORS_FEATURE_VID		= 0x10,
+	SENSORS_FEATURE_INTRUSION	= 0x11,
+	SENSORS_FEATURE_MAX_OTHER,
+	SENSORS_FEATURE_BEEP_ENABLE	= 0x18,
+	SENSORS_FEATURE_UNKNOWN		= INT_MAX,
+} sensors_feature_type;
+
+/* All the sensor types (in, fan, temp, vid) are a multiple of 0x100 apart,
+   and sensor subfeatures which have no compute mapping have bit 7 set. */
+typedef enum sensors_subfeature_type {
+	SENSORS_SUBFEATURE_IN_INPUT = SENSORS_FEATURE_IN << 8,
+	SENSORS_SUBFEATURE_IN_MIN,
+	SENSORS_SUBFEATURE_IN_MAX,
+	SENSORS_SUBFEATURE_IN_LCRIT,
+	SENSORS_SUBFEATURE_IN_CRIT,
+	SENSORS_SUBFEATURE_IN_AVERAGE,
+	SENSORS_SUBFEATURE_IN_LOWEST,
+	SENSORS_SUBFEATURE_IN_HIGHEST,
+	SENSORS_SUBFEATURE_IN_ALARM = (SENSORS_FEATURE_IN << 8) | 0x80,
+	SENSORS_SUBFEATURE_IN_MIN_ALARM,
+	SENSORS_SUBFEATURE_IN_MAX_ALARM,
+	SENSORS_SUBFEATURE_IN_BEEP,
+	SENSORS_SUBFEATURE_IN_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_IN_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_FAN_INPUT = SENSORS_FEATURE_FAN << 8,
+	SENSORS_SUBFEATURE_FAN_MIN,
+	SENSORS_SUBFEATURE_FAN_MAX,
+	SENSORS_SUBFEATURE_FAN_ALARM = (SENSORS_FEATURE_FAN << 8) | 0x80,
+	SENSORS_SUBFEATURE_FAN_FAULT,
+	SENSORS_SUBFEATURE_FAN_DIV,
+	SENSORS_SUBFEATURE_FAN_BEEP,
+	SENSORS_SUBFEATURE_FAN_PULSES,
+	SENSORS_SUBFEATURE_FAN_MIN_ALARM,
+	SENSORS_SUBFEATURE_FAN_MAX_ALARM,
+
+	SENSORS_SUBFEATURE_TEMP_INPUT = SENSORS_FEATURE_TEMP << 8,
+	SENSORS_SUBFEATURE_TEMP_MAX,
+	SENSORS_SUBFEATURE_TEMP_MAX_HYST,
+	SENSORS_SUBFEATURE_TEMP_MIN,
+	SENSORS_SUBFEATURE_TEMP_CRIT,
+	SENSORS_SUBFEATURE_TEMP_CRIT_HYST,
+	SENSORS_SUBFEATURE_TEMP_LCRIT,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST,
+	SENSORS_SUBFEATURE_TEMP_LOWEST,
+	SENSORS_SUBFEATURE_TEMP_HIGHEST,
+	SENSORS_SUBFEATURE_TEMP_ALARM = (SENSORS_FEATURE_TEMP << 8) | 0x80,
+	SENSORS_SUBFEATURE_TEMP_MAX_ALARM,
+	SENSORS_SUBFEATURE_TEMP_MIN_ALARM,
+	SENSORS_SUBFEATURE_TEMP_CRIT_ALARM,
+	SENSORS_SUBFEATURE_TEMP_FAULT,
+	SENSORS_SUBFEATURE_TEMP_TYPE,
+	SENSORS_SUBFEATURE_TEMP_OFFSET,
+	SENSORS_SUBFEATURE_TEMP_BEEP,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM,
+	SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM,
+
+	SENSORS_SUBFEATURE_POWER_AVERAGE = SENSORS_FEATURE_POWER << 8,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST,
+	SENSORS_SUBFEATURE_POWER_INPUT,
+	SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_INPUT_LOWEST,
+	SENSORS_SUBFEATURE_POWER_CAP,
+	SENSORS_SUBFEATURE_POWER_CAP_HYST,
+	SENSORS_SUBFEATURE_POWER_MAX,
+	SENSORS_SUBFEATURE_POWER_CRIT,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL = (SENSORS_FEATURE_POWER << 8) | 0x80,
+	SENSORS_SUBFEATURE_POWER_ALARM,
+	SENSORS_SUBFEATURE_POWER_CAP_ALARM,
+	SENSORS_SUBFEATURE_POWER_MAX_ALARM,
+	SENSORS_SUBFEATURE_POWER_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_ENERGY_INPUT = SENSORS_FEATURE_ENERGY << 8,
+
+	SENSORS_SUBFEATURE_CURR_INPUT = SENSORS_FEATURE_CURR << 8,
+	SENSORS_SUBFEATURE_CURR_MIN,
+	SENSORS_SUBFEATURE_CURR_MAX,
+	SENSORS_SUBFEATURE_CURR_LCRIT,
+	SENSORS_SUBFEATURE_CURR_CRIT,
+	SENSORS_SUBFEATURE_CURR_AVERAGE,
+	SENSORS_SUBFEATURE_CURR_LOWEST,
+	SENSORS_SUBFEATURE_CURR_HIGHEST,
+	SENSORS_SUBFEATURE_CURR_ALARM = (SENSORS_FEATURE_CURR << 8) | 0x80,
+	SENSORS_SUBFEATURE_CURR_MIN_ALARM,
+	SENSORS_SUBFEATURE_CURR_MAX_ALARM,
+	SENSORS_SUBFEATURE_CURR_BEEP,
+	SENSORS_SUBFEATURE_CURR_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_CURR_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_HUMIDITY_INPUT = SENSORS_FEATURE_HUMIDITY << 8,
+
+	SENSORS_SUBFEATURE_VID = SENSORS_FEATURE_VID << 8,
+
+	SENSORS_SUBFEATURE_INTRUSION_ALARM = SENSORS_FEATURE_INTRUSION << 8,
+	SENSORS_SUBFEATURE_INTRUSION_BEEP,
+
+	SENSORS_SUBFEATURE_BEEP_ENABLE = SENSORS_FEATURE_BEEP_ENABLE << 8,
+
+	SENSORS_SUBFEATURE_UNKNOWN = INT_MAX,
+} sensors_subfeature_type;
+
+/* Data about a single chip feature (or category leader) */
+struct sensors_feature {
+	char *name;
+	int number;
+	sensors_feature_type type;
+	/* Members below are for libsensors internal use only */
+	int first_subfeature;
+	int padding1;
+};
+
+/* Data about a single chip subfeature:
+   name is the string name used to refer to this subfeature (in config files)
+   number is the internal subfeature number, used in many functions to refer
+     to this subfeature
+   type is the subfeature type
+   mapping is the number of a main feature this subfeature belongs to
+     (for example subfeatures fan1_input, fan1_min, fan1_div and fan1_alarm
+      are mapped to main feature fan1)
+   flags is a bitfield, its value is a combination of SENSORS_MODE_R (readable),
+     SENSORS_MODE_W (writable) and SENSORS_COMPUTE_MAPPING (affected by the
+     computation rules of the main feature) */
+typedef struct sensors_subfeature {
+	char *name;
+	int number;
+	sensors_subfeature_type type;
+	int mapping;
+	unsigned int flags;
+} sensors_subfeature;
+
+/* This returns all main features of a specific chip. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr);
+
+/* This returns all subfeatures of a given main feature. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			    const sensors_feature *feature, int *nr);
+
+/* This returns the subfeature of the given type for a given main feature,
+   if it exists, NULL otherwise.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/sysfs.c b/tools/gator/daemon/libsensors/sysfs.c
new file mode 100644
index 000000000000..2b494c9975b4
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.c
@@ -0,0 +1,926 @@
+/*
+    sysfs.c - Part of libsensors, a library for reading Linux sensor data
+    Copyright (c) 2005 Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007-2010 Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to improve performance by substituting calls to fread() with calls to read() and to read non-scaled values. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "general.h"
+#include "sysfs.h"
+
+
+/****************************************************************************/
+
+#define ATTR_MAX	128
+#define SYSFS_MAGIC	0x62656572
+
+int sensors_sysfs_no_scaling;
+
+/*
+ * Read an attribute from sysfs
+ * Returns a pointer to a freshly allocated string; free it yourself.
+ * If the file doesn't exist or can't be read, NULL is returned.
+ */
+static char *sysfs_read_attr(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	char buf[ATTR_MAX], *p;
+	FILE *f;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+
+	if (!(f = fopen(path, "r")))
+		return NULL;
+	p = fgets(buf, ATTR_MAX, f);
+	fclose(f);
+	if (!p)
+		return NULL;
+
+	/* Last byte is a '\n'; chop that off */
+	p = strndup(buf, strlen(buf) - 1);
+	if (!p)
+		sensors_fatal_error(__func__, "Out of memory");
+	return p;
+}
+
+/*
+ * Call an arbitrary function for each class device of the given class
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_classdev(const char *class_name,
+				   int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/class/%s",
+			    sensors_sysfs_mount, class_name);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/*
+ * Call an arbitrary function for each device of the given bus type
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_busdev(const char *bus_type,
+				 int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/bus/%s/devices",
+			    sensors_sysfs_mount, bus_type);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/****************************************************************************/
+
+char sensors_sysfs_mount[NAME_MAX];
+
+#define MAX_MAIN_SENSOR_TYPES	(SENSORS_FEATURE_MAX_MAIN - SENSORS_FEATURE_IN)
+#define MAX_OTHER_SENSOR_TYPES	(SENSORS_FEATURE_MAX_OTHER - SENSORS_FEATURE_VID)
+#define MAX_SENSORS_PER_TYPE	24
+/* max_subfeatures is now computed dynamically */
+#define FEATURE_SIZE		(max_subfeatures * 2)
+#define FEATURE_TYPE_SIZE	(MAX_SENSORS_PER_TYPE * FEATURE_SIZE)
+
+/*
+ * Room for all 7 main types (in, fan, temp, power, energy, current, humidity)
+ * and 2 other types (VID, intrusion) with all their subfeatures + misc features
+ */
+#define SUB_OFFSET_OTHER	(MAX_MAIN_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define SUB_OFFSET_MISC		(SUB_OFFSET_OTHER + \
+				 MAX_OTHER_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define ALL_POSSIBLE_SUBFEATURES	(SUB_OFFSET_MISC + 1)
+
+static
+int get_type_scaling(sensors_subfeature_type type)
+{
+	/* Multipliers for subfeatures */
+	switch (type & 0xFF80) {
+	case SENSORS_SUBFEATURE_IN_INPUT:
+	case SENSORS_SUBFEATURE_TEMP_INPUT:
+	case SENSORS_SUBFEATURE_CURR_INPUT:
+	case SENSORS_SUBFEATURE_HUMIDITY_INPUT:
+		return 1000;
+	case SENSORS_SUBFEATURE_FAN_INPUT:
+		return 1;
+	case SENSORS_SUBFEATURE_POWER_AVERAGE:
+	case SENSORS_SUBFEATURE_ENERGY_INPUT:
+		return 1000000;
+	}
+
+	/* Multipliers for second class subfeatures
+	   that need their own multiplier */
+	switch (type) {
+	case SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL:
+	case SENSORS_SUBFEATURE_VID:
+	case SENSORS_SUBFEATURE_TEMP_OFFSET:
+		return 1000;
+	default:
+		return 1;
+	}
+}
+
+static
+char *get_feature_name(sensors_feature_type ftype, char *sfname)
+{
+	char *name, *underscore;
+
+	switch (ftype) {
+	case SENSORS_FEATURE_IN:
+	case SENSORS_FEATURE_FAN:
+	case SENSORS_FEATURE_TEMP:
+	case SENSORS_FEATURE_POWER:
+	case SENSORS_FEATURE_ENERGY:
+	case SENSORS_FEATURE_CURR:
+	case SENSORS_FEATURE_HUMIDITY:
+	case SENSORS_FEATURE_INTRUSION:
+		underscore = strchr(sfname, '_');
+		name = strndup(sfname, underscore - sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		break;
+	default:
+		name = strdup(sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+	}
+
+	return name;
+}
+
+/* Static mappings for use by sensors_subfeature_get_type() */
+struct subfeature_type_match
+{
+	const char *name;
+	sensors_subfeature_type type;
+};
+
+struct feature_type_match
+{
+	const char *name;
+	const struct subfeature_type_match *submatches;
+};
+
+static const struct subfeature_type_match temp_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_TEMP_INPUT },
+	{ "max", SENSORS_SUBFEATURE_TEMP_MAX },
+	{ "max_hyst", SENSORS_SUBFEATURE_TEMP_MAX_HYST },
+	{ "min", SENSORS_SUBFEATURE_TEMP_MIN },
+	{ "crit", SENSORS_SUBFEATURE_TEMP_CRIT },
+	{ "crit_hyst", SENSORS_SUBFEATURE_TEMP_CRIT_HYST },
+	{ "lcrit", SENSORS_SUBFEATURE_TEMP_LCRIT },
+	{ "emergency", SENSORS_SUBFEATURE_TEMP_EMERGENCY },
+	{ "emergency_hyst", SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST },
+	{ "lowest", SENSORS_SUBFEATURE_TEMP_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_TEMP_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_TEMP_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_TEMP_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_TEMP_MAX_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_TEMP_CRIT_ALARM },
+	{ "emergency_alarm", SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_TEMP_FAULT },
+	{ "type", SENSORS_SUBFEATURE_TEMP_TYPE },
+	{ "offset", SENSORS_SUBFEATURE_TEMP_OFFSET },
+	{ "beep", SENSORS_SUBFEATURE_TEMP_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match in_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_IN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_IN_MIN },
+	{ "max", SENSORS_SUBFEATURE_IN_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_IN_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_IN_CRIT },
+	{ "average", SENSORS_SUBFEATURE_IN_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_IN_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_IN_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_IN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_IN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_IN_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_IN_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_IN_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_IN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match fan_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_FAN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_FAN_MIN },
+	{ "max", SENSORS_SUBFEATURE_FAN_MAX },
+	{ "div", SENSORS_SUBFEATURE_FAN_DIV },
+	{ "pulses", SENSORS_SUBFEATURE_FAN_PULSES },
+	{ "alarm", SENSORS_SUBFEATURE_FAN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_FAN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_FAN_MAX_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_FAN_FAULT },
+	{ "beep", SENSORS_SUBFEATURE_FAN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match power_matches[] = {
+	{ "average", SENSORS_SUBFEATURE_POWER_AVERAGE },
+	{ "average_highest", SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST },
+	{ "average_lowest", SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST },
+	{ "input", SENSORS_SUBFEATURE_POWER_INPUT },
+	{ "input_highest", SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST },
+	{ "input_lowest", SENSORS_SUBFEATURE_POWER_INPUT_LOWEST },
+	{ "cap", SENSORS_SUBFEATURE_POWER_CAP },
+	{ "cap_hyst", SENSORS_SUBFEATURE_POWER_CAP_HYST },
+	{ "cap_alarm", SENSORS_SUBFEATURE_POWER_CAP_ALARM },
+	{ "alarm", SENSORS_SUBFEATURE_POWER_ALARM },
+	{ "max", SENSORS_SUBFEATURE_POWER_MAX },
+	{ "max_alarm", SENSORS_SUBFEATURE_POWER_MAX_ALARM },
+	{ "crit", SENSORS_SUBFEATURE_POWER_CRIT },
+	{ "crit_alarm", SENSORS_SUBFEATURE_POWER_CRIT_ALARM },
+	{ "average_interval", SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match energy_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_ENERGY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match curr_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_CURR_INPUT },
+	{ "min", SENSORS_SUBFEATURE_CURR_MIN },
+	{ "max", SENSORS_SUBFEATURE_CURR_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_CURR_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_CURR_CRIT },
+	{ "average", SENSORS_SUBFEATURE_CURR_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_CURR_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_CURR_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_CURR_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_CURR_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_CURR_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_CURR_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_CURR_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_CURR_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match humidity_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_HUMIDITY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match cpu_matches[] = {
+	{ "vid", SENSORS_SUBFEATURE_VID },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match intrusion_matches[] = {
+	{ "alarm", SENSORS_SUBFEATURE_INTRUSION_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_INTRUSION_BEEP },
+	{ NULL, 0 }
+};
+static struct feature_type_match matches[] = {
+	{ "temp%d%c", temp_matches },
+	{ "in%d%c", in_matches },
+	{ "fan%d%c", fan_matches },
+	{ "cpu%d%c", cpu_matches },
+	{ "power%d%c", power_matches },
+	{ "curr%d%c", curr_matches },
+	{ "energy%d%c", energy_matches },
+	{ "intrusion%d%c", intrusion_matches },
+	{ "humidity%d%c", humidity_matches },
+};
+
+/* Return the subfeature type and channel number based on the subfeature
+   name */
+static
+sensors_subfeature_type sensors_subfeature_get_type(const char *name, int *nr)
+{
+	char c;
+	int i, count;
+	const struct subfeature_type_match *submatches;
+
+	/* Special case */
+	if (!strcmp(name, "beep_enable")) {
+		*nr = 0;
+		return SENSORS_SUBFEATURE_BEEP_ENABLE;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(matches); i++)
+		if ((count = sscanf(name, matches[i].name, nr, &c)))
+			break;
+
+	if (i == ARRAY_SIZE(matches) || count != 2 || c != '_')
+		return SENSORS_SUBFEATURE_UNKNOWN;  /* no match */
+
+	submatches = matches[i].submatches;
+	name = strchr(name + 3, '_') + 1;
+	for (i = 0; submatches[i].name != NULL; i++)
+		if (!strcmp(name, submatches[i].name))
+			return submatches[i].type;
+
+	return SENSORS_SUBFEATURE_UNKNOWN;
+}
+
+static int sensors_compute_max(void)
+{
+	int i, j, max, offset;
+	const struct subfeature_type_match *submatches;
+	sensors_feature_type ftype;
+
+	max = 0;
+	for (i = 0; i < ARRAY_SIZE(matches); i++) {
+		submatches = matches[i].submatches;
+		for (j = 0; submatches[j].name != NULL; j++) {
+			ftype = submatches[j].type >> 8;
+
+			if (ftype < SENSORS_FEATURE_VID) {
+				offset = submatches[j].type & 0x7F;
+				if (offset >= max)
+					max = offset + 1;
+			} else {
+				offset = submatches[j].type & 0xFF;
+				if (offset >= max * 2)
+					max = ((offset + 1) + 1) / 2;
+			}
+		}
+	}
+
+	return max;
+}
+
+static int sensors_get_attr_mode(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	struct stat st;
+	int mode = 0;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+	if (!stat(path, &st)) {
+		if (st.st_mode & S_IRUSR)
+			mode |= SENSORS_MODE_R;
+		if (st.st_mode & S_IWUSR)
+			mode |= SENSORS_MODE_W;
+	}
+	return mode;
+}
+
+static int sensors_read_dynamic_chip(sensors_chip_features *chip,
+				     const char *dev_path)
+{
+	int i, fnum = 0, sfnum = 0, prev_slot;
+	static int max_subfeatures;
+	DIR *dir;
+	struct dirent *ent;
+	sensors_subfeature *all_subfeatures;
+	sensors_subfeature *dyn_subfeatures;
+	sensors_feature *dyn_features;
+	sensors_feature_type ftype;
+	sensors_subfeature_type sftype;
+
+	if (!(dir = opendir(dev_path)))
+		return -errno;
+
+	/* Dynamically figure out the max number of subfeatures */
+	if (!max_subfeatures)
+		max_subfeatures = sensors_compute_max();
+
+	/* We use a large sparse table at first to store all found
+	   subfeatures, so that we can store them sorted at type and index
+	   and then later create a dense sorted table. */
+	all_subfeatures = calloc(ALL_POSSIBLE_SUBFEATURES,
+				 sizeof(sensors_subfeature));
+	if (!all_subfeatures)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	while ((ent = readdir(dir))) {
+		char *name;
+		int nr;
+
+		/* Skip directories and symlinks */
+		if (ent->d_type != DT_REG)
+			continue;
+
+		name = ent->d_name;
+
+		sftype = sensors_subfeature_get_type(name, &nr);
+		if (sftype == SENSORS_SUBFEATURE_UNKNOWN)
+			continue;
+		ftype = sftype >> 8;
+
+		/* Adjust the channel number */
+		switch (ftype) {
+		case SENSORS_FEATURE_FAN:
+		case SENSORS_FEATURE_TEMP:
+		case SENSORS_FEATURE_POWER:
+		case SENSORS_FEATURE_ENERGY:
+		case SENSORS_FEATURE_CURR:
+		case SENSORS_FEATURE_HUMIDITY:
+			nr--;
+			break;
+		default:
+			break;
+		}
+
+		if (nr < 0 || nr >= MAX_SENSORS_PER_TYPE) {
+			/* More sensors of one type than MAX_SENSORS_PER_TYPE,
+			   we have to ignore it */
+#ifdef DEBUG
+			sensors_fatal_error(__func__,
+					    "Increase MAX_SENSORS_PER_TYPE!");
+#endif
+			continue;
+		}
+
+		/* "calculate" a place to store the subfeature in our sparse,
+		   sorted table */
+		switch (ftype) {
+		case SENSORS_FEATURE_VID:
+		case SENSORS_FEATURE_INTRUSION:
+			i = SUB_OFFSET_OTHER +
+			    (ftype - SENSORS_FEATURE_VID) * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE + (sftype & 0xFF);
+			break;
+		case SENSORS_FEATURE_BEEP_ENABLE:
+			i = SUB_OFFSET_MISC +
+			    (ftype - SENSORS_FEATURE_BEEP_ENABLE);
+			break;
+		default:
+			i = ftype * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE +
+			    ((sftype & 0x80) >> 7) * max_subfeatures +
+			    (sftype & 0x7F);
+		}
+
+		if (all_subfeatures[i].name) {
+#ifdef DEBUG
+			sensors_fatal_error(__func__, "Duplicate subfeature");
+#endif
+			continue;
+		}
+
+		/* fill in the subfeature members */
+		all_subfeatures[i].type = sftype;
+		all_subfeatures[i].name = strdup(name);
+		if (!all_subfeatures[i].name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		/* Other and misc subfeatures are never scaled */
+		if (sftype < SENSORS_SUBFEATURE_VID && !(sftype & 0x80))
+			all_subfeatures[i].flags |= SENSORS_COMPUTE_MAPPING;
+		all_subfeatures[i].flags |= sensors_get_attr_mode(dev_path, name);
+
+		sfnum++;
+	}
+	closedir(dir);
+
+	if (!sfnum) { /* No subfeature */
+		chip->subfeature = NULL;
+		goto exit_free;
+	}
+
+	/* How many main features? */
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+		}
+	}
+
+	dyn_subfeatures = calloc(sfnum, sizeof(sensors_subfeature));
+	dyn_features = calloc(fnum, sizeof(sensors_feature));
+	if (!dyn_subfeatures || !dyn_features)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	/* Copy from the sparse array to the compact array */
+	sfnum = 0;
+	fnum = -1;
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		/* New main feature? */
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			ftype = all_subfeatures[i].type >> 8;
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+
+			dyn_features[fnum].name = get_feature_name(ftype,
+						all_subfeatures[i].name);
+			dyn_features[fnum].number = fnum;
+			dyn_features[fnum].first_subfeature = sfnum;
+			dyn_features[fnum].type = ftype;
+		}
+
+		dyn_subfeatures[sfnum] = all_subfeatures[i];
+		dyn_subfeatures[sfnum].number = sfnum;
+		/* Back to the feature */
+		dyn_subfeatures[sfnum].mapping = fnum;
+
+		sfnum++;
+	}
+
+	chip->subfeature = dyn_subfeatures;
+	chip->subfeature_count = sfnum;
+	chip->feature = dyn_features;
+	chip->feature_count = ++fnum;
+
+exit_free:
+	free(all_subfeatures);
+	return 0;
+}
+
+/* returns !0 if sysfs filesystem was found, 0 otherwise */
+int sensors_init_sysfs(void)
+{
+	struct statfs statfsbuf;
+
+	snprintf(sensors_sysfs_mount, NAME_MAX, "%s", "/sys");
+	if (statfs(sensors_sysfs_mount, &statfsbuf) < 0
+	 || statfsbuf.f_type != SYSFS_MAGIC)
+		return 0;
+
+	return 1;
+}
+
+/* returns: number of devices added (0 or 1) if successful, <0 otherwise */
+static int sensors_read_one_sysfs_chip(const char *dev_path,
+				       const char *dev_name,
+				       const char *hwmon_path)
+{
+	int domain, bus, slot, fn, vendor, product, id;
+	int err = -SENSORS_ERR_KERNEL;
+	char *bus_attr;
+	char bus_path[NAME_MAX];
+	char linkpath[NAME_MAX];
+	char subsys_path[NAME_MAX], *subsys;
+	int sub_len;
+	sensors_chip_features entry;
+
+	/* ignore any device without name attribute */
+	if (!(entry.chip.prefix = sysfs_read_attr(hwmon_path, "name")))
+		return 0;
+
+	entry.chip.path = strdup(hwmon_path);
+	if (!entry.chip.path)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	if (dev_path == NULL) {
+		/* Virtual device */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+		entry.chip.bus.nr = 0;
+		/* For now we assume that virtual devices are unique */
+		entry.chip.addr = 0;
+		goto done;
+	}
+
+	/* Find bus type */
+	snprintf(linkpath, NAME_MAX, "%s/subsystem", dev_path);
+	sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	if (sub_len < 0 && errno == ENOENT) {
+		/* Fallback to "bus" link for kernels <= 2.6.17 */
+		snprintf(linkpath, NAME_MAX, "%s/bus", dev_path);
+		sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	}
+	if (sub_len < 0) {
+		/* Older kernels (<= 2.6.11) have neither the subsystem
+		   symlink nor the bus symlink */
+		if (errno == ENOENT)
+			subsys = NULL;
+		else
+			goto exit_free;
+	} else {
+		subsys_path[sub_len] = '\0';
+		subsys = strrchr(subsys_path, '/') + 1;
+	}
+
+	if ((!subsys || !strcmp(subsys, "i2c")) &&
+	    sscanf(dev_name, "%hd-%x", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* find out if legacy ISA or not */
+		if (entry.chip.bus.nr == 9191) {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+			entry.chip.bus.nr = 0;
+		} else {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_I2C;
+			snprintf(bus_path, sizeof(bus_path),
+				"%s/class/i2c-adapter/i2c-%d/device",
+				sensors_sysfs_mount, entry.chip.bus.nr);
+
+			if ((bus_attr = sysfs_read_attr(bus_path, "name"))) {
+				if (!strncmp(bus_attr, "ISA ", 4)) {
+					entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+					entry.chip.bus.nr = 0;
+				}
+
+				free(bus_attr);
+			}
+		}
+	} else
+	if ((!subsys || !strcmp(subsys, "spi")) &&
+	    sscanf(dev_name, "spi%hd.%d", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* SPI */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_SPI;
+	} else
+	if ((!subsys || !strcmp(subsys, "pci")) &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &domain, &bus, &slot, &fn) == 4) {
+		/* PCI */
+		entry.chip.addr = (domain << 16) + (bus << 8) + (slot << 3) + fn;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_PCI;
+		entry.chip.bus.nr = 0;
+	} else
+	if ((!subsys || !strcmp(subsys, "platform") ||
+			!strcmp(subsys, "of_platform"))) {
+		/* must be new ISA (platform driver) */
+		if (sscanf(dev_name, "%*[a-z0-9_].%d", &entry.chip.addr) != 1)
+			entry.chip.addr = 0;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+		entry.chip.bus.nr = 0;
+	} else if (subsys && !strcmp(subsys, "acpi")) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ACPI;
+		/* For now we assume that acpi devices are unique */
+		entry.chip.bus.nr = 0;
+		entry.chip.addr = 0;
+	} else
+	if (subsys && !strcmp(subsys, "hid") &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &bus, &vendor, &product, &id) == 4) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_HID;
+		/* As of kernel 2.6.32, the hid device names don't look good */
+		entry.chip.bus.nr = bus;
+		entry.chip.addr = id;
+	} else {
+		/* Ignore unknown device */
+		err = 0;
+		goto exit_free;
+	}
+
+done:
+	if (sensors_read_dynamic_chip(&entry, hwmon_path) < 0)
+		goto exit_free;
+	if (!entry.subfeature) { /* No subfeature, discard chip */
+		err = 0;
+		goto exit_free;
+	}
+	sensors_add_proc_chips(&entry);
+
+	return 1;
+
+exit_free:
+	free(entry.chip.prefix);
+	free(entry.chip.path);
+	return err;
+}
+
+static int sensors_add_hwmon_device_compat(const char *path,
+					   const char *dev_name)
+{
+	int err;
+
+	err = sensors_read_one_sysfs_chip(path, dev_name, path);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_read_sysfs_chips_compat(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_busdev("i2c", sensors_add_hwmon_device_compat);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+static int sensors_add_hwmon_device(const char *path, const char *classdev)
+{
+	char linkpath[NAME_MAX];
+	char device[NAME_MAX], *device_p;
+	int dev_len, err;
+	(void)classdev; /* hide warning */
+
+	snprintf(linkpath, NAME_MAX, "%s/device", path);
+	dev_len = readlink(linkpath, device, NAME_MAX - 1);
+	if (dev_len < 0) {
+		/* No device link? Treat as virtual */
+		err = sensors_read_one_sysfs_chip(NULL, NULL, path);
+	} else {
+		device[dev_len] = '\0';
+		device_p = strrchr(device, '/') + 1;
+
+		/* The attributes we want might be those of the hwmon class
+		   device, or those of the device itself. */
+		err = sensors_read_one_sysfs_chip(linkpath, device_p, path);
+		if (err == 0)
+			err = sensors_read_one_sysfs_chip(linkpath, device_p,
+							  linkpath);
+	}
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_chips(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("hwmon", sensors_add_hwmon_device);
+	if (ret == ENOENT) {
+		/* compatibility function for kernel 2.6.n where n <= 13 */
+		return sensors_read_sysfs_chips_compat();
+	}
+
+	if (ret > 0)
+		ret = -SENSORS_ERR_KERNEL;
+	return ret;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_add_i2c_bus(const char *path, const char *classdev)
+{
+	sensors_bus entry;
+
+	if (sscanf(classdev, "i2c-%hd", &entry.bus.nr) != 1 ||
+	    entry.bus.nr == 9191) /* legacy ISA */
+		return 0;
+	entry.bus.type = SENSORS_BUS_TYPE_I2C;
+
+	/* Get the adapter name from the classdev "name" attribute
+	 * (Linux 2.6.20 and later). If it fails, fall back to
+	 * the device "name" attribute (for older kernels). */
+	entry.adapter = sysfs_read_attr(path, "name");
+	if (!entry.adapter)
+		entry.adapter = sysfs_read_attr(path, "device/name");
+	if (entry.adapter)
+		sensors_add_proc_bus(&entry);
+
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_bus(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("i2c-adapter", sensors_add_i2c_bus);
+	if (ret == ENOENT)
+		ret = sysfs_foreach_busdev("i2c", sensors_add_i2c_bus);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value)
+{
+	char n[NAME_MAX];
+	int f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = open(n, O_RDONLY)) != -1) {
+		int res, err = 0;
+		char buf[512];
+		int count;
+
+		errno = 0;
+		if ((count = read(f, buf, sizeof(buf) - 1)) == -1) {
+			if (errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else 
+				err = -SENSORS_ERR_ACCESS_R;
+		} else {
+			buf[count] = '\0';
+			errno = 0;
+			res = sscanf(buf, "%lf", value);
+			if (res == EOF && errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else if (res != 1)
+				err = -SENSORS_ERR_ACCESS_R;
+		}
+		res = close(f);
+		if (err)
+			return err;
+
+		if (res != 0) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_R;
+		}
+		if (!sensors_sysfs_no_scaling)
+			*value /= get_type_scaling(subfeature->type);
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value)
+{
+	char n[NAME_MAX];
+	FILE *f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = fopen(n, "w"))) {
+		int res, err = 0;
+
+		if (!sensors_sysfs_no_scaling)
+			value *= get_type_scaling(subfeature->type);
+		res = fprintf(f, "%d", (int) value);
+		if (res == -EIO)
+			err = -SENSORS_ERR_IO;
+		else if (res < 0)
+			err = -SENSORS_ERR_ACCESS_W;
+		res = fclose(f);
+		if (err)
+			return err;
+
+		if (res == EOF) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_W;
+		}
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
diff --git a/tools/gator/daemon/libsensors/sysfs.h b/tools/gator/daemon/libsensors/sysfs.h
new file mode 100644
index 000000000000..38584afd028e
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.h
@@ -0,0 +1,43 @@
+/*
+    sysfs.h - part of libsensors, a library for reading Linux sensor data
+    Copyright (C)             Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef SENSORS_LIB_SYSFS_H
+#define SENSORS_LIB_SYSFS_H
+
+extern char sensors_sysfs_mount[];
+
+int sensors_init_sysfs(void);
+
+int sensors_read_sysfs_chips(void);
+
+int sensors_read_sysfs_bus(void);
+
+/* Read a value out of a sysfs attribute file */
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value);
+
+/* Write a value to a sysfs attribute file */
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value);
+
+#endif /* !SENSORS_LIB_SYSFS_H */
diff --git a/tools/gator/daemon/libsensors/version.h b/tools/gator/daemon/libsensors/version.h
new file mode 100644
index 000000000000..76ceb08c29d0
--- /dev/null
+++ b/tools/gator/daemon/libsensors/version.h
@@ -0,0 +1 @@
+#define LM_VERSION "3.3.2"
diff --git a/tools/gator/daemon/main.cpp b/tools/gator/daemon/main.cpp
new file mode 100644
index 000000000000..fbce1e15d0d0
--- /dev/null
+++ b/tools/gator/daemon/main.cpp
@@ -0,0 +1,584 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <arpa/inet.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "CCNDriver.h"
+#include "Child.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+extern Child* child;
+static int shutdownFilesystem();
+static pthread_mutex_t numSessions_mutex;
+static OlyServerSocket* sock = NULL;
+static Monitor monitor;
+static int numSessions = 0;
+static bool driverRunningAtStart = false;
+static bool driverMountedAtStart = false;
+
+struct cmdline_t {
+	char *module;
+	int port;
+	bool update;
+};
+
+#define DEFAULT_PORT 8080
+
+void cleanUp() {
+	if (shutdownFilesystem() == -1) {
+		logg->logMessage("Error shutting down gator filesystem");
+	}
+	delete sock;
+	delete util;
+	delete logg;
+}
+
+// CTRL C Signal Handler
+static void handler(int signum) {
+	logg->logMessage("Received signal %d, gator daemon exiting", signum);
+
+	// Case 1: both child and parent receive the signal
+	if (numSessions > 0) {
+		// Arbitrary sleep of 1 second to give time for the child to exit;
+		// if something bad happens, continue the shutdown process regardless
+		sleep(1);
+	}
+
+	// Case 2: only the parent received the signal
+	if (numSessions > 0) {
+		// Kill child threads - the first signal exits gracefully
+		logg->logMessage("Killing process group as %d child was running when signal was received", numSessions);
+		kill(0, SIGINT);
+
+		// Give time for the child to exit
+		sleep(1);
+
+		if (numSessions > 0) {
+			// The second signal force kills the child
+			logg->logMessage("Force kill the child");
+			kill(0, SIGINT);
+			// Again, sleep for 1 second
+			sleep(1);
+
+			if (numSessions > 0) {
+				// Something bad has really happened; the child is not exiting and therefore may hold the /dev/gator resource open
+				printf("Unable to kill the gatord child process, thus gator.ko may still be loaded.\n");
+			}
+		}
+	}
+
+	cleanUp();
+	exit(0);
+}
+
+// Child exit Signal Handler
+static void child_exit(int) {
+	int status;
+	int pid = wait(&status);
+	if (pid != -1) {
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions--;
+		pthread_mutex_unlock(&numSessions_mutex);
+		logg->logMessage("Child process %d exited with status %d", pid, status);
+	}
+}
+
+static const int UDP_REQ_PORT = 30001;
+
+typedef struct {
+	char rviHeader[8];
+	uint32_t messageID;
+	uint8_t ethernetAddress[8];
+	uint32_t ethernetType;
+	uint32_t dhcp;
+	char dhcpName[40];
+	uint32_t ipAddress;
+	uint32_t defaultGateway;
+	uint32_t subnetMask;
+	uint32_t activeConnections;
+} RVIConfigureInfo;
+
+static const char DST_REQ[] = { 'D', 'S', 'T', '_', 'R', 'E', 'Q', ' ', 0, 0, 0, 0x64 };
+
+class UdpListener {
+public:
+	UdpListener() : mDstAns(), mReq(-1) {}
+
+	void setup(int port) {
+		mReq = udpPort(UDP_REQ_PORT);
+
+		// Format the answer buffer
+		memset(&mDstAns, 0, sizeof(mDstAns));
+		memcpy(mDstAns.rviHeader, "STR_ANS ", sizeof(mDstAns.rviHeader));
+		if (gethostname(mDstAns.dhcpName, sizeof(mDstAns.dhcpName) - 1) != 0) {
+			logg->logError(__FILE__, __LINE__, "gethostname failed");
+			handleException();
+		}
+		// Subvert the defaultGateway field for the port number
+		if (port != DEFAULT_PORT) {
+			mDstAns.defaultGateway = port;
+		}
+		// Subvert the subnetMask field for the protocol version
+		mDstAns.subnetMask = PROTOCOL_VERSION;
+	}
+
+	int getReq() const {
+		return mReq;
+	}
+
+	void handle() {
+		char buf[128];
+		struct sockaddr_in6 sockaddr;
+		socklen_t addrlen;
+		int read;
+		addrlen = sizeof(sockaddr);
+		read = recvfrom(mReq, &buf, sizeof(buf), 0, (struct sockaddr *)&sockaddr, &addrlen);
+		if (read < 0) {
+			logg->logError(__FILE__, __LINE__, "recvfrom failed");
+			handleException();
+		} else if ((read == 12) && (memcmp(buf, DST_REQ, sizeof(DST_REQ)) == 0)) {
+			// Don't care if sendto fails - gatord shouldn't exit because of it and Streamline will retry
+			sendto(mReq, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen);
+		}
+	}
+
+	void close() {
+		::close(mReq);
+	}
+
+private:
+	int udpPort(int port) {
+		int s;
+		struct sockaddr_in6 sockaddr;
+		int on;
+		int family = AF_INET6;
+
+		s = socket_cloexec(AF_INET6, SOCK_DGRAM, IPPROTO_UDP);
+		if (s == -1) {
+			family = AF_INET;
+			s = socket_cloexec(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+			if (s == -1) {
+				logg->logError(__FILE__, __LINE__, "socket failed");
+				handleException();
+			}
+		}
+
+		on = 1;
+		if (setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+			logg->logError(__FILE__, __LINE__, "setsockopt failed");
+			handleException();
+		}
+
+		memset((void*)&sockaddr, 0, sizeof(sockaddr));
+		sockaddr.sin6_family = family;
+		sockaddr.sin6_port = htons(port);
+		sockaddr.sin6_addr = in6addr_any;
+		if (bind(s, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) < 0) {
+			logg->logError(__FILE__, __LINE__, "socket failed");
+			handleException();
+		}
+
+		return s;
+	}
+
+	RVIConfigureInfo mDstAns;
+	int mReq;
+};
+
+static UdpListener udpListener;
+
+// retval: -1 = failure; 0 = was already mounted; 1 = successfully mounted
+static int mountGatorFS() {
+	// If already mounted,
+	if (access("/dev/gator/buffer", F_OK) == 0) {
+		return 0;
+	}
+
+	// else, mount the filesystem
+	mkdir("/dev/gator", S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+	if (mount("nodev", "/dev/gator", "gatorfs", 0, NULL) != 0) {
+		return -1;
+	} else {
+		return 1;
+	}
+}
+
+static bool init_module (const char * const location) {
+	bool ret(false);
+	const int fd = open(location, O_RDONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		struct stat st;
+		if (fstat(fd, &st) == 0) {
+			void * const p = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+			if (p != MAP_FAILED) {
+				if (syscall(__NR_init_module, p, (unsigned long)st.st_size, "") == 0) {
+					ret = true;
+				}
+				munmap(p, st.st_size);
+			}
+		}
+		close(fd);
+	}
+
+	return ret;
+}
+
+static bool setupFilesystem(char* module) {
+	if (module) {
+		// unmount and rmmod if the module was specified on the commandline, i.e. ensure that the specified module is indeed running
+		shutdownFilesystem();
+
+		// if still mounted
+		if (access("/dev/gator/buffer", F_OK) == 0) {
+			logg->logError(__FILE__, __LINE__, "Unable to remove the running gator.ko. Manually remove the module or use the running module by not specifying one on the commandline");
+			handleException();
+		}
+	}
+
+	const int retval = mountGatorFS();
+	if (retval == 1) {
+		logg->logMessage("Driver already running at startup");
+		driverRunningAtStart = true;
+	} else if (retval == 0) {
+		logg->logMessage("Driver already mounted at startup");
+		driverRunningAtStart = driverMountedAtStart = true;
+	} else {
+		char command[256]; // arbitrarily large amount
+		char location[256]; // arbitrarily large amount
+
+		if (module) {
+			strncpy(location, module, sizeof(location));
+		} else {
+			// Is the driver co-located in the same directory?
+			if (util->getApplicationFullPath(location, sizeof(location)) != 0) { // allow some buffer space
+				logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+			}
+			strncat(location, "gator.ko", sizeof(location) - strlen(location) - 1);
+		}
+
+		if (access(location, F_OK) == -1) {
+			if (module == NULL) {
+				// The gator kernel is not already loaded and unable to locate gator.ko in the default location
+				return false;
+			} else {
+				// gator location specified on the command line but it was not found
+				logg->logError(__FILE__, __LINE__, "gator module not found at %s", location);
+				handleException();
+			}
+		}
+
+		// Load driver
+		bool success = init_module(location);
+		if (!success) {
+			logg->logMessage("init_module failed, trying insmod");
+			snprintf(command, sizeof(command), "insmod %s >/dev/null 2>&1", location);
+			if (system(command) != 0) {
+				logg->logMessage("Unable to load gator.ko driver with command: %s", command);
+				logg->logError(__FILE__, __LINE__, "Unable to load (insmod) gator.ko driver:\n  >>> gator.ko must be built against the current kernel version & configuration\n  >>> See dmesg for more details");
+				handleException();
+			}
+		}
+
+		if (mountGatorFS() == -1) {
+			logg->logError(__FILE__, __LINE__, "Unable to mount the gator filesystem needed for profiling.");
+			handleException();
+		}
+	}
+
+	return true;
+}
+
+static int shutdownFilesystem() {
+	if (driverMountedAtStart == false) {
+		umount("/dev/gator");
+	}
+	if (driverRunningAtStart == false) {
+		if (syscall(__NR_delete_module, "gator", O_NONBLOCK) != 0) {
+			logg->logMessage("delete_module failed, trying rmmod");
+			if (system("rmmod gator >/dev/null 2>&1") != 0) {
+				return -1;
+			}
+		}
+	}
+
+	return 0; // success
+}
+
+static const char OPTSTRING[] = "hvudap:s:c:e:m:o:";
+
+static bool hasDebugFlag(int argc, char** argv) {
+	int c;
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		if (c == 'd') {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static struct cmdline_t parseCommandLine(int argc, char** argv) {
+	struct cmdline_t cmdline;
+	cmdline.port = DEFAULT_PORT;
+	cmdline.module = NULL;
+	cmdline.update = false;
+	char version_string[256]; // arbitrary length to hold the version information
+	int c;
+
+	// build the version string
+	if (PROTOCOL_VERSION < PROTOCOL_DEV) {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord version %d (DS-5 v5.%d)", PROTOCOL_VERSION, PROTOCOL_VERSION);
+	} else {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord development version %d", PROTOCOL_VERSION);
+	}
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		switch (c) {
+			case 'c':
+				gSessionData->mConfigurationXMLPath = optarg;
+				break;
+			case 'd':
+				// Already handled
+				break;
+			case 'e':
+				gSessionData->mEventsXMLPath = optarg;
+				break;
+			case 'm':
+				cmdline.module = optarg;
+				break;
+			case 'p':
+				cmdline.port = strtol(optarg, NULL, 10);
+				break;
+			case 's':
+				gSessionData->mSessionXMLPath = optarg;
+				break;
+			case 'o':
+				gSessionData->mTargetPath = optarg;
+				break;
+			case 'u':
+				cmdline.update = true;
+				break;
+			case 'a':
+				gSessionData->mAllowCommands = true;
+				break;
+			case 'h':
+			case '?':
+				logg->logError(__FILE__, __LINE__,
+					"%s. All parameters are optional:\n"
+					"-c config_xml   path and filename of the configuration.xml to use\n"
+					"-e events_xml   path and filename of the events.xml to use\n"
+					"-h              this help page\n"
+					"-m module       path and filename of gator.ko\n"
+					"-p port_number  port upon which the server listens; default is 8080\n"
+					"-s session_xml  path and filename of a session.xml used for local capture\n"
+					"-o apc_dir      path and name of the output for a local capture\n"
+					"-v              version information\n"
+					"-d              enable debug messages\n"
+					"-a              allow the user user to provide a command to run at the start of a capture"
+					, version_string);
+				handleException();
+				break;
+			case 'v':
+				logg->logError(__FILE__, __LINE__, version_string);
+				handleException();
+				break;
+		}
+	}
+
+	// Error checking
+	if (cmdline.port != DEFAULT_PORT && gSessionData->mSessionXMLPath != NULL) {
+		logg->logError(__FILE__, __LINE__, "Only a port or a session xml can be specified, not both");
+		handleException();
+	}
+
+	if (gSessionData->mTargetPath != NULL && gSessionData->mSessionXMLPath == NULL) {
+		logg->logError(__FILE__, __LINE__, "Missing -s command line option required for a local capture.");
+		handleException();
+	}
+
+	if (optind < argc) {
+		logg->logError(__FILE__, __LINE__, "Unknown argument: %s. Use '-h' for help.", argv[optind]);
+		handleException();
+	}
+
+	return cmdline;
+}
+
+static void handleClient() {
+	OlySocket client(sock->acceptConnection());
+
+	int pid = fork();
+	if (pid < 0) {
+		// Error
+		logg->logError(__FILE__, __LINE__, "Fork process failed. Please power cycle the target device if this error persists.");
+	} else if (pid == 0) {
+		// Child
+		sock->closeServerSocket();
+		udpListener.close();
+		monitor.close();
+		child = new Child(&client, numSessions + 1);
+		child->run();
+		delete child;
+		exit(0);
+	} else {
+		// Parent
+		client.closeSocket();
+
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions++;
+		pthread_mutex_unlock(&numSessions_mutex);
+
+		// Maximum number of connections is 2
+		int wait = 0;
+		while (numSessions > 1) {
+			// Throttle until one of the children exits before continuing to accept another socket connection
+			logg->logMessage("%d sessions active!", numSessions);
+			if (wait++ >= 10) { // Wait no more than 10 seconds
+				// Kill last created child
+				kill(pid, SIGALRM);
+				break;
+			}
+			sleep(1);
+		}
+	}
+}
+
+// Gator data flow: collector -> collector fifo -> sender
+int main(int argc, char** argv) {
+	// Ensure proper signal handling by making gatord the process group leader
+	//   e.g. it may not be the group leader when launched as 'sudo gatord'
+	setsid();
+
+  // Set up global thread-safe logging
+	logg = new Logging(hasDebugFlag(argc, argv));
+	// Global data class
+	gSessionData = new SessionData();
+	// Set up global utility class
+	util = new OlyUtility();
+
+	// Initialize drivers
+	new CCNDriver();
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-main", 0, 0, 0);
+	pthread_mutex_init(&numSessions_mutex, NULL);
+
+	signal(SIGINT, handler);
+	signal(SIGTERM, handler);
+	signal(SIGABRT, handler);
+
+	// Set to high priority
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), -19) == -1) {
+		logg->logMessage("setpriority() failed");
+	}
+
+	// Parse the command line parameters
+	struct cmdline_t cmdline = parseCommandLine(argc, argv);
+
+	if (cmdline.update) {
+		return update(argv[0]);
+	}
+
+	// Verify root permissions
+	uid_t euid = geteuid();
+	if (euid) {
+		logg->logError(__FILE__, __LINE__, "gatord must be launched with root privileges");
+		handleException();
+	}
+
+	// Call before setting up the SIGCHLD handler, as system() spawns child processes
+	if (!setupFilesystem(cmdline.module)) {
+		logg->logMessage("Unable to setup gatorfs, trying perf");
+		if (!gSessionData->perf.setup()) {
+			logg->logError(__FILE__, __LINE__,
+				       "Unable to locate gator.ko driver:\n"
+				       "  >>> gator.ko should be co-located with gatord in the same directory\n"
+				       "  >>> OR insmod gator.ko prior to launching gatord\n"
+				       "  >>> OR specify the location of gator.ko on the command line\n"
+				       "  >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER) support to collect data via userspace only");
+			handleException();
+		}
+	}
+
+	{
+		EventsXML eventsXML;
+		mxml_node_t *xml = eventsXML.getTree();
+		// Initialize all drivers
+		for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+			driver->readEvents(xml);
+		}
+		mxmlDelete(xml);
+	}
+
+	// Handle child exit codes
+	signal(SIGCHLD, child_exit);
+
+	// Ignore the SIGPIPE signal so that any send to a broken socket will return an error code instead of asserting a signal
+	// Handling the error at the send function call is much easier than trying to do anything intelligent in the sig handler
+	signal(SIGPIPE, SIG_IGN);
+
+	// If the command line argument is a session xml file, no need to open a socket
+	if (gSessionData->mSessionXMLPath) {
+		child = new Child();
+		child->run();
+		delete child;
+	} else {
+		gSessionData->annotateListener.setup();
+		sock = new OlyServerSocket(cmdline.port);
+		udpListener.setup(cmdline.port);
+		if (!monitor.init() ||
+				!monitor.add(sock->getFd()) ||
+				!monitor.add(udpListener.getReq()) ||
+				!monitor.add(gSessionData->annotateListener.getFd()) ||
+				false) {
+			logg->logError(__FILE__, __LINE__, "Monitor setup failed");
+			handleException();
+		}
+		// Forever loop, can be exited via a signal or exception
+		while (1) {
+			struct epoll_event events[2];
+			logg->logMessage("Waiting on connection...");
+			int ready = monitor.wait(events, ARRAY_LENGTH(events), -1);
+			if (ready < 0) {
+				logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+				handleException();
+			}
+			for (int i = 0; i < ready; ++i) {
+				if (events[i].data.fd == sock->getFd()) {
+					handleClient();
+				} else if (events[i].data.fd == udpListener.getReq()) {
+					udpListener.handle();
+				} else if (events[i].data.fd == gSessionData->annotateListener.getFd()) {
+					gSessionData->annotateListener.handle();
+				}
+			}
+		}
+	}
+
+	cleanUp();
+	return 0;
+}
diff --git a/tools/gator/daemon/mxml/COPYING b/tools/gator/daemon/mxml/COPYING
new file mode 100644
index 000000000000..4d0aa78af224
--- /dev/null
+++ b/tools/gator/daemon/mxml/COPYING
@@ -0,0 +1,507 @@
+			   Mini-XML License
+			  September 18, 2010
+
+
+The Mini-XML library and included programs are provided under the
+terms of the GNU Library General Public License version 2 (LGPL2)
+with the following exceptions:
+
+  1. Static linking of applications to the Mini-XML library
+does not constitute a derivative work and does not require
+the author to provide source code for the application, use
+the shared Mini-XML libraries, or link their applications
+against a user-supplied version of Mini-XML.
+
+If you link the application to a modified version of
+Mini-XML, then the changes to Mini-XML must be provided
+under the terms of the LGPL2 in sections 1, 2, and 4.
+
+  2. You do not have to provide a copy of the Mini-XML license
+with programs that are linked to the Mini-XML library, nor
+do you have to identify the Mini-XML license in your
+program or documentation as required by section 6 of the
+LGPL2.
+
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+			 Version 2, June 1991
+
+	  Copyright (C) 1991 Free Software Foundation, Inc.
+       59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+     Everyone is permitted to copy and distribute verbatim copies
+      of this license document, but changing it is not allowed.
+
+    [This is the first released version of the library GPL.  It is
+   numbered 2 because it goes with version 2 of the ordinary GPL.]
+
+			       Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Library General Public License, applies to some
+specially designated Free Software Foundation software, and to any
+other libraries whose authors decide to use it.  You can use it for
+your libraries, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if
+you distribute copies of the library, or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link a program with the library, you must provide
+complete object files to the recipients so that they can relink them
+with the library, after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  Our method of protecting your rights has two steps: (1) copyright
+the library, and (2) offer you this license which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  Also, for each distributor's protection, we want to make certain
+that everyone understands that there is no warranty for this free
+library.  If the library is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original
+version, so that any problems introduced by others will not reflect on
+the original authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that companies distributing free
+software will individually obtain patent licenses, thus in effect
+transforming the program into proprietary software.  To prevent this,
+we have made it clear that any patent must be licensed for everyone's
+free use or not licensed at all.
+
+  Most GNU software, including some libraries, is covered by the ordinary
+GNU General Public License, which was designed for utility programs.  This
+license, the GNU Library General Public License, applies to certain
+designated libraries.  This license is quite different from the ordinary
+one; be sure to read it in full, and don't assume that anything in it is
+the same as in the ordinary license.
+
+  The reason we have a separate public license for some libraries is that
+they blur the distinction we usually make between modifying or adding to a
+program and simply using it.  Linking a program with a library, without
+changing the library, is in some sense simply using the library, and is
+analogous to running a utility program or application program.  However, in
+a textual and legal sense, the linked executable is a combined work, a
+derivative of the original library, and the ordinary General Public License
+treats it as such.
+
+  Because of this blurred distinction, using the ordinary General
+Public License for libraries did not effectively promote software
+sharing, because most developers did not use the libraries.  We
+concluded that weaker conditions might promote sharing better.
+
+  However, unrestricted linking of non-free programs would deprive the
+users of those programs of all benefit from the free status of the
+libraries themselves.  This Library General Public License is intended to
+permit developers of non-free programs to use free libraries, while
+preserving your freedom as a user of such programs to change the free
+libraries that are incorporated in them.  (We have not seen how to achieve
+this as regards changes in header files, but we have achieved it as regards
+changes in the actual functions of the Library.)  The hope is that this
+will lead to faster development of free libraries.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, while the latter only
+works together with the library.
+
+  Note that it is possible for a library to be covered by the ordinary
+General Public License rather than by this special one.
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library which
+contains a notice placed by the copyright holder or other authorized
+party saying it may be distributed under the terms of this Library
+General Public License (also called "this License").  Each licensee is
+addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also compile or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    c) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    d) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the source code distributed need not include anything that is normally
+distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Library General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+			    NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+     Appendix: How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/mxml/config.h b/tools/gator/daemon/mxml/config.h
new file mode 100644
index 000000000000..ad6df1d7debe
--- /dev/null
+++ b/tools/gator/daemon/mxml/config.h
@@ -0,0 +1,96 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/*
+ * "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Configuration file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <ctype.h>
+
+
+/*
+ * Version number...
+ */
+
+#define MXML_VERSION "Mini-XML v2.8"
+
+
+/*
+ * Inline function support...
+ */
+
+#define inline
+
+
+/*
+ * Long long support...
+ */
+
+#define HAVE_LONG_LONG 1
+
+
+/*
+ * Do we have the snprintf() and vsnprintf() functions?
+ */
+
+#define HAVE_SNPRINTF 1
+#define HAVE_VSNPRINTF 1
+
+
+/*
+ * Do we have the strXXX() functions?
+ */
+
+#define HAVE_STRDUP 1
+
+
+/*
+ * Do we have threading support?
+ */
+
+#define HAVE_PTHREAD_H 1
+
+
+/*
+ * Define prototypes for string functions as needed...
+ */
+
+#  ifndef HAVE_STRDUP
+extern char	*_mxml_strdup(const char *);
+#    define strdup _mxml_strdup
+#  endif /* !HAVE_STRDUP */
+
+extern char	*_mxml_strdupf(const char *, ...);
+extern char	*_mxml_vstrdupf(const char *, va_list);
+
+#  ifndef HAVE_SNPRINTF
+extern int	_mxml_snprintf(char *, size_t, const char *, ...);
+#    define snprintf _mxml_snprintf
+#  endif /* !HAVE_SNPRINTF */
+
+#  ifndef HAVE_VSNPRINTF
+extern int	_mxml_vsnprintf(char *, size_t, const char *, va_list);
+#    define vsnprintf _mxml_vsnprintf
+#  endif /* !HAVE_VSNPRINTF */
+
+/*
+ * End of "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-attr.c b/tools/gator/daemon/mxml/mxml-attr.c
new file mode 100644
index 000000000000..8e89cc1474f8
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-attr.c
@@ -0,0 +1,314 @@
+/*
+ * "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Attribute support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static int	mxml_set_attr(mxml_node_t *node, const char *name,
+		              char *value);
+
+
+/*
+ * 'mxmlElementDeleteAttr()' - Delete an attribute.
+ *
+ * @since Mini-XML 2.4@
+ */
+
+void
+mxmlElementDeleteAttr(mxml_node_t *node,/* I - Element */
+                      const char  *name)/* I - Attribute name */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementDeleteAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Delete this attribute...
+      */
+
+      free(attr->name);
+      free(attr->value);
+
+      i --;
+      if (i > 0)
+        memmove(attr, attr + 1, i * sizeof(mxml_attr_t));
+
+      node->value.element.num_attrs --;
+
+      if (node->value.element.num_attrs == 0)
+        free(node->value.element.attrs);
+      return;
+    }
+  }
+}
+
+
+/*
+ * 'mxmlElementGetAttr()' - Get an attribute.
+ *
+ * This function returns NULL if the node is not an element or the
+ * named attribute does not exist.
+ */
+
+const char *				/* O - Attribute value or NULL */
+mxmlElementGetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name)	/* I - Name of attribute */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementGetAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (NULL);
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+#ifdef DEBUG
+      printf("    Returning \"%s\"!\n", attr->value);
+#endif /* DEBUG */
+      return (attr->value);
+    }
+  }
+
+ /*
+  * Didn't find attribute, so return NULL...
+  */
+
+#ifdef DEBUG
+  puts("    Returning NULL!\n");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlElementSetAttr()' - Set an attribute.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new string value. The string value is copied
+ * into the element node. This function does nothing if the node is
+ * not an element.
+ */
+
+void
+mxmlElementSetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name,	/* I - Name of attribute */
+                   const char  *value)	/* I - Attribute value */
+{
+  char	*valuec;			/* Copy of value */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementSetAttr(node=%p, name=\"%s\", value=\"%s\")\n",
+          node, name ? name : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+  if (value)
+    valuec = strdup(value);
+  else
+    valuec = NULL;
+
+  if (mxml_set_attr(node, name, valuec))
+    free(valuec);
+}
+
+
+/*
+ * 'mxmlElementSetAttrf()' - Set an attribute with a formatted value.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new formatted string. The formatted string value is
+ * copied into the element node. This function does nothing if the node
+ * is not an element.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlElementSetAttrf(mxml_node_t *node,	/* I - Element node */
+                    const char  *name,	/* I - Name of attribute */
+                    const char  *format,/* I - Printf-style attribute value */
+		    ...)		/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument pointer */
+  char		*value;			/* Value */
+
+
+#ifdef DEBUG
+  fprintf(stderr,
+          "mxmlElementSetAttrf(node=%p, name=\"%s\", format=\"%s\", ...)\n",
+          node, name ? name : "(null)", format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name || !format)
+    return;
+
+ /*
+  * Format the value...
+  */
+
+  va_start(ap, format);
+  value = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  if (!value)
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+  else if (mxml_set_attr(node, name, value))
+    free(value);
+}
+
+
+/*
+ * 'mxml_set_attr()' - Set or add an attribute name/value pair.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_set_attr(mxml_node_t *node,	/* I - Element node */
+              const char  *name,	/* I - Attribute name */
+              char        *value)	/* I - Attribute value */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* New attribute */
+
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Free the old value as needed...
+      */
+
+      if (attr->value)
+        free(attr->value);
+
+      attr->value = value;
+
+      return (0);
+    }
+
+ /*
+  * Add a new attribute...
+  */
+
+  if (node->value.element.num_attrs == 0)
+    attr = malloc(sizeof(mxml_attr_t));
+  else
+    attr = realloc(node->value.element.attrs,
+                   (node->value.element.num_attrs + 1) * sizeof(mxml_attr_t));
+
+  if (!attr)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  node->value.element.attrs = attr;
+  attr += node->value.element.num_attrs;
+
+  if ((attr->name = strdup(name)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  attr->value = value;
+
+  node->value.element.num_attrs ++;
+
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-entity.c b/tools/gator/daemon/mxml/mxml-entity.c
new file mode 100644
index 000000000000..0d11df6a70bc
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-entity.c
@@ -0,0 +1,449 @@
+/*
+ * "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Character entity support code for Mini-XML, a small XML-like
+ * file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * 'mxmlEntityAddCallback()' - Add a callback to convert entities to Unicode.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlEntityAddCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to add */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  if (global->num_entity_cbs < (int)(sizeof(global->entity_cbs) / sizeof(global->entity_cbs[0])))
+  {
+    global->entity_cbs[global->num_entity_cbs] = cb;
+    global->num_entity_cbs ++;
+
+    return (0);
+  }
+  else
+  {
+    mxml_error("Unable to add entity callback!");
+
+    return (-1);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetName()' - Get the name that corresponds to the character value.
+ *
+ * If val does not need to be represented by a named entity, NULL is returned.
+ */
+
+const char *				/* O - Entity name or NULL */
+mxmlEntityGetName(int val)		/* I - Character value */
+{
+  switch (val)
+  {
+    case '&' :
+        return ("amp");
+
+    case '<' :
+        return ("lt");
+
+    case '>' :
+        return ("gt");
+
+    case '\"' :
+        return ("quot");
+
+    default :
+        return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetValue()' - Get the character corresponding to a named entity.
+ *
+ * The entity name can also be a numeric constant. -1 is returned if the
+ * name is not known.
+ */
+
+int					/* O - Character value or -1 on error */
+mxmlEntityGetValue(const char *name)	/* I - Entity name */
+{
+  int		i;			/* Looping var */
+  int		ch;			/* Character value */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if ((ch = (global->entity_cbs[i])(name)) >= 0)
+      return (ch);
+
+  return (-1);
+}
+
+
+/*
+ * 'mxmlEntityRemoveCallback()' - Remove a callback.
+ */
+
+void
+mxmlEntityRemoveCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to remove */
+{
+  int		i;			/* Looping var */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if (cb == global->entity_cbs[i])
+    {
+     /*
+      * Remove the callback...
+      */
+
+      global->num_entity_cbs --;
+
+      if (i < global->num_entity_cbs)
+        memmove(global->entity_cbs + i, global->entity_cbs + i + 1,
+	        (global->num_entity_cbs - i) * sizeof(global->entity_cbs[0]));
+
+      return;
+    }
+}
+
+
+/*
+ * '_mxml_entity_cb()' - Lookup standard (X)HTML entities.
+ */
+
+int					/* O - Unicode value or -1 */
+_mxml_entity_cb(const char *name)	/* I - Entity name */
+{
+  int	diff,				/* Difference between names */
+	current,			/* Current entity in search */
+	first,				/* First entity in search */
+	last;				/* Last entity in search */
+  static const struct
+  {
+    const char	*name;			/* Entity name */
+    int		val;			/* Character value */
+  }	entities[] =
+  {
+    { "AElig",		198 },
+    { "Aacute",		193 },
+    { "Acirc",		194 },
+    { "Agrave",		192 },
+    { "Alpha",		913 },
+    { "Aring",		197 },
+    { "Atilde",		195 },
+    { "Auml",		196 },
+    { "Beta",		914 },
+    { "Ccedil",		199 },
+    { "Chi",		935 },
+    { "Dagger",		8225 },
+    { "Delta",		916 },
+    { "Dstrok",		208 },
+    { "ETH",		208 },
+    { "Eacute",		201 },
+    { "Ecirc",		202 },
+    { "Egrave",		200 },
+    { "Epsilon",	917 },
+    { "Eta",		919 },
+    { "Euml",		203 },
+    { "Gamma",		915 },
+    { "Iacute",		205 },
+    { "Icirc",		206 },
+    { "Igrave",		204 },
+    { "Iota",		921 },
+    { "Iuml",		207 },
+    { "Kappa",		922 },
+    { "Lambda",		923 },
+    { "Mu",		924 },
+    { "Ntilde",		209 },
+    { "Nu",		925 },
+    { "OElig",		338 },
+    { "Oacute",		211 },
+    { "Ocirc",		212 },
+    { "Ograve",		210 },
+    { "Omega",		937 },
+    { "Omicron",	927 },
+    { "Oslash",		216 },
+    { "Otilde",		213 },
+    { "Ouml",		214 },
+    { "Phi",		934 },
+    { "Pi",		928 },
+    { "Prime",		8243 },
+    { "Psi",		936 },
+    { "Rho",		929 },
+    { "Scaron",		352 },
+    { "Sigma",		931 },
+    { "THORN",		222 },
+    { "Tau",		932 },
+    { "Theta",		920 },
+    { "Uacute",		218 },
+    { "Ucirc",		219 },
+    { "Ugrave",		217 },
+    { "Upsilon",	933 },
+    { "Uuml",		220 },
+    { "Xi",		926 },
+    { "Yacute",		221 },
+    { "Yuml",		376 },
+    { "Zeta",		918 },
+    { "aacute",		225 },
+    { "acirc",		226 },
+    { "acute",		180 },
+    { "aelig",		230 },
+    { "agrave",		224 },
+    { "alefsym",	8501 },
+    { "alpha",		945 },
+    { "amp",		'&' },
+    { "and",		8743 },
+    { "ang",		8736 },
+    { "apos",           '\'' },
+    { "aring",		229 },
+    { "asymp",		8776 },
+    { "atilde",		227 },
+    { "auml",		228 },
+    { "bdquo",		8222 },
+    { "beta",		946 },
+    { "brkbar",		166 },
+    { "brvbar",		166 },
+    { "bull",		8226 },
+    { "cap",		8745 },
+    { "ccedil",		231 },
+    { "cedil",		184 },
+    { "cent",		162 },
+    { "chi",		967 },
+    { "circ",		710 },
+    { "clubs",		9827 },
+    { "cong",		8773 },
+    { "copy",		169 },
+    { "crarr",		8629 },
+    { "cup",		8746 },
+    { "curren",		164 },
+    { "dArr",		8659 },
+    { "dagger",		8224 },
+    { "darr",		8595 },
+    { "deg",		176 },
+    { "delta",		948 },
+    { "diams",		9830 },
+    { "die",		168 },
+    { "divide",		247 },
+    { "eacute",		233 },
+    { "ecirc",		234 },
+    { "egrave",		232 },
+    { "empty",		8709 },
+    { "emsp",		8195 },
+    { "ensp",		8194 },
+    { "epsilon",	949 },
+    { "equiv",		8801 },
+    { "eta",		951 },
+    { "eth",		240 },
+    { "euml",		235 },
+    { "euro",		8364 },
+    { "exist",		8707 },
+    { "fnof",		402 },
+    { "forall",		8704 },
+    { "frac12",		189 },
+    { "frac14",		188 },
+    { "frac34",		190 },
+    { "frasl",		8260 },
+    { "gamma",		947 },
+    { "ge",		8805 },
+    { "gt",		'>' },
+    { "hArr",		8660 },
+    { "harr",		8596 },
+    { "hearts",		9829 },
+    { "hellip",		8230 },
+    { "hibar",		175 },
+    { "iacute",		237 },
+    { "icirc",		238 },
+    { "iexcl",		161 },
+    { "igrave",		236 },
+    { "image",		8465 },
+    { "infin",		8734 },
+    { "int",		8747 },
+    { "iota",		953 },
+    { "iquest",		191 },
+    { "isin",		8712 },
+    { "iuml",		239 },
+    { "kappa",		954 },
+    { "lArr",		8656 },
+    { "lambda",		955 },
+    { "lang",		9001 },
+    { "laquo",		171 },
+    { "larr",		8592 },
+    { "lceil",		8968 },
+    { "ldquo",		8220 },
+    { "le",		8804 },
+    { "lfloor",		8970 },
+    { "lowast",		8727 },
+    { "loz",		9674 },
+    { "lrm",		8206 },
+    { "lsaquo",		8249 },
+    { "lsquo",		8216 },
+    { "lt",		'<' },
+    { "macr",		175 },
+    { "mdash",		8212 },
+    { "micro",		181 },
+    { "middot",		183 },
+    { "minus",		8722 },
+    { "mu",		956 },
+    { "nabla",		8711 },
+    { "nbsp",		160 },
+    { "ndash",		8211 },
+    { "ne",		8800 },
+    { "ni",		8715 },
+    { "not",		172 },
+    { "notin",		8713 },
+    { "nsub",		8836 },
+    { "ntilde",		241 },
+    { "nu",		957 },
+    { "oacute",		243 },
+    { "ocirc",		244 },
+    { "oelig",		339 },
+    { "ograve",		242 },
+    { "oline",		8254 },
+    { "omega",		969 },
+    { "omicron",	959 },
+    { "oplus",		8853 },
+    { "or",		8744 },
+    { "ordf",		170 },
+    { "ordm",		186 },
+    { "oslash",		248 },
+    { "otilde",		245 },
+    { "otimes",		8855 },
+    { "ouml",		246 },
+    { "para",		182 },
+    { "part",		8706 },
+    { "permil",		8240 },
+    { "perp",		8869 },
+    { "phi",		966 },
+    { "pi",		960 },
+    { "piv",		982 },
+    { "plusmn",		177 },
+    { "pound",		163 },
+    { "prime",		8242 },
+    { "prod",		8719 },
+    { "prop",		8733 },
+    { "psi",		968 },
+    { "quot",		'\"' },
+    { "rArr",		8658 },
+    { "radic",		8730 },
+    { "rang",		9002 },
+    { "raquo",		187 },
+    { "rarr",		8594 },
+    { "rceil",		8969 },
+    { "rdquo",		8221 },
+    { "real",		8476 },
+    { "reg",		174 },
+    { "rfloor",		8971 },
+    { "rho",		961 },
+    { "rlm",		8207 },
+    { "rsaquo",		8250 },
+    { "rsquo",		8217 },
+    { "sbquo",		8218 },
+    { "scaron",		353 },
+    { "sdot",		8901 },
+    { "sect",		167 },
+    { "shy",		173 },
+    { "sigma",		963 },
+    { "sigmaf",		962 },
+    { "sim",		8764 },
+    { "spades",		9824 },
+    { "sub",		8834 },
+    { "sube",		8838 },
+    { "sum",		8721 },
+    { "sup",		8835 },
+    { "sup1",		185 },
+    { "sup2",		178 },
+    { "sup3",		179 },
+    { "supe",		8839 },
+    { "szlig",		223 },
+    { "tau",		964 },
+    { "there4",		8756 },
+    { "theta",		952 },
+    { "thetasym",	977 },
+    { "thinsp",		8201 },
+    { "thorn",		254 },
+    { "tilde",		732 },
+    { "times",		215 },
+    { "trade",		8482 },
+    { "uArr",		8657 },
+    { "uacute",		250 },
+    { "uarr",		8593 },
+    { "ucirc",		251 },
+    { "ugrave",		249 },
+    { "uml",		168 },
+    { "upsih",		978 },
+    { "upsilon",	965 },
+    { "uuml",		252 },
+    { "weierp",		8472 },
+    { "xi",		958 },
+    { "yacute",		253 },
+    { "yen",		165 },
+    { "yuml",		255 },
+    { "zeta",		950 },
+    { "zwj",		8205 },
+    { "zwnj",		8204 }
+  };
+
+
+ /*
+  * Do a binary search for the named entity...
+  */
+
+  first = 0;
+  last  = (int)(sizeof(entities) / sizeof(entities[0]) - 1);
+
+  while ((last - first) > 1)
+  {
+    current = (first + last) / 2;
+
+    if ((diff = strcmp(name, entities[current].name)) == 0)
+      return (entities[current].val);
+    else if (diff < 0)
+      last = current;
+    else
+      first = current;
+  }
+
+ /*
+  * If we get here, there is a small chance that there is still
+  * a match; check first and last...
+  */
+
+  if (!strcmp(name, entities[first].name))
+    return (entities[first].val);
+  else if (!strcmp(name, entities[last].name))
+    return (entities[last].val);
+  else
+    return (-1);
+}
+
+
+/*
+ * End of "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-file.c b/tools/gator/daemon/mxml/mxml-file.c
new file mode 100644
index 000000000000..3812c253fc3e
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-file.c
@@ -0,0 +1,3056 @@
+/*
+ * "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $"
+ *
+ * File loading code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*** This file modified by ARM on 25 Aug 2014 to avoid pointer overflow when checking if the write position is beyond the end of the buffer in mxmlSaveString and mxml_string_putc ***/
+
+/*
+ * Include necessary headers...
+ */
+
+#ifndef WIN32
+#  include <unistd.h>
+#endif /* !WIN32 */
+#include "mxml-private.h"
+
+
+/*
+ * Character encoding...
+ */
+
+#define ENCODE_UTF8	0		/* UTF-8 */
+#define ENCODE_UTF16BE	1		/* UTF-16 Big-Endian */
+#define ENCODE_UTF16LE	2		/* UTF-16 Little-Endian */
+
+
+/*
+ * Macro to test for a bad XML character...
+ */
+
+#define mxml_bad_char(ch) ((ch) < ' ' && (ch) != '\n' && (ch) != '\r' && (ch) != '\t')
+
+
+/*
+ * Types and structures...
+ */
+
+typedef int (*_mxml_getc_cb_t)(void *, int *);
+typedef int (*_mxml_putc_cb_t)(int, void *);
+
+typedef struct _mxml_fdbuf_s		/**** File descriptor buffer ****/
+{
+  int		fd;			/* File descriptor */
+  unsigned char	*current,		/* Current position in buffer */
+		*end,			/* End of buffer */
+		buffer[8192];		/* Character buffer */
+} _mxml_fdbuf_t;
+
+
+/*
+ * Local functions...
+ */
+
+static int		mxml_add_char(int ch, char **ptr, char **buffer,
+			              int *bufsize);
+static int		mxml_fd_getc(void *p, int *encoding);
+static int		mxml_fd_putc(int ch, void *p);
+static int		mxml_fd_read(_mxml_fdbuf_t *buf);
+static int		mxml_fd_write(_mxml_fdbuf_t *buf);
+static int		mxml_file_getc(void *p, int *encoding);
+static int		mxml_file_putc(int ch, void *p);
+static int		mxml_get_entity(mxml_node_t *parent, void *p,
+			                int *encoding,
+					_mxml_getc_cb_t getc_cb);
+static inline int	mxml_isspace(int ch)
+			{
+			  return (ch == ' ' || ch == '\t' || ch == '\r' ||
+			          ch == '\n');
+			}
+static mxml_node_t	*mxml_load_data(mxml_node_t *top, void *p,
+			                mxml_load_cb_t cb,
+			                _mxml_getc_cb_t getc_cb,
+                                        mxml_sax_cb_t sax_cb, void *sax_data);
+static int		mxml_parse_element(mxml_node_t *node, void *p,
+			                   int *encoding,
+					   _mxml_getc_cb_t getc_cb);
+static int		mxml_string_getc(void *p, int *encoding);
+static int		mxml_string_putc(int ch, void *p);
+static int		mxml_write_name(const char *s, void *p,
+					_mxml_putc_cb_t putc_cb);
+static int		mxml_write_node(mxml_node_t *node, void *p,
+			                mxml_save_cb_t cb, int col,
+					_mxml_putc_cb_t putc_cb,
+					_mxml_global_t *global);
+static int		mxml_write_string(const char *s, void *p,
+					  _mxml_putc_cb_t putc_cb);
+static int		mxml_write_ws(mxml_node_t *node, void *p,
+			              mxml_save_cb_t cb, int ws,
+				      int col, _mxml_putc_cb_t putc_cb);
+
+
+/*
+ * 'mxmlLoadFd()' - Load a file descriptor into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFd(mxml_node_t    *top,		/* I - Top node */
+           int            fd,		/* I - File descriptor to read from */
+           mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadFile()' - Load a file into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFile(mxml_node_t    *top,	/* I - Top node */
+             FILE           *fp,	/* I - File to read from */
+             mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadString()' - Load a string into an XML node tree.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlLoadString(mxml_node_t    *top,	/* I - Top node */
+               const char     *s,	/* I - String to load */
+               mxml_load_cb_t cb)	/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, MXML_NO_CALLBACK,
+                         NULL));
+}
+
+
+/*
+ * 'mxmlSaveAllocString()' - Save an XML tree to an allocated string.
+ *
+ * This function returns a pointer to a string containing the textual
+ * representation of the XML node tree.  The string should be freed
+ * using the free() function when you are done with it.  NULL is returned
+ * if the node would produce an empty string or if the string cannot be
+ * allocated.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+char *					/* O - Allocated string or NULL */
+mxmlSaveAllocString(
+    mxml_node_t    *node,		/* I - Node to write */
+    mxml_save_cb_t cb)			/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	bytes;				/* Required bytes */
+  char	buffer[8192];			/* Temporary buffer */
+  char	*s;				/* Allocated string */
+
+
+ /*
+  * Write the node to the temporary buffer...
+  */
+
+  bytes = mxmlSaveString(node, buffer, sizeof(buffer), cb);
+
+  if (bytes <= 0)
+    return (NULL);
+
+  if (bytes < (int)(sizeof(buffer) - 1))
+  {
+   /*
+    * Node fit inside the buffer, so just duplicate that string and
+    * return...
+    */
+
+    return (strdup(buffer));
+  }
+
+ /*
+  * Allocate a buffer of the required size and save the node to the
+  * new buffer...
+  */
+
+  if ((s = malloc(bytes + 1)) == NULL)
+    return (NULL);
+
+  mxmlSaveString(node, s, bytes + 1, cb);
+
+ /*
+  * Return the allocated string...
+  */
+
+  return (s);
+}
+
+
+/*
+ * 'mxmlSaveFd()' - Save an XML tree to a file descriptor.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFd(mxml_node_t    *node,	/* I - Node to write */
+           int            fd,		/* I - File descriptor to write to */
+	   mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int		col;			/* Final column */
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer + sizeof(buf.buffer);
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, &buf, cb, 0, mxml_fd_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (mxml_fd_putc('\n', &buf) < 0)
+      return (-1);
+
+ /*
+  * Flush and return...
+  */
+
+  return (mxml_fd_write(&buf));
+}
+
+
+/*
+ * 'mxmlSaveFile()' - Save an XML tree to a file.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFile(mxml_node_t    *node,	/* I - Node to write */
+             FILE           *fp,	/* I - File to write to */
+	     mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, fp, cb, 0, mxml_file_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (putc('\n', fp) < 0)
+      return (-1);
+
+ /*
+  * Return 0 (success)...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSaveString()' - Save an XML node tree to a string.
+ *
+ * This function returns the total number of bytes that would be
+ * required for the string but only copies (bufsize - 1) characters
+ * into the specified buffer.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - Size of string */
+mxmlSaveString(mxml_node_t    *node,	/* I - Node to write */
+               char           *buffer,	/* I - String buffer */
+               int            bufsize,	/* I - Size of string buffer */
+               mxml_save_cb_t cb)	/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  char	*ptr[3];			/* Pointers for putc_cb */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  ptr[0] = buffer;
+  ptr[1] = buffer + bufsize;
+  ptr[2] = 0;
+
+  if ((col = mxml_write_node(node, ptr, cb, 0, mxml_string_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    mxml_string_putc('\n', ptr);
+
+ /*
+  * Nul-terminate the buffer...
+  */
+
+  if (ptr[2] != 0)
+    buffer[bufsize - 1] = '\0';
+  else
+    ptr[0][0] = '\0';
+
+ /*
+  * Return the number of characters...
+  */
+
+  return (ptr[0] - buffer);
+}
+
+
+/*
+ * 'mxmlSAXLoadFd()' - Load a file descriptor into an XML node tree
+ *                     using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFd(mxml_node_t    *top,	/* I - Top node */
+              int            fd,	/* I - File descriptor to read from */
+              mxml_load_cb_t cb,	/* I - Callback function or MXML_NO_CALLBACK */
+              mxml_sax_cb_t  sax_cb,	/* I - SAX callback or MXML_NO_CALLBACK */
+              void           *sax_data)	/* I - SAX user data */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadFile()' - Load a file into an XML node tree
+ *                       using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFile(
+    mxml_node_t    *top,		/* I - Top node */
+    FILE           *fp,			/* I - File to read from */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadString()' - Load a string into an XML node tree
+ *                         using a SAX callback.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlSAXLoadString(
+    mxml_node_t    *top,		/* I - Top node */
+    const char     *s,			/* I - String to load */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSetCustomHandlers()' - Set the handling functions for custom data.
+ *
+ * The load function accepts a node pointer and a data string and must
+ * return 0 on success and non-zero on error.
+ *
+ * The save function accepts a node pointer and must return a malloc'd
+ * string on success and NULL on error.
+ *
+ */
+
+void
+mxmlSetCustomHandlers(
+    mxml_custom_load_cb_t load,		/* I - Load function */
+    mxml_custom_save_cb_t save)		/* I - Save function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->custom_load_cb = load;
+  global->custom_save_cb = save;
+}
+
+
+/*
+ * 'mxmlSetErrorCallback()' - Set the error message callback.
+ */
+
+void
+mxmlSetErrorCallback(mxml_error_cb_t cb)/* I - Error callback function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->error_cb = cb;
+}
+
+
+/*
+ * 'mxmlSetWrapMargin()' - Set the wrap margin when saving XML data.
+ *
+ * Wrapping is disabled when "column" is 0.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlSetWrapMargin(int column)		/* I - Column for wrapping, 0 to disable wrapping */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->wrap = column;
+}
+
+
+/*
+ * 'mxml_add_char()' - Add a character to a buffer, expanding as needed.
+ */
+
+static int				/* O  - 0 on success, -1 on error */
+mxml_add_char(int  ch,			/* I  - Character to add */
+              char **bufptr,		/* IO - Current position in buffer */
+	      char **buffer,		/* IO - Current buffer */
+	      int  *bufsize)		/* IO - Current buffer size */
+{
+  char	*newbuffer;			/* New buffer value */
+
+
+  if (*bufptr >= (*buffer + *bufsize - 4))
+  {
+   /*
+    * Increase the size of the buffer...
+    */
+
+    if (*bufsize < 1024)
+      (*bufsize) *= 2;
+    else
+      (*bufsize) += 1024;
+
+    if ((newbuffer = realloc(*buffer, *bufsize)) == NULL)
+    {
+      free(*buffer);
+
+      mxml_error("Unable to expand string buffer to %d bytes!", *bufsize);
+
+      return (-1);
+    }
+
+    *bufptr = newbuffer + (*bufptr - *buffer);
+    *buffer = newbuffer;
+  }
+
+  if (ch < 0x80)
+  {
+   /*
+    * Single byte ASCII...
+    */
+
+    *(*bufptr)++ = ch;
+  }
+  else if (ch < 0x800)
+  {
+   /*
+    * Two-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xc0 | (ch >> 6);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else if (ch < 0x10000)
+  {
+   /*
+    * Three-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xe0 | (ch >> 12);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else
+  {
+   /*
+    * Four-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xf0 | (ch >> 18);
+    *(*bufptr)++ = 0x80 | ((ch >> 12) & 0x3f);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_getc()' - Read a character from a file descriptor.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_fd_getc(void *p,			/* I  - File descriptor buffer */
+             int  *encoding)		/* IO - Encoding */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+  int		ch,			/* Current character */
+		temp;			/* Temporary character */
+
+
+ /*
+  * Grab the next character in the buffer...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_read(buf) < 0)
+      return (EOF);
+
+  ch = *(buf->current)++;
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+#if DEBUG > 1
+          printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch = (ch << 8) | temp;
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch = (lch << 8) | temp;
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch |= (temp << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch |= (temp << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_fd_putc()' - Write a character to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_putc(int  ch,			/* I - Character */
+             void *p)			/* I - File descriptor buffer */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+
+
+ /*
+  * Flush the write buffer as needed...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_write(buf) < 0)
+      return (-1);
+
+  *(buf->current)++ = ch;
+
+ /*
+  * Return successfully...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_read()' - Read a buffer of data from a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_read(_mxml_fdbuf_t *buf)		/* I - File descriptor buffer */
+{
+  int	bytes;				/* Bytes read... */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Read from the file descriptor...
+  */
+
+  while ((bytes = read(buf->fd, buf->buffer, sizeof(buf->buffer))) < 0)
+#ifdef EINTR
+    if (errno != EAGAIN && errno != EINTR)
+#else
+    if (errno != EAGAIN)
+#endif /* EINTR */
+      return (-1);
+
+  if (bytes == 0)
+    return (-1);
+
+ /*
+  * Update the pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+  buf->end     = buf->buffer + bytes;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_write()' - Write a buffer of data to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_write(_mxml_fdbuf_t *buf)	/* I - File descriptor buffer */
+{
+  int		bytes;			/* Bytes written */
+  unsigned char	*ptr;			/* Pointer into buffer */
+
+
+ /*
+  * Range check...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Return 0 if there is nothing to write...
+  */
+
+  if (buf->current == buf->buffer)
+    return (0);
+
+ /*
+  * Loop until we have written everything...
+  */
+
+  for (ptr = buf->buffer; ptr < buf->current; ptr += bytes)
+    if ((bytes = write(buf->fd, ptr, buf->current - ptr)) < 0)
+      return (-1);
+
+ /*
+  * All done, reset pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_file_getc()' - Get a character from a file.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_file_getc(void *p,			/* I  - Pointer to file */
+               int  *encoding)		/* IO - Encoding */
+{
+  int	ch,				/* Character from file */
+	temp;				/* Temporary character */
+  FILE	*fp;				/* Pointer to file */
+
+
+ /*
+  * Read a character from the file and see if it is EOF or ASCII...
+  */
+
+  fp = (FILE *)p;
+  ch = getc(fp);
+
+  if (ch == EOF)
+    return (EOF);
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+#if DEBUG > 1
+          printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	ch = (ch << 8) | getc(fp);
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch = (lch << 8) | getc(fp);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	ch |= (getc(fp) << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch |= (getc(fp) << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_file_putc()' - Write a character to a file.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_file_putc(int  ch,			/* I - Character to write */
+               void *p)			/* I - Pointer to file */
+{
+  return (putc(ch, (FILE *)p) == EOF ? -1 : 0);
+}
+
+
+/*
+ * 'mxml_get_entity()' - Get the character corresponding to an entity...
+ */
+
+static int				/* O  - Character value or EOF on error */
+mxml_get_entity(mxml_node_t *parent,	/* I  - Parent node */
+		void        *p,		/* I  - Pointer to source */
+		int         *encoding,	/* IO - Character encoding */
+                int         (*getc_cb)(void *, int *))
+					/* I  - Get character function */
+{
+  int	ch;				/* Current character */
+  char	entity[64],			/* Entity string */
+	*entptr;			/* Pointer into entity */
+
+
+  entptr = entity;
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+    if (ch > 126 || (!isalnum(ch) && ch != '#'))
+      break;
+    else if (entptr < (entity + sizeof(entity) - 1))
+      *entptr++ = ch;
+    else
+    {
+      mxml_error("Entity name too long under parent <%s>!",
+	         parent ? parent->value.element.name : "null");
+      break;
+    }
+
+  *entptr = '\0';
+
+  if (ch != ';')
+  {
+    mxml_error("Character entity \"%s\" not terminated under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  if (entity[0] == '#')
+  {
+    if (entity[1] == 'x')
+      ch = strtol(entity + 2, NULL, 16);
+    else
+      ch = strtol(entity + 1, NULL, 10);
+  }
+  else if ((ch = mxmlEntityGetValue(entity)) < 0)
+    mxml_error("Entity name \"%s;\" not supported under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+
+  if (mxml_bad_char(ch))
+  {
+    mxml_error("Bad control character 0x%02x under parent <%s> not allowed by XML standard!",
+               ch, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_load_data()' - Load data into an XML node tree.
+ */
+
+static mxml_node_t *			/* O - First node or NULL if the file could not be read. */
+mxml_load_data(
+    mxml_node_t     *top,		/* I - Top node */
+    void            *p,			/* I - Pointer to data */
+    mxml_load_cb_t  cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    _mxml_getc_cb_t getc_cb,		/* I - Read function */
+    mxml_sax_cb_t   sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void            *sax_data)		/* I - SAX user data */
+{
+  mxml_node_t	*node,			/* Current node */
+		*first,			/* First node added */
+		*parent;		/* Current parent node */
+  int		ch,			/* Character from file */
+		whitespace;		/* Non-zero if whitespace seen */
+  char		*buffer,		/* String buffer */
+		*bufptr;		/* Pointer into buffer */
+  int		bufsize;		/* Size of buffer */
+  mxml_type_t	type;			/* Current node type */
+  int		encoding;		/* Character encoding */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+  static const char * const types[] =	/* Type strings... */
+		{
+		  "MXML_ELEMENT",	/* XML element with attributes */
+		  "MXML_INTEGER",	/* Integer value */
+		  "MXML_OPAQUE",	/* Opaque string */
+		  "MXML_REAL",		/* Real value */
+		  "MXML_TEXT",		/* Text fragment */
+		  "MXML_CUSTOM"		/* Custom data */
+		};
+
+
+ /*
+  * Read elements and other nodes from the file...
+  */
+
+  if ((buffer = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate string buffer!");
+    return (NULL);
+  }
+
+  bufsize    = 64;
+  bufptr     = buffer;
+  parent     = top;
+  first      = NULL;
+  whitespace = 0;
+  encoding   = ENCODE_UTF8;
+
+  if (cb && parent)
+    type = (*cb)(parent);
+  else if (parent)
+    type = MXML_TEXT;
+  else
+    type = MXML_IGNORE;
+
+  while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+  {
+    if ((ch == '<' ||
+         (mxml_isspace(ch) && type != MXML_OPAQUE && type != MXML_CUSTOM)) &&
+        bufptr > buffer)
+    {
+     /*
+      * Add a new value node...
+      */
+
+      *bufptr = '\0';
+
+      switch (type)
+      {
+	case MXML_INTEGER :
+            node = mxmlNewInteger(parent, strtol(buffer, &bufptr, 0));
+	    break;
+
+	case MXML_OPAQUE :
+            node = mxmlNewOpaque(parent, buffer);
+	    break;
+
+	case MXML_REAL :
+            node = mxmlNewReal(parent, strtod(buffer, &bufptr));
+	    break;
+
+	case MXML_TEXT :
+            node = mxmlNewText(parent, whitespace, buffer);
+	    break;
+
+	case MXML_CUSTOM :
+	    if (global->custom_load_cb)
+	    {
+	     /*
+	      * Use the callback to fill in the custom data...
+	      */
+
+              node = mxmlNewCustom(parent, NULL, NULL);
+
+	      if ((*global->custom_load_cb)(node, buffer))
+	      {
+	        mxml_error("Bad custom value '%s' in parent <%s>!",
+		           buffer, parent ? parent->value.element.name : "null");
+		mxmlDelete(node);
+		node = NULL;
+	      }
+	      break;
+	    }
+
+        default : /* Ignore... */
+	    node = NULL;
+	    break;
+      }
+
+      if (*bufptr)
+      {
+       /*
+        * Bad integer/real number value...
+	*/
+
+        mxml_error("Bad %s value '%s' in parent <%s>!",
+	           type == MXML_INTEGER ? "integer" : "real", buffer,
+		   parent ? parent->value.element.name : "null");
+	break;
+      }
+
+      bufptr     = buffer;
+      whitespace = mxml_isspace(ch) && type == MXML_TEXT;
+
+      if (!node && type != MXML_IGNORE)
+      {
+       /*
+	* Print error and return...
+	*/
+
+	mxml_error("Unable to add value node of type %s to parent <%s>!",
+	           types[type], parent ? parent->value.element.name : "null");
+	goto error;
+      }
+
+      if (sax_cb)
+      {
+        (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+        if (!mxmlRelease(node))
+          node = NULL;
+      }
+
+      if (!first && node)
+        first = node;
+    }
+    else if (mxml_isspace(ch) && type == MXML_TEXT)
+      whitespace = 1;
+
+   /*
+    * Add lone whitespace node if we have an element and existing
+    * whitespace...
+    */
+
+    if (ch == '<' && whitespace && type == MXML_TEXT)
+    {
+      if (parent)
+      {
+	node = mxmlNewText(parent, whitespace, "");
+
+	if (sax_cb)
+	{
+	  (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+	  if (!mxmlRelease(node))
+	    node = NULL;
+	}
+
+	if (!first && node)
+	  first = node;
+      }
+
+      whitespace = 0;
+    }
+
+    if (ch == '<')
+    {
+     /*
+      * Start of open/close tag...
+      */
+
+      bufptr = buffer;
+
+      while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+        if (mxml_isspace(ch) || ch == '>' || (ch == '/' && bufptr > buffer))
+	  break;
+	else if (ch == '<')
+	{
+	  mxml_error("Bare < in element!");
+	  goto error;
+	}
+	else if (ch == '&')
+	{
+	  if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+
+	  if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+	else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	  goto error;
+	else if (((bufptr - buffer) == 1 && buffer[0] == '?') ||
+	         ((bufptr - buffer) == 3 && !strncmp(buffer, "!--", 3)) ||
+	         ((bufptr - buffer) == 8 && !strncmp(buffer, "![CDATA[", 8)))
+	  break;
+
+      *bufptr = '\0';
+
+      if (!strcmp(buffer, "!--"))
+      {
+       /*
+        * Gather rest of comment...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > (buffer + 4) &&
+	      bufptr[-3] != '-' && bufptr[-2] == '-' && bufptr[-1] == '-')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in comment node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add comment node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  break;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_COMMENT, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (!strcmp(buffer, "![CDATA["))
+      {
+       /*
+        * Gather CDATA section...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && !strncmp(bufptr - 2, "]]", 2))
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in CDATA node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add CDATA node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_CDATA, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (buffer[0] == '?')
+      {
+       /*
+        * Gather rest of processing instruction...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > buffer && bufptr[-1] == '?')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole processing instruction...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in processing instruction node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add processing instruction node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '!')
+      {
+       /*
+        * Gather rest of declaration...
+	*/
+
+	do
+	{
+	  if (ch == '>')
+	    break;
+	  else
+	  {
+            if (ch == '&')
+	      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+		goto error;
+
+	    if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	      goto error;
+	  }
+	}
+        while ((ch = (*getc_cb)(p, &encoding)) != EOF);
+
+       /*
+        * Error out if we didn't get the whole declaration...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in declaration node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add declaration node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '/')
+      {
+       /*
+        * Handle close tag...
+	*/
+
+        if (!parent || strcmp(buffer + 1, parent->value.element.name))
+	{
+	 /*
+	  * Close tag doesn't match tree; print an error for now...
+	  */
+
+	  mxml_error("Mismatched close tag <%s> under parent <%s>!",
+	             buffer, parent ? parent->value.element.name : "(null)");
+          goto error;
+	}
+
+       /*
+        * Keep reading until we see >...
+	*/
+
+        while (ch != '>' && ch != EOF)
+	  ch = (*getc_cb)(p, &encoding);
+
+        node   = parent;
+        parent = parent->parent;
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+	    first = NULL;
+        }
+
+       /*
+	* Ascend into the parent and set the value type as needed...
+	*/
+
+	if (cb && parent)
+	  type = (*cb)(parent);
+      }
+      else
+      {
+       /*
+        * Handle open tag...
+	*/
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+        if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add element node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (mxml_isspace(ch))
+        {
+	  if ((ch = mxml_parse_element(node, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+        }
+        else if (ch == '/')
+	{
+	  if ((ch = (*getc_cb)(p, &encoding)) != '>')
+	  {
+	    mxml_error("Expected > but got '%c' instead for element <%s/>!",
+	               ch, buffer);
+            mxmlDelete(node);
+            goto error;
+	  }
+
+	  ch = '/';
+	}
+
+        if (sax_cb)
+          (*sax_cb)(node, MXML_SAX_ELEMENT_OPEN, sax_data);
+
+        if (!first)
+	  first = node;
+
+	if (ch == EOF)
+	  break;
+
+        if (ch != '/')
+	{
+	 /*
+	  * Descend into this node, setting the value type as needed...
+	  */
+
+	  parent = node;
+
+	  if (cb && parent)
+	    type = (*cb)(parent);
+	}
+        else if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+            first = NULL;
+        }
+      }
+
+      bufptr  = buffer;
+    }
+    else if (ch == '&')
+    {
+     /*
+      * Add character entity to current buffer...
+      */
+
+      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	goto error;
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+    else if (type == MXML_OPAQUE || type == MXML_CUSTOM || !mxml_isspace(ch))
+    {
+     /*
+      * Add character to current buffer...
+      */
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+  }
+
+ /*
+  * Free the string buffer - we don't need it anymore...
+  */
+
+  free(buffer);
+
+ /*
+  * Find the top element and return it...
+  */
+
+  if (parent)
+  {
+    node = parent;
+
+    while (parent != top && parent->parent)
+      parent = parent->parent;
+
+    if (node != parent)
+    {
+      mxml_error("Missing close tag </%s> under parent <%s>!",
+	         node->value.element.name,
+		 node->parent ? node->parent->value.element.name : "(null)");
+
+      mxmlDelete(first);
+
+      return (NULL);
+    }
+  }
+
+  if (parent)
+    return (parent);
+  else
+    return (first);
+
+ /*
+  * Common error return...
+  */
+
+error:
+
+  mxmlDelete(first);
+
+  free(buffer);
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxml_parse_element()' - Parse an element for any attributes...
+ */
+
+static int				/* O  - Terminating character */
+mxml_parse_element(
+    mxml_node_t     *node,		/* I  - Element node */
+    void            *p,			/* I  - Data to read from */
+    int             *encoding,		/* IO - Encoding */
+    _mxml_getc_cb_t getc_cb)		/* I  - Data callback */
+{
+  int	ch,				/* Current character in file */
+	quote;				/* Quoting character */
+  char	*name,				/* Attribute name */
+	*value,				/* Attribute value */
+	*ptr;				/* Pointer into name/value */
+  int	namesize,			/* Size of name string */
+	valsize;			/* Size of value string */
+
+
+ /*
+  * Initialize the name and value buffers...
+  */
+
+  if ((name = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for name!");
+    return (EOF);
+  }
+
+  namesize = 64;
+
+  if ((value = malloc(64)) == NULL)
+  {
+    free(name);
+    mxml_error("Unable to allocate memory for value!");
+    return (EOF);
+  }
+
+  valsize = 64;
+
+ /*
+  * Loop until we hit a >, /, ?, or EOF...
+  */
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+  {
+#if DEBUG > 1
+    fprintf(stderr, "parse_element: ch='%c'\n", ch);
+#endif /* DEBUG > 1 */
+
+   /*
+    * Skip leading whitespace...
+    */
+
+    if (mxml_isspace(ch))
+      continue;
+
+   /*
+    * Stop at /, ?, or >...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        goto error;
+      }
+
+      break;
+    }
+    else if (ch == '<')
+    {
+      mxml_error("Bare < in element %s!", node->value.element.name);
+      goto error;
+    }
+    else if (ch == '>')
+      break;
+
+   /*
+    * Read the attribute name...
+    */
+
+    name[0] = ch;
+    ptr     = name + 1;
+
+    if (ch == '\"' || ch == '\'')
+    {
+     /*
+      * Name is in quotes, so get a quoted string...
+      */
+
+      quote = ch;
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+      {
+        if (ch == '&')
+	  if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	    goto error;
+
+	if (mxml_add_char(ch, &ptr, &name, &namesize))
+	  goto error;
+
+	if (ch == quote)
+          break;
+      }
+    }
+    else
+    {
+     /*
+      * Grab an normal, non-quoted name...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>' ||
+	    ch == '?')
+          break;
+	else
+	{
+          if (ch == '&')
+	    if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	      goto error;
+
+	  if (mxml_add_char(ch, &ptr, &name, &namesize))
+	    goto error;
+	}
+    }
+
+    *ptr = '\0';
+
+    if (mxmlElementGetAttr(node, name))
+      goto error;
+
+    while (ch != EOF && mxml_isspace(ch))
+      ch = (*getc_cb)(p, encoding);
+
+    if (ch == '=')
+    {
+     /*
+      * Read the attribute value...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF && mxml_isspace(ch));
+
+      if (ch == EOF)
+      {
+        mxml_error("Missing value for attribute '%s' in element %s!",
+	           name, node->value.element.name);
+        goto error;
+      }
+
+      if (ch == '\'' || ch == '\"')
+      {
+       /*
+        * Read quoted value...
+	*/
+
+        quote = ch;
+	ptr   = value;
+
+        while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (ch == quote)
+	    break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+      else
+      {
+       /*
+        * Read unquoted value...
+	*/
+
+	value[0] = ch;
+	ptr      = value + 1;
+
+	while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>')
+            break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+
+     /*
+      * Set the attribute with the given string value...
+      */
+
+      mxmlElementSetAttr(node, name, value);
+    }
+    else
+    {
+      mxml_error("Missing value for attribute '%s' in element %s!",
+	         name, node->value.element.name);
+      goto error;
+    }
+
+   /*
+    * Check the end character...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        ch = EOF;
+      }
+
+      break;
+    }
+    else if (ch == '>')
+      break;
+  }
+
+ /*
+  * Free the name and value buffers and return...
+  */
+
+  free(name);
+  free(value);
+
+  return (ch);
+
+ /*
+  * Common error return point...
+  */
+
+error:
+
+  free(name);
+  free(value);
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_getc()' - Get a character from a string.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_string_getc(void *p,		/* I  - Pointer to file */
+                 int  *encoding)	/* IO - Encoding */
+{
+  int		ch;			/* Character */
+  const char	**s;			/* Pointer to string pointer */
+
+
+  s = (const char **)p;
+
+  if ((ch = (*s)[0] & 255) != 0 || *encoding == ENCODE_UTF16LE)
+  {
+   /*
+    * Got character; convert UTF-8 to integer and return...
+    */
+
+    (*s)++;
+
+    switch (*encoding)
+    {
+      case ENCODE_UTF8 :
+	  if (!(ch & 0x80))
+	  {
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    if (mxml_bad_char(ch))
+	    {
+	      mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        		 ch);
+	      return (EOF);
+	    }
+
+	    return (ch);
+          }
+	  else if (ch == 0xfe)
+	  {
+	   /*
+	    * UTF-16 big-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xff)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16BE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if (ch == 0xff)
+	  {
+	   /*
+	    * UTF-16 little-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xfe)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16LE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if ((ch & 0xe0) == 0xc0)
+	  {
+	   /*
+	    * Two-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((ch & 0x1f) << 6) | ((*s)[0] & 0x3f);
+
+	    (*s)++;
+
+	    if (ch < 0x80)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf0) == 0xe0)
+	  {
+	   /*
+	    * Three-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((ch & 0x0f) << 6) | ((*s)[0] & 0x3f)) << 6) | ((*s)[1] & 0x3f);
+
+	    (*s) += 2;
+
+	    if (ch < 0x800)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+	   /*
+	    * Ignore (strip) Byte Order Mark (BOM)...
+	    */
+
+	    if (ch == 0xfeff)
+	      return (mxml_string_getc(p, encoding));
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf8) == 0xf0)
+	  {
+	   /*
+	    * Four-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80 ||
+        	((*s)[2] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((((ch & 0x07) << 6) | ((*s)[0] & 0x3f)) << 6) |
+        	   ((*s)[1] & 0x3f)) << 6) | ((*s)[2] & 0x3f);
+
+	    (*s) += 3;
+
+	    if (ch < 0x10000)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else
+	    return (EOF);
+
+      case ENCODE_UTF16BE :
+	 /*
+          * Read UTF-16 big-endian char...
+	  */
+
+	  ch = (ch << 8) | ((*s)[0] & 255);
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[0])
+	      return (EOF);
+
+            lch = (((*s)[0] & 255) << 8) | ((*s)[1] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+
+      case ENCODE_UTF16LE :
+	 /*
+          * Read UTF-16 little-endian char...
+	  */
+
+	  ch = ch | (((*s)[0] & 255) << 8);
+
+	  if (!ch)
+	  {
+	    (*s) --;
+	    return (EOF);
+	  }
+
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[1])
+	      return (EOF);
+
+            lch = (((*s)[1] & 255) << 8) | ((*s)[0] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+    }
+  }
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_putc()' - Write a character to a string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_string_putc(int  ch,		/* I - Character to write */
+                 void *p)		/* I - Pointer to string pointers */
+{
+  char	**pp;				/* Pointer to string pointers */
+
+
+  pp = (char **)p;
+
+  if (pp[2] == 0) {
+    if (pp[0] < pp[1])
+      pp[0][0] = ch;
+    else
+      pp[2] = (char *)1;
+  }
+
+  pp[0] ++;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_name()' - Write a name string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_name(const char *s,		/* I - Name to write */
+                void       *p,		/* I - Write pointer */
+		int        (*putc_cb)(int, void *))
+					/* I - Write callback */
+{
+  char		quote;			/* Quote character */
+  const char	*name;			/* Entity name */
+
+
+  if (*s == '\"' || *s == '\'')
+  {
+   /*
+    * Write a quoted name string...
+    */
+
+    if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    quote = *s++;
+
+    while (*s && *s != quote)
+    {
+      if ((name = mxmlEntityGetName(*s)) != NULL)
+      {
+	if ((*putc_cb)('&', p) < 0)
+          return (-1);
+
+        while (*name)
+	{
+	  if ((*putc_cb)(*name, p) < 0)
+            return (-1);
+
+          name ++;
+	}
+
+	if ((*putc_cb)(';', p) < 0)
+          return (-1);
+      }
+      else if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+
+   /*
+    * Write the end quote...
+    */
+
+    if ((*putc_cb)(quote, p) < 0)
+      return (-1);
+  }
+  else
+  {
+   /*
+    * Write a non-quoted name string...
+    */
+
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_node()' - Save an XML node to a file.
+ */
+
+static int				/* O - Column or -1 on error */
+mxml_write_node(mxml_node_t     *node,	/* I - Node to write */
+                void            *p,	/* I - File to write to */
+	        mxml_save_cb_t  cb,	/* I - Whitespace callback */
+		int             col,	/* I - Current column */
+		_mxml_putc_cb_t putc_cb,/* I - Output callback */
+		_mxml_global_t  *global)/* I - Global data */
+{
+  int		i,			/* Looping var */
+		width;			/* Width of attr + value */
+  mxml_attr_t	*attr;			/* Current attribute */
+  char		s[255];			/* Temporary string */
+
+
+ /*
+  * Print the node value...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+	col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_OPEN, col, putc_cb);
+
+	if ((*putc_cb)('<', p) < 0)
+	  return (-1);
+	if (node->value.element.name[0] == '?' ||
+	    !strncmp(node->value.element.name, "!--", 3) ||
+	    !strncmp(node->value.element.name, "![CDATA[", 8))
+	{
+	 /*
+	  * Comments, CDATA, and processing instructions do not
+	  * use character entities.
+	  */
+
+	  const char	*ptr;		/* Pointer into name */
+
+
+	  for (ptr = node->value.element.name; *ptr; ptr ++)
+	    if ((*putc_cb)(*ptr, p) < 0)
+	      return (-1);
+	}
+	else if (mxml_write_name(node->value.element.name, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.element.name) + 1;
+
+	for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+	     i > 0;
+	     i --, attr ++)
+	{
+	  width = strlen(attr->name);
+
+	  if (attr->value)
+	    width += strlen(attr->value) + 3;
+
+	  if (global->wrap > 0 && (col + width) > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else
+	  {
+	    if ((*putc_cb)(' ', p) < 0)
+	      return (-1);
+
+	    col ++;
+	  }
+
+	  if (mxml_write_name(attr->name, p, putc_cb) < 0)
+	    return (-1);
+
+	  if (attr->value)
+	  {
+	    if ((*putc_cb)('=', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(attr->value, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	  }
+
+	  col += width;
+	}
+
+	if (node->child)
+	{
+	 /*
+	  * Write children...
+	  */
+
+	  mxml_node_t *child;		/* Current child */
+
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+
+          for (child = node->child; child; child = child->next)
+	  {
+	    if ((col = mxml_write_node(child, p, cb, col, putc_cb, global)) < 0)
+	      return (-1);
+	  }
+
+	 /*
+	  * The ? and ! elements are special-cases and have no end tags...
+	  */
+
+	  if (node->value.element.name[0] != '!' &&
+	      node->value.element.name[0] != '?')
+	  {
+	    col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_CLOSE, col, putc_cb);
+
+	    if ((*putc_cb)('<', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('/', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(node->value.element.name, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('>', p) < 0)
+	      return (-1);
+
+	    col += strlen(node->value.element.name) + 3;
+
+	    col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_CLOSE, col, putc_cb);
+	  }
+	}
+	else if (node->value.element.name[0] == '!' ||
+		 node->value.element.name[0] == '?')
+	{
+	 /*
+	  * The ? and ! elements are special-cases...
+	  */
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	else
+	{
+	  if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('/', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+
+	  col += 3;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	break;
+
+    case MXML_INTEGER :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%d", node->value.integer);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_OPAQUE :
+	if (mxml_write_string(node->value.opaque, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.opaque);
+	break;
+
+    case MXML_REAL :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%f", node->value.real);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_TEXT :
+	if (node->value.text.whitespace && col > 0)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	if (mxml_write_string(node->value.text.string, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.text.string);
+	break;
+
+    case MXML_CUSTOM :
+	if (global->custom_save_cb)
+	{
+	  char	*data;		/* Custom data string */
+	  const char	*newline;	/* Last newline in string */
+
+
+	  if ((data = (*global->custom_save_cb)(node)) == NULL)
+	    return (-1);
+
+	  if (mxml_write_string(data, p, putc_cb) < 0)
+	    return (-1);
+
+	  if ((newline = strrchr(data, '\n')) == NULL)
+	    col += strlen(data);
+	  else
+	    col = strlen(newline);
+
+	  free(data);
+	  break;
+	}
+
+    default : /* Should never happen */
+	return (-1);
+  }
+
+  return (col);
+}
+
+
+/*
+ * 'mxml_write_string()' - Write a string, escaping & and < as needed.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_string(
+    const char      *s,			/* I - String to write */
+    void            *p,			/* I - Write pointer */
+    _mxml_putc_cb_t putc_cb)		/* I - Write callback */
+{
+  const char	*name;			/* Entity name, if any */
+
+
+  while (*s)
+  {
+    if ((name = mxmlEntityGetName(*s)) != NULL)
+    {
+      if ((*putc_cb)('&', p) < 0)
+        return (-1);
+
+      while (*name)
+      {
+	if ((*putc_cb)(*name, p) < 0)
+          return (-1);
+        name ++;
+      }
+
+      if ((*putc_cb)(';', p) < 0)
+        return (-1);
+    }
+    else if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    s ++;
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_ws()' - Do whitespace callback...
+ */
+
+static int				/* O - New column */
+mxml_write_ws(mxml_node_t     *node,	/* I - Current node */
+              void            *p,	/* I - Write pointer */
+              mxml_save_cb_t  cb,	/* I - Callback function */
+	      int             ws,	/* I - Where value */
+	      int             col,	/* I - Current column */
+              _mxml_putc_cb_t putc_cb)	/* I - Write callback */
+{
+  const char	*s;			/* Whitespace string */
+
+
+  if (cb && (s = (*cb)(node, ws)) != NULL)
+  {
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+      else if (*s == '\n')
+	col = 0;
+      else if (*s == '\t')
+      {
+	col += MXML_TAB;
+	col = col - (col % MXML_TAB);
+      }
+      else
+	col ++;
+
+      s ++;
+    }
+  }
+
+  return (col);
+}
+
+
+/*
+ * End of "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-get.c b/tools/gator/daemon/mxml/mxml-get.c
new file mode 100644
index 000000000000..40ed3d0839b4
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-get.c
@@ -0,0 +1,452 @@
+/*
+ * "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node get functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlGetCDATA()' - Get the value for a CDATA node.
+ *
+ * @code NULL@ is returned if the node is not a CDATA element.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - CDATA value or NULL */
+mxmlGetCDATA(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (NULL);
+
+ /*
+  * Return the text following the CDATA declaration...
+  */
+
+  return (node->value.element.name + 8);
+}
+
+
+/*
+ * 'mxmlGetCustom()' - Get the value for a custom node.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a custom
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const void *				/* O - Custom value or NULL */
+mxmlGetCustom(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_CUSTOM)
+    return (node->value.custom.data);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_CUSTOM)
+    return (node->child->value.custom.data);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetElement()' - Get the name for an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Element name or NULL */
+mxmlGetElement(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the element name...
+  */
+
+  return (node->value.element.name);
+}
+
+
+/*
+ * 'mxmlGetFirstChild()' - Get the first child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - First child or NULL */
+mxmlGetFirstChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the first child node...
+  */
+
+  return (node->child);
+}
+
+
+/*
+ * 'mxmlGetInteger()' - Get the integer value from the specified node or its
+ *                      first child.
+ *
+ * 0 is returned if the node (or its first child) is not an integer value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - Integer value or 0 */
+mxmlGetInteger(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_INTEGER)
+    return (node->value.integer);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_INTEGER)
+    return (node->child->value.integer);
+  else
+    return (0);
+}
+
+
+/*
+ * 'mxmlGetLastChild()' - Get the last child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Last child or NULL */
+mxmlGetLastChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->last_child);
+}
+
+
+/*
+ * 'mxmlGetNextSibling()' - Get the next node for the current parent.
+ *
+ * @code NULL@ is returned if this is the last child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *
+mxmlGetNextSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->next);
+}
+
+
+/*
+ * 'mxmlGetOpaque()' - Get an opaque string value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not an opaque
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Opaque string or NULL */
+mxmlGetOpaque(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_OPAQUE)
+    return (node->value.opaque);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_OPAQUE)
+    return (node->child->value.opaque);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetParent()' - Get the parent node.
+ *
+ * @code NULL@ is returned for a root node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Parent node or NULL */
+mxmlGetParent(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->parent);
+}
+
+
+/*
+ * 'mxmlGetPrevSibling()' - Get the previous node for the current parent.
+ *
+ * @code NULL@ is returned if this is the first child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlGetPrevSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->prev);
+}
+
+
+/*
+ * 'mxmlGetReal()' - Get the real value for a node or its first child.
+ *
+ * 0.0 is returned if the node (or its first child) is not a real value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+double					/* O - Real value or 0.0 */
+mxmlGetReal(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0.0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_REAL)
+    return (node->value.real);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_REAL)
+    return (node->child->value.real);
+  else
+    return (0.0);
+}
+
+
+/*
+ * 'mxmlGetText()' - Get the text value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a text node.
+ * The "whitespace" argument can be NULL.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Text string or NULL */
+mxmlGetText(mxml_node_t *node,		/* I - Node to get */
+            int         *whitespace)	/* O - 1 if string is preceded by whitespace, 0 otherwise */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->value.text.whitespace;
+
+    return (node->value.text.string);
+  }
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->child->value.text.whitespace;
+
+    return (node->child->value.text.string);
+  }
+  else
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlGetType()' - Get the node type.
+ *
+ * @code MXML_IGNORE@ is returned if "node" is @code NULL@.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_type_t				/* O - Type of node */
+mxmlGetType(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (MXML_IGNORE);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->type);
+}
+
+
+/*
+ * 'mxmlGetUserData()' - Get the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+void *					/* O - User data pointer */
+mxmlGetUserData(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the user data pointer...
+  */
+
+  return (node->user_data);
+}
+
+
+/*
+ * End of "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-index.c b/tools/gator/daemon/mxml/mxml-index.c
new file mode 100644
index 000000000000..10814390d3a0
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-index.c
@@ -0,0 +1,659 @@
+/*
+ * "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Index support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Sort functions...
+ */
+
+static int	index_compare(mxml_index_t *ind, mxml_node_t *first,
+		              mxml_node_t *second);
+static int	index_find(mxml_index_t *ind, const char *element,
+		           const char *value, mxml_node_t *node);
+static void	index_sort(mxml_index_t *ind, int left, int right);
+
+
+/*
+ * 'mxmlIndexDelete()' - Delete an index.
+ */
+
+void
+mxmlIndexDelete(mxml_index_t *ind)	/* I - Index to delete */
+{
+ /*
+  * Range check input..
+  */
+
+  if (!ind)
+    return;
+
+ /*
+  * Free memory...
+  */
+
+  if (ind->attr)
+    free(ind->attr);
+
+  if (ind->alloc_nodes)
+    free(ind->nodes);
+
+  free(ind);
+}
+
+
+/*
+ * 'mxmlIndexEnum()' - Return the next node in the index.
+ *
+ * Nodes are returned in the sorted order of the index.
+ */
+
+mxml_node_t *				/* O - Next node or NULL if there is none */
+mxmlIndexEnum(mxml_index_t *ind)	/* I - Index to enumerate */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Return the next node...
+  */
+
+  if (ind->cur_node < ind->num_nodes)
+    return (ind->nodes[ind->cur_node ++]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexFind()' - Find the next matching node.
+ *
+ * You should call mxmlIndexReset() prior to using this function for
+ * the first time with a particular set of "element" and "value"
+ * strings. Passing NULL for both "element" and "value" is equivalent
+ * to calling mxmlIndexEnum().
+ */
+
+mxml_node_t *				/* O - Node or NULL if none found */
+mxmlIndexFind(mxml_index_t *ind,	/* I - Index to search */
+              const char   *element,	/* I - Element name to find, if any */
+	      const char   *value)	/* I - Attribute value, if any */
+{
+  int		diff,			/* Difference between names */
+		current,		/* Current entity in search */
+		first,			/* First entity in search */
+		last;			/* Last entity in search */
+
+
+#ifdef DEBUG
+  printf("mxmlIndexFind(ind=%p, element=\"%s\", value=\"%s\")\n",
+         ind, element ? element : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind || (!ind->attr && value))
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    printf("    ind->attr=\"%s\"\n", ind->attr ? ind->attr : "(null)");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If both element and value are NULL, just enumerate the nodes in the
+  * index...
+  */
+
+  if (!element && !value)
+    return (mxmlIndexEnum(ind));
+
+ /*
+  * If there are no nodes in the index, return NULL...
+  */
+
+  if (!ind->num_nodes)
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    puts("    no nodes!");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If cur_node == 0, then find the first matching node...
+  */
+
+  if (ind->cur_node == 0)
+  {
+   /*
+    * Find the first node using a modified binary search algorithm...
+    */
+
+    first = 0;
+    last  = ind->num_nodes - 1;
+
+#ifdef DEBUG
+    printf("    find first time, num_nodes=%d...\n", ind->num_nodes);
+#endif /* DEBUG */
+
+    while ((last - first) > 1)
+    {
+      current = (first + last) / 2;
+
+#ifdef DEBUG
+      printf("    first=%d, last=%d, current=%d\n", first, last, current);
+#endif /* DEBUG */
+
+      if ((diff = index_find(ind, element, value, ind->nodes[current])) == 0)
+      {
+       /*
+        * Found a match, move back to find the first...
+	*/
+
+#ifdef DEBUG
+        puts("    match!");
+#endif /* DEBUG */
+
+        while (current > 0 &&
+	       !index_find(ind, element, value, ind->nodes[current - 1]))
+	  current --;
+
+#ifdef DEBUG
+        printf("    returning first match=%d\n", current);
+#endif /* DEBUG */
+
+       /*
+        * Return the first match and save the index to the next...
+	*/
+
+        ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+      else if (diff < 0)
+	last = current;
+      else
+	first = current;
+
+#ifdef DEBUG
+      printf("    diff=%d\n", diff);
+#endif /* DEBUG */
+    }
+
+   /*
+    * If we get this far, then we found exactly 0 or 1 matches...
+    */
+
+    for (current = first; current <= last; current ++)
+      if (!index_find(ind, element, value, ind->nodes[current]))
+      {
+       /*
+	* Found exactly one (or possibly two) match...
+	*/
+
+#ifdef DEBUG
+	printf("    returning only match %d...\n", current);
+#endif /* DEBUG */
+
+	ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+
+   /*
+    * No matches...
+    */
+
+    ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+    puts("    returning NULL...");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+  else if (ind->cur_node < ind->num_nodes &&
+           !index_find(ind, element, value, ind->nodes[ind->cur_node]))
+  {
+   /*
+    * Return the next matching node...
+    */
+
+#ifdef DEBUG
+    printf("    returning next match %d...\n", ind->cur_node);
+#endif /* DEBUG */
+
+    return (ind->nodes[ind->cur_node ++]);
+  }
+
+ /*
+  * If we get this far, then we have no matches...
+  */
+
+  ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+  puts("    returning NULL...");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexGetCount()' - Get the number of nodes in an index.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* I - Number of nodes in index */
+mxmlIndexGetCount(mxml_index_t *ind)	/* I - Index of nodes */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (0);
+
+ /*
+  * Return the number of nodes in the index...
+  */
+
+  return (ind->num_nodes);
+}
+
+
+/*
+ * 'mxmlIndexNew()' - Create a new index.
+ *
+ * The index will contain all nodes that contain the named element and/or
+ * attribute. If both "element" and "attr" are NULL, then the index will
+ * contain a sorted list of the elements in the node tree.  Nodes are
+ * sorted by element name and optionally by attribute value if the "attr"
+ * argument is not NULL.
+ */
+
+mxml_index_t *				/* O - New index */
+mxmlIndexNew(mxml_node_t *node,		/* I - XML node tree */
+             const char  *element,	/* I - Element to index or NULL for all */
+             const char  *attr)		/* I - Attribute to index or NULL for none */
+{
+  mxml_index_t	*ind;			/* New index */
+  mxml_node_t	*current,		/* Current node in index */
+  		**temp;			/* Temporary node pointer array */
+
+
+ /*
+  * Range check input...
+  */
+
+#ifdef DEBUG
+  printf("mxmlIndexNew(node=%p, element=\"%s\", attr=\"%s\")\n",
+         node, element ? element : "(null)", attr ? attr : "(null)");
+#endif /* DEBUG */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Create a new index...
+  */
+
+  if ((ind = calloc(1, sizeof(mxml_index_t))) == NULL)
+  {
+    mxml_error("Unable to allocate %d bytes for index - %s",
+               sizeof(mxml_index_t), strerror(errno));
+    return (NULL);
+  }
+
+  if (attr)
+    ind->attr = strdup(attr);
+
+  if (!element && !attr)
+    current = node;
+  else
+    current = mxmlFindElement(node, node, element, attr, NULL, MXML_DESCEND);
+
+  while (current)
+  {
+    if (ind->num_nodes >= ind->alloc_nodes)
+    {
+      if (!ind->alloc_nodes)
+        temp = malloc(64 * sizeof(mxml_node_t *));
+      else
+        temp = realloc(ind->nodes, (ind->alloc_nodes + 64) * sizeof(mxml_node_t *));
+
+      if (!temp)
+      {
+       /*
+        * Unable to allocate memory for the index, so abort...
+	*/
+
+        mxml_error("Unable to allocate %d bytes for index: %s",
+	           (ind->alloc_nodes + 64) * sizeof(mxml_node_t *),
+		   strerror(errno));
+
+        mxmlIndexDelete(ind);
+	return (NULL);
+      }
+
+      ind->nodes       = temp;
+      ind->alloc_nodes += 64;
+    }
+
+    ind->nodes[ind->num_nodes ++] = current;
+
+    current = mxmlFindElement(current, node, element, attr, NULL, MXML_DESCEND);
+  }
+
+ /*
+  * Sort nodes based upon the search criteria...
+  */
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    printf("%d node(s) in index.\n\n", ind->num_nodes);
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+  if (ind->num_nodes > 1)
+    index_sort(ind, 0, ind->num_nodes - 1);
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    puts("After sorting:\n");
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+ /*
+  * Return the new index...
+  */
+
+  return (ind);
+}
+
+
+/*
+ * 'mxmlIndexReset()' - Reset the enumeration/find pointer in the index and
+ *                      return the first node in the index.
+ *
+ * This function should be called prior to using mxmlIndexEnum() or
+ * mxmlIndexFind() for the first time.
+ */
+
+mxml_node_t *				/* O - First node or NULL if there is none */
+mxmlIndexReset(mxml_index_t *ind)	/* I - Index to reset */
+{
+#ifdef DEBUG
+  printf("mxmlIndexReset(ind=%p)\n", ind);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Set the index to the first element...
+  */
+
+  ind->cur_node = 0;
+
+ /*
+  * Return the first node...
+  */
+
+  if (ind->num_nodes)
+    return (ind->nodes[0]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'index_compare()' - Compare two nodes.
+ */
+
+static int				/* O - Result of comparison */
+index_compare(mxml_index_t *ind,	/* I - Index */
+              mxml_node_t  *first,	/* I - First node */
+              mxml_node_t  *second)	/* I - Second node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if ((diff = strcmp(first->value.element.name,
+                     second->value.element.name)) != 0)
+    return (diff);
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (ind->attr)
+  {
+    if ((diff = strcmp(mxmlElementGetAttr(first, ind->attr),
+                       mxmlElementGetAttr(second, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_find()' - Compare a node with index values.
+ */
+
+static int				/* O - Result of comparison */
+index_find(mxml_index_t *ind,		/* I - Index */
+           const char   *element,	/* I - Element name or NULL */
+	   const char   *value,		/* I - Attribute value or NULL */
+           mxml_node_t  *node)		/* I - Node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if (element)
+  {
+    if ((diff = strcmp(element, node->value.element.name)) != 0)
+      return (diff);
+  }
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (value)
+  {
+    if ((diff = strcmp(value, mxmlElementGetAttr(node, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_sort()' - Sort the nodes in the index...
+ *
+ * This function implements the classic quicksort algorithm...
+ */
+
+static void
+index_sort(mxml_index_t *ind,		/* I - Index to sort */
+           int          left,		/* I - Left node in partition */
+	   int          right)		/* I - Right node in partition */
+{
+  mxml_node_t	*pivot,			/* Pivot node */
+		*temp;			/* Swap node */
+  int		templ,			/* Temporary left node */
+		tempr;			/* Temporary right node */
+
+
+ /*
+  * Loop until we have sorted all the way to the right...
+  */
+
+  do
+  {
+   /*
+    * Sort the pivot in the current partition...
+    */
+
+    pivot = ind->nodes[left];
+
+    for (templ = left, tempr = right; templ < tempr;)
+    {
+     /*
+      * Move left while left node <= pivot node...
+      */
+
+      while ((templ < right) &&
+             index_compare(ind, ind->nodes[templ], pivot) <= 0)
+	templ ++;
+
+     /*
+      * Move right while right node > pivot node...
+      */
+
+      while ((tempr > left) &&
+             index_compare(ind, ind->nodes[tempr], pivot) > 0)
+	tempr --;
+
+     /*
+      * Swap nodes if needed...
+      */
+
+      if (templ < tempr)
+      {
+	temp              = ind->nodes[templ];
+	ind->nodes[templ] = ind->nodes[tempr];
+	ind->nodes[tempr] = temp;
+      }
+    }
+
+   /*
+    * When we get here, the right (tempr) node is the new position for the
+    * pivot node...
+    */
+
+    if (index_compare(ind, pivot, ind->nodes[tempr]) > 0)
+    {
+      ind->nodes[left]  = ind->nodes[tempr];
+      ind->nodes[tempr] = pivot;
+    }
+
+   /*
+    * Recursively sort the left partition as needed...
+    */
+
+    if (left < (tempr - 1))
+      index_sort(ind, left, tempr - 1);
+  }
+  while (right > (left = tempr + 1));
+}
+
+
+/*
+ * End of "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-node.c b/tools/gator/daemon/mxml/mxml-node.c
new file mode 100644
index 000000000000..128cda1a4cf2
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-node.c
@@ -0,0 +1,788 @@
+/*
+ * "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static mxml_node_t	*mxml_new(mxml_node_t *parent, mxml_type_t type);
+
+
+/*
+ * 'mxmlAdd()' - Add a node to a tree.
+ *
+ * Adds the specified node to the parent. If the child argument is not
+ * NULL, puts the new node before or after the specified child depending
+ * on the value of the where argument. If the child argument is NULL,
+ * puts the new node at the beginning of the child list (MXML_ADD_BEFORE)
+ * or at the end of the child list (MXML_ADD_AFTER). The constant
+ * MXML_ADD_TO_PARENT can be used to specify a NULL child pointer.
+ */
+
+void
+mxmlAdd(mxml_node_t *parent,		/* I - Parent node */
+        int         where,		/* I - Where to add, MXML_ADD_BEFORE or MXML_ADD_AFTER */
+        mxml_node_t *child,		/* I - Child node for where or MXML_ADD_TO_PARENT */
+	mxml_node_t *node)		/* I - Node to add */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlAdd(parent=%p, where=%d, child=%p, node=%p)\n", parent,
+          where, child, node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!parent || !node)
+    return;
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    BEFORE: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    BEFORE: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    BEFORE: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    BEFORE: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+
+ /*
+  * Remove the node from any existing parent...
+  */
+
+  if (node->parent)
+    mxmlRemove(node);
+
+ /*
+  * Reset pointers...
+  */
+
+  node->parent = parent;
+
+  switch (where)
+  {
+    case MXML_ADD_BEFORE :
+        if (!child || child == parent->child || child->parent != parent)
+	{
+	 /*
+	  * Insert as first node under parent...
+	  */
+
+	  node->next = parent->child;
+
+	  if (parent->child)
+	    parent->child->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  parent->child = node;
+	}
+	else
+	{
+	 /*
+	  * Insert node before this child...
+	  */
+
+	  node->next = child;
+	  node->prev = child->prev;
+
+	  if (child->prev)
+	    child->prev->next = node;
+	  else
+	    parent->child = node;
+
+	  child->prev = node;
+	}
+        break;
+
+    case MXML_ADD_AFTER :
+        if (!child || child == parent->last_child || child->parent != parent)
+	{
+	 /*
+	  * Insert as last node under parent...
+	  */
+
+	  node->parent = parent;
+	  node->prev   = parent->last_child;
+
+	  if (parent->last_child)
+	    parent->last_child->next = node;
+	  else
+	    parent->child = node;
+
+	  parent->last_child = node;
+        }
+	else
+	{
+	 /*
+	  * Insert node after this child...
+	  */
+
+	  node->prev = child;
+	  node->next = child->next;
+
+	  if (child->next)
+	    child->next->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  child->next = node;
+	}
+        break;
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    AFTER: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    AFTER: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    AFTER: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    AFTER: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlDelete()' - Delete a node and all of its children.
+ *
+ * If the specified node has a parent, this function first removes the
+ * node from its parent using the mxmlRemove() function.
+ */
+
+void
+mxmlDelete(mxml_node_t *node)		/* I - Node to delete */
+{
+  int	i;				/* Looping var */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlDelete(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return;
+
+ /*
+  * Remove the node from its parent, if any...
+  */
+
+  mxmlRemove(node);
+
+ /*
+  * Delete children...
+  */
+
+  while (node->child)
+    mxmlDelete(node->child);
+
+ /*
+  * Now delete any node data...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+        if (node->value.element.name)
+	  free(node->value.element.name);
+
+	if (node->value.element.num_attrs)
+	{
+	  for (i = 0; i < node->value.element.num_attrs; i ++)
+	  {
+	    if (node->value.element.attrs[i].name)
+	      free(node->value.element.attrs[i].name);
+	    if (node->value.element.attrs[i].value)
+	      free(node->value.element.attrs[i].value);
+	  }
+
+          free(node->value.element.attrs);
+	}
+        break;
+    case MXML_INTEGER :
+       /* Nothing to do */
+        break;
+    case MXML_OPAQUE :
+        if (node->value.opaque)
+	  free(node->value.opaque);
+        break;
+    case MXML_REAL :
+       /* Nothing to do */
+        break;
+    case MXML_TEXT :
+        if (node->value.text.string)
+	  free(node->value.text.string);
+        break;
+    case MXML_CUSTOM :
+        if (node->value.custom.data &&
+	    node->value.custom.destroy)
+	  (*(node->value.custom.destroy))(node->value.custom.data);
+	break;
+    default :
+        break;
+  }
+
+ /*
+  * Free this node...
+  */
+
+  free(node);
+}
+
+
+/*
+ * 'mxmlGetRefCount()' - Get the current reference (use) count for a node.
+ *
+ * The initial reference count of new nodes is 1. Use the @link mxmlRetain@
+ * and @link mxmlRelease@ functions to increment and decrement a node's
+ * reference count.
+ *
+ * @since Mini-XML 2.7@.
+ */
+
+int					/* O - Reference count */
+mxmlGetRefCount(mxml_node_t *node)	/* I - Node */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the reference count...
+  */
+
+  return (node->ref_count);
+}
+
+
+/*
+ * 'mxmlNewCDATA()' - Create a new CDATA node.
+ *
+ * The new CDATA node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * CDATA node has no parent. The data string must be nul-terminated and
+ * is copied into the new node. CDATA nodes use the MXML_ELEMENT type.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCDATA(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+	     const char  *data)		/* I - Data string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCDATA(parent=%p, data=\"%s\")\n",
+          parent, data ? data : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!data)
+    return (NULL);
+
+ /*
+  * Create the node and set the name value...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewCustom()' - Create a new custom data node.
+ *
+ * The new custom node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent. NULL can be passed when the data in the
+ * node is not dynamically allocated or is separately managed.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCustom(
+    mxml_node_t              *parent,	/* I - Parent node or MXML_NO_PARENT */
+    void                     *data,	/* I - Pointer to data */
+    mxml_custom_destroy_cb_t destroy)	/* I - Function to destroy data */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCustom(parent=%p, data=%p, destroy=%p)\n", parent,
+          data, destroy);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the value...
+  */
+
+  if ((node = mxml_new(parent, MXML_CUSTOM)) != NULL)
+  {
+    node->value.custom.data    = data;
+    node->value.custom.destroy = destroy;
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewElement()' - Create a new element node.
+ *
+ * The new element node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewElement(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               const char  *name)	/* I - Name of element */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewElement(parent=%p, name=\"%s\")\n", parent,
+          name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!name)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = strdup(name);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewInteger()' - Create a new integer node.
+ *
+ * The new integer node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * integer node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewInteger(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               int         integer)	/* I - Integer value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewInteger(parent=%p, integer=%d)\n", parent, integer);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_INTEGER)) != NULL)
+    node->value.integer = integer;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewOpaque()' - Create a new opaque string.
+ *
+ * The new opaque node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * opaque node has no parent. The opaque string must be nul-terminated and
+ * is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewOpaque(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+              const char  *opaque)	/* I - Opaque string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewOpaque(parent=%p, opaque=\"%s\")\n", parent,
+          opaque ? opaque : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!opaque)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_OPAQUE)) != NULL)
+    node->value.opaque = strdup(opaque);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewReal()' - Create a new real number node.
+ *
+ * The new real number node is added to the end of the specified parent's
+ * child list. The constant MXML_NO_PARENT can be used to specify that
+ * the new real number node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewReal(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            double      real)		/* I - Real number value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewReal(parent=%p, real=%g)\n", parent, real);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_REAL)) != NULL)
+    node->value.real = real;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewText()' - Create a new text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The text
+ * string must be nul-terminated and is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewText(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewText(parent=%p, whitespace=%d, string=\"%s\")\n",
+          parent, whitespace, string ? string : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!string)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = strdup(string);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewTextf()' - Create a new formatted text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The format
+ * string must be nul-terminated and is formatted into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewTextf(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	     const char  *format,	/* I - Printf-style frmat string */
+	     ...)			/* I - Additional args as needed */
+{
+  mxml_node_t	*node;			/* New node */
+  va_list	ap;			/* Pointer to arguments */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewTextf(parent=%p, whitespace=%d, format=\"%s\", ...)\n",
+          parent, whitespace, format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    va_start(ap, format);
+
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = _mxml_vstrdupf(format, ap);
+
+    va_end(ap);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlRemove()' - Remove a node from its parent.
+ *
+ * Does not free memory used by the node - use mxmlDelete() for that.
+ * This function does nothing if the node has no parent.
+ */
+
+void
+mxmlRemove(mxml_node_t *node)		/* I - Node to remove */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlRemove(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !node->parent)
+    return;
+
+ /*
+  * Remove from parent...
+  */
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    BEFORE: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    BEFORE: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    BEFORE: node->child=%p\n", node->child);
+  fprintf(stderr, "    BEFORE: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    BEFORE: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    BEFORE: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+
+  if (node->prev)
+    node->prev->next = node->next;
+  else
+    node->parent->child = node->next;
+
+  if (node->next)
+    node->next->prev = node->prev;
+  else
+    node->parent->last_child = node->prev;
+
+  node->parent = NULL;
+  node->prev   = NULL;
+  node->next   = NULL;
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    AFTER: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    AFTER: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    AFTER: node->child=%p\n", node->child);
+  fprintf(stderr, "    AFTER: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    AFTER: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    AFTER: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlNewXML()' - Create a new XML document tree.
+ *
+ * The "version" argument specifies the version number to put in the
+ * ?xml element node. If NULL, version 1.0 is assumed.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New ?xml node */
+mxmlNewXML(const char *version)		/* I - Version number to use */
+{
+  char	element[1024];			/* Element text */
+
+
+  snprintf(element, sizeof(element), "?xml version=\"%s\" encoding=\"utf-8\"?",
+           version ? version : "1.0");
+
+  return (mxmlNewElement(NULL, element));
+}
+
+
+/*
+ * 'mxmlRelease()' - Release a node.
+ *
+ * When the reference count reaches zero, the node (and any children)
+ * is deleted via mxmlDelete().
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRelease(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+  {
+    if ((-- node->ref_count) <= 0)
+    {
+      mxmlDelete(node);
+      return (0);
+    }
+    else
+      return (node->ref_count);
+  }
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxmlRetain()' - Retain a node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRetain(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+    return (++ node->ref_count);
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxml_new()' - Create a new node.
+ */
+
+static mxml_node_t *			/* O - New node */
+mxml_new(mxml_node_t *parent,		/* I - Parent node */
+         mxml_type_t type)		/* I - Node type */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#if DEBUG > 1
+  fprintf(stderr, "mxml_new(parent=%p, type=%d)\n", parent, type);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Allocate memory for the node...
+  */
+
+  if ((node = calloc(1, sizeof(mxml_node_t))) == NULL)
+  {
+#if DEBUG > 1
+    fputs("    returning NULL\n", stderr);
+#endif /* DEBUG > 1 */
+
+    return (NULL);
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    returning %p\n", node);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Set the node type...
+  */
+
+  node->type      = type;
+  node->ref_count = 1;
+
+ /*
+  * Add to the parent if present...
+  */
+
+  if (parent)
+    mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+
+ /*
+  * Return the new node...
+  */
+
+  return (node);
+}
+
+
+/*
+ * End of "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.c b/tools/gator/daemon/mxml/mxml-private.c
new file mode 100644
index 000000000000..bec4bbfbf378
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.c
@@ -0,0 +1,323 @@
+/*
+ * "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * Some crazy people think that unloading a shared object is a good or safe
+ * thing to do.  Unfortunately, most objects are simply *not* safe to unload
+ * and bad things *will* happen.
+ *
+ * The following mess of conditional code allows us to provide a destructor
+ * function in Mini-XML for our thread-global storage so that it can possibly
+ * be unloaded safely, although since there is no standard way to do so I
+ * can't even provide any guarantees that you can do it safely on all platforms.
+ *
+ * This code currently supports AIX, HP-UX, Linux, Mac OS X, Solaris, and
+ * Windows.  It might work on the BSDs and IRIX, but I haven't tested that.
+ */
+
+#if defined(__sun) || defined(_AIX)
+#  pragma fini(_mxml_fini)
+#  define _MXML_FINI _mxml_fini
+#elif defined(__hpux)
+#  pragma FINI _mxml_fini
+#  define _MXML_FINI _mxml_fini
+#elif defined(__GNUC__) /* Linux and Mac OS X */
+#  define _MXML_FINI __attribute((destructor)) _mxml_fini
+#else
+#  define _MXML_FINI _fini
+#endif /* __sun */
+
+
+/*
+ * 'mxml_error()' - Display an error message.
+ */
+
+void
+mxml_error(const char *format,		/* I - Printf-style format string */
+           ...)				/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+  char		s[1024];		/* Message string */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return;
+
+ /*
+  * Format the error message string...
+  */
+
+  va_start(ap, format);
+
+  vsnprintf(s, sizeof(s), format, ap);
+
+  va_end(ap);
+
+ /*
+  * And then display the error message...
+  */
+
+  if (global->error_cb)
+    (*global->error_cb)(s);
+  else
+    fprintf(stderr, "mxml: %s\n", s);
+}
+
+
+/*
+ * 'mxml_ignore_cb()' - Default callback for ignored values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_ignore_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_IGNORE);
+}
+
+
+/*
+ * 'mxml_integer_cb()' - Default callback for integer values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_integer_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_INTEGER);
+}
+
+
+/*
+ * 'mxml_opaque_cb()' - Default callback for opaque values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_opaque_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_OPAQUE);
+}
+
+
+/*
+ * 'mxml_real_cb()' - Default callback for real number values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_real_cb(mxml_node_t *node)		/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_REAL);
+}
+
+
+#ifdef HAVE_PTHREAD_H			/**** POSIX threading ****/
+#  include <pthread.h>
+
+static pthread_key_t	_mxml_key = -1;	/* Thread local storage key */
+static pthread_once_t	_mxml_key_once = PTHREAD_ONCE_INIT;
+					/* One-time initialization object */
+static void		_mxml_init(void);
+static void		_mxml_destructor(void *g);
+
+
+/*
+ * '_mxml_destructor()' - Free memory used for globals...
+ */
+
+static void
+_mxml_destructor(void *g)		/* I - Global data */
+{
+  free(g);
+}
+
+
+/*
+ * '_mxml_fini()' - Clean up when unloaded.
+ */
+
+static void
+_MXML_FINI(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if (_mxml_key != -1)
+  {
+    if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) != NULL)
+      _mxml_destructor(global);
+
+    pthread_key_delete(_mxml_key);
+    _mxml_key = -1;
+  }
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  pthread_once(&_mxml_key_once, _mxml_init);
+
+  if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+    pthread_setspecific(_mxml_key, global);
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+  }
+
+  return (global);
+}
+
+
+/*
+ * '_mxml_init()' - Initialize global data...
+ */
+
+static void
+_mxml_init(void)
+{
+  pthread_key_create(&_mxml_key, _mxml_destructor);
+}
+
+
+#elif defined(WIN32) && defined(MXML1_EXPORTS) /**** WIN32 threading ****/
+#  include <windows.h>
+
+static DWORD _mxml_tls_index;		/* Index for global storage */
+
+
+/*
+ * 'DllMain()' - Main entry for library.
+ */
+
+BOOL WINAPI				/* O - Success/failure */
+DllMain(HINSTANCE hinst,		/* I - DLL module handle */
+        DWORD     reason,		/* I - Reason */
+        LPVOID    reserved)		/* I - Unused */
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  (void)hinst;
+  (void)reserved;
+
+  switch (reason)
+  {
+    case DLL_PROCESS_ATTACH :		/* Called on library initialization */
+        if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES)
+          return (FALSE);
+        break;
+
+    case DLL_THREAD_DETACH :		/* Called when a thread terminates */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+        break;
+
+    case DLL_PROCESS_DETACH :		/* Called when library is unloaded */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+
+        TlsFree(_mxml_tls_index);
+        break;
+
+    default:
+        break;
+  }
+
+  return (TRUE);
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+
+    TlsSetValue(_mxml_tls_index, (LPVOID)global);
+  }
+
+  return (global);
+}
+
+
+#else					/**** No threading ****/
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  static _mxml_global_t	global =	/* Global data */
+  {
+    NULL,				/* error_cb */
+    1,					/* num_entity_cbs */
+    { _mxml_entity_cb },		/* entity_cbs */
+    72,					/* wrap */
+    NULL,				/* custom_load_cb */
+    NULL				/* custom_save_cb */
+  };
+
+
+  return (&global);
+}
+#endif /* HAVE_PTHREAD_H */
+
+
+/*
+ * End of "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.h b/tools/gator/daemon/mxml/mxml-private.h
new file mode 100644
index 000000000000..c5e4e6b6f27a
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.h
@@ -0,0 +1,50 @@
+/*
+ * "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private definitions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Global, per-thread data...
+ */
+
+typedef struct _mxml_global_s
+{
+  void	(*error_cb)(const char *);
+  int	num_entity_cbs;
+  int	(*entity_cbs[100])(const char *name);
+  int	wrap;
+  mxml_custom_load_cb_t	custom_load_cb;
+  mxml_custom_save_cb_t	custom_save_cb;
+} _mxml_global_t;
+
+
+/*
+ * Functions...
+ */
+
+extern _mxml_global_t	*_mxml_global(void);
+extern int		_mxml_entity_cb(const char *name);
+
+
+/*
+ * End of "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-search.c b/tools/gator/daemon/mxml/mxml-search.c
new file mode 100644
index 000000000000..313a52f0ce2f
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-search.c
@@ -0,0 +1,280 @@
+/*
+ * "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Search/navigation functions for Mini-XML, a small XML-like file
+ * parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlFindElement()' - Find the named element.
+ *
+ * The search is constrained by the name, attribute name, and value; any
+ * NULL names or values are treated as wildcards, so different kinds of
+ * searches can be implemented by looking for all elements of a given name
+ * or all elements with a specific attribute. The descend argument determines
+ * whether the search descends into child nodes; normally you will use
+ * MXML_DESCEND_FIRST for the initial search and MXML_NO_DESCEND to find
+ * additional direct descendents of the node. The top node argument
+ * constrains the search to a particular node's children.
+ */
+
+mxml_node_t *				/* O - Element node or NULL */
+mxmlFindElement(mxml_node_t *node,	/* I - Current node */
+                mxml_node_t *top,	/* I - Top node */
+                const char  *name,	/* I - Element name or NULL for any */
+		const char  *attr,	/* I - Attribute name, or NULL for none */
+		const char  *value,	/* I - Attribute value, or NULL for any */
+		int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  const char	*temp;			/* Current attribute value */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !top || (!attr && value))
+    return (NULL);
+
+ /*
+  * Start with the next node...
+  */
+
+  node = mxmlWalkNext(node, top, descend);
+
+ /*
+  * Loop until we find a matching element...
+  */
+
+  while (node != NULL)
+  {
+   /*
+    * See if this node matches...
+    */
+
+    if (node->type == MXML_ELEMENT &&
+        node->value.element.name &&
+	(!name || !strcmp(node->value.element.name, name)))
+    {
+     /*
+      * See if we need to check for an attribute...
+      */
+
+      if (!attr)
+        return (node);			/* No attribute search, return it... */
+
+     /*
+      * Check for the attribute...
+      */
+
+      if ((temp = mxmlElementGetAttr(node, attr)) != NULL)
+      {
+       /*
+        * OK, we have the attribute, does it match?
+	*/
+
+	if (!value || !strcmp(value, temp))
+	  return (node);		/* Yes, return it... */
+      }
+    }
+
+   /*
+    * No match, move on to the next node...
+    */
+
+    if (descend == MXML_DESCEND)
+      node = mxmlWalkNext(node, top, MXML_DESCEND);
+    else
+      node = node->next;
+  }
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlFindPath()' - Find a node with the given path.
+ *
+ * The "path" is a slash-separated list of element names. The name "*" is
+ * considered a wildcard for one or more levels of elements.  For example,
+ * "foo/one/two", "bar/two/one", "*\/one", and so forth.
+ *
+ * The first child node of the found node is returned if the given node has
+ * children and the first child is a value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Found node or NULL */
+mxmlFindPath(mxml_node_t *top,		/* I - Top node */
+	     const char  *path)		/* I - Path to element */
+{
+  mxml_node_t	*node;			/* Current node */
+  char		element[256];		/* Current element name */
+  const char	*pathsep;		/* Separator in path */
+  int		descend;		/* mxmlFindElement option */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!top || !path || !*path)
+    return (NULL);
+
+ /*
+  * Search each element in the path...
+  */
+
+  node = top;
+  while (*path)
+  {
+   /*
+    * Handle wildcards...
+    */
+
+    if (!strncmp(path, "*/", 2))
+    {
+      path += 2;
+      descend = MXML_DESCEND;
+    }
+    else
+      descend = MXML_DESCEND_FIRST;
+
+   /*
+    * Get the next element in the path...
+    */
+
+    if ((pathsep = strchr(path, '/')) == NULL)
+      pathsep = path + strlen(path);
+
+    if (pathsep == path || (pathsep - path) >= sizeof(element))
+      return (NULL);
+
+    memcpy(element, path, pathsep - path);
+    element[pathsep - path] = '\0';
+
+    if (*pathsep)
+      path = pathsep + 1;
+    else
+      path = pathsep;
+
+   /*
+    * Search for the element...
+    */
+
+    if ((node = mxmlFindElement(node, node, element, NULL, NULL,
+                                descend)) == NULL)
+      return (NULL);
+  }
+
+ /*
+  * If we get this far, return the node or its first child...
+  */
+
+  if (node->child && node->child->type != MXML_ELEMENT)
+    return (node->child);
+  else
+    return (node);
+}
+
+
+/*
+ * 'mxmlWalkNext()' - Walk to the next logical node in the tree.
+ *
+ * The descend argument controls whether the first child is considered
+ * to be the next node. The top node argument constrains the walk to
+ * the node's children.
+ */
+
+mxml_node_t *				/* O - Next node or NULL */
+mxmlWalkNext(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node)
+    return (NULL);
+  else if (node->child && descend)
+    return (node->child);
+  else if (node == top)
+    return (NULL);
+  else if (node->next)
+    return (node->next);
+  else if (node->parent && node->parent != top)
+  {
+    node = node->parent;
+
+    while (!node->next)
+      if (node->parent == top || !node->parent)
+        return (NULL);
+      else
+        node = node->parent;
+
+    return (node->next);
+  }
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlWalkPrev()' - Walk to the previous logical node in the tree.
+ *
+ * The descend argument controls whether the previous node's last child
+ * is considered to be the previous node. The top node argument constrains
+ * the walk to the node's children.
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlWalkPrev(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node || node == top)
+    return (NULL);
+  else if (node->prev)
+  {
+    if (node->prev->last_child && descend)
+    {
+     /*
+      * Find the last child under the previous node...
+      */
+
+      node = node->prev->last_child;
+
+      while (node->last_child)
+        node = node->last_child;
+
+      return (node);
+    }
+    else
+      return (node->prev);
+  }
+  else if (node->parent != top)
+    return (node->parent);
+  else
+    return (NULL);
+}
+
+
+/*
+ * End of "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-set.c b/tools/gator/daemon/mxml/mxml-set.c
new file mode 100644
index 000000000000..16d4bf1050dd
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-set.c
@@ -0,0 +1,337 @@
+/*
+ * "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node set functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlSetCDATA()' - Set the element name of a CDATA node.
+ *
+ * The node is not changed if it (or its first child) is not a CDATA element node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCDATA(mxml_node_t *node,		/* I - Node to set */
+             const char  *data)		/* I - New data string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      strncmp(node->value.element.name, "![CDATA[", 8) &&
+      node->child && node->child->type == MXML_ELEMENT &&
+      !strncmp(node->child->value.element.name, "![CDATA[", 8))
+    node = node->child;
+
+  if (!node || node->type != MXML_ELEMENT || !data ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetCustom()' - Set the data and destructor of a custom data node.
+ *
+ * The node is not changed if it (or its first child) is not a custom node.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCustom(
+    mxml_node_t              *node,	/* I - Node to set */
+    void                     *data,	/* I - New data pointer */
+    mxml_custom_destroy_cb_t destroy)	/* I - New destructor function */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_CUSTOM)
+    node = node->child;
+
+  if (!node || node->type != MXML_CUSTOM)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.custom.data && node->value.custom.destroy)
+    (*(node->value.custom.destroy))(node->value.custom.data);
+
+  node->value.custom.data    = data;
+  node->value.custom.destroy = destroy;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetElement()' - Set the name of an element node.
+ *
+ * The node is not changed if it is not an element node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetElement(mxml_node_t *node,	/* I - Node to set */
+               const char  *name)	/* I - New name string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = strdup(name);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetInteger()' - Set the value of an integer node.
+ *
+ * The node is not changed if it (or its first child) is not an integer node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetInteger(mxml_node_t *node,	/* I - Node to set */
+               int         integer)	/* I - Integer value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_INTEGER)
+    node = node->child;
+
+  if (!node || node->type != MXML_INTEGER)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.integer = integer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetOpaque()' - Set the value of an opaque node.
+ *
+ * The node is not changed if it (or its first child) is not an opaque node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetOpaque(mxml_node_t *node,	/* I - Node to set */
+              const char  *opaque)	/* I - Opaque string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_OPAQUE)
+    node = node->child;
+
+  if (!node || node->type != MXML_OPAQUE || !opaque)
+    return (-1);
+
+ /*
+  * Free any old opaque value and set the new value...
+  */
+
+  if (node->value.opaque)
+    free(node->value.opaque);
+
+  node->value.opaque = strdup(opaque);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetReal()' - Set the value of a real number node.
+ *
+ * The node is not changed if it (or its first child) is not a real number node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetReal(mxml_node_t *node,		/* I - Node to set */
+            double      real)		/* I - Real number value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_REAL)
+    node = node->child;
+
+  if (!node || node->type != MXML_REAL)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.real = real;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetText()' - Set the value of a text node.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetText(mxml_node_t *node,		/* I - Node to set */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !string)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = strdup(string);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetTextf()' - Set the value of a text node to a formatted string.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetTextf(mxml_node_t *node,		/* I - Node to set */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+             const char  *format,	/* I - Printf-style format string */
+	     ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !format)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  va_start(ap, format);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = _mxml_strdupf(format, ap);
+
+  va_end(ap);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetUserData()' - Set the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetUserData(mxml_node_t *node,	/* I - Node to set */
+                void        *data)	/* I - User data pointer */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (-1);
+
+ /*
+  * Set the user data pointer and return...
+  */
+
+  node->user_data = data;
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-string.c b/tools/gator/daemon/mxml/mxml-string.c
new file mode 100644
index 000000000000..9d5b58e6adb7
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-string.c
@@ -0,0 +1,469 @@
+/*
+ * "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $"
+ *
+ * String functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+
+
+/*
+ * The va_copy macro is part of C99, but many compilers don't implement it.
+ * Provide a "direct assignment" implmentation when va_copy isn't defined...
+ */
+
+#ifndef va_copy
+#  ifdef __va_copy
+#    define va_copy(dst,src) __va_copy(dst,src)
+#  else
+#    define va_copy(dst,src) memcpy(&dst, src, sizeof(va_list))
+#  endif /* __va_copy */
+#endif /* va_copy */
+
+
+#ifndef HAVE_SNPRINTF
+/*
+ * '_mxml_snprintf()' - Format a string.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_snprintf(char       *buffer,	/* I - Output buffer */
+               size_t     bufsize,	/* I - Size of output buffer */
+	       const char *format,	/* I - Printf-style format string */
+	       ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument list */
+  int		bytes;			/* Number of bytes formatted */
+
+
+  va_start(ap, format);
+  bytes = vsnprintf(buffer, bufsize, format, ap);
+  va_end(ap);
+
+  return (bytes);
+}
+#endif /* !HAVE_SNPRINTF */
+
+
+/*
+ * '_mxml_strdup()' - Duplicate a string.
+ */
+
+#ifndef HAVE_STRDUP
+char *					/* O - New string pointer */
+_mxml_strdup(const char *s)		/* I - String to duplicate */
+{
+  char	*t;				/* New string pointer */
+
+
+  if (s == NULL)
+    return (NULL);
+
+  if ((t = malloc(strlen(s) + 1)) == NULL)
+    return (NULL);
+
+  return (strcpy(t, s));
+}
+#endif /* !HAVE_STRDUP */
+
+
+/*
+ * '_mxml_strdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_strdupf(const char *format,	/* I - Printf-style format string */
+              ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to additional arguments */
+  char		*s;			/* Pointer to formatted string */
+
+
+ /*
+  * Get a pointer to the additional arguments, format the string,
+  * and return it...
+  */
+
+  va_start(ap, format);
+  s = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  return (s);
+}
+
+
+#ifndef HAVE_VSNPRINTF
+/*
+ * '_mxml_vsnprintf()' - Format a string into a fixed size buffer.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_vsnprintf(char       *buffer,	/* O - Output buffer */
+                size_t     bufsize,	/* O - Size of output buffer */
+		const char *format,	/* I - Printf-style format string */
+ 		va_list    ap)		/* I - Pointer to additional arguments */
+{
+  char		*bufptr,		/* Pointer to position in buffer */
+		*bufend,		/* Pointer to end of buffer */
+		sign,			/* Sign of format width */
+		size,			/* Size character (h, l, L) */
+		type;			/* Format type character */
+  int		width,			/* Width of field */
+		prec;			/* Number of characters of precision */
+  char		tformat[100],		/* Temporary format string for sprintf() */
+		*tptr,			/* Pointer into temporary format */
+		temp[1024];		/* Buffer for formatted numbers */
+  char		*s;			/* Pointer to string */
+  int		slen;			/* Length of string */
+  int		bytes;			/* Total number of bytes needed */
+
+
+ /*
+  * Loop through the format string, formatting as needed...
+  */
+
+  bufptr = buffer;
+  bufend = buffer + bufsize - 1;
+  bytes  = 0;
+
+  while (*format)
+  {
+    if (*format == '%')
+    {
+      tptr = tformat;
+      *tptr++ = *format++;
+
+      if (*format == '%')
+      {
+        if (bufptr && bufptr < bufend)
+          *bufptr++ = *format;
+        bytes ++;
+        format ++;
+	continue;
+      }
+      else if (strchr(" -+#\'", *format))
+      {
+        *tptr++ = *format;
+        sign = *format++;
+      }
+      else
+        sign = 0;
+
+      if (*format == '*')
+      {
+       /*
+        * Get width from argument...
+	*/
+
+	format ++;
+	width = va_arg(ap, int);
+
+	snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", width);
+	tptr += strlen(tptr);
+      }
+      else
+      {
+	width = 0;
+
+	while (isdigit(*format & 255))
+	{
+	  if (tptr < (tformat + sizeof(tformat) - 1))
+	    *tptr++ = *format;
+
+	  width = width * 10 + *format++ - '0';
+	}
+      }
+
+      if (*format == '.')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        format ++;
+
+        if (*format == '*')
+	{
+         /*
+	  * Get precision from argument...
+	  */
+
+	  format ++;
+	  prec = va_arg(ap, int);
+
+	  snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", prec);
+	  tptr += strlen(tptr);
+	}
+	else
+	{
+	  prec = 0;
+
+	  while (isdigit(*format & 255))
+	  {
+	    if (tptr < (tformat + sizeof(tformat) - 1))
+	      *tptr++ = *format;
+
+	    prec = prec * 10 + *format++ - '0';
+	  }
+	}
+      }
+      else
+        prec = -1;
+
+      if (*format == 'l' && format[1] == 'l')
+      {
+        size = 'L';
+
+	if (tptr < (tformat + sizeof(tformat) - 2))
+	{
+	  *tptr++ = 'l';
+	  *tptr++ = 'l';
+	}
+
+	format += 2;
+      }
+      else if (*format == 'h' || *format == 'l' || *format == 'L')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        size = *format++;
+      }
+
+      if (!*format)
+        break;
+
+      if (tptr < (tformat + sizeof(tformat) - 1))
+        *tptr++ = *format;
+
+      type  = *format++;
+      *tptr = '\0';
+
+      switch (type)
+      {
+	case 'E' : /* Floating point formats */
+	case 'G' :
+	case 'e' :
+	case 'f' :
+	case 'g' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, double));
+
+            bytes += strlen(temp);
+
+            if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'B' : /* Integer formats */
+	case 'X' :
+	case 'b' :
+        case 'd' :
+	case 'i' :
+	case 'o' :
+	case 'u' :
+	case 'x' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+#ifdef HAVE_LONG_LONG
+	    if (size == 'L')
+	      sprintf(temp, tformat, va_arg(ap, long long));
+	    else
+#endif /* HAVE_LONG_LONG */
+	    sprintf(temp, tformat, va_arg(ap, int));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+	case 'p' : /* Pointer value */
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, void *));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'c' : /* Character or character array */
+	    bytes += width;
+
+	    if (bufptr)
+	    {
+	      if (width <= 1)
+	        *bufptr++ = va_arg(ap, int);
+	      else
+	      {
+		if ((bufptr + width) > bufend)
+		  width = bufend - bufptr;
+
+		memcpy(bufptr, va_arg(ap, char *), (size_t)width);
+		bufptr += width;
+	      }
+	    }
+	    break;
+
+	case 's' : /* String */
+	    if ((s = va_arg(ap, char *)) == NULL)
+	      s = "(null)";
+
+	    slen = strlen(s);
+	    if (slen > width && prec != width)
+	      width = slen;
+
+            bytes += width;
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + width) > bufend)
+	        width = bufend - bufptr;
+
+              if (slen > width)
+	        slen = width;
+
+	      if (sign == '-')
+	      {
+		strncpy(bufptr, s, (size_t)slen);
+		memset(bufptr + slen, ' ', (size_t)(width - slen));
+	      }
+	      else
+	      {
+		memset(bufptr, ' ', (size_t)(width - slen));
+		strncpy(bufptr + width - slen, s, (size_t)slen);
+	      }
+
+	      bufptr += width;
+	    }
+	    break;
+
+	case 'n' : /* Output number of chars so far */
+	    *(va_arg(ap, int *)) = bytes;
+	    break;
+      }
+    }
+    else
+    {
+      bytes ++;
+
+      if (bufptr && bufptr < bufend)
+        *bufptr++ = *format;
+
+      format ++;
+    }
+  }
+
+ /*
+  * Nul-terminate the string and return the number of characters needed.
+  */
+
+  *bufptr = '\0';
+
+  return (bytes);
+}
+#endif /* !HAVE_VSNPRINTF */
+
+
+/*
+ * '_mxml_vstrdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_vstrdupf(const char *format,	/* I - Printf-style format string */
+               va_list    ap)		/* I - Pointer to additional arguments */
+{
+  int		bytes;			/* Number of bytes required */
+  char		*buffer,		/* String buffer */
+		temp[256];		/* Small buffer for first vsnprintf */
+  va_list	apcopy;			/* Copy of argument list */
+
+
+ /*
+  * First format with a tiny buffer; this will tell us how many bytes are
+  * needed...
+  */
+
+  va_copy(apcopy, ap);
+  bytes = vsnprintf(temp, sizeof(temp), format, apcopy);
+
+  if (bytes < sizeof(temp))
+  {
+   /*
+    * Hey, the formatted string fits in the tiny buffer, so just dup that...
+    */
+
+    return (strdup(temp));
+  }
+
+ /*
+  * Allocate memory for the whole thing and reformat to the new, larger
+  * buffer...
+  */
+
+  if ((buffer = calloc(1, bytes + 1)) != NULL)
+    vsnprintf(buffer, bytes + 1, format, ap);
+
+ /*
+  * Return the new string...
+  */
+
+  return (buffer);
+}
+
+
+/*
+ * End of "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml.h b/tools/gator/daemon/mxml/mxml.h
new file mode 100644
index 000000000000..bba5fd23a67b
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml.h
@@ -0,0 +1,332 @@
+/*
+ * "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Header file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Prevent multiple inclusion...
+ */
+
+#ifndef _mxml_h_
+#  define _mxml_h_
+
+/*
+ * Include necessary headers...
+ */
+
+#  include <stdio.h>
+#  include <stdlib.h>
+#  include <string.h>
+#  include <ctype.h>
+#  include <errno.h>
+
+
+/*
+ * Constants...
+ */
+
+#  define MXML_MAJOR_VERSION	2	/* Major version number */
+#  define MXML_MINOR_VERSION	8	/* Minor version number */
+
+#  define MXML_TAB		8	/* Tabs every N columns */
+
+#  define MXML_NO_CALLBACK	0	/* Don't use a type callback */
+#  define MXML_INTEGER_CALLBACK	mxml_integer_cb
+					/* Treat all data as integers */
+#  define MXML_OPAQUE_CALLBACK	mxml_opaque_cb
+					/* Treat all data as opaque */
+#  define MXML_REAL_CALLBACK	mxml_real_cb
+					/* Treat all data as real numbers */
+#  define MXML_TEXT_CALLBACK	0	/* Treat all data as text */
+#  define MXML_IGNORE_CALLBACK	mxml_ignore_cb
+					/* Ignore all non-element content */
+
+#  define MXML_NO_PARENT	0	/* No parent for the node */
+
+#  define MXML_DESCEND		1	/* Descend when finding/walking */
+#  define MXML_NO_DESCEND	0	/* Don't descend when finding/walking */
+#  define MXML_DESCEND_FIRST	-1	/* Descend for first find */
+
+#  define MXML_WS_BEFORE_OPEN	0	/* Callback for before open tag */
+#  define MXML_WS_AFTER_OPEN	1	/* Callback for after open tag */
+#  define MXML_WS_BEFORE_CLOSE	2	/* Callback for before close tag */
+#  define MXML_WS_AFTER_CLOSE	3	/* Callback for after close tag */
+
+#  define MXML_ADD_BEFORE	0	/* Add node before specified node */
+#  define MXML_ADD_AFTER	1	/* Add node after specified node */
+#  define MXML_ADD_TO_PARENT	NULL	/* Add node relative to parent */
+
+
+/*
+ * Data types...
+ */
+
+typedef enum mxml_sax_event_e		/**** SAX event type. ****/
+{
+  MXML_SAX_CDATA,			/* CDATA node */
+  MXML_SAX_COMMENT,			/* Comment node */
+  MXML_SAX_DATA,			/* Data node */
+  MXML_SAX_DIRECTIVE,			/* Processing directive node */
+  MXML_SAX_ELEMENT_CLOSE,		/* Element closed */
+  MXML_SAX_ELEMENT_OPEN			/* Element opened */
+} mxml_sax_event_t;
+
+typedef enum mxml_type_e		/**** The XML node type. ****/
+{
+  MXML_IGNORE = -1,			/* Ignore/throw away node @since Mini-XML 2.3@ */
+  MXML_ELEMENT,				/* XML element with attributes */
+  MXML_INTEGER,				/* Integer value */
+  MXML_OPAQUE,				/* Opaque string */
+  MXML_REAL,				/* Real value */
+  MXML_TEXT,				/* Text fragment */
+  MXML_CUSTOM				/* Custom data @since Mini-XML 2.1@ */
+} mxml_type_t;
+
+typedef void (*mxml_custom_destroy_cb_t)(void *);
+					/**** Custom data destructor ****/
+
+typedef void (*mxml_error_cb_t)(const char *);
+					/**** Error callback function ****/
+
+typedef struct mxml_attr_s		/**** An XML element attribute value. @private@ ****/
+{
+  char			*name;		/* Attribute name */
+  char			*value;		/* Attribute value */
+} mxml_attr_t;
+
+typedef struct mxml_element_s		/**** An XML element value. @private@ ****/
+{
+  char			*name;		/* Name of element */
+  int			num_attrs;	/* Number of attributes */
+  mxml_attr_t		*attrs;		/* Attributes */
+} mxml_element_t;
+
+typedef struct mxml_text_s		/**** An XML text value. @private@ ****/
+{
+  int			whitespace;	/* Leading whitespace? */
+  char			*string;	/* Fragment string */
+} mxml_text_t;
+
+typedef struct mxml_custom_s		/**** An XML custom value. @private@ ****/
+{
+  void			*data;		/* Pointer to (allocated) custom data */
+  mxml_custom_destroy_cb_t destroy;	/* Pointer to destructor function */
+} mxml_custom_t;
+
+typedef union mxml_value_u		/**** An XML node value. @private@ ****/
+{
+  mxml_element_t	element;	/* Element */
+  int			integer;	/* Integer number */
+  char			*opaque;	/* Opaque string */
+  double		real;		/* Real number */
+  mxml_text_t		text;		/* Text fragment */
+  mxml_custom_t		custom;		/* Custom data @since Mini-XML 2.1@ */
+} mxml_value_t;
+
+struct mxml_node_s			/**** An XML node. @private@ ****/
+{
+  mxml_type_t		type;		/* Node type */
+  struct mxml_node_s	*next;		/* Next node under same parent */
+  struct mxml_node_s	*prev;		/* Previous node under same parent */
+  struct mxml_node_s	*parent;	/* Parent node */
+  struct mxml_node_s	*child;		/* First child node */
+  struct mxml_node_s	*last_child;	/* Last child node */
+  mxml_value_t		value;		/* Node value */
+  int			ref_count;	/* Use count */
+  void			*user_data;	/* User data */
+};
+
+typedef struct mxml_node_s mxml_node_t;	/**** An XML node. ****/
+
+struct mxml_index_s			 /**** An XML node index. @private@ ****/
+{
+  char			*attr;		/* Attribute used for indexing or NULL */
+  int			num_nodes;	/* Number of nodes in index */
+  int			alloc_nodes;	/* Allocated nodes in index */
+  int			cur_node;	/* Current node */
+  mxml_node_t		**nodes;	/* Node array */
+};
+
+typedef struct mxml_index_s mxml_index_t;
+					/**** An XML node index. ****/
+
+typedef int (*mxml_custom_load_cb_t)(mxml_node_t *, const char *);
+					/**** Custom data load callback function ****/
+
+typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *);
+					/**** Custom data save callback function ****/
+
+typedef int (*mxml_entity_cb_t)(const char *);
+					/**** Entity callback function */
+
+typedef mxml_type_t (*mxml_load_cb_t)(mxml_node_t *);
+					/**** Load callback function ****/
+
+typedef const char *(*mxml_save_cb_t)(mxml_node_t *, int);
+					/**** Save callback function ****/
+
+typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *);
+					/**** SAX callback function ****/
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+extern "C" {
+#  endif /* __cplusplus */
+
+/*
+ * Prototypes...
+ */
+
+extern void		mxmlAdd(mxml_node_t *parent, int where,
+			        mxml_node_t *child, mxml_node_t *node);
+extern void		mxmlDelete(mxml_node_t *node);
+extern void		mxmlElementDeleteAttr(mxml_node_t *node,
+			                      const char *name);
+extern const char	*mxmlElementGetAttr(mxml_node_t *node, const char *name);
+extern void		mxmlElementSetAttr(mxml_node_t *node, const char *name,
+			                   const char *value);
+extern void		mxmlElementSetAttrf(mxml_node_t *node, const char *name,
+			                    const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlEntityAddCallback(mxml_entity_cb_t cb);
+extern const char	*mxmlEntityGetName(int val);
+extern int		mxmlEntityGetValue(const char *name);
+extern void		mxmlEntityRemoveCallback(mxml_entity_cb_t cb);
+extern mxml_node_t	*mxmlFindElement(mxml_node_t *node, mxml_node_t *top,
+			                 const char *name, const char *attr,
+					 const char *value, int descend);
+extern mxml_node_t	*mxmlFindPath(mxml_node_t *node, const char *path);
+extern const char	*mxmlGetCDATA(mxml_node_t *node);
+extern const void	*mxmlGetCustom(mxml_node_t *node);
+extern const char	*mxmlGetElement(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetFirstChild(mxml_node_t *node);
+extern int		mxmlGetInteger(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetLastChild(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetNextSibling(mxml_node_t *node);
+extern const char	*mxmlGetOpaque(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetParent(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetPrevSibling(mxml_node_t *node);
+extern double		mxmlGetReal(mxml_node_t *node);
+extern int		mxmlGetRefCount(mxml_node_t *node);
+extern const char	*mxmlGetText(mxml_node_t *node, int *whitespace);
+extern mxml_type_t	mxmlGetType(mxml_node_t *node);
+extern void		*mxmlGetUserData(mxml_node_t *node);
+extern void		mxmlIndexDelete(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexEnum(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexFind(mxml_index_t *ind,
+			               const char *element,
+			               const char *value);
+extern int		mxmlIndexGetCount(mxml_index_t *ind);
+extern mxml_index_t	*mxmlIndexNew(mxml_node_t *node, const char *element,
+			              const char *attr);
+extern mxml_node_t	*mxmlIndexReset(mxml_index_t *ind);
+extern mxml_node_t	*mxmlLoadFd(mxml_node_t *top, int fd,
+			            mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadFile(mxml_node_t *top, FILE *fp,
+			              mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadString(mxml_node_t *top, const char *s,
+			                mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlNewCDATA(mxml_node_t *parent, const char *string);
+extern mxml_node_t	*mxmlNewCustom(mxml_node_t *parent, void *data,
+			               mxml_custom_destroy_cb_t destroy);
+extern mxml_node_t	*mxmlNewElement(mxml_node_t *parent, const char *name);
+extern mxml_node_t	*mxmlNewInteger(mxml_node_t *parent, int integer);
+extern mxml_node_t	*mxmlNewOpaque(mxml_node_t *parent, const char *opaque);
+extern mxml_node_t	*mxmlNewReal(mxml_node_t *parent, double real);
+extern mxml_node_t	*mxmlNewText(mxml_node_t *parent, int whitespace,
+			             const char *string);
+extern mxml_node_t	*mxmlNewTextf(mxml_node_t *parent, int whitespace,
+			              const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern mxml_node_t	*mxmlNewXML(const char *version);
+extern int		mxmlRelease(mxml_node_t *node);
+extern void		mxmlRemove(mxml_node_t *node);
+extern int		mxmlRetain(mxml_node_t *node);
+extern char		*mxmlSaveAllocString(mxml_node_t *node,
+			        	     mxml_save_cb_t cb);
+extern int		mxmlSaveFd(mxml_node_t *node, int fd,
+			           mxml_save_cb_t cb);
+extern int		mxmlSaveFile(mxml_node_t *node, FILE *fp,
+			             mxml_save_cb_t cb);
+extern int		mxmlSaveString(mxml_node_t *node, char *buffer,
+			               int bufsize, mxml_save_cb_t cb);
+extern mxml_node_t	*mxmlSAXLoadFd(mxml_node_t *top, int fd,
+			               mxml_type_t (*cb)(mxml_node_t *),
+			               mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadFile(mxml_node_t *top, FILE *fp,
+			                 mxml_type_t (*cb)(mxml_node_t *),
+			                 mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadString(mxml_node_t *top, const char *s,
+			                   mxml_type_t (*cb)(mxml_node_t *),
+			                   mxml_sax_cb_t sax, void *sax_data);
+extern int		mxmlSetCDATA(mxml_node_t *node, const char *data);
+extern int		mxmlSetCustom(mxml_node_t *node, void *data,
+			              mxml_custom_destroy_cb_t destroy);
+extern void		mxmlSetCustomHandlers(mxml_custom_load_cb_t load,
+			                      mxml_custom_save_cb_t save);
+extern int		mxmlSetElement(mxml_node_t *node, const char *name);
+extern void		mxmlSetErrorCallback(mxml_error_cb_t cb);
+extern int		mxmlSetInteger(mxml_node_t *node, int integer);
+extern int		mxmlSetOpaque(mxml_node_t *node, const char *opaque);
+extern int		mxmlSetReal(mxml_node_t *node, double real);
+extern int		mxmlSetText(mxml_node_t *node, int whitespace,
+			            const char *string);
+extern int		mxmlSetTextf(mxml_node_t *node, int whitespace,
+			             const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlSetUserData(mxml_node_t *node, void *data);
+extern void		mxmlSetWrapMargin(int column);
+extern mxml_node_t	*mxmlWalkNext(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+extern mxml_node_t	*mxmlWalkPrev(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+
+
+/*
+ * Semi-private functions...
+ */
+
+extern void		mxml_error(const char *format, ...);
+extern mxml_type_t	mxml_ignore_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_integer_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_opaque_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_real_cb(mxml_node_t *node);
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+}
+#  endif /* __cplusplus */
+#endif /* !_mxml_h_ */
+
+
+/*
+ * End of "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
index 926cbf3efc7f..2c5a19733357 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/lk/Makefile
@@ -1,5 +1,8 @@
 include ../../scripts/Makefile.include
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # guard against environment variables
 LIB_H=
 LIB_OBJS=
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c
index 099e7cd022e4..7c4347962353 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/lk/debugfs.c
@@ -5,7 +5,6 @@
 #include <stdbool.h>
 #include <sys/vfs.h>
 #include <sys/mount.h>
-#include <linux/magic.h>
 #include <linux/kernel.h>
 
 #include "debugfs.h"
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 46878daca5cc..c9eac3edfe4d 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -101,7 +101,7 @@ static int setup_cpunode_map(void)
 
 	dir1 = opendir(PATH_SYS_NODE);
 	if (!dir1)
-		return -1;
+		return 0;
 
 	while ((dent1 = readdir(dir1)) != NULL) {
 		if (dent1->d_type != DT_DIR ||
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4bf91b09d62d..794bb1a120be 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -113,7 +113,7 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  (hpp_snprint_fn)percent_color_snprintf, true);	\
+			  percent_color_snprintf, true);			\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 11e46da17bbb..66e44a5019d5 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -318,8 +318,15 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
 	return r;
 }
 
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
-	const char *color = get_percent_color(percent);
+	va_list args;
+	double percent;
+	const char *color;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
+	color = get_percent_color(percent);
 	return color_snprintf(bf, size, color, fmt, percent);
 }
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index dea082b79602..fced3840e99c 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,7 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 07b1a3ad3e24..63b6f8c8edf2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1514,7 +1514,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel,
 	switch (err) {
 	case EPERM:
 	case EACCES:
-		return scnprintf(msg, size, "%s",
+		return scnprintf(msg, size,
 		 "You may not have permission to collect %sstats.\n"
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
 		 " -1 - Not paranoid at all\n"
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 14c2fe20aa62..20764e01df16 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -34,6 +34,7 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_unordered_events;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6fcb9de62340..8bcdf9e54089 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -21,6 +21,7 @@ const char *map_type__name[MAP__NR_TYPES] = {
 static inline int is_anon_memory(const char *filename)
 {
 	return !strcmp(filename, "//anon") ||
+	       !strcmp(filename, "/dev/zero (deleted)") ||
 	       !strcmp(filename, "/anon_hugepage (deleted)");
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index eacec859f299..b4741b027a8f 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
 	event = find_cache_event(evsel);
 	if (!event)
-		die("ug! no event found for type %" PRIu64, evsel->attr.config);
+		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
 	pid = raw_field_value(event, "common_pid", data);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cf1fe01b7e89..6f593a704ea5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -656,8 +656,7 @@ static int perf_session_queue_event(struct perf_session *s, union perf_event *ev
 		return -ETIME;
 
 	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
+		s->stats.nr_unordered_events++;
 	}
 
 	if (!list_empty(sc)) {
@@ -811,6 +810,7 @@ static struct machine *
 					       union perf_event *event)
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct machine *machine;
 
 	if (perf_guest &&
 	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
@@ -822,7 +822,11 @@ static struct machine *
 		else
 			pid = event->ip.pid;
 
-		return perf_session__findnew_machine(session, pid);
+		machine = perf_session__find_machine(session, pid);
+		if (!machine)
+			machine = perf_session__findnew_machine(session,
+						DEFAULT_GUEST_KERNEL_ID);
+		return machine;
 	}
 
 	return &session->machines.host;
@@ -1052,6 +1056,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
 			    session->stats.nr_unprocessable_samples);
 	}
+	if (session->stats.nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
 }
 
 #define session_done()	(*(volatile int *)(&session_done))
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index dc4de3762111..bcf1d2f0b791 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -18,9 +18,9 @@
 #include "helpers/bitmask.h"
 
 static struct option set_opts[] = {
-	{ .name = "perf-bias",	.has_arg = optional_argument,	.flag = NULL,	.val = 'b'},
-	{ .name = "sched-mc",	.has_arg = optional_argument,	.flag = NULL,	.val = 'm'},
-	{ .name = "sched-smt",	.has_arg = optional_argument,	.flag = NULL,	.val = 's'},
+	{ .name = "perf-bias",	.has_arg = required_argument,	.flag = NULL,	.val = 'b'},
+	{ .name = "sched-mc",	.has_arg = required_argument,	.flag = NULL,	.val = 'm'},
+	{ .name = "sched-smt",	.has_arg = required_argument,	.flag = NULL,	.val = 's'},
 	{ },
 };
 
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f09641da40d4..d1b3a361e526 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -5,7 +5,7 @@ DESTDIR		:=
 
 turbostat : turbostat.c
 CFLAGS +=	-Wall
-CFLAGS +=	-I../../../../arch/x86/include/uapi/
+CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index fe702076ca46..6a7ee5f21c9b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,7 +20,7 @@
  */
 
 #define _GNU_SOURCE
-#include <asm/msr.h>
+#include MSRHEADER
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -35,6 +35,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <cpuid.h>
 
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
@@ -1894,7 +1895,7 @@ void check_cpuid()
 
 	eax = ebx = ecx = edx = 0;
 
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0));
+	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1903,7 +1904,7 @@ void check_cpuid()
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
+	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -1925,7 +1926,7 @@ void check_cpuid()
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000));
+	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
 
 	if (max_level < 0x80000007) {
 		fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level);
@@ -1936,7 +1937,7 @@ void check_cpuid()
 	 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 	 * this check is valid for both Intel and AMD
 	 */
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
+	__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
 	has_invariant_tsc = edx & (1 << 8);
 
 	if (!has_invariant_tsc) {
@@ -1949,7 +1950,7 @@ void check_cpuid()
 	 * this check is valid for both Intel and AMD
 	 */
 
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
+	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0a63658065f0..2cee2b79b4de 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -4,6 +4,7 @@ TARGETS += efivarfs
 TARGETS += kcmp
 TARGETS += memory-hotplug
 TARGETS += mqueue
+TARGETS += mount
 TARGETS += net
 TARGETS += ptrace
 TARGETS += vm
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 000000000000..337d853c2b72
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,17 @@
+# Makefile for mount selftests.
+
+all: unprivileged-remount-test
+
+unprivileged-remount-test: unprivileged-remount-test.c
+	gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test
+
+# Allow specific tests to be selected.
+test_unprivileged_remount: unprivileged-remount-test
+	@if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi
+
+run_tests: all test_unprivileged_remount
+
+clean:
+	rm -f unprivileged-remount-test
+
+.PHONY: all test_unprivileged_remount
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 000000000000..517785052f1c
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,370 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
+#ifndef MS_RELATIME
+# define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+# define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+	va_list ap;
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
+{
+	char buf[4096];
+	int fd;
+	ssize_t written;
+	int buf_len;
+
+	buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+	if (buf_len < 0) {
+		die("vsnprintf failed: %s\n",
+		    strerror(errno));
+	}
+	if (buf_len >= sizeof(buf)) {
+		die("vsnprintf output truncated\n");
+	}
+
+	fd = open(filename, O_WRONLY);
+	if (fd < 0) {
+		if ((errno == ENOENT) && enoent_ok)
+			return;
+		die("open of %s failed: %s\n",
+		    filename, strerror(errno));
+	}
+	written = write(fd, buf, buf_len);
+	if (written != buf_len) {
+		if (written >= 0) {
+			die("short write to %s\n", filename);
+		} else {
+			die("write to %s failed: %s\n",
+				filename, strerror(errno));
+		}
+	}
+	if (close(fd) != 0) {
+		die("close of %s failed: %s\n",
+			filename, strerror(errno));
+	}
+}
+
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(true, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(false, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+	int ret;
+	struct statvfs stat;
+	int mnt_flags;
+
+	ret = statvfs(path, &stat);
+	if (ret != 0) {
+		die("statvfs of %s failed: %s\n",
+			path, strerror(errno));
+	}
+	if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+			ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+			ST_SYNCHRONOUS | ST_MANDLOCK)) {
+		die("Unrecognized mount flags\n");
+	}
+	mnt_flags = 0;
+	if (stat.f_flag & ST_RDONLY)
+		mnt_flags |= MS_RDONLY;
+	if (stat.f_flag & ST_NOSUID)
+		mnt_flags |= MS_NOSUID;
+	if (stat.f_flag & ST_NODEV)
+		mnt_flags |= MS_NODEV;
+	if (stat.f_flag & ST_NOEXEC)
+		mnt_flags |= MS_NOEXEC;
+	if (stat.f_flag & ST_NOATIME)
+		mnt_flags |= MS_NOATIME;
+	if (stat.f_flag & ST_NODIRATIME)
+		mnt_flags |= MS_NODIRATIME;
+	if (stat.f_flag & ST_RELATIME)
+		mnt_flags |= MS_RELATIME;
+	if (stat.f_flag & ST_SYNCHRONOUS)
+		mnt_flags |= MS_SYNCHRONOUS;
+	if (stat.f_flag & ST_MANDLOCK)
+		mnt_flags |= ST_MANDLOCK;
+
+	return mnt_flags;
+}
+
+static void create_and_enter_userns(void)
+{
+	uid_t uid;
+	gid_t gid;
+
+	uid = getuid();
+	gid = getgid();
+
+	if (unshare(CLONE_NEWUSER) !=0) {
+		die("unshare(CLONE_NEWUSER) failed: %s\n",
+			strerror(errno));
+	}
+
+	maybe_write_file("/proc/self/setgroups", "deny");
+	write_file("/proc/self/uid_map", "0 %d 1", uid);
+	write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+	if (setgid(0) != 0) {
+		die ("setgid(0) failed %s\n",
+			strerror(errno));
+	}
+	if (setuid(0) != 0) {
+		die("setuid(0) failed %s\n",
+			strerror(errno));
+	}
+}
+
+static
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+			 int mount_flags, int remount_flags, int invalid_flags)
+{
+	pid_t child;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+	}
+
+	create_and_enter_userns();
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+		die("mount of %s with options '%s' on /tmp failed: %s\n",
+		    fstype,
+		    mount_options? mount_options : "",
+		    strerror(errno));
+	}
+
+	create_and_enter_userns();
+
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp with invalid flags "
+		    "succeeded unexpectedly\n");
+	}
+	exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+				   invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+	pid_t child;
+	int ret;
+	const char *orig_path = "/dev";
+	const char *dest_path = "/tmp";
+	int orig_mnt_flags, remount_mnt_flags;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+	}
+
+	orig_mnt_flags = read_mnt_flags(orig_path);
+
+	create_and_enter_userns();
+	ret = unshare(CLONE_NEWNS);
+	if (ret != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+	if (ret != 0) {
+		die("recursive bind mount of %s onto %s failed: %s\n",
+			orig_path, dest_path, strerror(errno));
+	}
+
+	ret = mount(dest_path, dest_path, "none",
+		    MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+	if (ret != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	remount_mnt_flags = read_mnt_flags(dest_path);
+	if (orig_mnt_flags != remount_mnt_flags) {
+		die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+			dest_path, orig_path);
+	}
+	exit(EXIT_SUCCESS);
+}
+
+int main(int argc, char **argv)
+{
+	if (!test_unpriv_remount_simple(MS_RDONLY)) {
+		die("MS_RDONLY malfunctions\n");
+	}
+	if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
+		die("MS_NODEV malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOSUID)) {
+		die("MS_NOSUID malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOEXEC)) {
+		die("MS_NOEXEC malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME|MS_DIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
+	{
+		die("Default atime malfunctions\n");
+	}
+	if (!test_priv_mount_unpriv_remount()) {
+		die("Mount flags unexpectedly changed after remount\n");
+	}
+	return EXIT_SUCCESS;
+}
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index fe1e66b6ef40..a87e99f37c52 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -116,8 +116,8 @@ static const struct {
 	.header = {
 		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
 		.length = cpu_to_le32(sizeof descriptors),
-		.fs_count = 3,
-		.hs_count = 3,
+		.fs_count = cpu_to_le32(3),
+		.hs_count = cpu_to_le32(3),
 	},
 	.fs_descs = {
 		.intf = {
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index ce9ed99ad7dc..b47541dd798f 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -203,10 +203,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
 	spin_lock(&ioapic->lock);
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
-		if (!e->fields.mask &&
-			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
-			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
-				 index) || index == RTC_GSI)) {
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 				e->fields.dest_id, e->fields.dest_mode)) {
 				__set_bit(e->fields.vector,
@@ -306,7 +305,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
 				ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi = ret;
+		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
 
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index a3b14109049b..36f4e82c6b24 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -43,13 +43,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
 static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
-			   unsigned long size)
+			   unsigned long npages)
 {
 	gfn_t end_gfn;
 	pfn_t pfn;
 
 	pfn     = gfn_to_pfn_memslot(slot, gfn);
-	end_gfn = gfn + (size >> PAGE_SHIFT);
+	end_gfn = gfn + npages;
 	gfn    += 1;
 
 	if (is_error_noslot_pfn(pfn))
@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	return pfn;
 }
 
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
 	gfn_t gfn, end_gfn;
@@ -103,11 +111,15 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		while ((gfn << PAGE_SHIFT) & (page_size - 1))
 			page_size >>= 1;
 
+		/* Make sure hva is aligned to the page size we want to map */
+		while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
+			page_size >>= 1;
+
 		/*
 		 * Pin all pages we are about to map in memory. This is
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
-		pfn = kvm_pin_pages(slot, gfn, page_size);
+		pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
 		if (is_error_noslot_pfn(pfn)) {
 			gfn += 1;
 			continue;
@@ -119,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%llx\n", pfn);
+			kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
 			goto unmap_pages;
 		}
 
@@ -130,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	return 0;
 
 unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
 	return r;
 }
 
@@ -260,14 +273,6 @@ out_unlock:
 	return r;
 }
 
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
-	unsigned long i;
-
-	for (i = 0; i < npages; ++i)
-		kvm_release_pfn_clean(pfn + i);
-}
-
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9cae94206f41..4eed4cd9b58b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -52,6 +52,7 @@
 
 #include <asm/processor.h>
 #include <asm/io.h>
+#include <asm/ioctl.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
@@ -1977,6 +1978,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
 
+	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+		return -EINVAL;
+
 #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
 	/*
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,